linux-sg2042/tools/perf/util/event.c

734 lines
19 KiB
C
Raw Normal View History

#include <linux/types.h>
#include "event.h"
#include "debug.h"
#include "machine.h"
#include "sort.h"
#include "string.h"
#include "strlist.h"
#include "thread.h"
#include "thread_map.h"
static const char *perf_event__names[] = {
[0] = "TOTAL",
[PERF_RECORD_MMAP] = "MMAP",
[PERF_RECORD_LOST] = "LOST",
[PERF_RECORD_COMM] = "COMM",
[PERF_RECORD_EXIT] = "EXIT",
[PERF_RECORD_THROTTLE] = "THROTTLE",
[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
};
const char *perf_event__name(unsigned int id)
{
if (id >= ARRAY_SIZE(perf_event__names))
return "INVALID";
if (!perf_event__names[id])
return "UNKNOWN";
return perf_event__names[id];
}
static struct perf_sample synth_sample = {
.pid = -1,
.tid = -1,
.time = -1,
.stream_id = -1,
.cpu = -1,
.period = 1,
};
static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len)
{
char filename[PATH_MAX];
char bf[BUFSIZ];
FILE *fp;
size_t size = 0;
pid_t tgid = -1;
snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
fp = fopen(filename, "r");
if (fp == NULL) {
pr_debug("couldn't open %s\n", filename);
return 0;
}
while (!comm[0] || (tgid < 0)) {
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (fgets(bf, sizeof(bf), fp) == NULL) {
pr_warning("couldn't get COMM and pgid, malformed %s\n",
filename);
break;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
}
if (memcmp(bf, "Name:", 5) == 0) {
char *name = bf + 5;
while (*name && isspace(*name))
++name;
size = strlen(name) - 1;
if (size >= len)
size = len - 1;
memcpy(comm, name, size);
comm[size] = '\0';
} else if (memcmp(bf, "Tgid:", 5) == 0) {
char *tgids = bf + 5;
while (*tgids && isspace(*tgids))
++tgids;
tgid = atoi(tgids);
}
}
fclose(fp);
return tgid;
}
static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
union perf_event *event, pid_t pid,
int full,
perf_event__handler_t process,
struct machine *machine)
{
char filename[PATH_MAX];
size_t size;
DIR *tasks;
struct dirent dirent, *next;
pid_t tgid;
memset(&event->comm, 0, sizeof(event->comm));
tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
sizeof(event->comm.comm));
if (tgid < 0)
goto out;
event->comm.pid = tgid;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->comm.header.type = PERF_RECORD_COMM;
size = strlen(event->comm.comm) + 1;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:01 +08:00
size = PERF_ALIGN(size, sizeof(u64));
memset(event->comm.comm + size, 0, machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->comm.header.size = (sizeof(event->comm) -
(sizeof(event->comm.comm) - size) +
machine->id_hdr_size);
if (!full) {
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->comm.tid = pid;
if (process(tool, event, &synth_sample, machine) != 0)
return -1;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
goto out;
}
snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
tasks = opendir(filename);
if (tasks == NULL) {
pr_debug("couldn't open %s\n", filename);
return 0;
}
while (!readdir_r(tasks, &dirent, &next) && next) {
char *end;
pid = strtol(dirent.d_name, &end, 10);
if (*end)
continue;
/* already have tgid; jut want to update the comm */
(void) perf_event__get_comm_tgid(pid, event->comm.comm,
sizeof(event->comm.comm));
size = strlen(event->comm.comm) + 1;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:01 +08:00
size = PERF_ALIGN(size, sizeof(u64));
memset(event->comm.comm + size, 0, machine->id_hdr_size);
event->comm.header.size = (sizeof(event->comm) -
(sizeof(event->comm.comm) - size) +
machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->comm.tid = pid;
if (process(tool, event, &synth_sample, machine) != 0) {
tgid = -1;
break;
}
}
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
closedir(tasks);
out:
return tgid;
}
static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
perf_event__handler_t process,
struct machine *machine)
{
char filename[PATH_MAX];
FILE *fp;
int rc = 0;
snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
fp = fopen(filename, "r");
if (fp == NULL) {
/*
* We raced with a task exiting - just return:
*/
pr_debug("couldn't open %s\n", filename);
return -1;
}
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->header.type = PERF_RECORD_MMAP;
/*
* Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
*/
event->header.misc = PERF_RECORD_MISC_USER;
while (1) {
char bf[BUFSIZ];
char prot[5];
char execname[PATH_MAX];
char anonstr[] = "//anon";
size_t size;
if (fgets(bf, sizeof(bf), fp) == NULL)
break;
/* ensure null termination since stack will be reused. */
strcpy(execname, "");
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
&event->mmap.start, &event->mmap.len, prot,
&event->mmap.pgoff, execname);
if (prot[2] != 'x')
continue;
if (!strcmp(execname, ""))
strcpy(execname, anonstr);
size = strlen(execname) + 1;
memcpy(event->mmap.filename, execname, size);
size = PERF_ALIGN(size, sizeof(u64));
event->mmap.len -= event->mmap.start;
event->mmap.header.size = (sizeof(event->mmap) -
(sizeof(event->mmap.filename) - size));
memset(event->mmap.filename + size, 0, machine->id_hdr_size);
event->mmap.header.size += machine->id_hdr_size;
event->mmap.pid = tgid;
event->mmap.tid = pid;
if (process(tool, event, &synth_sample, machine) != 0) {
rc = -1;
break;
}
}
fclose(fp);
return rc;
}
int perf_event__synthesize_modules(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine)
{
int rc = 0;
struct rb_node *nd;
struct map_groups *kmaps = &machine->kmaps;
union perf_event *event = zalloc((sizeof(event->mmap) +
machine->id_hdr_size));
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
return -1;
}
event->header.type = PERF_RECORD_MMAP;
/*
* kernel uses 0 for user space maps, see kernel/perf_event.c
* __perf_event_mmap
*/
if (machine__is_host(machine))
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->header.misc = PERF_RECORD_MISC_KERNEL;
else
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
nd; nd = rb_next(nd)) {
size_t size;
struct map *pos = rb_entry(nd, struct map, rb_node);
if (pos->dso->kernel)
continue;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:01 +08:00
size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->mmap.header.type = PERF_RECORD_MMAP;
event->mmap.header.size = (sizeof(event->mmap) -
(sizeof(event->mmap.filename) - size));
memset(event->mmap.filename + size, 0, machine->id_hdr_size);
event->mmap.header.size += machine->id_hdr_size;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->mmap.start = pos->start;
event->mmap.len = pos->end - pos->start;
event->mmap.pid = machine->pid;
memcpy(event->mmap.filename, pos->dso->long_name,
pos->dso->long_name_len + 1);
if (process(tool, event, &synth_sample, machine) != 0) {
rc = -1;
break;
}
}
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
free(event);
return rc;
}
static int __event__synthesize_thread(union perf_event *comm_event,
union perf_event *mmap_event,
perf tools: Fix comm for processes with named threads perf does not properly handle monitoring of processes with named threads. For example: $ ps -C myapp -L PID LWP TTY TIME CMD 25118 25118 ? 00:00:00 myapp 25118 25119 ? 00:00:00 myapp:worker perf record -e cs -c 1 -fo /tmp/perf.data -p 25118 -- sleep 10 perf report --stdio -i /tmp/perf.data 100.00% myapp:worker [kernel.kallsyms] [k] perf_event_task_sched_out The process name is set to the name of the last thread it finds for the process. The Problem: perf-top and perf-record both create a thread_map of threads to be monitored. That map is used in perf_event__synthesize_thread_map which loops over the entries in thread_map and calls __event__synthesize_thread to generate COMM and MMAP events. __event__synthesize_thread calls perf_event__synthesize_comm which opens /proc/pid/status, reads the name of the task and its thread group id. That's all fine. The problem is that it then reads /proc/pid/task and generates COMM events for each task it finds - but using the name found in /proc/pid/status where pid is the thread of interest. The end result (looping over thread_map + synthesizing comm events for each thread each time) means the name of the last thread processed sets the name for all threads in the process - which is not good for multithreaded processes with named threads. The Fix: perf_event__synthesize_comm has an input argument (full) that decides whether to process task entries for each pid it is passed. It currently never set to 0 (perf_event__synthesize_comm has a single caller and it always passes the value 1). Let's fix that. Add the full input argument to __event__synthesize_thread which passes it to perf_event__synthesize_comm. For thread/process monitoring set full to 0 which means COMM and MMAP events are only generated for the pid passed to it. For system wide monitoring set full to 1 so that COMM events are generated for all threads in a process. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1324578603-12762-2-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-23 02:30:01 +08:00
pid_t pid, int full,
perf_event__handler_t process,
struct perf_tool *tool,
struct machine *machine)
{
perf tools: Fix comm for processes with named threads perf does not properly handle monitoring of processes with named threads. For example: $ ps -C myapp -L PID LWP TTY TIME CMD 25118 25118 ? 00:00:00 myapp 25118 25119 ? 00:00:00 myapp:worker perf record -e cs -c 1 -fo /tmp/perf.data -p 25118 -- sleep 10 perf report --stdio -i /tmp/perf.data 100.00% myapp:worker [kernel.kallsyms] [k] perf_event_task_sched_out The process name is set to the name of the last thread it finds for the process. The Problem: perf-top and perf-record both create a thread_map of threads to be monitored. That map is used in perf_event__synthesize_thread_map which loops over the entries in thread_map and calls __event__synthesize_thread to generate COMM and MMAP events. __event__synthesize_thread calls perf_event__synthesize_comm which opens /proc/pid/status, reads the name of the task and its thread group id. That's all fine. The problem is that it then reads /proc/pid/task and generates COMM events for each task it finds - but using the name found in /proc/pid/status where pid is the thread of interest. The end result (looping over thread_map + synthesizing comm events for each thread each time) means the name of the last thread processed sets the name for all threads in the process - which is not good for multithreaded processes with named threads. The Fix: perf_event__synthesize_comm has an input argument (full) that decides whether to process task entries for each pid it is passed. It currently never set to 0 (perf_event__synthesize_comm has a single caller and it always passes the value 1). Let's fix that. Add the full input argument to __event__synthesize_thread which passes it to perf_event__synthesize_comm. For thread/process monitoring set full to 0 which means COMM and MMAP events are only generated for the pid passed to it. For system wide monitoring set full to 1 so that COMM events are generated for all threads in a process. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1324578603-12762-2-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-23 02:30:01 +08:00
pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full,
process, machine);
if (tgid == -1)
return -1;
return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
process, machine);
}
int perf_event__synthesize_thread_map(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
struct machine *machine)
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
{
union perf_event *comm_event, *mmap_event;
perf tools: Fix comm for processes with named threads perf does not properly handle monitoring of processes with named threads. For example: $ ps -C myapp -L PID LWP TTY TIME CMD 25118 25118 ? 00:00:00 myapp 25118 25119 ? 00:00:00 myapp:worker perf record -e cs -c 1 -fo /tmp/perf.data -p 25118 -- sleep 10 perf report --stdio -i /tmp/perf.data 100.00% myapp:worker [kernel.kallsyms] [k] perf_event_task_sched_out The process name is set to the name of the last thread it finds for the process. The Problem: perf-top and perf-record both create a thread_map of threads to be monitored. That map is used in perf_event__synthesize_thread_map which loops over the entries in thread_map and calls __event__synthesize_thread to generate COMM and MMAP events. __event__synthesize_thread calls perf_event__synthesize_comm which opens /proc/pid/status, reads the name of the task and its thread group id. That's all fine. The problem is that it then reads /proc/pid/task and generates COMM events for each task it finds - but using the name found in /proc/pid/status where pid is the thread of interest. The end result (looping over thread_map + synthesizing comm events for each thread each time) means the name of the last thread processed sets the name for all threads in the process - which is not good for multithreaded processes with named threads. The Fix: perf_event__synthesize_comm has an input argument (full) that decides whether to process task entries for each pid it is passed. It currently never set to 0 (perf_event__synthesize_comm has a single caller and it always passes the value 1). Let's fix that. Add the full input argument to __event__synthesize_thread which passes it to perf_event__synthesize_comm. For thread/process monitoring set full to 0 which means COMM and MMAP events are only generated for the pid passed to it. For system wide monitoring set full to 1 so that COMM events are generated for all threads in a process. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1324578603-12762-2-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-23 02:30:01 +08:00
int err = -1, thread, j;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (comm_event == NULL)
goto out;
mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (mmap_event == NULL)
goto out_free_comm;
perf tools: Fix thread_map event synthesizing in top and record Jeff Moyer reported these messages: Warning: ... trying to fall back to cpu-clock-ticks couldn't open /proc/-1/status couldn't open /proc/-1/maps [ls output] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (~363 samples) ] That lead me and David Ahern to see that something was fishy on the thread synthesizing routines, at least for the case where the workload is started from 'perf record', as -1 is the default for target_tid in 'perf record --tid' parameter, so somehow we were trying to synthesize the PERF_RECORD_MMAP and PERF_RECORD_COMM events for the thread -1, a bug. So I investigated this and noticed that when we introduced support for recording a process and its threads using --pid some bugs were introduced and that the way to fix it was to instead of passing the target_tid to the event synthesizing routines we should better pass the thread_map that has the list of threads for a --pid or just the single thread for a --tid. Checked in the following ways: On a 8-way machine run cyclictest: [root@emilia ~]# perf record cyclictest -a -t -n -p99 -i100 -d50 policy: fifo: loadavg: 0.00 0.13 0.31 2/139 28798 T: 0 (28791) P:99 I:100 C: 25072 Min: 4 Act: 5 Avg: 6 Max: 122 T: 1 (28792) P:98 I:150 C: 16715 Min: 4 Act: 6 Avg: 5 Max: 27 T: 2 (28793) P:97 I:200 C: 12534 Min: 4 Act: 5 Avg: 4 Max: 8 T: 3 (28794) P:96 I:250 C: 10028 Min: 4 Act: 5 Avg: 5 Max: 96 T: 4 (28795) P:95 I:300 C: 8357 Min: 5 Act: 6 Avg: 5 Max: 12 T: 5 (28796) P:94 I:350 C: 7163 Min: 5 Act: 6 Avg: 5 Max: 12 T: 6 (28797) P:93 I:400 C: 6267 Min: 4 Act: 5 Avg: 5 Max: 9 T: 7 (28798) P:92 I:450 C: 5571 Min: 4 Act: 5 Avg: 5 Max: 9 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.108 MB perf.data (~4719 samples) ] [root@emilia ~]# This will create one extra thread per CPU: [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28825 OTHER 0 0xff 2169 671 cyclictest 28832 FIFO 93 6 52338 1 cyclictest 28833 FIFO 92 7 46524 1 cyclictest 28826 FIFO 99 0 209360 1 cyclictest 28827 FIFO 98 1 139577 1 cyclictest 28828 FIFO 97 2 104686 0 cyclictest 28829 FIFO 96 3 83751 1 cyclictest 28830 FIFO 95 4 69794 1 cyclictest 28831 FIFO 94 5 59825 1 cyclictest [root@emilia ~]# So we should expect only samples for the above 9 threads when using the --dump-raw-trace|-D perf report switch to look at the column with the tid: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 629 28825 110 28826 491 28827 308 28828 198 28829 621 28830 225 28831 203 28832 89 28833 [root@emilia ~]# So for workloads started by 'perf record' seems to work, now for existing workloads, just run cyclictest first, without 'perf record': [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28859 OTHER 0 0xff 594 200 cyclictest 28864 FIFO 95 4 16587 1 cyclictest 28865 FIFO 94 5 14219 1 cyclictest 28866 FIFO 93 6 12443 0 cyclictest 28867 FIFO 92 7 11062 1 cyclictest 28860 FIFO 99 0 49779 1 cyclictest 28861 FIFO 98 1 33190 1 cyclictest 28862 FIFO 97 2 24895 1 cyclictest 28863 FIFO 96 3 19918 1 cyclictest [root@emilia ~]# and then later did: [root@emilia ~]# perf record --pid 28859 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.027 MB perf.data (~1195 samples) ] [root@emilia ~]# To collect 3 seconds worth of samples for pid 28859 and its children: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 15 28859 33 28860 19 28861 13 28862 13 28863 10 28864 11 28865 9 28866 255 28867 [root@emilia ~]# Works, last thing is to check if looking at just one of those threads also works: [root@emilia ~]# perf record --tid 28866 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.006 MB perf.data (~242 samples) ] [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 3 28866 [root@emilia ~]# Works too. Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: 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: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-10 22:52:47 +08:00
err = 0;
for (thread = 0; thread < threads->nr; ++thread) {
if (__event__synthesize_thread(comm_event, mmap_event,
perf tools: Fix comm for processes with named threads perf does not properly handle monitoring of processes with named threads. For example: $ ps -C myapp -L PID LWP TTY TIME CMD 25118 25118 ? 00:00:00 myapp 25118 25119 ? 00:00:00 myapp:worker perf record -e cs -c 1 -fo /tmp/perf.data -p 25118 -- sleep 10 perf report --stdio -i /tmp/perf.data 100.00% myapp:worker [kernel.kallsyms] [k] perf_event_task_sched_out The process name is set to the name of the last thread it finds for the process. The Problem: perf-top and perf-record both create a thread_map of threads to be monitored. That map is used in perf_event__synthesize_thread_map which loops over the entries in thread_map and calls __event__synthesize_thread to generate COMM and MMAP events. __event__synthesize_thread calls perf_event__synthesize_comm which opens /proc/pid/status, reads the name of the task and its thread group id. That's all fine. The problem is that it then reads /proc/pid/task and generates COMM events for each task it finds - but using the name found in /proc/pid/status where pid is the thread of interest. The end result (looping over thread_map + synthesizing comm events for each thread each time) means the name of the last thread processed sets the name for all threads in the process - which is not good for multithreaded processes with named threads. The Fix: perf_event__synthesize_comm has an input argument (full) that decides whether to process task entries for each pid it is passed. It currently never set to 0 (perf_event__synthesize_comm has a single caller and it always passes the value 1). Let's fix that. Add the full input argument to __event__synthesize_thread which passes it to perf_event__synthesize_comm. For thread/process monitoring set full to 0 which means COMM and MMAP events are only generated for the pid passed to it. For system wide monitoring set full to 1 so that COMM events are generated for all threads in a process. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1324578603-12762-2-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-23 02:30:01 +08:00
threads->map[thread], 0,
process, tool, machine)) {
perf tools: Fix thread_map event synthesizing in top and record Jeff Moyer reported these messages: Warning: ... trying to fall back to cpu-clock-ticks couldn't open /proc/-1/status couldn't open /proc/-1/maps [ls output] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (~363 samples) ] That lead me and David Ahern to see that something was fishy on the thread synthesizing routines, at least for the case where the workload is started from 'perf record', as -1 is the default for target_tid in 'perf record --tid' parameter, so somehow we were trying to synthesize the PERF_RECORD_MMAP and PERF_RECORD_COMM events for the thread -1, a bug. So I investigated this and noticed that when we introduced support for recording a process and its threads using --pid some bugs were introduced and that the way to fix it was to instead of passing the target_tid to the event synthesizing routines we should better pass the thread_map that has the list of threads for a --pid or just the single thread for a --tid. Checked in the following ways: On a 8-way machine run cyclictest: [root@emilia ~]# perf record cyclictest -a -t -n -p99 -i100 -d50 policy: fifo: loadavg: 0.00 0.13 0.31 2/139 28798 T: 0 (28791) P:99 I:100 C: 25072 Min: 4 Act: 5 Avg: 6 Max: 122 T: 1 (28792) P:98 I:150 C: 16715 Min: 4 Act: 6 Avg: 5 Max: 27 T: 2 (28793) P:97 I:200 C: 12534 Min: 4 Act: 5 Avg: 4 Max: 8 T: 3 (28794) P:96 I:250 C: 10028 Min: 4 Act: 5 Avg: 5 Max: 96 T: 4 (28795) P:95 I:300 C: 8357 Min: 5 Act: 6 Avg: 5 Max: 12 T: 5 (28796) P:94 I:350 C: 7163 Min: 5 Act: 6 Avg: 5 Max: 12 T: 6 (28797) P:93 I:400 C: 6267 Min: 4 Act: 5 Avg: 5 Max: 9 T: 7 (28798) P:92 I:450 C: 5571 Min: 4 Act: 5 Avg: 5 Max: 9 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.108 MB perf.data (~4719 samples) ] [root@emilia ~]# This will create one extra thread per CPU: [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28825 OTHER 0 0xff 2169 671 cyclictest 28832 FIFO 93 6 52338 1 cyclictest 28833 FIFO 92 7 46524 1 cyclictest 28826 FIFO 99 0 209360 1 cyclictest 28827 FIFO 98 1 139577 1 cyclictest 28828 FIFO 97 2 104686 0 cyclictest 28829 FIFO 96 3 83751 1 cyclictest 28830 FIFO 95 4 69794 1 cyclictest 28831 FIFO 94 5 59825 1 cyclictest [root@emilia ~]# So we should expect only samples for the above 9 threads when using the --dump-raw-trace|-D perf report switch to look at the column with the tid: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 629 28825 110 28826 491 28827 308 28828 198 28829 621 28830 225 28831 203 28832 89 28833 [root@emilia ~]# So for workloads started by 'perf record' seems to work, now for existing workloads, just run cyclictest first, without 'perf record': [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28859 OTHER 0 0xff 594 200 cyclictest 28864 FIFO 95 4 16587 1 cyclictest 28865 FIFO 94 5 14219 1 cyclictest 28866 FIFO 93 6 12443 0 cyclictest 28867 FIFO 92 7 11062 1 cyclictest 28860 FIFO 99 0 49779 1 cyclictest 28861 FIFO 98 1 33190 1 cyclictest 28862 FIFO 97 2 24895 1 cyclictest 28863 FIFO 96 3 19918 1 cyclictest [root@emilia ~]# and then later did: [root@emilia ~]# perf record --pid 28859 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.027 MB perf.data (~1195 samples) ] [root@emilia ~]# To collect 3 seconds worth of samples for pid 28859 and its children: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 15 28859 33 28860 19 28861 13 28862 13 28863 10 28864 11 28865 9 28866 255 28867 [root@emilia ~]# Works, last thing is to check if looking at just one of those threads also works: [root@emilia ~]# perf record --tid 28866 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.006 MB perf.data (~242 samples) ] [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 3 28866 [root@emilia ~]# Works too. Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: 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: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-10 22:52:47 +08:00
err = -1;
break;
}
perf tools: Fix comm for processes with named threads perf does not properly handle monitoring of processes with named threads. For example: $ ps -C myapp -L PID LWP TTY TIME CMD 25118 25118 ? 00:00:00 myapp 25118 25119 ? 00:00:00 myapp:worker perf record -e cs -c 1 -fo /tmp/perf.data -p 25118 -- sleep 10 perf report --stdio -i /tmp/perf.data 100.00% myapp:worker [kernel.kallsyms] [k] perf_event_task_sched_out The process name is set to the name of the last thread it finds for the process. The Problem: perf-top and perf-record both create a thread_map of threads to be monitored. That map is used in perf_event__synthesize_thread_map which loops over the entries in thread_map and calls __event__synthesize_thread to generate COMM and MMAP events. __event__synthesize_thread calls perf_event__synthesize_comm which opens /proc/pid/status, reads the name of the task and its thread group id. That's all fine. The problem is that it then reads /proc/pid/task and generates COMM events for each task it finds - but using the name found in /proc/pid/status where pid is the thread of interest. The end result (looping over thread_map + synthesizing comm events for each thread each time) means the name of the last thread processed sets the name for all threads in the process - which is not good for multithreaded processes with named threads. The Fix: perf_event__synthesize_comm has an input argument (full) that decides whether to process task entries for each pid it is passed. It currently never set to 0 (perf_event__synthesize_comm has a single caller and it always passes the value 1). Let's fix that. Add the full input argument to __event__synthesize_thread which passes it to perf_event__synthesize_comm. For thread/process monitoring set full to 0 which means COMM and MMAP events are only generated for the pid passed to it. For system wide monitoring set full to 1 so that COMM events are generated for all threads in a process. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1324578603-12762-2-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-23 02:30:01 +08:00
/*
* comm.pid is set to thread group id by
* perf_event__synthesize_comm
*/
if ((int) comm_event->comm.pid != threads->map[thread]) {
bool need_leader = true;
/* is thread group leader in thread_map? */
for (j = 0; j < threads->nr; ++j) {
if ((int) comm_event->comm.pid == threads->map[j]) {
need_leader = false;
break;
}
}
/* if not, generate events for it */
if (need_leader &&
__event__synthesize_thread(comm_event,
mmap_event,
comm_event->comm.pid, 0,
process, tool, machine)) {
err = -1;
break;
}
}
perf tools: Fix thread_map event synthesizing in top and record Jeff Moyer reported these messages: Warning: ... trying to fall back to cpu-clock-ticks couldn't open /proc/-1/status couldn't open /proc/-1/maps [ls output] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (~363 samples) ] That lead me and David Ahern to see that something was fishy on the thread synthesizing routines, at least for the case where the workload is started from 'perf record', as -1 is the default for target_tid in 'perf record --tid' parameter, so somehow we were trying to synthesize the PERF_RECORD_MMAP and PERF_RECORD_COMM events for the thread -1, a bug. So I investigated this and noticed that when we introduced support for recording a process and its threads using --pid some bugs were introduced and that the way to fix it was to instead of passing the target_tid to the event synthesizing routines we should better pass the thread_map that has the list of threads for a --pid or just the single thread for a --tid. Checked in the following ways: On a 8-way machine run cyclictest: [root@emilia ~]# perf record cyclictest -a -t -n -p99 -i100 -d50 policy: fifo: loadavg: 0.00 0.13 0.31 2/139 28798 T: 0 (28791) P:99 I:100 C: 25072 Min: 4 Act: 5 Avg: 6 Max: 122 T: 1 (28792) P:98 I:150 C: 16715 Min: 4 Act: 6 Avg: 5 Max: 27 T: 2 (28793) P:97 I:200 C: 12534 Min: 4 Act: 5 Avg: 4 Max: 8 T: 3 (28794) P:96 I:250 C: 10028 Min: 4 Act: 5 Avg: 5 Max: 96 T: 4 (28795) P:95 I:300 C: 8357 Min: 5 Act: 6 Avg: 5 Max: 12 T: 5 (28796) P:94 I:350 C: 7163 Min: 5 Act: 6 Avg: 5 Max: 12 T: 6 (28797) P:93 I:400 C: 6267 Min: 4 Act: 5 Avg: 5 Max: 9 T: 7 (28798) P:92 I:450 C: 5571 Min: 4 Act: 5 Avg: 5 Max: 9 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.108 MB perf.data (~4719 samples) ] [root@emilia ~]# This will create one extra thread per CPU: [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28825 OTHER 0 0xff 2169 671 cyclictest 28832 FIFO 93 6 52338 1 cyclictest 28833 FIFO 92 7 46524 1 cyclictest 28826 FIFO 99 0 209360 1 cyclictest 28827 FIFO 98 1 139577 1 cyclictest 28828 FIFO 97 2 104686 0 cyclictest 28829 FIFO 96 3 83751 1 cyclictest 28830 FIFO 95 4 69794 1 cyclictest 28831 FIFO 94 5 59825 1 cyclictest [root@emilia ~]# So we should expect only samples for the above 9 threads when using the --dump-raw-trace|-D perf report switch to look at the column with the tid: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 629 28825 110 28826 491 28827 308 28828 198 28829 621 28830 225 28831 203 28832 89 28833 [root@emilia ~]# So for workloads started by 'perf record' seems to work, now for existing workloads, just run cyclictest first, without 'perf record': [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28859 OTHER 0 0xff 594 200 cyclictest 28864 FIFO 95 4 16587 1 cyclictest 28865 FIFO 94 5 14219 1 cyclictest 28866 FIFO 93 6 12443 0 cyclictest 28867 FIFO 92 7 11062 1 cyclictest 28860 FIFO 99 0 49779 1 cyclictest 28861 FIFO 98 1 33190 1 cyclictest 28862 FIFO 97 2 24895 1 cyclictest 28863 FIFO 96 3 19918 1 cyclictest [root@emilia ~]# and then later did: [root@emilia ~]# perf record --pid 28859 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.027 MB perf.data (~1195 samples) ] [root@emilia ~]# To collect 3 seconds worth of samples for pid 28859 and its children: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 15 28859 33 28860 19 28861 13 28862 13 28863 10 28864 11 28865 9 28866 255 28867 [root@emilia ~]# Works, last thing is to check if looking at just one of those threads also works: [root@emilia ~]# perf record --tid 28866 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.006 MB perf.data (~242 samples) ] [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 3 28866 [root@emilia ~]# Works too. Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: 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: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-10 22:52:47 +08:00
}
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
free(mmap_event);
out_free_comm:
free(comm_event);
out:
return err;
}
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine)
{
DIR *proc;
struct dirent dirent, *next;
union perf_event *comm_event, *mmap_event;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
int err = -1;
comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (comm_event == NULL)
goto out;
mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (mmap_event == NULL)
goto out_free_comm;
proc = opendir("/proc");
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (proc == NULL)
goto out_free_mmap;
while (!readdir_r(proc, &dirent, &next) && next) {
char *end;
pid_t pid = strtol(dirent.d_name, &end, 10);
if (*end) /* only interested in proper numerical dirents */
continue;
/*
* We may race with exiting thread, so don't stop just because
* one thread couldn't be synthesized.
*/
__event__synthesize_thread(comm_event, mmap_event, pid, 1,
process, tool, machine);
}
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
err = 0;
closedir(proc);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
out_free_mmap:
free(mmap_event);
out_free_comm:
free(comm_event);
out:
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
struct process_symbol_args {
const char *name;
u64 start;
};
static int find_symbol_cb(void *arg, const char *name, char type,
u64 start)
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
{
struct process_symbol_args *args = arg;
/*
* Must be a function or at least an alias, as in PARISC64, where "_text" is
* an 'A' to the same address as "_stext".
*/
if (!(symbol_type__is_a(type, MAP__FUNCTION) ||
type == 'A') || strcmp(name, args->name))
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
return 0;
args->start = start;
return 1;
}
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine,
const char *symbol_name)
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
{
size_t size;
const char *filename, *mmap_name;
char path[PATH_MAX];
char name_buff[PATH_MAX];
struct map *map;
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
int 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
/*
* We should get this from /sys/kernel/sections/.text, but till that is
* available use this, and after it is use this as a fallback for older
* kernels.
*/
struct process_symbol_args args = { .name = symbol_name, };
union perf_event *event = zalloc((sizeof(event->mmap) +
machine->id_hdr_size));
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
return -1;
}
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
mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
if (machine__is_host(machine)) {
/*
* kernel uses PERF_RECORD_MISC_USER for user space maps,
* see kernel/perf_event.c __perf_event_mmap
*/
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->header.misc = PERF_RECORD_MISC_KERNEL;
filename = "/proc/kallsyms";
} else {
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
if (machine__is_default_guest(machine))
filename = (char *) symbol_conf.default_guest_kallsyms;
else {
sprintf(path, "%s/proc/kallsyms", machine->root_dir);
filename = path;
}
}
if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
free(event);
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
return -ENOENT;
}
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
map = machine->vmlinux_maps[MAP__FUNCTION];
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
"%s%s", mmap_name, symbol_name) + 1;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:01 +08:00
size = PERF_ALIGN(size, sizeof(u64));
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->mmap.header.type = PERF_RECORD_MMAP;
event->mmap.header.size = (sizeof(event->mmap) -
(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
event->mmap.pgoff = args.start;
event->mmap.start = map->start;
event->mmap.len = map->end - event->mmap.start;
event->mmap.pid = machine->pid;
err = process(tool, event, &synth_sample, machine);
perf tools: Ask for ID PERF_SAMPLE_ info on all PERF_RECORD_ events So that we can use -T == --timestamp, asking for PERF_SAMPLE_TIME: $ perf record -aT $ perf report -D | grep PERF_RECORD_ <SNIP> 3 5951915425 0x47530 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff8138c1a2 period: 215979 cpu:3 3 5952026879 0x47588 [0x90]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff810cb480 period: 215979 cpu:3 3 5952059959 0x47618 [0x38]: PERF_RECORD_FORK(6853:6853):(16811:16811) 3 5952138878 0x47650 [0x78]: PERF_RECORD_SAMPLE(IP, 1): 16811/16811: 0xffffffff811bac35 period: 431478 cpu:3 3 5952375068 0x476c8 [0x30]: PERF_RECORD_COMM: find:6853 3 5952395923 0x476f8 [0x50]: PERF_RECORD_MMAP 6853/6853: [0x400000(0x25000) @ 0]: /usr/bin/find 3 5952413756 0x47748 [0xa0]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff810d080f period: 859332 cpu:3 3 5952419837 0x477e8 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44600000(0x21d000) @ 0]: /lib64/ld-2.5.so 3 5952437929 0x47840 [0x48]: PERF_RECORD_MMAP 6853/6853: [0x7fff7e1c9000(0x1000) @ 0x7fff7e1c9000]: [vdso] 3 5952570127 0x47888 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f46200000(0x218000) @ 0]: /lib64/libselinux.so.1 3 5952623637 0x478e0 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44a00000(0x356000) @ 0]: /lib64/libc-2.5.so 3 5952675720 0x47938 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f44e00000(0x204000) @ 0]: /lib64/libdl-2.5.so 3 5952710080 0x47990 [0x58]: PERF_RECORD_MMAP 6853/6853: [0x3f45a00000(0x246000) @ 0]: /lib64/libsepol.so.1 3 5952847802 0x479e8 [0x58]: PERF_RECORD_SAMPLE(IP, 1): 6853/6853: 0xffffffff813897f0 period: 1142536 cpu:3 <SNIP> First column is the cpu and the second the timestamp. That way we can investigate problems in the event stream. If the new perf binary is run on an older kernel, it will disable this feature automatically. Tested-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> LKML-Reference: <1291318772-30880-5-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 20:25:28 +08:00
free(event);
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
}
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
{
return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_comm_event(machine, event);
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_lost_event(machine, event);
}
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
event->mmap.pid, event->mmap.tid, event->mmap.start,
event->mmap.len, event->mmap.pgoff, event->mmap.filename);
}
int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_mmap_event(machine, event);
}
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
{
return fprintf(fp, "(%d:%d):(%d:%d)\n",
event->fork.pid, event->fork.tid,
event->fork.ppid, event->fork.ptid);
}
int perf_event__process_fork(struct perf_tool *tool __maybe_unused,
union perf_event *event,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_fork_event(machine, event);
}
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_exit_event(machine, event);
}
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
perf_event__name(event->header.type));
switch (event->header.type) {
case PERF_RECORD_COMM:
ret += perf_event__fprintf_comm(event, fp);
break;
case PERF_RECORD_FORK:
case PERF_RECORD_EXIT:
ret += perf_event__fprintf_task(event, fp);
break;
case PERF_RECORD_MMAP:
ret += perf_event__fprintf_mmap(event, fp);
break;
default:
ret += fprintf(fp, "\n");
}
return ret;
}
int perf_event__process(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return machine__process_event(machine, event);
}
void thread__find_addr_map(struct thread *self,
struct machine *machine, u8 cpumode,
enum map_type type, u64 addr,
struct addr_location *al)
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
{
struct map_groups *mg = &self->mg;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->thread = self;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->addr = addr;
al->cpumode = cpumode;
al->filtered = false;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
if (machine == NULL) {
al->map = NULL;
return;
}
if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->level = 'k';
mg = &machine->kmaps;
} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->level = '.';
} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
al->level = 'g';
mg = &machine->kmaps;
} else {
/*
* 'u' means guest os user space.
* TODO: We don't support guest user space. Might support late.
*/
if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
al->level = 'u';
else
al->level = 'H';
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->map = NULL;
if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
!perf_guest)
al->filtered = true;
if ((cpumode == PERF_RECORD_MISC_USER ||
cpumode == PERF_RECORD_MISC_KERNEL) &&
!perf_host)
al->filtered = true;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
return;
}
try_again:
al->map = map_groups__find(mg, type, al->addr);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
if (al->map == NULL) {
/*
* If this is outside of all known maps, and is a negative
* address, try to look it up in the kernel dso, as it might be
* a vsyscall or vdso (which executes in user-mode).
*
* XXX This is nasty, we should have a symbol list in the
* "[vdso]" dso, but for now lets use the old trick of looking
* in the whole kernel symbol list.
*/
if ((long long)al->addr < 0 &&
cpumode == PERF_RECORD_MISC_USER &&
machine && mg != &machine->kmaps) {
mg = &machine->kmaps;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
goto try_again;
}
} else
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
al->addr = al->map->map_ip(al->map, al->addr);
}
void thread__find_addr_location(struct thread *thread, struct machine *machine,
u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
{
thread__find_addr_map(thread, machine, cpumode, type, addr, al);
if (al->map != NULL)
al->sym = map__find_symbol(al->map, al->addr, filter);
else
al->sym = NULL;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
}
int perf_event__preprocess_sample(const union perf_event *event,
struct machine *machine,
struct addr_location *al,
struct perf_sample *sample,
symbol_filter_t filter)
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
{
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
if (thread == NULL)
return -1;
if (symbol_conf.comm_list &&
!strlist__has_entry(symbol_conf.comm_list, thread->comm))
goto out_filtered;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
/*
* Have we already created the kernel maps for this machine?
*
* This should have happened earlier, when we processed the kernel MMAP
* events, but for older perf.data files there was no such thing, so do
* it now.
*/
if (cpumode == PERF_RECORD_MISC_KERNEL &&
machine->vmlinux_maps[MAP__FUNCTION] == NULL)
machine__create_kernel_maps(machine);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
event->ip.ip, al);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
dump_printf(" ...... dso: %s\n",
al->map ? al->map->dso->long_name :
al->level == 'H' ? "[hypervisor]" : "<not found>");
al->sym = NULL;
al->cpu = sample->cpu;
if (al->map) {
struct dso *dso = al->map->dso;
if (symbol_conf.dso_list &&
(!dso || !(strlist__has_entry(symbol_conf.dso_list,
dso->short_name) ||
(dso->short_name != dso->long_name &&
strlist__has_entry(symbol_conf.dso_list,
dso->long_name)))))
goto out_filtered;
al->sym = map__find_symbol(al->map, al->addr, filter);
}
if (symbol_conf.sym_list &&
(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
al->sym->name)))
goto out_filtered;
return 0;
out_filtered:
al->filtered = true;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
return 0;
}