#include "trace-event.h"
#include "util/parse-events.h"
#include "util/bpf-loader.h"
+#include "callchain.h"
#include "syscalltbl.h"
+#include "rb_resort.h"
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
#include <stdlib.h>
-#include <sys/mman.h>
-#include <linux/futex.h>
#include <linux/err.h>
-#include <linux/seccomp.h>
#include <linux/filter.h>
#include <linux/audit.h>
#include <sys/ptrace.h>
#include <linux/random.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
+#include <linux/stringify.h>
#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 trace {
struct perf_tool tool;
struct syscalltbl *sctbl;
u64 vfs_getname,
proc_getname;
} stats;
+ unsigned int max_stack;
+ unsigned int min_stack;
bool not_ev_qualifier;
bool live;
bool full_time;
bool show_comm;
bool show_tool_stats;
bool trace_syscalls;
+ bool kernel_syscallchains;
bool force;
bool vfs_getname;
int trace_pgfaults;
#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 *bpf_cmd[] = {
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
"MAP_GET_NEXT_KEY", "PROG_LOAD",
};
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)
{
#define SCA_FILENAME syscall_arg__scnprintf_filename
-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)
{
#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.
static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
#endif /* defined(__i386__) || defined(__x86_64__) */
-static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg)
-{
- int op = arg->val;
- size_t printed = 0;
-
- switch (op) {
-#define P_SECCOMP_SET_MODE_OP(n) case SECCOMP_SET_MODE_##n: printed = scnprintf(bf, size, #n); break
- P_SECCOMP_SET_MODE_OP(STRICT);
- P_SECCOMP_SET_MODE_OP(FILTER);
-#undef P_SECCOMP_SET_MODE_OP
- default: printed = scnprintf(bf, size, "%#x", op); break;
- }
-
- return printed;
-}
-
-#define SCA_SECCOMP_OP syscall_arg__scnprintf_seccomp_op
-
-static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, flags = arg->val;
-
-#define P_FLAG(n) \
- if (flags & SECCOMP_FILTER_FLAG_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~SECCOMP_FILTER_FLAG_##n; \
- }
-
- P_FLAG(TSYNC);
-#undef P_FLAG
-
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
- return printed;
-}
-
-#define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_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)
.arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
.arg_parm = { [arg] = &strarray__##array, }
-#include "trace/beauty/pid.c"
+#include "trace/beauty/eventfd.c"
+#include "trace/beauty/flock.c"
+#include "trace/beauty/futex_op.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"
static struct syscall_fmt {
[1] = SCA_FILENAME, /* filename */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "perf_event_open", .errmsg = true,
- .arg_scnprintf = { [1] = SCA_INT, /* pid */
- [2] = SCA_INT, /* cpu */
+ .arg_scnprintf = { [2] = SCA_INT, /* cpu */
[3] = SCA_FD, /* group_fd */
[4] = SCA_PERF_FLAGS, /* flags */ }, },
{ .name = "pipe2", .errmsg = true,
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 (trace->host == NULL)
return -ENOMEM;
- if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+ if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
return -errno;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
"%ld", val);
}
}
- } else {
+ } 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.
+ */
int i = 0;
while (i < 6) {
goto out_put;
}
- if (!trace->summary_only)
+ if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
trace__printf_interrupted_entry(trace, sample);
ttrace->entry_time = sample->time;
args, trace, thread);
if (sc->is_exit) {
- if (!trace->duration_filter && !trace->summary_only) {
+ if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
- fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+ fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
}
} else {
ttrace->entry_pending = true;
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;
+
+ if (machine__resolve(trace->host, &al, sample) < 0 ||
+ thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->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 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;
+ 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;
} 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)
goto out;
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;
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
+ 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, sample);
trace__fprintf_tstamp(trace, sample->time, trace->output);
}
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));
+out:
return 0;
}
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;
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:
return true;
}
-static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
- u64 config)
+static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
{
struct perf_evsel *evsel;
struct perf_event_attr attr = {
event_attr_init(&attr);
evsel = perf_evsel__new(&attr);
- if (!evsel)
- return -ENOMEM;
+ if (evsel)
+ evsel->handler = trace__pgfault;
- evsel->handler = trace__pgfault;
- perf_evlist__add(evlist, evsel);
-
- return 0;
+ return evsel;
}
static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
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;
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = trace->evlist;
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
if (trace->trace_syscalls)
trace->vfs_getname = 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_PFMAJ)) {
+ pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
+ if (pgfault_maj == NULL)
+ goto out_error_mem;
+ perf_evlist__add(evlist, pgfault_maj);
}
- if ((trace->trace_pgfaults & TRACE_PFMIN) &&
- perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
- goto out_error_mem;
+ 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_evlist__add(evlist, pgfault_min);
+ }
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
goto out_delete_evlist;
}
- perf_evlist__config(evlist, &trace->opts);
+ perf_evlist__config(evlist, &trace->opts, NULL);
+
+ if (callchain_param.enabled) {
+ bool use_identifier = false;
+
+ if (trace->syscalls.events.sys_exit) {
+ perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
+ &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (pgfault_maj) {
+ perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (pgfault_min) {
+ perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (use_identifier) {
+ /*
+ * Now we have evsels with different sample_ids, use
+ * PERF_SAMPLE_IDENTIFIER to map from sample to evsel
+ * from a fixed position in each ring buffer record.
+ *
+ * As of this the changeset introducing this comment, this
+ * isn't strictly needed, as the fields that can come before
+ * PERF_SAMPLE_ID are all used, but we'll probably disable
+ * some of those for things like copying the payload of
+ * pointer syscall arguments, and for vfs_getname we don't
+ * need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this
+ * here as a warning we need to use PERF_SAMPLE_IDENTIFIER.
+ */
+ perf_evlist__set_sample_bit(evlist, IDENTIFIER);
+ perf_evlist__reset_sample_bit(evlist, ID);
+ }
+ }
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
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)
{
- struct stats *stats;
size_t printed = 0;
struct syscall *sc;
- struct int_node *inode = intlist__first(ttrace->syscall_stats);
+ struct rb_node *nd;
+ DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
- if (inode == NULL)
+ if (syscall_stats == NULL)
return 0;
printed += fprintf(fp, "\n");
printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n");
printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n");
- /* each int_node is a syscall */
- while (inode) {
- stats = inode->priv;
+ resort_rb__for_each(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;
pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
avg /= NSEC_PER_MSEC;
- sc = &trace->syscalls.table[inode->i];
+ 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, avg * n, min, avg);
+ n, syscall_stats_entry->msecs, min, avg);
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
}
-
- inode = intlist__next(inode);
}
+ resort_rb__delete(syscall_stats);
printed += fprintf(fp, "\n\n");
return printed;
}
-/* struct used to pass data to per-thread function */
-struct summary_data {
- FILE *fp;
- struct trace *trace;
- size_t printed;
-};
-
-static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
{
- struct summary_data *data = priv;
- FILE *fp = data->fp;
- size_t printed = data->printed;
- struct trace *trace = data->trace;
+ size_t printed = 0;
struct thread_trace *ttrace = thread__priv(thread);
double ratio;
printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
if (ttrace->pfmin)
printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
- printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+ 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);
- data->printed += printed;
+ return printed;
+}
- return 0;
+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)
{
- struct summary_data data = {
- .fp = fp,
- .trace = trace
- };
- data.printed = trace__fprintf_threads_header(fp);
+ DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
+ size_t printed = trace__fprintf_threads_header(fp);
+ struct rb_node *nd;
- machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+ if (threads == NULL) {
+ fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+ return 0;
+ }
- return data.printed;
+ resort_rb__for_each(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,
.output = stderr,
.show_comm = true,
.trace_syscalls = true,
+ .kernel_syscallchains = false,
+ .max_stack = UINT_MAX,
};
const char *output_name = NULL;
const char *ev_qualifier_str = NULL;
"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_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
OPT_END()
};
+ bool __maybe_unused max_stack_user_set = true;
+ bool mmap_pages_user_set = true;
const char * const trace_subcommands[] = { "record", NULL };
int err;
char bf[BUFSIZ];
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_perf_event_max_stack;
+ max_stack_user_set = false;
+ }
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
+ 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);
return -1;
}
+ if (!trace.trace_syscalls && ev_qualifier_str) {
+ pr_err("The -e option can't be used with --no-syscalls.\n");
+ goto out;
+ }
+
if (output_name != NULL) {
err = trace__open_output(&trace, output_name);
if (err < 0) {