Get best of the week

Linux Strace: History, Design, and Usage


In Unix-like operating systems, the program communicates with the outside world and the operating system through a small set of functions - system calls. So, for debugging purposes, it is useful to spy on system calls performed by processes.


« » Linux strace, . «» strace .





OC Unix — (. system calls, syscalls), .


Unix (Version 6 Unix, 1975 ) . Bell Labs (Version 7 Unix, 1979 ) — ptrace.


ptrace , 80- ( System V Release 4) — .


strace comp.sources.sun 1992 trace Sun. , SunOS, 1994 strace System V, Solaris Linux.


strace Linux ptrace, .


( ) strace — . , , , . , - «» "strace".


, ptrace POSIX, Linux, FreeBSD, OpenBSD Unix.


strace : Piglet Trace


"You are not expected to understand this" ( , Version 6 Unix)

: , ( «», ). , Unix open-source-.


strace . . , strace , — Piglet Trace (ptr). , — — :


$ gcc examples/piglet-trace.c -o ptr
$ ptr echo test > /dev/null
BRK(12) -> 94744690540544
ACCESS(21) -> 18446744073709551614
ACCESS(21) -> 18446744073709551614
unknown(257) -> 3
FSTAT(5) -> 0
MMAP(9) -> 140694657216512
CLOSE(3) -> 0
ACCESS(21) -> 18446744073709551614
unknown(257) -> 3
READ(0) -> 832
FSTAT(5) -> 0
MMAP(9) -> 140694657208320
MMAP(9) -> 140694650953728
MPROTECT(10) -> 0
MMAP(9) -> 140694655045632
MMAP(9) -> 140694655070208
CLOSE(3) -> 0
unknown(158) -> 0
MPROTECT(10) -> 0
MPROTECT(10) -> 0
MPROTECT(10) -> 0
MUNMAP(11) -> 0
BRK(12) -> 94744690540544
BRK(12) -> 94744690675712
unknown(257) -> 3
FSTAT(5) -> 0
MMAP(9) -> 140694646390784
CLOSE(3) -> 0
FSTAT(5) -> 0
IOCTL(16) -> 18446744073709551591
WRITE(1) -> 5
CLOSE(3) -> 0
CLOSE(3) -> 0
unknown(231)
Tracee terminated

Piglet Trace Linux (. ) x86-64. .


. Linux , , ptrace. , PTRACE_TRACEME, PTRACE_SYSCALL PTRACE_GETREGS.


Unix-: fork(2) , exec(3) . — ptrace(PTRACE_TRACEME) exec: - , - :


pid_t child_pid = fork();
switch (child_pid) {
case -1:
    err(EXIT_FAILURE, "fork");
case 0:
    /* Child here */
    /* A traced mode has to be enabled. A parent will have to wait(2) for it
     * to happen. */
    ptrace(PTRACE_TRACEME, 0, NULL, NULL);
    /* Replace itself with a program to be run. */
    execvp(argv[1], argv + 1);
    err(EXIT_FAILURE, "exec");
}

- wait(2) , , :


/* Parent */

/* First we wait for the child to set the traced mode (see
 * ptrace(PTRACE_TRACEME) above) */
if (waitpid(child_pid, NULL, 0) == -1)
    err(EXIT_FAILURE, "traceme -> waitpid");

.


ptrace(PTRACE_SYSCALL) , wait , . - : , .


ptrace(PTRACE_GETREGS), rax ( ) ( ).


, :


/* A system call tracing loop, one interation per call. */
for (;;) {
    /* A non-portable structure defined for ptrace/GDB/strace usage mostly.
     * It allows to conveniently dump and access register state using
     * ptrace. */
    struct user_regs_struct registers;

    /* Enter syscall: continue execution until the next system call
     * beginning. Stop right before syscall.
     *
     * It's possible to change the system call number, system call
     * arguments, return value or even avoid executing the system call
     * completely. */
  if (ptrace(PTRACE_SYSCALL, child_pid, NULL, NULL) == -1)
      err(EXIT_FAILURE, "enter_syscall");
  if (waitpid(child_pid, NULL, 0) == -1)
      err(EXIT_FAILURE, "enter_syscall -> waitpid");

  /* According to the x86-64 system call convention on Linux (see man 2
   * syscall) the number identifying a syscall should be put into the rax
   * general purpose register, with the rest of the arguments residing in
   * other general purpose registers (rdi,rsi, rdx, r10, r8, r9). */
  if (ptrace(PTRACE_GETREGS, child_pid, NULL, &registers) == -1)
      err(EXIT_FAILURE, "enter_syscall -> getregs");

  /* Note how orig_rax is used here. That's because on x86-64 rax is used
   * both for executing a syscall, and returning a value from it. To
   * differentiate between the cases both rax and orig_rax are updated on
   * syscall entry/exit, and only rax is updated on exit. */
  print_syscall_enter(registers.orig_rax);

  /* Exit syscall: execute of the syscall, and stop on system
   * call exit.
   *
   * More system call tinkering possible: change the return value, record
   * time it took to finish the system call, etc. */
  if (ptrace(PTRACE_SYSCALL, child_pid, NULL, NULL) == -1)
      err(EXIT_FAILURE, "exit_syscall");
  if (waitpid(child_pid, NULL, 0) == -1)
      err(EXIT_FAILURE, "exit_syscall -> waitpid");

  /* Retrieve register state again as we want to inspect system call
   * return value. */
  if (ptrace(PTRACE_GETREGS, child_pid, NULL, &registers) == -1) {
      /* ESRCH is returned when a child terminates using a syscall and no
       * return value is possible, e.g. as a result of exit(2). */
      if (errno == ESRCH) {
          fprintf(stderr, "\nTracee terminated\n");
          break;
      }
      err(EXIT_FAILURE, "exit_syscall -> getregs");
  }

  /* Done with this system call, let the next iteration handle the next
   * one */
  print_syscall_exit(registers.rax);
}

. , DTrace Linux.


: strace


strace, , — strace.


, write:


int main(int argc, char *argv[])
{
    char str[] = "write me to stdout\n";
    /* write(2) is a simple wrapper around a syscall so it should be easy to
     * find in the syscall trace. */
    if (sizeof(str) != write(STDOUT_FILENO, str, sizeof(str))){
        perror("write");
        return EXIT_FAILURE;
    }
    return EXIT_SUCCESS;
}

, :


$ gcc examples/write-simple.c -o write-simple
$ ./write-simple
write me to stdout

strace:


$ strace ./write-simple
pexecve("./write", ["./write"], 0x7ffebd6145b0 /* 71 vars */) = 0
brk(NULL)                               = 0x55ff5489e000
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
openat(AT_FDCWD, "/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=197410, ...}) = 0
mmap(NULL, 197410, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7a2a633000
close(3)                                = 0
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "\177ELF\2\1\1\3\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0\260\34\2\0\0\0\0\0"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2030544, ...}) = 0
mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f7a2a631000
mmap(NULL, 4131552, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7a2a04c000
mprotect(0x7f7a2a233000, 2097152, PROT_NONE) = 0
mmap(0x7f7a2a433000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1e7000) = 0x7f7a2a433000
mmap(0x7f7a2a439000, 15072, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x7f7a2a439000
close(3)                                = 0
arch_prctl(ARCH_SET_FS, 0x7f7a2a6324c0) = 0
mprotect(0x7f7a2a433000, 16384, PROT_READ) = 0
mprotect(0x55ff52b52000, 4096, PROT_READ) = 0
mprotect(0x7f7a2a664000, 4096, PROT_READ) = 0
munmap(0x7f7a2a633000, 197410)          = 0
write(1, "write me to stdout\n\0", 20write me to stdout
)  = 20
exit_group(0)                           = ?

«» . : strace , .


strace -o, -.


«» . , write. -e , . — , trace=*, .


-o -e :


$ strace -e trace=write -owrite-simple.log ./write-simple
write me to stdout
$ cat write-simple.log
write(1, "write me to stdout\n\0", 20
)  = 20
+++ exited with 0 +++

, , .


— , :


$ strace -e trace=\!brk,mmap,mprotect,munmap -owrite-simple.log ./write-simple
write me to stdout
$ cat write-simple.log
execve("./write-simple", ["./write-simple"], 0x7ffe9972a498 /* 69 vars */) = 0
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
openat(AT_FDCWD, "/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=124066, ...}) = 0
close(3)                                = 0
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
openat(AT_FDCWD, "/lib/x86_64-linux-gnu/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "\177ELF\2\1\1\3\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0\260\34\2\0\0\0\0\0"..., 832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2030544, ...}) = 0
close(3)                                = 0
arch_prctl(ARCH_SET_FS, 0x7f00f0be74c0) = 0
write(1, "write me to stdout\n\0", 20)  = 20
exit_group(0)                           = ?
+++ exited with 0 +++

: (. shell).


glibc exit_group, _exit. : , , . , .


:


ptrace, strace, . , , Version 6 Unix. : , . — . strace .


:


int main(int argc, char *argv[])
{
    (void) argc; (void) argv;

    char str[] = "write me\n";

    write(STDOUT_FILENO, str, sizeof(str));

    /* Sleep indefinitely or until a signal arrives */
    pause();

    write(STDOUT_FILENO, str, sizeof(str));

    return EXIT_SUCCESS;
}

, :


$ gcc examples/write-sleep.c -o write-sleep
$ ./write-sleep
./write-sleep
write me
^C
$

:


$ ./write-sleep &
[1] 15329
write me
$ strace -p 15329
strace: Process 15329 attached
pause(
^Cstrace: Process 15329 detached
 <detached ...>

pause. , :


$ strace -o write-sleep.log -p 15329 &
strace: Process 15329 attached
$
$ kill -CONT 15329
$ cat write-sleep.log
pause()                                 = ? ERESTARTNOHAND (To be restarted if no handler)
--- SIGCONT {si_signo=SIGCONT, si_code=SI_USER, si_pid=14989, si_uid=1001} ---
pause(
$
$ kill -TERM 15329
$ cat write-sleep.log
pause()                                 = ? ERESTARTNOHAND (To be restarted if no handler)
--- SIGCONT {si_signo=SIGCONT, si_code=SI_USER, si_pid=14989, si_uid=1001} ---
pause()                                 = ? ERESTARTNOHAND (To be restarted if no handler)
--- SIGTERM {si_signo=SIGTERM, si_code=SI_USER, si_pid=14989, si_uid=1001} ---
+++ killed by SIGTERM +++

strace. : pause , , strace , .


:


fork — Unix. , strace «» :


int main(int argc, char *argv[])
{
    pid_t parent_pid = getpid();
    pid_t child_pid = fork();
    if (child_pid == 0) {
        /* A child is born! */
        child_pid = getpid();

        /* In the end of the day printf is just a call to write(2). */
        printf("child (self=%d)\n", child_pid);
        exit(EXIT_SUCCESS);
    }

    printf("parent (self=%d, child=%d)\n", parent_pid, child_pid);

    wait(NULL);

    exit(EXIT_SUCCESS);
}

, :


$ gcc examples/fork-write.c -o fork-write
$ ./fork-write
parent (self=11274, child=11275)
child (self=11275)

:


$ strace -e trace=write -ofork-write.log ./fork-write
child (self=22049)
parent (self=22048, child=22049)
$ cat fork-write.log
write(1, "parent (self=22048, child=22049)"..., 33) = 33
--- SIGCHLD {si_signo=SIGCHLD, si_code=CLD_EXITED, si_pid=22049, si_uid=1001, si_status=0, si_utime=0, si_stime=0} ---
+++ exited with 0 +++

-f, strace -. pid , :


$ strace -f -e trace=write -ofork-write.log ./fork-write
parent (self=22710, child=22711)
child (self=22711)
$ cat fork-write.log
22710 write(1, "parent (self=22710, child=22711)"..., 33) = 33
22711 write(1, "child (self=22711)\n", 19) = 19
22711 +++ exited with 0 +++
22710 --- SIGCHLD {si_signo=SIGCHLD, si_code=CLD_EXITED, si_pid=22711, si_uid=1001, si_status=0, si_utime=0, si_stime=0} ---
22710 +++ exited with 0 +++

:


$ strace -f -e trace=%process -ofork-write.log ./fork-write
parent (self=23610, child=23611)
child (self=23611)
$ cat fork-write.log
23610 execve("./fork-write", ["./fork-write"], 0x7fff696ff720 /* 63 vars */) = 0
23610 arch_prctl(ARCH_SET_FS, 0x7f3d03ba44c0) = 0
23610 clone(child_stack=NULL, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, child_tidptr=0x7f3d03ba4790) = 23611
23610 wait4(-1,  <unfinished ...>
23611 exit_group(0)                     = ?
23611 +++ exited with 0 +++
23610 <... wait4 resumed> NULL, 0, NULL) = 23611
23610 --- SIGCHLD {si_signo=SIGCHLD, si_code=CLD_EXITED, si_pid=23611, si_uid=1001, si_status=0, si_utime=0, si_stime=0} ---
23610 exit_group(0)                     = ?
23610 +++ exited with 0 +++

, ?


:


, , , , , .


:


void do_write(int out_fd)
{
    char str[] = "write me to a file\n";

    if (sizeof(str) != write(out_fd, str, sizeof(str))){
        perror("write");
        exit(EXIT_FAILURE);
    }
}

int main(int argc, char *argv[])
{
    char tmp_filename_template[] = "/tmp/output_fileXXXXXX";

    int out_fd = mkstemp(tmp_filename_template);
    if (out_fd == -1) {
        perror("mkstemp");
        exit(EXIT_FAILURE);
    }

    do_write(out_fd);

    return EXIT_SUCCESS;
}

strace -, :


$ strace -e trace=write -o write-tmp-file.log ./write-tmp-file
$ cat write-tmp-file.log
write(3, "write me to a file\n\0", 20)  = 20
+++ exited with 0 +++

-y , :


$ strace -y -e trace=write -o write-tmp-file.log ./write-tmp-file
$ cat write-tmp-file.log
write(3</tmp/output_fileCf5MyW>, "write me to a file\n\0", 20) = 20
+++ exited with 0 +++

:


: , . , :


void do_write(int out_fd)
{
    char str[] = "write me to a file\n";

    if (sizeof(str) != write(out_fd, str, sizeof(str))){
        perror("write");
        exit(EXIT_FAILURE);
    }
}

int main(int argc, char *argv[])
{
    /*
     * Path will be provided by the first program argument.
     *  */
    const char *path = argv[1];

    /*
     * Open an existing file for writing in append mode.
     *  */
    int out_fd = open(path, O_APPEND | O_WRONLY);
    if (out_fd == -1) {
        perror("open");
        exit(EXIT_FAILURE);
    }

    do_write(out_fd);

    return EXIT_SUCCESS;
}

strace . -P strace :


$ strace -y -P/tmp/test_file.log -o write-file.log ./write-file /tmp/test_file.log
$ cat write-file.log
openat(AT_FDCWD, "/tmp/test_file.log", O_WRONLY|O_APPEND) = 3</tmp/test_file.log>
write(3</tmp/test_file.log>, "write me to a file\n\0", 20) = 20
+++ exited with 0 +++

:


strace . :


void *thread(void *arg)
{
    (void) arg;

    printf("Secondary thread: working\n");
    sleep(1);
    printf("Secondary thread: done\n");

    return NULL;
}

int main(int argc, char *argv[])
{
    printf("Initial thread: launching a thread\n");

    pthread_t thr;
    if (0 != pthread_create(&thr, NULL, thread, NULL)) {
        fprintf(stderr, "Initial thread: failed to create a thread");
        exit(EXIT_FAILURE);
    }

    printf("Initial thread: joining a thread\n");
    if (0 != pthread_join(thr, NULL)) {
        fprintf(stderr, "Initial thread: failed to join a thread");
        exit(EXIT_FAILURE);
    };

    printf("Initial thread: done");

    exit(EXIT_SUCCESS);
}

, , — -pthread:


$ gcc examples/thread-write.c -pthread -o thread-write
$ ./thread-write
/thread-write
Initial thread: launching a thread
Initial thread: joining a thread
Secondary thread: working
Secondary thread: done
Initial thread: done
$

-f, , pid .


, POSIX Threads, , Linux. — , .

:


$ strace -f -othread-write.log ./thread-write
$ wc -l thread-write.log
60 thread-write.log

write:


$ strace -f -e trace="%process,write" -othread-write.log ./thread-write
$ cat thread-write.log
18211 execve("./thread-write", ["./thread-write"], 0x7ffc6b8d58f0 /* 64 vars */) = 0
18211 arch_prctl(ARCH_SET_FS, 0x7f38ea3b7740) = 0
18211 write(1, "Initial thread: launching a thre"..., 35) = 35
18211 clone(child_stack=0x7f38e9ba2fb0, flags=CLONE_VM|CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|CLONE_SYSVSEM|CLONE_SETTLS|CLONE_PARENT_SETTID|CLONE_CHILD_CLEARTID, parent_tidptr=0x7f38e9ba39d0, tls=0x7f38e9ba3700, child_tidptr=0x7f38e9ba39d0) = 18212
18211 write(1, "Initial thread: joining a thread"..., 33) = 33
18212 write(1, "Secondary thread: working\n", 26) = 26
18212 write(1, "Secondary thread: done\n", 23) = 23
18212 exit(0)                           = ?
18212 +++ exited with 0 +++
18211 write(1, "Initial thread: done", 20) = 20
18211 exit_group(0)                     = ?
18211 +++ exited with 0 +++

, . ? ?


-:


strace — . :


void do_write(void)
{
    char str[] = "write me to stdout\n";
    if (sizeof(str) != write(STDOUT_FILENO, str, sizeof(str))){
        perror("write");
        exit(EXIT_FAILURE);
    }
}

int main(int argc, char *argv[])
{
    do_write();
    return EXIT_SUCCESS;
}

, , , -k ( ), :


$ gcc examples/write-simple.c -o write-simple
$ strace -k -e trace=write -o write-simple.log ./write-simple
write me to stdout
$ cat write-simple.log
write(1, "write me to stdout\n\0", 20)  = 20
 > /lib/x86_64-linux-gnu/libc-2.27.so(__write+0x14) [0x110154]
 > /home/vkazanov/projects-my/strace-post/write-simple(do_write+0x50) [0x78a]
 > /home/vkazanov/projects-my/strace-post/write-simple(main+0x14) [0x7d1]
 > /lib/x86_64-linux-gnu/libc-2.27.so(__libc_start_main+0xe7) [0x21b97]
 > /home/vkazanov/projects-my/strace-post/write-simple(_start+0x2a) [0x65a]
+++ exited with 0 +++

-:


: . , :


#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>

void do_write(const char *str, ssize_t len)
{
    if (len != write(STDOUT_FILENO, str, (size_t)len)){
        perror("write");
        exit(EXIT_FAILURE);
    }
}

int main(int argc, char *argv[])
{
    (void) argc; (void) argv;

    char str1[] = "write me 1\n";
    do_write(str1, sizeof(str1));

    char str2[] = "write me 2\n";
    do_write(str2, sizeof(str2));

    return EXIT_SUCCESS;
}

write:


$ gcc examples/write-twice.c -o write-twice
$ ./write-twice
write me 1
write me 2
$ strace -e trace=write -owrite-twice.log ./write-twice
write me 1
write me 2
$ cat write-twice.log
write(1, "write me 1\n\0", 12)          = 12
write(1, "write me 2\n\0", 12)          = 12
+++ exited with 0 +++

inject, EBADF write:


$ strace -e trace=write -e inject=write:error=EBADF -owrite-twice.log ./write-twice
$ cat write-twice.log
write(1, "write me 1\n\0", 12)          = -1 EBADF (Bad file descriptor) (INJECTED)
write(3, "write: Bad file descriptor\n", 27) = -1 EBADF (Bad file descriptor) (INJECTED)
+++ exited with 1 +++

, write, , perror. :


$ strace -e trace=write -e inject=write:error=EBADF:when=1 -owrite-twice.log ./write-twice
write: Bad file descriptor
$ cat write-twice.log
write(1, "write me 1\n\0", 12)          = -1 EBADF (Bad file descriptor) (INJECTED)
write(3, "write: Bad file descriptor\n", 27) = 27
+++ exited with 1 +++

:


$ strace -e trace=write -e inject=write:error=EBADF:when=2 -owrite-twice.log ./write-twice
write me 1
write: Bad file descriptor
$ cat write-twice.log
write(1, "write me 1\n\0", 12)          = 12
write(1, "write me 2\n\0", 12)          = -1 EBADF (Bad file descriptor) (INJECTED)
write(3, "write: Bad file descriptor\n", 27) = 27
+++ exited with 1 +++

:


$ strace -e trace=write -e fault=write:when=1 -owrite-twice.log ./write-twice
$ cat write-twice.log
write(1, "write me 1\n\0", 12)          = -1 ENOSYS (Function not implemented) (INJECTED)
write(3, "write: Function not implemented\n", 32) = 32
+++ exited with 1 +++

«» . :


$ strace -y -P/tmp/test_file.log -e inject=file:error=ENOENT -o write-file.log ./write-file /tmp/test_file.log
open: No such file or directory
$ cat write-file.log
openat(AT_FDCWD, "/tmp/test_file.log", O_WRONLY|O_APPEND) = -1 ENOENT (No such file or directory) (INJECTED)
+++ exited with 1 +++

, .



strace — . . , ltrace, SystemTap ftrace, perf. strace — , .


, Unix, man 1 strace !

More articles:


All Articles