blob: 39ad4d0ca88427cb222fa3ce7c0a35c7b77ed243 [file] [log] [blame]
#include <traceevent/event-parse.h>
#include "builtin.h"
#include "util/color.h"
#include "util/debug.h"
#include "util/evlist.h"
#include "util/machine.h"
#include "util/session.h"
#include "util/thread.h"
#include "util/parse-options.h"
#include "util/strlist.h"
#include "util/intlist.h"
#include "util/thread_map.h"
#include "util/stat.h"
#include "trace-event.h"
#include "util/parse-events.h"
#include <libaudit.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <linux/futex.h>
/* For older distros: */
#ifndef MAP_STACK
# define MAP_STACK 0x20000
#endif
#ifndef MADV_HWPOISON
# define MADV_HWPOISON 100
#endif
#ifndef MADV_MERGEABLE
# define MADV_MERGEABLE 12
#endif
#ifndef MADV_UNMERGEABLE
# define MADV_UNMERGEABLE 13
#endif
#ifndef EFD_SEMAPHORE
# define EFD_SEMAPHORE 1
#endif
#ifndef EFD_NONBLOCK
# define EFD_NONBLOCK 00004000
#endif
#ifndef EFD_CLOEXEC
# define EFD_CLOEXEC 02000000
#endif
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#endif
#ifndef SOCK_DCCP
# define SOCK_DCCP 6
#endif
#ifndef SOCK_CLOEXEC
# define SOCK_CLOEXEC 02000000
#endif
#ifndef SOCK_NONBLOCK
# define SOCK_NONBLOCK 00004000
#endif
#ifndef MSG_CMSG_CLOEXEC
# define MSG_CMSG_CLOEXEC 0x40000000
#endif
#ifndef PERF_FLAG_FD_NO_GROUP
# define PERF_FLAG_FD_NO_GROUP (1UL << 0)
#endif
#ifndef PERF_FLAG_FD_OUTPUT
# define PERF_FLAG_FD_OUTPUT (1UL << 1)
#endif
#ifndef PERF_FLAG_PID_CGROUP
# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
#endif
#ifndef PERF_FLAG_FD_CLOEXEC
# define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
#endif
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,
struct format_field *format_field,
bool needs_swap)
{
field->offset = format_field->offset;
switch (format_field->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 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, struct format_field *format_field)
{
field->offset = format_field->offset;
field->pointer = tp_field__ptr;
return 0;
}
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 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 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, 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__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 (evsel == NULL)
evsel = perf_evsel__newtp("syscalls", direction);
if (evsel) {
if (perf_evsel__init_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); })
static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist,
void *sys_enter_handler,
void *sys_exit_handler)
{
int ret = -1;
struct perf_evsel *sys_enter, *sys_exit;
sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler);
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__syscall_newtp("sys_exit", sys_exit_handler);
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_evlist__add(evlist, sys_enter);
perf_evlist__add(evlist, 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;
}
struct syscall_arg {
unsigned long val;
struct thread *thread;
struct trace *trace;
void *parm;
u8 idx;
u8 mask;
};
struct strarray {
int offset;
int nr_entries;
const char **entries;
};
#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
.nr_entries = ARRAY_SIZE(array), \
.entries = array, \
}
#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
.offset = off, \
.nr_entries = ARRAY_SIZE(array), \
.entries = array, \
}
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
const char *intfmt,
struct syscall_arg *arg)
{
struct strarray *sa = arg->parm;
int idx = arg->val - sa->offset;
if (idx < 0 || idx >= sa->nr_entries)
return scnprintf(bf, size, intfmt, arg->val);
return scnprintf(bf, size, "%s", sa->entries[idx]);
}
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
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches as soon as the ioctl beautifier
* gets rewritten to support all arches.
*/
static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
struct syscall_arg *arg)
{
return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
}
#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
#endif /* defined(__i386__) || defined(__x86_64__) */
static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
struct syscall_arg *arg);
#define SCA_FD syscall_arg__scnprintf_fd
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
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
struct syscall_arg *arg)
{
return scnprintf(bf, size, "%#lx", arg->val);
}
#define SCA_HEX syscall_arg__scnprintf_hex
static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
struct syscall_arg *arg)
{
return scnprintf(bf, size, "%d", arg->val);
}
#define SCA_INT syscall_arg__scnprintf_int
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, prot = arg->val;
if (prot == PROT_NONE)
return scnprintf(bf, size, "NONE");
#define P_MMAP_PROT(n) \
if (prot & PROT_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
prot &= ~PROT_##n; \
}
P_MMAP_PROT(EXEC);
P_MMAP_PROT(READ);
P_MMAP_PROT(WRITE);
#ifdef PROT_SEM
P_MMAP_PROT(SEM);
#endif
P_MMAP_PROT(GROWSDOWN);
P_MMAP_PROT(GROWSUP);
#undef P_MMAP_PROT
if (prot)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot);
return printed;
}
#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
#define P_MMAP_FLAG(n) \
if (flags & MAP_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~MAP_##n; \
}
P_MMAP_FLAG(SHARED);
P_MMAP_FLAG(PRIVATE);
#ifdef MAP_32BIT
P_MMAP_FLAG(32BIT);
#endif
P_MMAP_FLAG(ANONYMOUS);
P_MMAP_FLAG(DENYWRITE);
P_MMAP_FLAG(EXECUTABLE);
P_MMAP_FLAG(FILE);
P_MMAP_FLAG(FIXED);
P_MMAP_FLAG(GROWSDOWN);
#ifdef MAP_HUGETLB
P_MMAP_FLAG(HUGETLB);
#endif
P_MMAP_FLAG(LOCKED);
P_MMAP_FLAG(NONBLOCK);
P_MMAP_FLAG(NORESERVE);
P_MMAP_FLAG(POPULATE);
P_MMAP_FLAG(STACK);
#ifdef MAP_UNINITIALIZED
P_MMAP_FLAG(UNINITIALIZED);
#endif
#undef P_MMAP_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
#define P_MREMAP_FLAG(n) \
if (flags & MREMAP_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~MREMAP_##n; \
}
P_MREMAP_FLAG(MAYMOVE);
#ifdef MREMAP_FIXED
P_MREMAP_FLAG(FIXED);
#endif
#undef P_MREMAP_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
struct syscall_arg *arg)
{
int behavior = arg->val;
switch (behavior) {
#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
P_MADV_BHV(NORMAL);
P_MADV_BHV(RANDOM);
P_MADV_BHV(SEQUENTIAL);
P_MADV_BHV(WILLNEED);
P_MADV_BHV(DONTNEED);
P_MADV_BHV(REMOVE);
P_MADV_BHV(DONTFORK);
P_MADV_BHV(DOFORK);
P_MADV_BHV(HWPOISON);
#ifdef MADV_SOFT_OFFLINE
P_MADV_BHV(SOFT_OFFLINE);
#endif
P_MADV_BHV(MERGEABLE);
P_MADV_BHV(UNMERGEABLE);
#ifdef MADV_HUGEPAGE
P_MADV_BHV(HUGEPAGE);
#endif
#ifdef MADV_NOHUGEPAGE
P_MADV_BHV(NOHUGEPAGE);
#endif
#ifdef MADV_DONTDUMP
P_MADV_BHV(DONTDUMP);
#endif
#ifdef MADV_DODUMP
P_MADV_BHV(DODUMP);
#endif
#undef P_MADV_PHV
default: break;
}
return scnprintf(bf, size, "%#x", behavior);
}
#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, op = arg->val;
if (op == 0)
return scnprintf(bf, size, "NONE");
#define P_CMD(cmd) \
if ((op & LOCK_##cmd) == LOCK_##cmd) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \
op &= ~LOCK_##cmd; \
}
P_CMD(SH);
P_CMD(EX);
P_CMD(NB);
P_CMD(UN);
P_CMD(MAND);
P_CMD(RW);
P_CMD(READ);
P_CMD(WRITE);
#undef P_OP
if (op)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op);
return printed;
}
#define SCA_FLOCK syscall_arg__scnprintf_flock
static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
{
enum syscall_futex_args {
SCF_UADDR = (1 << 0),
SCF_OP = (1 << 1),
SCF_VAL = (1 << 2),
SCF_TIMEOUT = (1 << 3),
SCF_UADDR2 = (1 << 4),
SCF_VAL3 = (1 << 5),
};
int op = arg->val;
int cmd = op & FUTEX_CMD_MASK;
size_t printed = 0;
switch (cmd) {
#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break;
P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break;
P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break;
P_FUTEX_OP(WAKE_OP); break;
P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break;
P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break;
P_FUTEX_OP(WAIT_REQUEUE_PI); break;
default: printed = scnprintf(bf, size, "%#x", cmd); break;
}
if (op & FUTEX_PRIVATE_FLAG)
printed += scnprintf(bf + printed, size - printed, "|PRIV");
if (op & FUTEX_CLOCK_REALTIME)
printed += scnprintf(bf + printed, size - printed, "|CLKRT");
return printed;
}
#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op
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 *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", "F_GETLK64",
"F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
"F_GETOWNER_UIDS",
};
static DEFINE_STRARRAY(fcntl_cmds);
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",
};
static DEFINE_STRARRAY(clockid);
static const char *socket_families[] = {
"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
"ALG", "NFC", "VSOCK",
};
static DEFINE_STRARRAY(socket_families);
#ifndef SOCK_TYPE_MASK
#define SOCK_TYPE_MASK 0xf
#endif
static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size,
struct syscall_arg *arg)
{
size_t printed;
int type = arg->val,
flags = type & ~SOCK_TYPE_MASK;
type &= SOCK_TYPE_MASK;
/*
* Can't use a strarray, MIPS may override for ABI reasons.
*/
switch (type) {
#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break;
P_SK_TYPE(STREAM);
P_SK_TYPE(DGRAM);
P_SK_TYPE(RAW);
P_SK_TYPE(RDM);
P_SK_TYPE(SEQPACKET);
P_SK_TYPE(DCCP);
P_SK_TYPE(PACKET);
#undef P_SK_TYPE
default:
printed = scnprintf(bf, size, "%#x", type);
}
#define P_SK_FLAG(n) \
if (flags & SOCK_##n) { \
printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
flags &= ~SOCK_##n; \
}
P_SK_FLAG(CLOEXEC);
P_SK_FLAG(NONBLOCK);
#undef P_SK_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "|%#x", flags);
return printed;
}
#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type
#ifndef MSG_PROBE
#define MSG_PROBE 0x10
#endif
#ifndef MSG_WAITFORONE
#define MSG_WAITFORONE 0x10000
#endif
#ifndef MSG_SENDPAGE_NOTLAST
#define MSG_SENDPAGE_NOTLAST 0x20000
#endif
#ifndef MSG_FASTOPEN
#define MSG_FASTOPEN 0x20000000
#endif
static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
if (flags == 0)
return scnprintf(bf, size, "NONE");
#define P_MSG_FLAG(n) \
if (flags & MSG_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~MSG_##n; \
}
P_MSG_FLAG(OOB);
P_MSG_FLAG(PEEK);
P_MSG_FLAG(DONTROUTE);
P_MSG_FLAG(TRYHARD);
P_MSG_FLAG(CTRUNC);
P_MSG_FLAG(PROBE);
P_MSG_FLAG(TRUNC);
P_MSG_FLAG(DONTWAIT);
P_MSG_FLAG(EOR);
P_MSG_FLAG(WAITALL);
P_MSG_FLAG(FIN);
P_MSG_FLAG(SYN);
P_MSG_FLAG(CONFIRM);
P_MSG_FLAG(RST);
P_MSG_FLAG(ERRQUEUE);
P_MSG_FLAG(NOSIGNAL);
P_MSG_FLAG(MORE);
P_MSG_FLAG(WAITFORONE);
P_MSG_FLAG(SENDPAGE_NOTLAST);
P_MSG_FLAG(FASTOPEN);
P_MSG_FLAG(CMSG_CLOEXEC);
#undef P_MSG_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
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_open_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
if (!(flags & O_CREAT))
arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
if (flags == 0)
return scnprintf(bf, size, "RDONLY");
#define P_FLAG(n) \
if (flags & O_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~O_##n; \
}
P_FLAG(APPEND);
P_FLAG(ASYNC);
P_FLAG(CLOEXEC);
P_FLAG(CREAT);
P_FLAG(DIRECT);
P_FLAG(DIRECTORY);
P_FLAG(EXCL);
P_FLAG(LARGEFILE);
P_FLAG(NOATIME);
P_FLAG(NOCTTY);
#ifdef O_NONBLOCK
P_FLAG(NONBLOCK);
#elif O_NDELAY
P_FLAG(NDELAY);
#endif
#ifdef O_PATH
P_FLAG(PATH);
#endif
P_FLAG(RDWR);
#ifdef O_DSYNC
if ((flags & O_SYNC) == O_SYNC)
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
else {
P_FLAG(DSYNC);
}
#else
P_FLAG(SYNC);
#endif
P_FLAG(TRUNC);
P_FLAG(WRONLY);
#undef P_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
if (flags == 0)
return 0;
#define P_FLAG(n) \
if (flags & PERF_FLAG_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~PERF_FLAG_##n; \
}
P_FLAG(FD_NO_GROUP);
P_FLAG(FD_OUTPUT);
P_FLAG(PID_CGROUP);
P_FLAG(FD_CLOEXEC);
#undef P_FLAG
if (flags)
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
return printed;
}
#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
if (flags == 0)
return scnprintf(bf, size, "NONE");
#define P_FLAG(n) \
if (flags & EFD_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~EFD_##n; \
}
P_FLAG(SEMAPHORE);
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_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags
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
static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
{
int sig = arg->val;
switch (sig) {
#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
P_SIGNUM(HUP);
P_SIGNUM(INT);
P_SIGNUM(QUIT);
P_SIGNUM(ILL);
P_SIGNUM(TRAP);
P_SIGNUM(ABRT);
P_SIGNUM(BUS);
P_SIGNUM(FPE);
P_SIGNUM(KILL);
P_SIGNUM(USR1);
P_SIGNUM(SEGV);
P_SIGNUM(USR2);
P_SIGNUM(PIPE);
P_SIGNUM(ALRM);
P_SIGNUM(TERM);
P_SIGNUM(CHLD);
P_SIGNUM(CONT);
P_SIGNUM(STOP);
P_SIGNUM(TSTP);
P_SIGNUM(TTIN);
P_SIGNUM(TTOU);
P_SIGNUM(URG);
P_SIGNUM(XCPU);
P_SIGNUM(XFSZ);
P_SIGNUM(VTALRM);
P_SIGNUM(PROF);
P_SIGNUM(WINCH);
P_SIGNUM(IO);
P_SIGNUM(PWR);
P_SIGNUM(SYS);
#ifdef SIGEMT
P_SIGNUM(EMT);
#endif
#ifdef SIGSTKFLT
P_SIGNUM(STKFLT);
#endif
#ifdef SIGSWI
P_SIGNUM(SWI);
#endif
default: break;
}
return scnprintf(bf, size, "%#x", sig);
}
#define SCA_SIGNUM syscall_arg__scnprintf_signum
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
*/
#define TCGETS 0x5401
static const char *tioctls[] = {
"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
"TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
"TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
"TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
"TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
"TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
"TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
"TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
"TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
"TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
[0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
"TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
};
static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
#endif /* defined(__i386__) || defined(__x86_64__) */
#define STRARRAY(arg, name, array) \
.arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
.arg_parm = { [arg] = &strarray__##array, }
static struct syscall_fmt {
const char *name;
const char *alias;
size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
void *arg_parm[6];
bool errmsg;
bool timeout;
bool hexret;
} syscall_fmts[] = {
{ .name = "access", .errmsg = true,
.arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
{ .name = "arch_prctl", .errmsg = true, .alias = "prctl", },
{ .name = "brk", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
{ .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), },
{ .name = "close", .errmsg = true,
.arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
{ .name = "connect", .errmsg = true, },
{ .name = "dup", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "dup2", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "dup3", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
{ .name = "eventfd2", .errmsg = true,
.arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
{ .name = "faccessat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "fadvise64", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fallocate", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchdir", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchmod", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchmodat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "fchown", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fchownat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "fcntl", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[1] = SCA_STRARRAY, /* cmd */ },
.arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
{ .name = "fdatasync", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "flock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[1] = SCA_FLOCK, /* cmd */ }, },
{ .name = "fsetxattr", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fstat", .errmsg = true, .alias = "newfstat",
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fstatat", .errmsg = true, .alias = "newfstatat",
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "fstatfs", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "fsync", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "ftruncate", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "futex", .errmsg = true,
.arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
{ .name = "futimesat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "getdents", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "getdents64", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "ioctl", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
#if defined(__i386__) || defined(__x86_64__)
/*
* FIXME: Make this available to all arches.
*/
[1] = SCA_STRHEXARRAY, /* cmd */
[2] = SCA_HEX, /* arg */ },
.arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, },
#else
[2] = SCA_HEX, /* arg */ }, },
#endif
{ .name = "kill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "linkat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "lseek", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
[2] = SCA_STRARRAY, /* whence */ },
.arg_parm = { [2] = &strarray__whences, /* whence */ }, },
{ .name = "lstat", .errmsg = true, .alias = "newlstat", },
{ .name = "madvise", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MADV_BHV, /* behavior */ }, },
{ .name = "mkdirat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "mknodat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
{ .name = "mlock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mlockall", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mmap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[2] = SCA_MMAP_PROT, /* prot */
[3] = SCA_MMAP_FLAGS, /* flags */
[4] = SCA_FD, /* fd */ }, },
{ .name = "mprotect", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* start */
[2] = SCA_MMAP_PROT, /* prot */ }, },
{ .name = "mremap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[3] = SCA_MREMAP_FLAGS, /* flags */
[4] = SCA_HEX, /* new_addr */ }, },
{ .name = "munlock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "munmap", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "name_to_handle_at", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "newfstatat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "open", .errmsg = true,
.arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "open_by_handle_at", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "openat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "perf_event_open", .errmsg = true,
.arg_scnprintf = { [1] = SCA_INT, /* pid */
[2] = SCA_INT, /* cpu */
[3] = SCA_FD, /* group_fd */
[4] = SCA_PERF_FLAGS, /* flags */ }, },
{ .name = "pipe2", .errmsg = true,
.arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
{ .name = "poll", .errmsg = true, .timeout = true, },
{ .name = "ppoll", .errmsg = true, .timeout = true, },
{ .name = "pread", .errmsg = true, .alias = "pread64",
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "preadv", .errmsg = true, .alias = "pread",
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
{ .name = "pwrite", .errmsg = true, .alias = "pwrite64",
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "pwritev", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "read", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "readlinkat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "readv", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "recvfrom", .errmsg = true,
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "recvmmsg", .errmsg = true,
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "recvmsg", .errmsg = true,
.arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "renameat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "rt_sigaction", .errmsg = true,
.arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
{ .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), },
{ .name = "rt_sigqueueinfo", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "rt_tgsigqueueinfo", .errmsg = true,
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
{ .name = "select", .errmsg = true, .timeout = true, },
{ .name = "sendmmsg", .errmsg = true,
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "sendmsg", .errmsg = true,
.arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "sendto", .errmsg = true,
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
{ .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), },
{ .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "shutdown", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "socket", .errmsg = true,
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
[1] = SCA_SK_TYPE, /* type */ },
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
{ .name = "socketpair", .errmsg = true,
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
[1] = SCA_SK_TYPE, /* type */ },
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
{ .name = "stat", .errmsg = true, .alias = "newstat", },
{ .name = "symlinkat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "tgkill", .errmsg = true,
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
{ .name = "tkill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "uname", .errmsg = true, .alias = "newuname", },
{ .name = "unlinkat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
{ .name = "utimensat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
{ .name = "write", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
{ .name = "writev", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
};
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);
}
struct syscall {
struct event_format *tp_format;
int nr_args;
struct format_field *args;
const char *name;
bool filtered;
bool is_exit;
struct syscall_fmt *fmt;
size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
void **arg_parm;
};
static size_t fprintf_duration(unsigned long t, FILE *fp)
{
double duration = (double)t / NSEC_PER_MSEC;
size_t printed = fprintf(fp, "(");
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, "): ");
}
struct thread_trace {
u64 entry_time;
u64 exit_time;
bool entry_pending;
unsigned long nr_events;
unsigned long pfmaj, pfmin;
char *entry_str;
double runtime_ms;
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;
}
#define TRACE_PFMAJ (1 << 0)
#define TRACE_PFMIN (1 << 1)
struct trace {
struct perf_tool tool;
struct {
int machine;
int open_id;
} audit;
struct {
int max;
struct syscall *table;
} syscalls;
struct record_opts opts;
struct perf_evlist *evlist;
struct machine *host;
struct thread *current;
u64 base_time;
FILE *output;
unsigned long nr_events;
struct strlist *ev_qualifier;
const char *last_vfs_getname;
struct intlist *tid_list;
struct intlist *pid_list;
struct {
size_t nr;
pid_t *entries;
} filter_pids;
double duration_filter;
double runtime_ms;
struct {
u64 vfs_getname,
proc_getname;
} stats;
bool not_ev_qualifier;
bool live;
bool full_time;
bool sched;
bool multiple_threads;
bool summary;
bool summary_only;
bool show_comm;
bool show_tool_stats;
bool trace_syscalls;
bool force;
int trace_pgfaults;
};
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];
}
static 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;
}
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 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);
}
static bool done = false;
static bool interrupted = false;
static void sig_handler(int sig)
{
done = true;
interrupted = sig == SIGINT;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
u64 duration, u64 tstamp, FILE *fp)
{
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
printed += fprintf_duration(duration, fp);
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 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);
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 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 = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
evlist->threads, trace__tool_process, false,
trace->opts.proc_map_timeout);
if (err)
symbol__exit();
return err;
}
static int syscall__set_arg_fmts(struct syscall *sc)
{
struct format_field *field;
int idx = 0;
sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
if (sc->arg_scnprintf == NULL)
return -1;
if (sc->fmt)
sc->arg_parm = sc->fmt->arg_parm;
for (field = sc->args; field; field = field->next) {
if (sc->fmt && sc->fmt->arg_scnprintf[idx])
sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
else if (field->flags & FIELD_IS_POINTER)
sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
++idx;
}
return 0;
}
static int trace__read_syscall_info(struct trace *trace, int id)
{
char tp_name[128];
struct syscall *sc;
const char *name = audit_syscall_to_name(id, trace->audit.machine);
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;
if (trace->ev_qualifier) {
bool in = strlist__find(trace->ev_qualifier, name) != NULL;
if (!(in ^ trace->not_ev_qualifier)) {
sc->filtered = true;
/*
* No need to do read tracepoint information since this will be
* filtered out.
*/
return 0;
}
}
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 (sc->tp_format == NULL && 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 (sc->tp_format == NULL)
return -1;
sc->args = sc->tp_format->format.fields;
sc->nr_args = sc->tp_format->format.nr_fields;
/* drop nr field - not relevant here; does not exist on older kernels */
if (sc->args && strcmp(sc->args->name, "nr") == 0) {
sc->args = sc->args->next;
--sc->nr_args;
}
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
return syscall__set_arg_fmts(sc);
}
static int trace__validate_ev_qualifier(struct trace *trace)
{
int err = 0;
struct str_node *pos;
strlist__for_each(pos, trace->ev_qualifier) {
const char *sc = pos->s;
if (audit_name_to_syscall(sc, trace->audit.machine) < 0) {
if (err == 0) {
fputs("Error:\tInvalid syscall ", trace->output);
err = -EINVAL;
} else {
fputs(", ", trace->output);
}
fputs(sc, trace->output);
}
}
if (err < 0) {
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
"\nHint:\tand: 'man syscalls'\n", trace->output);
}
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
*/
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
unsigned char *args, struct trace *trace,
struct thread *thread)
{
size_t printed = 0;
unsigned char *p;
unsigned long val;
if (sc->args != NULL) {
struct format_field *field;
u8 bit = 1;
struct syscall_arg arg = {
.idx = 0,
.mask = 0,
.trace = trace,
.thread = thread,
};
for (field = sc->args; field;
field = field->next, ++arg.idx, bit <<= 1) {
if (arg.mask & bit)
continue;
/* special care for unaligned accesses */
p = args + sizeof(unsigned long) * arg.idx;
memcpy(&val, p, sizeof(val));
/*
* 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_scnprintf &&
sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
sc->arg_parm[arg.idx]))
continue;
printed += scnprintf(bf + printed, size - printed,
"%s%s: ", printed ? ", " : "", field->name);
if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
arg.val = val;
if (sc->arg_parm)
arg.parm = sc->arg_parm[arg.idx];
printed += sc->arg_scnprintf[arg.idx](bf + printed,
size - printed, &arg);
} else {
printed += scnprintf(bf + printed, size - printed,
"%ld", val);
}
}
} else {
int i = 0;
while (i < 6) {
/* special care for unaligned accesses */
p = args + sizeof(unsigned long) * i;
memcpy(&val, p, sizeof(val));
printed += scnprintf(bf + printed, size - printed,
"%sarg%d: %ld",
printed ? ", " : "", i, val);
++i;
}
}
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) {
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 perf_sample *sample)
{
struct thread_trace *ttrace;
u64 duration;
size_t printed;
if (trace->current == NULL)
return 0;
ttrace = thread__priv(trace->current);
if (!ttrace->entry_pending)
return 0;
duration = sample->time - ttrace->entry_time;
printed = trace__fprintf_entry_head(trace, trace->current, duration, sample->time, trace->output);
printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
ttrace->entry_pending = false;
return printed;
}
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;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
return -1;
if (sc->filtered)
return 0;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
if (ttrace->entry_str == NULL) {
ttrace->entry_str = malloc(1024);
if (!ttrace->entry_str)
goto out_put;
}
if (!trace->summary_only)
trace__printf_interrupted_entry(trace, sample);
ttrace->entry_time = sample->time;
msg = ttrace->entry_str;
printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name);
printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
args, trace, thread);
if (sc->is_exit) {
if (!trace->duration_filter && !trace->summary_only) {
trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
fprintf(trace->output, "%-70s\n", ttrace->entry_str);
}
} else
ttrace->entry_pending = true;
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__sys_exit(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
long ret;
u64 duration = 0;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (sc == NULL)
return -1;
if (sc->filtered)
return 0;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
if (trace->summary)
thread__update_stats(ttrace, id, sample);
ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
trace->last_vfs_getname = NULL;
++trace->stats.vfs_getname;
}
ttrace->exit_time = sample->time;
if (ttrace->entry_time) {
duration = sample->time - ttrace->entry_time;
if (trace__filter_duration(trace, duration))
goto out;
} else if (trace->duration_filter)
goto out;
if (trace->summary_only)
goto out;
trace__fprintf_entry_head(trace, thread, duration, sample->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) {
signed_print:
fprintf(trace->output, ") = %ld", ret);
} else if (ret < 0 && sc->fmt->errmsg) {
char bf[STRERR_BUFSIZE];
const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
*e = audit_errno_to_name(-ret);
fprintf(trace->output, ") = -1 %s %s", e, emsg);
} else if (ret == 0 && sc->fmt->timeout)
fprintf(trace->output, ") = 0 Timeout");
else if (sc->fmt->hexret)
fprintf(trace->output, ") = %#lx", ret);
else
goto signed_print;
fputc('\n', trace->output);
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)
{
trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
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;
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"));
thread__put(thread);
return 0;
}
static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
trace__printf_interrupted_entry(trace, sample);
trace__fprintf_tstamp(trace, sample->time, trace->output);
if (trace->trace_syscalls)
fprintf(trace->output, "( ): ");
fprintf(trace->output, "%s:", evsel->name);
if (evsel->tp_format) {
event_format__fprintf(evsel->tp_format, sample->cpu,
sample->raw_data, sample->raw_size,
trace->output);
}
fprintf(trace->output, ")\n");
return 0;
}
static void print_location(FILE *f, struct perf_sample *sample,
struct addr_location *al,
bool print_dso, bool print_sym)
{
if ((verbose || print_dso) && al->map)
fprintf(f, "%s@", al->map->dso->long_name);
if ((verbose || 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,
struct perf_sample *sample)
{
struct thread *thread;
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
struct addr_location al;
char map_type = 'd';
struct thread_trace *ttrace;
int err = -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
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_addr_location(thread, cpumode, MAP__FUNCTION,
sample->ip, &al);
trace__fprintf_entry_head(trace, thread, 0, 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_addr_location(thread, cpumode, MAP__VARIABLE,
sample->addr, &al);
if (!al.map) {
thread__find_addr_location(thread, cpumode,
MAP__FUNCTION, 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);
out:
err = 0;
out_put:
thread__put(thread);
return err;
}
static bool skip_sample(struct trace *trace, struct perf_sample *sample)
{
if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
(trace->tid_list && intlist__find(trace->tid_list, sample->tid)))
return false;
if (trace->pid_list || trace->tid_list)
return true;
return false;
}
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);
int err = 0;
tracepoint_handler handler = evsel->handler;
if (skip_sample(trace, sample))
return 0;
if (!trace->full_time && trace->base_time == 0)
trace->base_time = sample->time;
if (handler) {
++trace->nr_events;
handler(trace, evsel, event, sample);
}
return err;
}
static int parse_target_str(struct trace *trace)
{
if (trace->opts.target.pid) {
trace->pid_list = intlist__new(trace->opts.target.pid);
if (trace->pid_list == NULL) {
pr_err("Error parsing process id string\n");
return -EINVAL;
}
}
if (trace->opts.target.tid) {
trace->tid_list = intlist__new(trace->opts.target.tid);
if (trace->tid_list == NULL) {
pr_err("Error parsing thread id string\n");
return -EINVAL;
}
}
return 0;
}
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");
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, NULL);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
if (evsel == NULL)
return;
if (perf_evsel__field(evsel, "pathname") == NULL) {
perf_evsel__delete(evsel);
return;
}
evsel->handler = trace__vfs_getname;
perf_evlist__add(evlist, evsel);
}
static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
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)
return -ENOMEM;
evsel->handler = trace__pgfault;
perf_evlist__add(evlist, evsel);
return 0;
}
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 (!trace->full_time && trace->base_time == 0)
trace->base_time = sample->time;
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;
}
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__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = trace->evlist;
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
bool draining = false;
trace->live = true;
if (trace->trace_syscalls &&
perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
trace__sys_exit))
goto out_error_raw_syscalls;
if (trace->trace_syscalls)
perf_evlist__add_vfs_getname(evlist);
if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) {
goto out_error_mem;
}
if ((trace->trace_pgfaults & TRACE_PFMIN) &&
perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
goto out_error_mem;
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
trace__sched_stat_runtime))
goto out_error_sched_stat_runtime;
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);
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;
/*
* 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 = perf_evlist__set_filter_pid(evlist, getpid());
if (err < 0) {
printf("err=%d,%s\n", -err, strerror(-err));
exit(1);
}
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
if (err < 0)
goto out_error_mmap;
if (!target__none(&trace->opts.target))
perf_evlist__enable(evlist);
if (forks)
perf_evlist__start_workload(evlist);
trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
evlist->threads->nr > 1 ||
perf_evlist__first(evlist)->attr.inherit;
again:
before = trace->nr_events;
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
while ((event = perf_evlist__mmap_read(evlist, i)) != 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_evlist__mmap_consume(evlist, i);
if (interrupted)
goto out_disable;
if (done && !draining) {
perf_evlist__disable(evlist);
draining = true;
}
}
}
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:
perf_evlist__delete(evlist);
trace->evlist = NULL;
trace->live = false;
return err;
{
char errbuf[BUFSIZ];
out_error_sched_stat_runtime:
debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
goto out_error;
out_error_raw_syscalls:
debugfs__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_mem:
fprintf(trace->output, "Not enough memory to run!\n");
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_file 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;