WSL2-Linux-Kernel/tools/perf/builtin-trace.c

3478 строки
97 KiB
C

/*
* builtin-trace.c
*
* Builtin 'trace' command:
*
* Display a continuously updated trace of any workload, CPU, specific PID,
* system wide, etc. Default format is loosely strace like, but any other
* event may be specified using --event.
*
* Copyright (C) 2012, 2013, 2014, 2015 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Initially based on the 'trace' prototype by Thomas Gleixner:
*
* http://lwn.net/Articles/415728/ ("Announcing a new utility: 'trace'")
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include <traceevent/event-parse.h>
#include <api/fs/tracing_path.h>
#include "builtin.h"
#include "util/cgroup.h"
#include "util/color.h"
#include "util/debug.h"
#include "util/env.h"
#include "util/event.h"
#include "util/evlist.h"
#include <subcmd/exec-cmd.h>
#include "util/machine.h"
#include "util/path.h"
#include "util/session.h"
#include "util/thread.h"
#include <subcmd/parse-options.h>
#include "util/strlist.h"
#include "util/intlist.h"
#include "util/thread_map.h"
#include "util/stat.h"
#include "trace/beauty/beauty.h"
#include "trace-event.h"
#include "util/parse-events.h"
#include "util/bpf-loader.h"
#include "callchain.h"
#include "print_binary.h"
#include "string2.h"
#include "syscalltbl.h"
#include "rb_resort.h"
#include <errno.h>
#include <inttypes.h>
#include <poll.h>
#include <signal.h>
#include <stdlib.h>
#include <string.h>
#include <linux/err.h>
#include <linux/filter.h>
#include <linux/kernel.h>
#include <linux/random.h>
#include <linux/stringify.h>
#include <linux/time64.h>
#include <fcntl.h>
#include "sane_ctype.h"
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#endif
#ifndef F_LINUX_SPECIFIC_BASE
# define F_LINUX_SPECIFIC_BASE 1024
#endif
struct trace {
struct perf_tool tool;
struct syscalltbl *sctbl;
struct {
int max;
struct syscall *table;
struct {
struct perf_evsel *sys_enter,
*sys_exit,
*augmented;
} events;
} syscalls;
struct record_opts opts;
struct perf_evlist *evlist;
struct machine *host;
struct thread *current;
struct cgroup *cgroup;
u64 base_time;
FILE *output;
unsigned long nr_events;
struct strlist *ev_qualifier;
struct {
size_t nr;
int *entries;
} ev_qualifier_ids;
struct {
size_t nr;
pid_t *entries;
} filter_pids;
double duration_filter;
double runtime_ms;
struct {
u64 vfs_getname,
proc_getname;
} stats;
unsigned int max_stack;
unsigned int min_stack;
bool not_ev_qualifier;
bool live;
bool full_time;
bool sched;
bool multiple_threads;
bool summary;
bool summary_only;
bool failure_only;
bool show_comm;
bool print_sample;
bool show_tool_stats;
bool trace_syscalls;
bool kernel_syscallchains;
bool force;
bool vfs_getname;
int trace_pgfaults;
};
struct tp_field {
int offset;
union {
u64 (*integer)(struct tp_field *field, struct perf_sample *sample);
void *(*pointer)(struct tp_field *field, struct perf_sample *sample);
};
};
#define TP_UINT_FIELD(bits) \
static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
u##bits value; \
memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
return value; \
}
TP_UINT_FIELD(8);
TP_UINT_FIELD(16);
TP_UINT_FIELD(32);
TP_UINT_FIELD(64);
#define TP_UINT_FIELD__SWAPPED(bits) \
static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
u##bits value; \
memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
return bswap_##bits(value);\
}
TP_UINT_FIELD__SWAPPED(16);
TP_UINT_FIELD__SWAPPED(32);
TP_UINT_FIELD__SWAPPED(64);
static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap)
{
field->offset = offset;
switch (size) {
case 1:
field->integer = tp_field__u8;
break;
case 2:
field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16;
break;
case 4:
field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32;
break;
case 8:
field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64;
break;
default:
return -1;
}
return 0;
}
static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap)
{
return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
}
static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
{
return sample->raw_data + field->offset;
}
static int __tp_field__init_ptr(struct tp_field *field, int offset)
{
field->offset = offset;
field->pointer = tp_field__ptr;
return 0;
}
static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field)
{
return __tp_field__init_ptr(field, format_field->offset);
}
struct syscall_tp {
struct tp_field id;
union {
struct tp_field args, ret;
};
};
static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
struct tp_field *field,
const char *name)
{
struct tep_format_field *format_field = perf_evsel__field(evsel, name);
if (format_field == NULL)
return -1;
return tp_field__init_uint(field, format_field, evsel->needs_swap);
}
#define perf_evsel__init_sc_tp_uint_field(evsel, name) \
({ struct syscall_tp *sc = evsel->priv;\
perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
struct tp_field *field,
const char *name)
{
struct tep_format_field *format_field = perf_evsel__field(evsel, name);
if (format_field == NULL)
return -1;
return tp_field__init_ptr(field, format_field);
}
#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
({ struct syscall_tp *sc = evsel->priv;\
perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
static void perf_evsel__delete_priv(struct perf_evsel *evsel)
{
zfree(&evsel->priv);
perf_evsel__delete(evsel);
}
static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel)
{
struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
if (evsel->priv != NULL) {
if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr"))
goto out_delete;
return 0;
}
return -ENOMEM;
out_delete:
zfree(&evsel->priv);
return -ENOENT;
}
static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel)
{
struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
if (evsel->priv != NULL) { /* field, sizeof_field, offsetof_field */
if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap))
goto out_delete;
return 0;
}
return -ENOMEM;
out_delete:
zfree(&evsel->priv);
return -EINVAL;
}
static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
{
struct syscall_tp *sc = evsel->priv;
return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
}
static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
{
struct syscall_tp *sc = evsel->priv;
return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
}
static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
{
evsel->priv = malloc(sizeof(struct syscall_tp));
if (evsel->priv != NULL) {
if (perf_evsel__init_sc_tp_uint_field(evsel, id))
goto out_delete;
evsel->handler = handler;
return 0;
}
return -ENOMEM;
out_delete:
zfree(&evsel->priv);
return -ENOENT;
}
static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler)
{
struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
if (IS_ERR(evsel))
evsel = perf_evsel__newtp("syscalls", direction);
if (IS_ERR(evsel))
return NULL;
if (perf_evsel__init_raw_syscall_tp(evsel, handler))
goto out_delete;
return evsel;
out_delete:
perf_evsel__delete_priv(evsel);
return NULL;
}
#define perf_evsel__sc_tp_uint(evsel, name, sample) \
({ struct syscall_tp *fields = evsel->priv; \
fields->name.integer(&fields->name, sample); })
#define perf_evsel__sc_tp_ptr(evsel, name, sample) \
({ struct syscall_tp *fields = evsel->priv; \
fields->name.pointer(&fields->name, sample); })
size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val)
{
int idx = val - sa->offset;
if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
return scnprintf(bf, size, intfmt, val);
return scnprintf(bf, size, "%s", sa->entries[idx]);
}
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
const char *intfmt,
struct syscall_arg *arg)
{
return strarray__scnprintf(arg->parm, bf, size, intfmt, arg->val);
}
static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
struct syscall_arg *arg)
{
return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg);
}
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
struct strarrays {
int nr_entries;
struct strarray **entries;
};
#define DEFINE_STRARRAYS(array) struct strarrays strarrays__##array = { \
.nr_entries = ARRAY_SIZE(array), \
.entries = array, \
}
size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size,
struct syscall_arg *arg)
{
struct strarrays *sas = arg->parm;
int i;
for (i = 0; i < sas->nr_entries; ++i) {
struct strarray *sa = sas->entries[i];
int idx = arg->val - sa->offset;
if (idx >= 0 && idx < sa->nr_entries) {
if (sa->entries[idx] == NULL)
break;
return scnprintf(bf, size, "%s", sa->entries[idx]);
}
}
return scnprintf(bf, size, "%d", arg->val);
}
#ifndef AT_FDCWD
#define AT_FDCWD -100
#endif
static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
struct syscall_arg *arg)
{
int fd = arg->val;
if (fd == AT_FDCWD)
return scnprintf(bf, size, "CWD");
return syscall_arg__scnprintf_fd(bf, size, arg);
}
#define SCA_FDAT syscall_arg__scnprintf_fd_at
static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
struct syscall_arg *arg);
#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg)
{
return scnprintf(bf, size, "%#lx", arg->val);
}
size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg)
{
return scnprintf(bf, size, "%d", arg->val);
}
size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg)
{
return scnprintf(bf, size, "%ld", arg->val);
}
static const char *bpf_cmd[] = {
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
"MAP_GET_NEXT_KEY", "PROG_LOAD",
};
static DEFINE_STRARRAY(bpf_cmd);
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
static DEFINE_STRARRAY(itimers);
static const char *keyctl_options[] = {
"GET_KEYRING_ID", "JOIN_SESSION_KEYRING", "UPDATE", "REVOKE", "CHOWN",
"SETPERM", "DESCRIBE", "CLEAR", "LINK", "UNLINK", "SEARCH", "READ",
"INSTANTIATE", "NEGATE", "SET_REQKEY_KEYRING", "SET_TIMEOUT",
"ASSUME_AUTHORITY", "GET_SECURITY", "SESSION_TO_PARENT", "REJECT",
"INSTANTIATE_IOV", "INVALIDATE", "GET_PERSISTENT",
};
static DEFINE_STRARRAY(keyctl_options);
static const char *whences[] = { "SET", "CUR", "END",
#ifdef SEEK_DATA
"DATA",
#endif
#ifdef SEEK_HOLE
"HOLE",
#endif
};
static DEFINE_STRARRAY(whences);
static const char *fcntl_cmds[] = {
"DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
"SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "GETLK64",
"SETLK64", "SETLKW64", "SETOWN_EX", "GETOWN_EX",
"GETOWNER_UIDS",
};
static DEFINE_STRARRAY(fcntl_cmds);
static const char *fcntl_linux_specific_cmds[] = {
"SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
"SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
"GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
};
static DEFINE_STRARRAY_OFFSET(fcntl_linux_specific_cmds, F_LINUX_SPECIFIC_BASE);
static struct strarray *fcntl_cmds_arrays[] = {
&strarray__fcntl_cmds,
&strarray__fcntl_linux_specific_cmds,
};
static DEFINE_STRARRAYS(fcntl_cmds_arrays);
static const char *rlimit_resources[] = {
"CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
"MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
"RTTIME",
};
static DEFINE_STRARRAY(rlimit_resources);
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
static DEFINE_STRARRAY(sighow);
static const char *clockid[] = {
"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE", "BOOTTIME",
"REALTIME_ALARM", "BOOTTIME_ALARM", "SGI_CYCLE", "TAI"
};
static DEFINE_STRARRAY(clockid);
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
struct syscall_arg *arg)
{
size_t printed = 0;
int mode = arg->val;
if (mode == F_OK) /* 0 */
return scnprintf(bf, size, "F");
#define P_MODE(n) \
if (mode & n##_OK) { \
printed += scnprintf(bf + printed, size - printed, "%s", #n); \
mode &= ~n##_OK; \
}
P_MODE(R);
P_MODE(W);
P_MODE(X);
#undef P_MODE
if (mode)
printed += scnprintf(bf + printed, size - printed, "|%#x", mode);
return printed;
}
#define SCA_ACCMODE syscall_arg__scnprintf_access_mode
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
struct syscall_arg *arg);
#define SCA_FILENAME syscall_arg__scnprintf_filename
static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
#define P_FLAG(n) \
if (flags & O_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~O_##n; \
}
P_FLAG(CLOEXEC);
P_FLAG(NONBLOCK);
#undef P_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
#ifndef GRND_NONBLOCK
#define GRND_NONBLOCK 0x0001
#endif
#ifndef GRND_RANDOM
#define GRND_RANDOM 0x0002
#endif
static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
#define P_FLAG(n) \
if (flags & GRND_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~GRND_##n; \
}
P_FLAG(RANDOM);
P_FLAG(NONBLOCK);
#undef P_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags
#define STRARRAY(name, array) \
{ .scnprintf = SCA_STRARRAY, \
.parm = &strarray__##array, }
#include "trace/beauty/arch_errno_names.c"
#include "trace/beauty/eventfd.c"
#include "trace/beauty/futex_op.c"
#include "trace/beauty/futex_val3.c"
#include "trace/beauty/mmap.c"
#include "trace/beauty/mode_t.c"
#include "trace/beauty/msg_flags.c"
#include "trace/beauty/open_flags.c"
#include "trace/beauty/perf_event_open.c"
#include "trace/beauty/pid.c"
#include "trace/beauty/sched_policy.c"
#include "trace/beauty/seccomp.c"
#include "trace/beauty/signum.c"
#include "trace/beauty/socket_type.c"
#include "trace/beauty/waitid_options.c"
struct syscall_arg_fmt {
size_t (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
void *parm;
const char *name;
bool show_zero;
};
static struct syscall_fmt {
const char *name;
const char *alias;
struct syscall_arg_fmt arg[6];
u8 nr_args;
bool errpid;
bool timeout;
bool hexret;
} syscall_fmts[] = {
{ .name = "access",
.arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, },
{ .name = "bind",
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
{ .name = "bpf",
.arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
{ .name = "brk", .hexret = true,
.arg = { [0] = { .scnprintf = SCA_HEX, /* brk */ }, }, },
{ .name = "clock_gettime",
.arg = { [0] = STRARRAY(clk_id, clockid), }, },
{ .name = "clone", .errpid = true, .nr_args = 5,
.arg = { [0] = { .name = "flags", .scnprintf = SCA_CLONE_FLAGS, },
[1] = { .name = "child_stack", .scnprintf = SCA_HEX, },
[2] = { .name = "parent_tidptr", .scnprintf = SCA_HEX, },
[3] = { .name = "child_tidptr", .scnprintf = SCA_HEX, },
[4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, },
{ .name = "close",
.arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
{ .name = "connect",
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
{ .name = "epoll_ctl",
.arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
{ .name = "eventfd2",
.arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, },
{ .name = "fchmodat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "fchownat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "fcntl",
.arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */
.parm = &strarrays__fcntl_cmds_arrays,
.show_zero = true, },
[2] = { .scnprintf = SCA_FCNTL_ARG, /* arg */ }, }, },
{ .name = "flock",
.arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
{ .name = "fstat", .alias = "newfstat", },
{ .name = "fstatat", .alias = "newfstatat", },
{ .name = "futex",
.arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ },
[5] = { .scnprintf = SCA_FUTEX_VAL3, /* val3 */ }, }, },
{ .name = "futimesat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "getitimer",
.arg = { [0] = STRARRAY(which, itimers), }, },
{ .name = "getpid", .errpid = true, },
{ .name = "getpgid", .errpid = true, },
{ .name = "getppid", .errpid = true, },
{ .name = "getrandom",
.arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
{ .name = "getrlimit",
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
{ .name = "gettid", .errpid = true, },
{ .name = "ioctl",
.arg = {
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
*/
[1] = { .scnprintf = SCA_IOCTL_CMD, /* cmd */ },
[2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
#else
[2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
#endif
{ .name = "kcmp", .nr_args = 5,
.arg = { [0] = { .name = "pid1", .scnprintf = SCA_PID, },
[1] = { .name = "pid2", .scnprintf = SCA_PID, },
[2] = { .name = "type", .scnprintf = SCA_KCMP_TYPE, },
[3] = { .name = "idx1", .scnprintf = SCA_KCMP_IDX, },
[4] = { .name = "idx2", .scnprintf = SCA_KCMP_IDX, }, }, },
{ .name = "keyctl",
.arg = { [0] = STRARRAY(option, keyctl_options), }, },
{ .name = "kill",
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "linkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "lseek",
.arg = { [2] = STRARRAY(whence, whences), }, },
{ .name = "lstat", .alias = "newlstat", },
{ .name = "madvise",
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
[2] = { .scnprintf = SCA_MADV_BHV, /* behavior */ }, }, },
{ .name = "mkdirat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "mknodat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
{ .name = "mlock",
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
{ .name = "mlockall",
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
{ .name = "mmap", .hexret = true,
/* The standard mmap maps to old_mmap on s390x */
#if defined(__s390x__)
.alias = "old_mmap",
#endif
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ },
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ },
[3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ }, }, },
{ .name = "mprotect",
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, }, },
{ .name = "mq_unlink",
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* u_name */ }, }, },
{ .name = "mremap", .hexret = true,
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ },
[3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ },
[4] = { .scnprintf = SCA_HEX, /* new_addr */ }, }, },
{ .name = "munlock",
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
{ .name = "munmap",
.arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
{ .name = "name_to_handle_at",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "newfstatat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "open",
.arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
{ .name = "open_by_handle_at",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
[2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
{ .name = "openat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
[2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
{ .name = "perf_event_open",
.arg = { [2] = { .scnprintf = SCA_INT, /* cpu */ },
[3] = { .scnprintf = SCA_FD, /* group_fd */ },
[4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
{ .name = "pipe2",
.arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, },
{ .name = "pkey_alloc",
.arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS, /* access_rights */ }, }, },
{ .name = "pkey_free",
.arg = { [0] = { .scnprintf = SCA_INT, /* key */ }, }, },
{ .name = "pkey_mprotect",
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ },
[3] = { .scnprintf = SCA_INT, /* pkey */ }, }, },
{ .name = "poll", .timeout = true, },
{ .name = "ppoll", .timeout = true, },
{ .name = "prctl", .alias = "arch_prctl",
.arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
[1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
[2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
{ .name = "pread", .alias = "pread64", },
{ .name = "preadv", .alias = "pread", },
{ .name = "prlimit64",
.arg = { [1] = STRARRAY(resource, rlimit_resources), }, },
{ .name = "pwrite", .alias = "pwrite64", },
{ .name = "readlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "recvfrom",
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "recvmmsg",
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "recvmsg",
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "renameat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "rt_sigaction",
.arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "rt_sigprocmask",
.arg = { [0] = STRARRAY(how, sighow), }, },
{ .name = "rt_sigqueueinfo",
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "rt_tgsigqueueinfo",
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "sched_setscheduler",
.arg = { [1] = { .scnprintf = SCA_SCHED_POLICY, /* policy */ }, }, },
{ .name = "seccomp",
.arg = { [0] = { .scnprintf = SCA_SECCOMP_OP, /* op */ },
[1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, },
{ .name = "select", .timeout = true, },
{ .name = "sendmmsg",
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "sendmsg",
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "sendto",
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
[4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
{ .name = "set_tid_address", .errpid = true, },
{ .name = "setitimer",
.arg = { [0] = STRARRAY(which, itimers), }, },
{ .name = "setrlimit",
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
{ .name = "socket",
.arg = { [0] = STRARRAY(family, socket_families),
[1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
[2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "socketpair",
.arg = { [0] = STRARRAY(family, socket_families),
[1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
[2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "stat", .alias = "newstat", },
{ .name = "statx",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ },
[2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } ,
[3] = { .scnprintf = SCA_STATX_MASK, /* mask */ }, }, },
{ .name = "swapoff",
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
{ .name = "swapon",
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
{ .name = "symlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "tgkill",
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "tkill",
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "umount2", .alias = "umount", },
{ .name = "uname", .alias = "newuname", },
{ .name = "unlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
{ .name = "utimensat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, },
{ .name = "wait4", .errpid = true,
.arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
{ .name = "waitid", .errpid = true,
.arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
};
static int syscall_fmt__cmp(const void *name, const void *fmtp)
{
const struct syscall_fmt *fmt = fmtp;
return strcmp(name, fmt->name);
}
static struct syscall_fmt *syscall_fmt__find(const char *name)
{
const int nmemb = ARRAY_SIZE(syscall_fmts);
return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
}
/*
* is_exit: is this "exit" or "exit_group"?
* is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
* args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
*/
struct syscall {
struct tep_event_format *tp_format;
int nr_args;
int args_size;
bool is_exit;
bool is_open;
struct tep_format_field *args;
const char *name;
struct syscall_fmt *fmt;
struct syscall_arg_fmt *arg_fmt;
};
/*
* We need to have this 'calculated' boolean because in some cases we really
* don't know what is the duration of a syscall, for instance, when we start
* a session and some threads are waiting for a syscall to finish, say 'poll',
* in which case all we can do is to print "( ? ) for duration and for the
* start timestamp.
*/
static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
{
double duration = (double)t / NSEC_PER_MSEC;
size_t printed = fprintf(fp, "(");
if (!calculated)
printed += fprintf(fp, " ");
else if (duration >= 1.0)
printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
else if (duration >= 0.01)
printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
else
printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration);
return printed + fprintf(fp, "): ");
}
/**
* filename.ptr: The filename char pointer that will be vfs_getname'd
* filename.entry_str_pos: Where to insert the string translated from
* filename.ptr by the vfs_getname tracepoint/kprobe.
* ret_scnprintf: syscall args may set this to a different syscall return
* formatter, for instance, fcntl may return fds, file flags, etc.
*/
struct thread_trace {
u64 entry_time;
bool entry_pending;
unsigned long nr_events;
unsigned long pfmaj, pfmin;
char *entry_str;
double runtime_ms;
size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
struct {
unsigned long ptr;
short int entry_str_pos;
bool pending_open;
unsigned int namelen;
char *name;
} filename;
struct {
int max;
char **table;
} paths;
struct intlist *syscall_stats;
};
static struct thread_trace *thread_trace__new(void)
{
struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace));
if (ttrace)
ttrace->paths.max = -1;
ttrace->syscall_stats = intlist__new(NULL);
return ttrace;
}
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
{
struct thread_trace *ttrace;
if (thread == NULL)
goto fail;
if (thread__priv(thread) == NULL)
thread__set_priv(thread, thread_trace__new());
if (thread__priv(thread) == NULL)
goto fail;
ttrace = thread__priv(thread);
++ttrace->nr_events;
return ttrace;
fail:
color_fprintf(fp, PERF_COLOR_RED,
"WARNING: not enough memory, dropping samples!\n");
return NULL;
}
void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg))
{
struct thread_trace *ttrace = thread__priv(arg->thread);
ttrace->ret_scnprintf = ret_scnprintf;
}
#define TRACE_PFMAJ (1 << 0)
#define TRACE_PFMIN (1 << 1)
static const size_t trace__entry_str_size = 2048;
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
{
struct thread_trace *ttrace = thread__priv(thread);
if (fd > ttrace->paths.max) {
char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
if (npath == NULL)
return -1;
if (ttrace->paths.max != -1) {
memset(npath + ttrace->paths.max + 1, 0,
(fd - ttrace->paths.max) * sizeof(char *));
} else {
memset(npath, 0, (fd + 1) * sizeof(char *));
}
ttrace->paths.table = npath;
ttrace->paths.max = fd;
}
ttrace->paths.table[fd] = strdup(pathname);
return ttrace->paths.table[fd] != NULL ? 0 : -1;
}
static int thread__read_fd_path(struct thread *thread, int fd)
{
char linkname[PATH_MAX], pathname[PATH_MAX];
struct stat st;
int ret;
if (thread->pid_ == thread->tid) {
scnprintf(linkname, sizeof(linkname),
"/proc/%d/fd/%d", thread->pid_, fd);
} else {
scnprintf(linkname, sizeof(linkname),
"/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
}
if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
return -1;
ret = readlink(linkname, pathname, sizeof(pathname));
if (ret < 0 || ret > st.st_size)
return -1;
pathname[ret] = '\0';
return trace__set_fd_pathname(thread, fd, pathname);
}
static const char *thread__fd_path(struct thread *thread, int fd,
struct trace *trace)
{
struct thread_trace *ttrace = thread__priv(thread);
if (ttrace == NULL)
return NULL;
if (fd < 0)
return NULL;
if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
if (!trace->live)
return NULL;
++trace->stats.proc_getname;
if (thread__read_fd_path(thread, fd))
return NULL;
}
return ttrace->paths.table[fd];
}
size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
{
int fd = arg->val;
size_t printed = scnprintf(bf, size, "%d", fd);
const char *path = thread__fd_path(arg->thread, fd, arg->trace);
if (path)
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
return printed;
}
size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size)
{
size_t printed = scnprintf(bf, size, "%d", fd);
struct thread *thread = machine__find_thread(trace->host, pid, pid);
if (thread) {
const char *path = thread__fd_path(thread, fd, trace);
if (path)
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
thread__put(thread);
}
return printed;
}
static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
struct syscall_arg *arg)
{
int fd = arg->val;
size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
struct thread_trace *ttrace = thread__priv(arg->thread);
if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
zfree(&ttrace->paths.table[fd]);
return printed;
}
static void thread__set_filename_pos(struct thread *thread, const char *bf,
unsigned long ptr)
{
struct thread_trace *ttrace = thread__priv(thread);
ttrace->filename.ptr = ptr;
ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
}
static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
{
struct augmented_arg *augmented_arg = arg->augmented.args;
return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
}
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
struct syscall_arg *arg)
{
unsigned long ptr = arg->val;
if (arg->augmented.args)
return syscall_arg__scnprintf_augmented_string(arg, bf, size);
if (!arg->trace->vfs_getname)
return scnprintf(bf, size, "%#x", ptr);
thread__set_filename_pos(arg->thread, bf, ptr);
return 0;
}
static bool trace__filter_duration(struct trace *trace, double t)
{
return t < (trace->duration_filter * NSEC_PER_MSEC);
}
static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
return fprintf(fp, "%10.3f ", ts);
}
/*
* We're handling tstamp=0 as an undefined tstamp, i.e. like when we are
* using ttrace->entry_time for a thread that receives a sys_exit without
* first having received a sys_enter ("poll" issued before tracing session
* starts, lost sys_enter exit due to ring buffer overflow).
*/
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
if (tstamp > 0)
return __trace__fprintf_tstamp(trace, tstamp, fp);
return fprintf(fp, " ? ");
}
static bool done = false;
static bool interrupted = false;
static void sig_handler(int sig)
{
done = true;
interrupted = sig == SIGINT;
}
static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
{
size_t printed = 0;
if (trace->multiple_threads) {
if (trace->show_comm)
printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
printed += fprintf(fp, "%d ", thread->tid);
}
return printed;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
{
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
printed += fprintf_duration(duration, duration_calculated, fp);
return printed + trace__fprintf_comm_tid(trace, thread, fp);
}
static int trace__process_event(struct trace *trace, struct machine *machine,
union perf_event *event, struct perf_sample *sample)
{
int ret = 0;
switch (event->header.type) {
case PERF_RECORD_LOST:
color_fprintf(trace->output, PERF_COLOR_RED,
"LOST %" PRIu64 " events!\n", event->lost.lost);
ret = machine__process_lost_event(machine, event, sample);
break;
default:
ret = machine__process_event(machine, event, sample);
break;
}
return ret;
}
static int trace__tool_process(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
struct trace *trace = container_of(tool, struct trace, tool);
return trace__process_event(trace, machine, event, sample);
}
static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
{
struct machine *machine = vmachine;
if (machine->kptr_restrict_warned)
return NULL;
if (symbol_conf.kptr_restrict) {
pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
"Check /proc/sys/kernel/kptr_restrict.\n\n"
"Kernel samples will not be resolved.\n");
machine->kptr_restrict_warned = true;
return NULL;
}
return machine__resolve_kernel_addr(vmachine, addrp, modp);
}
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
{
int err = symbol__init(NULL);
if (err)
return err;
trace->host = machine__new_host();
if (trace->host == NULL)
return -ENOMEM;
err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
if (err < 0)
goto out;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
evlist->threads, trace__tool_process, false,
trace->opts.proc_map_timeout, 1);
out:
if (err)
symbol__exit();
return err;
}
static void trace__symbols__exit(struct trace *trace)
{
machine__exit(trace->host);
trace->host = NULL;
symbol__exit();
}
static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
{
int idx;
if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
nr_args = sc->fmt->nr_args;
sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
if (sc->arg_fmt == NULL)
return -1;
for (idx = 0; idx < nr_args; ++idx) {
if (sc->fmt)
sc->arg_fmt[idx] = sc->fmt->arg[idx];
}
sc->nr_args = nr_args;
return 0;
}
static int syscall__set_arg_fmts(struct syscall *sc)
{
struct tep_format_field *field, *last_field = NULL;
int idx = 0, len;
for (field = sc->args; field; field = field->next, ++idx) {
last_field = field;
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
continue;
if (strcmp(field->type, "const char *") == 0 &&
(strcmp(field->name, "filename") == 0 ||
strcmp(field->name, "path") == 0 ||
strcmp(field->name, "pathname") == 0))
sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
else if (field->flags & TEP_FIELD_IS_POINTER)
sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
else if (strcmp(field->type, "pid_t") == 0)
sc->arg_fmt[idx].scnprintf = SCA_PID;
else if (strcmp(field->type, "umode_t") == 0)
sc->arg_fmt[idx].scnprintf = SCA_MODE_T;
else if ((strcmp(field->type, "int") == 0 ||
strcmp(field->type, "unsigned int") == 0 ||
strcmp(field->type, "long") == 0) &&
(len = strlen(field->name)) >= 2 &&
strcmp(field->name + len - 2, "fd") == 0) {
/*
* /sys/kernel/tracing/events/syscalls/sys_enter*
* egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
* 65 int
* 23 unsigned int
* 7 unsigned long
*/
sc->arg_fmt[idx].scnprintf = SCA_FD;
}
}
if (last_field)
sc->args_size = last_field->offset + last_field->size;
return 0;
}
static int trace__read_syscall_info(struct trace *trace, int id)
{
char tp_name[128];
struct syscall *sc;
const char *name = syscalltbl__name(trace->sctbl, id);
if (name == NULL)
return -1;
if (id > trace->syscalls.max) {
struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
if (nsyscalls == NULL)
return -1;
if (trace->syscalls.max != -1) {
memset(nsyscalls + trace->syscalls.max + 1, 0,
(id - trace->syscalls.max) * sizeof(*sc));
} else {
memset(nsyscalls, 0, (id + 1) * sizeof(*sc));
}
trace->syscalls.table = nsyscalls;
trace->syscalls.max = id;
}
sc = trace->syscalls.table + id;
sc->name = name;
sc->fmt = syscall_fmt__find(sc->name);
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
if (IS_ERR(sc->tp_format) && sc->fmt && sc->fmt->alias) {
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
}
if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
return -1;
if (IS_ERR(sc->tp_format))
return -1;
sc->args = sc->tp_format->format.fields;
/*
* We need to check and discard the first variable '__syscall_nr'
* or 'nr' that mean the syscall number. It is needless here.
* So drop '__syscall_nr' or 'nr' field but does not exist on older kernels.
*/
if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) {
sc->args = sc->args->next;
--sc->nr_args;
}
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat");
return syscall__set_arg_fmts(sc);
}
static int trace__validate_ev_qualifier(struct trace *trace)
{
int err = 0, i;
size_t nr_allocated;
struct str_node *pos;
trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
trace->ev_qualifier_ids.entries = malloc(trace->ev_qualifier_ids.nr *
sizeof(trace->ev_qualifier_ids.entries[0]));
if (trace->ev_qualifier_ids.entries == NULL) {
fputs("Error:\tNot enough memory for allocating events qualifier ids\n",
trace->output);
err = -EINVAL;
goto out;
}
nr_allocated = trace->ev_qualifier_ids.nr;
i = 0;
strlist__for_each_entry(pos, trace->ev_qualifier) {
const char *sc = pos->s;
int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
if (id < 0) {
id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
if (id >= 0)
goto matches;
if (err == 0) {
fputs("Error:\tInvalid syscall ", trace->output);
err = -EINVAL;
} else {
fputs(", ", trace->output);
}
fputs(sc, trace->output);
}
matches:
trace->ev_qualifier_ids.entries[i++] = id;
if (match_next == -1)
continue;
while (1) {
id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
if (id < 0)
break;
if (nr_allocated == trace->ev_qualifier_ids.nr) {
void *entries;
nr_allocated += 8;
entries = realloc(trace->ev_qualifier_ids.entries,
nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
if (entries == NULL) {
err = -ENOMEM;
fputs("\nError:\t Not enough memory for parsing\n", trace->output);
goto out_free;
}
trace->ev_qualifier_ids.entries = entries;
}
trace->ev_qualifier_ids.nr++;
trace->ev_qualifier_ids.entries[i++] = id;
}
}
if (err < 0) {
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
"\nHint:\tand: 'man syscalls'\n", trace->output);
out_free:
zfree(&trace->ev_qualifier_ids.entries);
trace->ev_qualifier_ids.nr = 0;
}
out:
return err;
}
/*
* args is to be interpreted as a series of longs but we need to handle
* 8-byte unaligned accesses. args points to raw_data within the event
* and raw_data is guaranteed to be 8-byte unaligned because it is
* preceded by raw_size which is a u32. So we need to copy args to a temp
* variable to read it. Most notably this avoids extended load instructions
* on unaligned addresses
*/
unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx)
{
unsigned long val;
unsigned char *p = arg->args + sizeof(unsigned long) * idx;
memcpy(&val, p, sizeof(val));
return val;
}
static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
struct syscall_arg *arg)
{
if (sc->arg_fmt && sc->arg_fmt[arg->idx].name)
return scnprintf(bf, size, "%s: ", sc->arg_fmt[arg->idx].name);
return scnprintf(bf, size, "arg%d: ", arg->idx);
}
static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
struct syscall_arg *arg, unsigned long val)
{
if (sc->arg_fmt && sc->arg_fmt[arg->idx].scnprintf) {
arg->val = val;
if (sc->arg_fmt[arg->idx].parm)
arg->parm = sc->arg_fmt[arg->idx].parm;
return sc->arg_fmt[arg->idx].scnprintf(bf, size, arg);
}
return scnprintf(bf, size, "%ld", val);
}
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
unsigned char *args, void *augmented_args, int augmented_args_size,
struct trace *trace, struct thread *thread)
{
size_t printed = 0;
unsigned long val;
u8 bit = 1;
struct syscall_arg arg = {
.args = args,
.augmented = {
.size = augmented_args_size,
.args = augmented_args,
},
.idx = 0,
.mask = 0,
.trace = trace,
.thread = thread,
};
struct thread_trace *ttrace = thread__priv(thread);
/*
* Things like fcntl will set this in its 'cmd' formatter to pick the
* right formatter for the return value (an fd? file flags?), which is
* not needed for syscalls that always return a given type, say an fd.
*/
ttrace->ret_scnprintf = NULL;
if (sc->args != NULL) {
struct tep_format_field *field;
for (field = sc->args; field;
field = field->next, ++arg.idx, bit <<= 1) {
if (arg.mask & bit)
continue;
val = syscall_arg__val(&arg, arg.idx);
/*
* Suppress this argument if its value is zero and
* and we don't have a string associated in an
* strarray for it.
*/
if (val == 0 &&
!(sc->arg_fmt &&
(sc->arg_fmt[arg.idx].show_zero ||
sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAY ||
sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAYS) &&
sc->arg_fmt[arg.idx].parm))
continue;
printed += scnprintf(bf + printed, size - printed,
"%s%s: ", printed ? ", " : "", field->name);
printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
}
} else if (IS_ERR(sc->tp_format)) {
/*
* If we managed to read the tracepoint /format file, then we
* may end up not having any args, like with gettid(), so only
* print the raw args when we didn't manage to read it.
*/
while (arg.idx < sc->nr_args) {
if (arg.mask & bit)
goto next_arg;
val = syscall_arg__val(&arg, arg.idx);
if (printed)
printed += scnprintf(bf + printed, size - printed, ", ");
printed += syscall__scnprintf_name(sc, bf + printed, size - printed, &arg);
printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
next_arg:
++arg.idx;
bit <<= 1;
}
}
return printed;
}
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event,
struct perf_sample *sample);
static struct syscall *trace__syscall_info(struct trace *trace,
struct perf_evsel *evsel, int id)
{
if (id < 0) {
/*
* XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
* before that, leaving at a higher verbosity level till that is
* explained. Reproduced with plain ftrace with:
*
* echo 1 > /t/events/raw_syscalls/sys_exit/enable
* grep "NR -1 " /t/trace_pipe
*
* After generating some load on the machine.
*/
if (verbose > 1) {
static u64 n;
fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
id, perf_evsel__name(evsel), ++n);
}
return NULL;
}
if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) &&
trace__read_syscall_info(trace, id))
goto out_cant_read;
if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL))
goto out_cant_read;
return &trace->syscalls.table[id];
out_cant_read:
if (verbose > 0) {
fprintf(trace->output, "Problems reading syscall %d", id);
if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
fputs(" information\n", trace->output);
}
return NULL;
}
static void thread__update_stats(struct thread_trace *ttrace,
int id, struct perf_sample *sample)
{
struct int_node *inode;
struct stats *stats;
u64 duration = 0;
inode = intlist__findnew(ttrace->syscall_stats, id);
if (inode == NULL)
return;
stats = inode->priv;
if (stats == NULL) {
stats = malloc(sizeof(struct stats));
if (stats == NULL)
return;
init_stats(stats);
inode->priv = stats;
}
if (ttrace->entry_time && sample->time > ttrace->entry_time)
duration = sample->time - ttrace->entry_time;
update_stats(stats, duration);
}
static int trace__printf_interrupted_entry(struct trace *trace)
{
struct thread_trace *ttrace;
size_t printed;
if (trace->failure_only || trace->current == NULL)
return 0;
ttrace = thread__priv(trace->current);
if (!ttrace->entry_pending)
return 0;
printed = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
ttrace->entry_pending = false;
return printed;
}
static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample, struct thread *thread)
{
int printed = 0;
if (trace->print_sample) {
double ts = (double)sample->time / NSEC_PER_MSEC;
printed += fprintf(trace->output, "%22s %10.3f %s %d/%d [%d]\n",
perf_evsel__name(evsel), ts,
thread__comm_str(thread),
sample->pid, sample->tid, sample->cpu);
}
return printed;
}
static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
{
void *augmented_args = NULL;
*augmented_args_size = sample->raw_size - sc->args_size;
if (*augmented_args_size > 0)
augmented_args = sample->raw_data + sc->args_size;
return augmented_args;
}
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
char *msg;
void *args;
size_t printed = 0;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
int augmented_args_size = 0;
void *augmented_args = NULL;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
return -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
trace__fprintf_sample(trace, evsel, sample, thread);
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
if (ttrace->entry_str == NULL) {
ttrace->entry_str = malloc(trace__entry_str_size);
if (!ttrace->entry_str)
goto out_put;
}
if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
trace__printf_interrupted_entry(trace);
/*
* If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
* arguments, even if the syscall being handled, say "openat", uses only 4 arguments
* this breaks syscall__augmented_args() check for augmented args, as we calculate
* syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
* so when handling, say the openat syscall, we end up getting 6 args for the
* raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
* thinking that the extra 2 u64 args are the augmented filename, so just check
* here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
*/
if (evsel != trace->syscalls.events.sys_enter)
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
ttrace->entry_time = sample->time;
msg = ttrace->entry_str;
printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
args, augmented_args, augmented_args_size, trace, thread);
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
}
} else {
ttrace->entry_pending = true;
/* See trace__vfs_getname & trace__sys_exit */
ttrace->filename.pending_open = false;
}
if (trace->current != thread) {
thread__put(trace->current);
trace->current = thread__get(thread);
}
err = 0;
out_put:
thread__put(thread);
return err;
}
static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample)
{
struct thread_trace *ttrace;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
char msg[1024];
void *args, *augmented_args = NULL;
int augmented_args_size;
if (sc == NULL)
return -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
/*
* We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
* and the rest of the beautifiers accessing it via struct syscall_arg touches it.
*/
if (ttrace == NULL)
goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
fprintf(trace->output, "%s", msg);
err = 0;
out_put:
thread__put(thread);
return err;
}
static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample,
struct callchain_cursor *cursor)
{
struct addr_location al;
int max_stack = evsel->attr.sample_max_stack ?
evsel->attr.sample_max_stack :
trace->max_stack;
if (machine__resolve(trace->host, &al, sample) < 0 ||
thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
return -1;
return 0;
}
static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
{
/* TODO: user-configurable print_opts */
const unsigned int print_opts = EVSEL__PRINT_SYM |
EVSEL__PRINT_DSO |
EVSEL__PRINT_UNKNOWN_AS_ADDR;
return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output);
}
static const char *errno_to_name(struct perf_evsel *evsel, int err)
{
struct perf_env *env = perf_evsel__env(evsel);
const char *arch_name = perf_env__arch(env);
return arch_syscalls__strerrno(arch_name, err);
}
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
long ret;
u64 duration = 0;
bool duration_calculated = false;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
return -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
trace__fprintf_sample(trace, evsel, sample, thread);
if (trace->summary)
thread__update_stats(ttrace, id, sample);
ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) {
trace__set_fd_pathname(thread, ret, ttrace->filename.name);
ttrace->filename.pending_open = false;
++trace->stats.vfs_getname;
}
if (ttrace->entry_time) {
duration = sample->time - ttrace->entry_time;
if (trace__filter_duration(trace, duration))
goto out;
duration_calculated = true;
} else if (trace->duration_filter)
goto out;
if (sample->callchain) {
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
if (callchain_ret == 0) {
if (callchain_cursor.nr < trace->min_stack)
goto out;
callchain_ret = 1;
}
}
if (trace->summary_only || (ret >= 0 && trace->failure_only))
goto out;
trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
if (ttrace->entry_pending) {
fprintf(trace->output, "%-70s", ttrace->entry_str);
} else {
fprintf(trace->output, " ... [");
color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
fprintf(trace->output, "]: %s()", sc->name);
}
if (sc->fmt == NULL) {
if (ret < 0)
goto errno_print;
signed_print:
fprintf(trace->output, ") = %ld", ret);
} else if (ret < 0) {
errno_print: {
char bf[STRERR_BUFSIZE];
const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
*e = errno_to_name(evsel, -ret);
fprintf(trace->output, ") = -1 %s %s", e, emsg);
}
} else if (ret == 0 && sc->fmt->timeout)
fprintf(trace->output, ") = 0 Timeout");
else if (ttrace->ret_scnprintf) {
char bf[1024];
struct syscall_arg arg = {
.val = ret,
.thread = thread,
.trace = trace,
};
ttrace->ret_scnprintf(bf, sizeof(bf), &arg);
ttrace->ret_scnprintf = NULL;
fprintf(trace->output, ") = %s", bf);
} else if (sc->fmt->hexret)
fprintf(trace->output, ") = %#lx", ret);
else if (sc->fmt->errpid) {
struct thread *child = machine__find_thread(trace->host, ret, ret);
if (child != NULL) {
fprintf(trace->output, ") = %ld", ret);
if (child->comm_set)
fprintf(trace->output, " (%s)", thread__comm_str(child));
thread__put(child);
}
} else
goto signed_print;
fputc('\n', trace->output);
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
out:
ttrace->entry_pending = false;
err = 0;
out_put:
thread__put(thread);
return err;
}
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
struct thread_trace *ttrace;
size_t filename_len, entry_str_len, to_move;
ssize_t remaining_space;
char *pos;
const char *filename = perf_evsel__rawptr(evsel, sample, "pathname");
if (!thread)
goto out;
ttrace = thread__priv(thread);
if (!ttrace)
goto out_put;
filename_len = strlen(filename);
if (filename_len == 0)
goto out_put;
if (ttrace->filename.namelen < filename_len) {
char *f = realloc(ttrace->filename.name, filename_len + 1);
if (f == NULL)
goto out_put;
ttrace->filename.namelen = filename_len;
ttrace->filename.name = f;
}
strcpy(ttrace->filename.name, filename);
ttrace->filename.pending_open = true;
if (!ttrace->filename.ptr)
goto out_put;
entry_str_len = strlen(ttrace->entry_str);
remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
if (remaining_space <= 0)
goto out_put;
if (filename_len > (size_t)remaining_space) {
filename += filename_len - remaining_space;
filename_len = remaining_space;
}
to_move = entry_str_len - ttrace->filename.entry_str_pos + 1; /* \0 */
pos = ttrace->entry_str + ttrace->filename.entry_str_pos;
memmove(pos + filename_len, pos, to_move);
memcpy(pos, filename, filename_len);
ttrace->filename.ptr = 0;
ttrace->filename.entry_str_pos = 0;
out_put:
thread__put(thread);
out:
return 0;
}
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
double runtime_ms = (double)runtime / NSEC_PER_MSEC;
struct thread *thread = machine__findnew_thread(trace->host,
sample->pid,
sample->tid);
struct thread_trace *ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_dump;
ttrace->runtime_ms += runtime_ms;
trace->runtime_ms += runtime_ms;
out_put:
thread__put(thread);
return 0;
out_dump:
fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
evsel->name,
perf_evsel__strval(evsel, sample, "comm"),
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
runtime,
perf_evsel__intval(evsel, sample, "vruntime"));
goto out_put;
}
static int bpf_output__printer(enum binary_printer_ops op,
unsigned int val, void *extra __maybe_unused, FILE *fp)
{
unsigned char ch = (unsigned char)val;
switch (op) {
case BINARY_PRINT_CHAR_DATA:
return fprintf(fp, "%c", isprint(ch) ? ch : '.');
case BINARY_PRINT_DATA_BEGIN:
case BINARY_PRINT_LINE_BEGIN:
case BINARY_PRINT_ADDR:
case BINARY_PRINT_NUM_DATA:
case BINARY_PRINT_NUM_PAD:
case BINARY_PRINT_SEP:
case BINARY_PRINT_CHAR_PAD:
case BINARY_PRINT_LINE_END:
case BINARY_PRINT_DATA_END:
default:
break;
}
return 0;
}
static void bpf_output__fprintf(struct trace *trace,
struct perf_sample *sample)
{
binary__fprintf(sample->raw_data, sample->raw_size, 8,
bpf_output__printer, NULL, trace->output);
}
static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
int callchain_ret = 0;
if (sample->callchain) {
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
if (callchain_ret == 0) {
if (callchain_cursor.nr < trace->min_stack)
goto out;
callchain_ret = 1;
}
}
trace__printf_interrupted_entry(trace);
trace__fprintf_tstamp(trace, sample->time, trace->output);
if (trace->trace_syscalls)
fprintf(trace->output, "( ): ");
if (thread)
trace__fprintf_comm_tid(trace, thread, trace->output);
if (evsel == trace->syscalls.events.augmented) {
int id = perf_evsel__sc_tp_uint(evsel, id, sample);
struct syscall *sc = trace__syscall_info(trace, evsel, id);
if (sc) {
fprintf(trace->output, "%s(", sc->name);
trace__fprintf_sys_enter(trace, evsel, sample);
fputc(')', trace->output);
goto newline;
}
/*
* XXX: Not having the associated syscall info or not finding/adding
* the thread should never happen, but if it does...
* fall thru and print it as a bpf_output event.
*/
}
fprintf(trace->output, "%s:", evsel->name);
if (perf_evsel__is_bpf_output(evsel)) {
bpf_output__fprintf(trace, sample);
} else if (evsel->tp_format) {
if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
trace__fprintf_sys_enter(trace, evsel, sample)) {
event_format__fprintf(evsel->tp_format, sample->cpu,
sample->raw_data, sample->raw_size,
trace->output);
}
}
newline:
fprintf(trace->output, "\n");
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
thread__put(thread);
out:
return 0;
}
static void print_location(FILE *f, struct perf_sample *sample,
struct addr_location *al,
bool print_dso, bool print_sym)
{
if ((verbose > 0 || print_dso) && al->map)
fprintf(f, "%s@", al->map->dso->long_name);
if ((verbose > 0 || print_sym) && al->sym)
fprintf(f, "%s+0x%" PRIx64, al->sym->name,
al->addr - al->sym->start);
else if (al->map)
fprintf(f, "0x%" PRIx64, al->addr);
else
fprintf(f, "0x%" PRIx64, sample->addr);
}
static int trace__pgfault(struct trace *trace,
struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
struct thread *thread;
struct addr_location al;
char map_type = 'd';
struct thread_trace *ttrace;
int err = -1;
int callchain_ret = 0;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
if (sample->callchain) {
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
if (callchain_ret == 0) {
if (callchain_cursor.nr < trace->min_stack)
goto out_put;
callchain_ret = 1;
}
}
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
ttrace->pfmaj++;
else
ttrace->pfmin++;
if (trace->summary_only)
goto out;
thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
fprintf(trace->output, "%sfault [",
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
"maj" : "min");
print_location(trace->output, sample, &al, false, true);
fprintf(trace->output, "] => ");
thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
if (!al.map) {
thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
if (al.map)
map_type = 'x';
else
map_type = '?';
}
print_location(trace->output, sample, &al, true, false);
fprintf(trace->output, " (%c%c)\n", map_type, al.level);
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
out:
err = 0;
out_put:
thread__put(thread);
return err;
}
static void trace__set_base_time(struct trace *trace,
struct perf_evsel *evsel,
struct perf_sample *sample)
{
/*
* BPF events were not setting PERF_SAMPLE_TIME, so be more robust
* and don't use sample->time unconditionally, we may end up having
* some other event in the future without PERF_SAMPLE_TIME for good
* reason, i.e. we may not be interested in its timestamps, just in
* it taking place, picking some piece of information when it
* appears in our event stream (vfs_getname comes to mind).
*/
if (trace->base_time == 0 && !trace->full_time &&
(evsel->attr.sample_type & PERF_SAMPLE_TIME))
trace->base_time = sample->time;
}
static int trace__process_sample(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine __maybe_unused)
{
struct trace *trace = container_of(tool, struct trace, tool);
struct thread *thread;
int err = 0;
tracepoint_handler handler = evsel->handler;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
if (thread && thread__is_filtered(thread))
goto out;
trace__set_base_time(trace, evsel, sample);
if (handler) {
++trace->nr_events;
handler(trace, evsel, event, sample);
}
out:
thread__put(thread);
return err;
}
static int trace__record(struct trace *trace, int argc, const char **argv)
{
unsigned int rec_argc, i, j;
const char **rec_argv;
const char * const record_args[] = {
"record",
"-R",
"-m", "1024",
"-c", "1",
};
const char * const sc_args[] = { "-e", };
unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
const char * const majpf_args[] = { "-e", "major-faults" };
unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
const char * const minpf_args[] = { "-e", "minor-faults" };
unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
/* +1 is for the event string below */
rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
majpf_args_nr + minpf_args_nr + argc;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
return -ENOMEM;
j = 0;
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[j++] = record_args[i];
if (trace->trace_syscalls) {
for (i = 0; i < sc_args_nr; i++)
rec_argv[j++] = sc_args[i];
/* event string may be different for older kernels - e.g., RHEL6 */
if (is_valid_tracepoint("raw_syscalls:sys_enter"))
rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
else if (is_valid_tracepoint("syscalls:sys_enter"))
rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
else {
pr_err("Neither raw_syscalls nor syscalls events exist.\n");
free(rec_argv);
return -1;
}
}
if (trace->trace_pgfaults & TRACE_PFMAJ)
for (i = 0; i < majpf_args_nr; i++)
rec_argv[j++] = majpf_args[i];
if (trace->trace_pgfaults & TRACE_PFMIN)
for (i = 0; i < minpf_args_nr; i++)
rec_argv[j++] = minpf_args[i];
for (i = 0; i < (unsigned int)argc; i++)
rec_argv[j++] = argv[i];
return cmd_record(j, rec_argv);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
if (IS_ERR(evsel))
return false;
if (perf_evsel__field(evsel, "pathname") == NULL) {
perf_evsel__delete(evsel);
return false;
}
evsel->handler = trace__vfs_getname;
perf_evlist__add(evlist, evsel);
return true;
}
static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
{
struct perf_evsel *evsel;
struct perf_event_attr attr = {
.type = PERF_TYPE_SOFTWARE,
.mmap_data = 1,
};
attr.config = config;
attr.sample_period = 1;
event_attr_init(&attr);
evsel = perf_evsel__new(&attr);
if (evsel)
evsel->handler = trace__pgfault;
return evsel;
}
static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
{
const u32 type = event->header.type;
struct perf_evsel *evsel;
if (type != PERF_RECORD_SAMPLE) {
trace__process_event(trace, trace->host, event, sample);
return;
}
evsel = perf_evlist__id2evsel(trace->evlist, sample->id);
if (evsel == NULL) {
fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id);
return;
}
trace__set_base_time(trace, evsel, sample);
if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
sample->raw_data == NULL) {
fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
perf_evsel__name(evsel), sample->tid,
sample->cpu, sample->raw_size);
} else {
tracepoint_handler handler = evsel->handler;
handler(trace, evsel, event, sample);
}
}
static int trace__add_syscall_newtp(struct trace *trace)
{
int ret = -1;
struct perf_evlist *evlist = trace->evlist;
struct perf_evsel *sys_enter, *sys_exit;
sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter);
if (sys_enter == NULL)
goto out;
if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
goto out_delete_sys_enter;
sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit);
if (sys_exit == NULL)
goto out_delete_sys_enter;
if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
goto out_delete_sys_exit;
perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
perf_evlist__add(evlist, sys_enter);
perf_evlist__add(evlist, sys_exit);
if (callchain_param.enabled && !trace->kernel_syscallchains) {
/*
* We're interested only in the user space callchain
* leading to the syscall, allow overriding that for
* debugging reasons using --kernel_syscall_callchains
*/
sys_exit->attr.exclude_callchain_kernel = 1;
}
trace->syscalls.events.sys_enter = sys_enter;
trace->syscalls.events.sys_exit = sys_exit;
ret = 0;
out:
return ret;
out_delete_sys_exit:
perf_evsel__delete_priv(sys_exit);
out_delete_sys_enter:
perf_evsel__delete_priv(sys_enter);
goto out;
}
static int trace__set_ev_qualifier_filter(struct trace *trace)
{
int err = -1;
struct perf_evsel *sys_exit;
char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier,
trace->ev_qualifier_ids.nr,
trace->ev_qualifier_ids.entries);
if (filter == NULL)
goto out_enomem;
if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
filter)) {
sys_exit = trace->syscalls.events.sys_exit;
err = perf_evsel__append_tp_filter(sys_exit, filter);
}
free(filter);
out:
return err;
out_enomem:
errno = ENOMEM;
goto out;
}
static int trace__set_filter_loop_pids(struct trace *trace)
{
unsigned int nr = 1;
pid_t pids[32] = {
getpid(),
};
struct thread *thread = machine__find_thread(trace->host, pids[0], pids[0]);
while (thread && nr < ARRAY_SIZE(pids)) {
struct thread *parent = machine__find_thread(trace->host, thread->ppid, thread->ppid);
if (parent == NULL)
break;
if (!strcmp(thread__comm_str(parent), "sshd")) {
pids[nr++] = parent->tid;
break;
}
thread = parent;
}
return perf_evlist__set_filter_pids(trace->evlist, nr, pids);
}
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = trace->evlist;
struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
bool draining = false;
trace->live = true;
if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
goto out_error_raw_syscalls;
if (trace->trace_syscalls)
trace->vfs_getname = perf_evlist__add_vfs_getname(evlist);
if ((trace->trace_pgfaults & TRACE_PFMAJ)) {
pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
if (pgfault_maj == NULL)
goto out_error_mem;
perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
perf_evlist__add(evlist, pgfault_maj);
}
if ((trace->trace_pgfaults & TRACE_PFMIN)) {
pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
if (pgfault_min == NULL)
goto out_error_mem;
perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
perf_evlist__add(evlist, pgfault_min);
}
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
trace__sched_stat_runtime))
goto out_error_sched_stat_runtime;
/*
* If a global cgroup was set, apply it to all the events without an
* explicit cgroup. I.e.:
*
* trace -G A -e sched:*switch
*
* Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
* _and_ sched:sched_switch to the 'A' cgroup, while:
*
* trace -e sched:*switch -G A
*
* will only set the sched:sched_switch event to the 'A' cgroup, all the
* other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
* a cgroup (on the root cgroup, sys wide, etc).
*
* Multiple cgroups:
*
* trace -G A -e sched:*switch -G B
*
* the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
* to the 'B' cgroup.
*
* evlist__set_default_cgroup() grabs a reference of the passed cgroup
* only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL.
*/
if (trace->cgroup)
evlist__set_default_cgroup(trace->evlist, trace->cgroup);
err = perf_evlist__create_maps(evlist, &trace->opts.target);
if (err < 0) {
fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
goto out_delete_evlist;
}
err = trace__symbols_init(trace, evlist);
if (err < 0) {
fprintf(trace->output, "Problems initializing symbol libraries!\n");
goto out_delete_evlist;
}
perf_evlist__config(evlist, &trace->opts, &callchain_param);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
if (forks) {
err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
argv, false, NULL);
if (err < 0) {
fprintf(trace->output, "Couldn't run the workload!\n");
goto out_delete_evlist;
}
}
err = perf_evlist__open(evlist);
if (err < 0)
goto out_error_open;
err = bpf__apply_obj_config();
if (err) {
char errbuf[BUFSIZ];
bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
pr_err("ERROR: Apply config to BPF failed: %s\n",
errbuf);
goto out_error_open;
}
/*
* Better not use !target__has_task() here because we need to cover the
* case where no threads were specified in the command line, but a
* workload was, and in that case we will fill in the thread_map when
* we fork the workload in perf_evlist__prepare_workload.
*/
if (trace->filter_pids.nr > 0)
err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
else if (thread_map__pid(evlist->threads, 0) == -1)
err = trace__set_filter_loop_pids(trace);
if (err < 0)
goto out_error_mem;
if (trace->ev_qualifier_ids.nr > 0) {
err = trace__set_ev_qualifier_filter(trace);
if (err < 0)
goto out_errno;
pr_debug("event qualifier tracepoint filter: %s\n",
trace->syscalls.events.sys_exit->filter);
}
err = perf_evlist__apply_filters(evlist, &evsel);
if (err < 0)
goto out_error_apply_filters;
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
if (err < 0)
goto out_error_mmap;
if (!target__none(&trace->opts.target) && !trace->opts.initial_delay)
perf_evlist__enable(evlist);
if (forks)
perf_evlist__start_workload(evlist);
if (trace->opts.initial_delay) {
usleep(trace->opts.initial_delay * 1000);
perf_evlist__enable(evlist);
}
trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
evlist->threads->nr > 1 ||
perf_evlist__first(evlist)->attr.inherit;
/*
* Now that we already used evsel->attr to ask the kernel to setup the
* events, lets reuse evsel->attr.sample_max_stack as the limit in
* trace__resolve_callchain(), allowing per-event max-stack settings
* to override an explicitely set --max-stack global setting.
*/
evlist__for_each_entry(evlist, evsel) {
if (evsel__has_callchain(evsel) &&
evsel->attr.sample_max_stack == 0)
evsel->attr.sample_max_stack = trace->max_stack;
}
again:
before = trace->nr_events;
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
struct perf_mmap *md;
md = &evlist->mmap[i];
if (perf_mmap__read_init(md) < 0)
continue;
while ((event = perf_mmap__read_event(md)) != NULL) {
struct perf_sample sample;
++trace->nr_events;
err = perf_evlist__parse_sample(evlist, event, &sample);
if (err) {
fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
goto next_event;
}
trace__handle_event(trace, event, &sample);
next_event:
perf_mmap__consume(md);
if (interrupted)
goto out_disable;
if (done && !draining) {
perf_evlist__disable(evlist);
draining = true;
}
}
perf_mmap__read_done(md);
}
if (trace->nr_events == before) {
int timeout = done ? 100 : -1;
if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
draining = true;
goto again;
}
} else {
goto again;
}
out_disable:
thread__zput(trace->current);
perf_evlist__disable(evlist);
if (!err) {
if (trace->summary)
trace__fprintf_thread_summary(trace, trace->output);
if (trace->show_tool_stats) {
fprintf(trace->output, "Stats:\n "
" vfs_getname : %" PRIu64 "\n"
" proc_getname: %" PRIu64 "\n",
trace->stats.vfs_getname,
trace->stats.proc_getname);
}
}
out_delete_evlist:
trace__symbols__exit(trace);
perf_evlist__delete(evlist);
cgroup__put(trace->cgroup);
trace->evlist = NULL;
trace->live = false;
return err;
{
char errbuf[BUFSIZ];
out_error_sched_stat_runtime:
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
goto out_error;
out_error_raw_syscalls:
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)");
goto out_error;
out_error_mmap:
perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf));
goto out_error;
out_error_open:
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
out_error:
fprintf(trace->output, "%s\n", errbuf);
goto out_delete_evlist;
out_error_apply_filters:
fprintf(trace->output,
"Failed to set filter \"%s\" on event %s with %d (%s)\n",
evsel->filter, perf_evsel__name(evsel), errno,
str_error_r(errno, errbuf, sizeof(errbuf)));
goto out_delete_evlist;
}
out_error_mem:
fprintf(trace->output, "Not enough memory to run!\n");
goto out_delete_evlist;
out_errno:
fprintf(trace->output, "errno=%d,%s\n", errno, strerror(errno));
goto out_delete_evlist;
}
static int trace__replay(struct trace *trace)
{
const struct perf_evsel_str_handler handlers[] = {
{ "probe:vfs_getname", trace__vfs_getname, },
};
struct perf_data data = {
.file = {
.path = input_name,
},
.mode = PERF_DATA_MODE_READ,
.force = trace->force,
};
struct perf_session *session;
struct perf_evsel *evsel;
int err = -1;
trace->tool.sample = trace__process_sample;
trace->tool.mmap = perf_event__process_mmap;
trace->tool.mmap2 = perf_event__process_mmap2;
trace->tool.comm = perf_event__process_comm;
trace->tool.exit = perf_event__process_exit;
trace->tool.fork = perf_event__process_fork;
trace->tool.attr = perf_event__process_attr;
trace->tool.tracing_data = perf_event__process_tracing_data;
trace->tool.build_id = perf_event__process_build_id;
trace->tool.namespaces = perf_event__process_namespaces;
trace->tool.ordered_events = true;
trace->tool.ordering_requires_timestamps = true;
/* add tid to output */
trace->multiple_threads = true;
session = perf_session__new(&data, false, &trace->tool);
if (session == NULL)
return -1;
if (trace->opts.target.pid)
symbol_conf.pid_list_str = strdup(trace->opts.target.pid);
if (trace->opts.target.tid)
symbol_conf.tid_list_str = strdup(trace->opts.target.tid);
if (symbol__init(&session->header.env) < 0)
goto out;
trace->host = &session->machines.host;
err = perf_session__set_tracepoints_handlers(session, handlers);
if (err)
goto out;
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"raw_syscalls:sys_enter");
/* older kernels have syscalls tp versus raw_syscalls */
if (evsel == NULL)
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"syscalls:sys_enter");
if (evsel &&
(perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
pr_err("Error during initialize raw_syscalls:sys_enter event\n");
goto out;
}
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"raw_syscalls:sys_exit");
if (evsel == NULL)
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"syscalls:sys_exit");
if (evsel &&
(perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
pr_err("Error during initialize raw_syscalls:sys_exit event\n");
goto out;
}
evlist__for_each_entry(session->evlist, evsel) {
if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
(evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS))
evsel->handler = trace__pgfault;
}
setup_pager();
err = perf_session__process_events(session);
if (err)
pr_err("Failed to process events, error %d", err);
else if (trace->summary)
trace__fprintf_thread_summary(trace, trace->output);
out:
perf_session__delete(session);
return err;
}
static size_t trace__fprintf_threads_header(FILE *fp)
{
size_t printed;
printed = fprintf(fp, "\n Summary of events:\n\n");
return printed;
}
DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
struct stats *stats;
double msecs;
int syscall;
)
{
struct int_node *source = rb_entry(nd, struct int_node, rb_node);
struct stats *stats = source->priv;
entry->syscall = source->i;
entry->stats = stats;
entry->msecs = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
}
static size_t thread__dump_stats(struct thread_trace *ttrace,
struct trace *trace, FILE *fp)
{
size_t printed = 0;
struct syscall *sc;
struct rb_node *nd;
DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
if (syscall_stats == NULL)
return 0;
printed += fprintf(fp, "\n");
printed += fprintf(fp, " syscall calls total min avg max stddev\n");
printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n");
printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n");
resort_rb__for_each_entry(nd, syscall_stats) {
struct stats *stats = syscall_stats_entry->stats;
if (stats) {
double min = (double)(stats->min) / NSEC_PER_MSEC;
double max = (double)(stats->max) / NSEC_PER_MSEC;
double avg = avg_stats(stats);
double pct;
u64 n = (u64) stats->n;
pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
avg /= NSEC_PER_MSEC;
sc = &trace->syscalls.table[syscall_stats_entry->syscall];
printed += fprintf(fp, " %-15s", sc->name);
printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
n, syscall_stats_entry->msecs, min, avg);
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
}
}
resort_rb__delete(syscall_stats);
printed += fprintf(fp, "\n\n");
return printed;
}
static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
{
size_t printed = 0;
struct thread_trace *ttrace = thread__priv(thread);
double ratio;
if (ttrace == NULL)
return 0;
ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
printed += fprintf(fp, "%.1f%%", ratio);
if (ttrace->pfmaj)
printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
if (ttrace->pfmin)
printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
if (trace->sched)
printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
else if (fputc('\n', fp) != EOF)
++printed;
printed += thread__dump_stats(ttrace, trace, fp);
return printed;
}
static unsigned long thread__nr_events(struct thread_trace *ttrace)
{
return ttrace ? ttrace->nr_events : 0;
}
DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)),
struct thread *thread;
)
{
entry->thread = rb_entry(nd, struct thread, rb_node);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
size_t printed = trace__fprintf_threads_header(fp);
struct rb_node *nd;
int i;
for (i = 0; i < THREADS__TABLE_SIZE; i++) {
DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
if (threads == NULL) {
fprintf(fp, "%s", "Error sorting output by nr_events!\n");
return 0;
}
resort_rb__for_each_entry(nd, threads)
printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
resort_rb__delete(threads);
}
return printed;
}
static int trace__set_duration(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct trace *trace = opt->value;
trace->duration_filter = atof(str);
return 0;
}
static int trace__set_filter_pids(const struct option *opt, const char *str,
int unset __maybe_unused)
{
int ret = -1;
size_t i;
struct trace *trace = opt->value;
/*
* FIXME: introduce a intarray class, plain parse csv and create a
* { int nr, int entries[] } struct...
*/
struct intlist *list = intlist__new(str);
if (list == NULL)
return -1;
i = trace->filter_pids.nr = intlist__nr_entries(list) + 1;
trace->filter_pids.entries = calloc(i, sizeof(pid_t));
if (trace->filter_pids.entries == NULL)
goto out;
trace->filter_pids.entries[0] = getpid();
for (i = 1; i < trace->filter_pids.nr; ++i)
trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i;
intlist__delete(list);
ret = 0;
out:
return ret;
}
static int trace__open_output(struct trace *trace, const char *filename)
{
struct stat st;
if (!stat(filename, &st) && st.st_size) {
char oldname[PATH_MAX];
scnprintf(oldname, sizeof(oldname), "%s.old", filename);
unlink(oldname);
rename(filename, oldname);
}
trace->output = fopen(filename, "w");
return trace->output == NULL ? -errno : 0;
}
static int parse_pagefaults(const struct option *opt, const char *str,
int unset __maybe_unused)
{
int *trace_pgfaults = opt->value;
if (strcmp(str, "all") == 0)
*trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN;
else if (strcmp(str, "maj") == 0)
*trace_pgfaults |= TRACE_PFMAJ;
else if (strcmp(str, "min") == 0)
*trace_pgfaults |= TRACE_PFMIN;
else
return -1;
return 0;
}
static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
{
struct perf_evsel *evsel;
evlist__for_each_entry(evlist, evsel)
evsel->handler = handler;
}
static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
if (evsel->priv || !evsel->tp_format)
continue;
if (strcmp(evsel->tp_format->system, "syscalls"))
continue;
if (perf_evsel__init_syscall_tp(evsel))
return -1;
if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
struct syscall_tp *sc = evsel->priv;
if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)))
return -1;
} else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) {
struct syscall_tp *sc = evsel->priv;
if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap))
return -1;
}
}
return 0;
}
/*
* XXX: Hackish, just splitting the combined -e+--event (syscalls
* (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
* existing facilities unchanged (trace->ev_qualifier + parse_options()).
*
* It'd be better to introduce a parse_options() variant that would return a
* list with the terms it didn't match to an event...
*/
static int trace__parse_events_option(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct trace *trace = (struct trace *)opt->value;
const char *s = str;
char *sep = NULL, *lists[2] = { NULL, NULL, };
int len = strlen(str) + 1, err = -1, list, idx;
char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
char group_name[PATH_MAX];
if (strace_groups_dir == NULL)
return -1;
if (*s == '!') {
++s;
trace->not_ev_qualifier = true;
}
while (1) {
if ((sep = strchr(s, ',')) != NULL)
*sep = '\0';
list = 0;
if (syscalltbl__id(trace->sctbl, s) >= 0 ||
syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
list = 1;
} else {
path__join(group_name, sizeof(group_name), strace_groups_dir, s);
if (access(group_name, R_OK) == 0)
list = 1;
}
if (lists[list]) {
sprintf(lists[list] + strlen(lists[list]), ",%s", s);
} else {
lists[list] = malloc(len);
if (lists[list] == NULL)
goto out;
strcpy(lists[list], s);
}
if (!sep)
break;
*sep = ',';
s = sep + 1;
}
if (lists[1] != NULL) {
struct strlist_config slist_config = {
.dirname = strace_groups_dir,
};
trace->ev_qualifier = strlist__new(lists[1], &slist_config);
if (trace->ev_qualifier == NULL) {
fputs("Not enough memory to parse event qualifier", trace->output);
goto out;
}
if (trace__validate_ev_qualifier(trace))
goto out;
trace->trace_syscalls = true;
}
err = 0;
if (lists[0]) {
struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option);
err = parse_events_option(&o, lists[0], 0);
}
out:
if (sep)
*sep = ',';
return err;
}
static int trace__parse_cgroups(const struct option *opt, const char *str, int unset)
{
struct trace *trace = opt->value;
if (!list_empty(&trace->evlist->entries))
return parse_cgroups(opt, str, unset);
trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
return 0;
}
int cmd_trace(int argc, const char **argv)
{
const char *trace_usage[] = {
"perf trace [<options>] [<command>]",
"perf trace [<options>] -- <command> [<options>]",
"perf trace record [<options>] [<command>]",
"perf trace record [<options>] -- <command> [<options>]",
NULL
};
struct trace trace = {
.syscalls = {
. max = -1,
},
.opts = {
.target = {
.uid = UINT_MAX,
.uses_mmap = true,
},
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.no_buffering = true,
.mmap_pages = UINT_MAX,
.proc_map_timeout = 500,
},
.output = stderr,
.show_comm = true,
.trace_syscalls = false,
.kernel_syscallchains = false,
.max_stack = UINT_MAX,
};
const char *output_name = NULL;
const struct option trace_options[] = {
OPT_CALLBACK('e', "event", &trace, "event",
"event/syscall selector. use 'perf list' to list available events",
trace__parse_events_option),
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
trace__parse_events_option),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
"trace events on existing process id"),
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
"trace events on existing thread id"),
OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
"pids to filter (by the kernel)", trace__set_filter_pids),
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
"child tasks do not inherit counters"),
OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
"number of mmap data pages",
perf_evlist__parse_mmap_pages),
OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
"user to profile"),
OPT_CALLBACK(0, "duration", &trace, "float",
"show only events with duration > N.M ms",
trace__set_duration),
OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
OPT_BOOLEAN('T', "time", &trace.full_time,
"Show full timestamp, not time relative to first start"),
OPT_BOOLEAN(0, "failure", &trace.failure_only,
"Show only syscalls that failed"),
OPT_BOOLEAN('s', "summary", &trace.summary_only,
"Show only syscall summary with statistics"),
OPT_BOOLEAN('S', "with-summary", &trace.summary,
"Show all syscalls and summary with statistics"),
OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
"Trace pagefaults", parse_pagefaults, "maj"),
OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
OPT_CALLBACK(0, "call-graph", &trace.opts,
"record_mode[,record_size]", record_callchain_help,
&record_parse_callchain_opt),
OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
"Show the kernel callchains on the syscall exit path"),
OPT_UINTEGER(0, "min-stack", &trace.min_stack,
"Set the minimum stack depth when parsing the callchain, "
"anything below the specified depth will be ignored."),
OPT_UINTEGER(0, "max-stack", &trace.max_stack,
"Set the maximum stack depth when parsing the callchain, "
"anything beyond the specified depth will be ignored. "
"Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN(0, "print-sample", &trace.print_sample,
"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
trace__parse_cgroups),
OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
"ms to wait before starting measurement after program "
"start"),
OPT_END()
};
bool __maybe_unused max_stack_user_set = true;
bool mmap_pages_user_set = true;
struct perf_evsel *evsel;
const char * const trace_subcommands[] = { "record", NULL };
int err = -1;
char bf[BUFSIZ];
signal(SIGSEGV, sighandler_dump_stack);
signal(SIGFPE, sighandler_dump_stack);
trace.evlist = perf_evlist__new();
trace.sctbl = syscalltbl__new();
if (trace.evlist == NULL || trace.sctbl == NULL) {
pr_err("Not enough memory to run!\n");
err = -ENOMEM;
goto out;
}
argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
usage_with_options_msg(trace_usage, trace_options,
"cgroup monitoring only available in system-wide mode");
}
evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
if (IS_ERR(evsel)) {
bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
goto out;
}
if (evsel)
trace.syscalls.events.augmented = evsel;
err = bpf__setup_stdout(trace.evlist);
if (err) {
bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
goto out;
}
err = -1;
if (trace.trace_pgfaults) {
trace.opts.sample_address = true;
trace.opts.sample_time = true;
}
if (trace.opts.mmap_pages == UINT_MAX)
mmap_pages_user_set = false;
if (trace.max_stack == UINT_MAX) {
trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
max_stack_user_set = false;
}
#ifdef HAVE_DWARF_UNWIND_SUPPORT
if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) {
record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
}
#endif
if (callchain_param.enabled) {
if (!mmap_pages_user_set && geteuid() == 0)
trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4;
symbol_conf.use_callchain = true;
}
if (trace.evlist->nr_entries > 0) {
evlist__set_evsel_handler(trace.evlist, trace__event_handler);
if (evlist__set_syscall_tp_fields(trace.evlist)) {
perror("failed to set syscalls:* tracepoint fields");
goto out;
}
}
/*
* If we are augmenting syscalls, then combine what we put in the
* __augmented_syscalls__ BPF map with what is in the
* syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
* combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
*
* We'll switch to look at two BPF maps, one for sys_enter and the
* other for sys_exit when we start augmenting the sys_exit paths with
* buffers that are being copied from kernel to userspace, think 'read'
* syscall.
*/
if (trace.syscalls.events.augmented) {
evsel = trace.syscalls.events.augmented;
if (perf_evsel__init_augmented_syscall_tp(evsel) ||
perf_evsel__init_augmented_syscall_tp_args(evsel))
goto out;
evsel->handler = trace__sys_enter;
evlist__for_each_entry(trace.evlist, evsel) {
if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
perf_evsel__init_augmented_syscall_tp(evsel);
perf_evsel__init_augmented_syscall_tp_ret(evsel);
evsel->handler = trace__sys_exit;
}
}
}
if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
return trace__record(&trace, argc-1, &argv[1]);
/* summary_only implies summary option, but don't overwrite summary if set */
if (trace.summary_only)
trace.summary = trace.summary_only;
if (!trace.trace_syscalls && !trace.trace_pgfaults &&
trace.evlist->nr_entries == 0 /* Was --events used? */) {
trace.trace_syscalls = true;
}
if (output_name != NULL) {
err = trace__open_output(&trace, output_name);
if (err < 0) {
perror("failed to create output file");
goto out;
}
}
err = target__validate(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
fprintf(trace.output, "%s", bf);
goto out_close;
}
err = target__parse_uid(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
fprintf(trace.output, "%s", bf);
goto out_close;
}
if (!argc && target__none(&trace.opts.target))
trace.opts.target.system_wide = true;
if (input_name)
err = trace__replay(&trace);
else
err = trace__run(&trace, argc, argv);
out_close:
if (output_name != NULL)
fclose(trace.output);
out:
return err;
}