> Could you please re-test with this patch applied?
It turned out that this patch did not make much difference. the step-simple is
still failing with the patch applied. It could be reproduced a few times after
a fresh reboot. The test exited with 1 here,
/* Known bug in 2.6.28-rc7 + utrace patch:
* child was left to run freely, and exited
* Deterministic (happens even with NUM_SINGLESTEPS = 1)
*/
if (WIFEXITED (status))
{
VERBOSE("PTRACE_SINGLESTEP did not stop (step #%d)\n", i+1);
assert (WEXITSTATUS (status) == 42);
exit (1);
}
Here was the strace output when failure.
# strace ./step-simple
execve("./step-simple", ["./step-simple"], [/* 28 vars */]) = 0
brk(0) = 0x80003000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x20000027000
access("/etc/ld.so.preload", R_OK) = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=44711, ...}) = 0
mmap(NULL, 44711, PROT_READ, MAP_PRIVATE, 3, 0) = 0x20000028000
close(3) = 0
open("/lib64/libc.so.6", O_RDONLY) = 3
read(3,
"\177ELF\2\2\1\0\0\0\0\0\0\0\0\0\0\3\0\26\0\0\0\1\0\0\0\0\0\2\10\364\0"...,
832) = 832
fstat(3, {st_mode=S_IFREG|0755, st_size=2703224, ...}) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x20000033000
mmap(NULL, 1729920, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) =
0x20000034000
mmap(0x200001d1000, 20480, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x19c000) = 0x200001d1000
mmap(0x200001d6000, 17792, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x200001d6000
close(3) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x200001db000
mprotect(0x200001d1000, 16384, PROT_READ) = 0
mprotect(0x20000022000, 4096, PROT_READ) = 0
munmap(0x20000028000, 44711) = 0
rt_sigaction(SIGABRT, {0x80000e7c, [ABRT], SA_RESTART}, {SIG_DFL, [], 0}, 8) = 0
rt_sigaction(SIGINT, {0x80000e7c, [INT], SA_RESTART}, {SIG_DFL, [], 0}, 8) = 0
rt_sigaction(SIGALRM, {0x80000e7c, [ALRM], SA_RESTART}, {SIG_DFL, [], 0}, 8) = 0
alarm(5) = 0
clone(child_stack=0, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD,
child_tidptr=0x200001db7c0) = 2026
wait4(2026, [{WIFSTOPPED(s) && WSTOPSIG(s) == SIGSTOP}], 0, NULL) = 2026
--- SIGCHLD (Child exited) @ 0 (0) ---
ptrace(PTRACE_SINGLESTEP, 2026, 0, SIG_0) = 0
wait4(2026, [{WIFEXITED(s) && WEXITSTATUS(s) == 42}], 0, NULL) = 2026
--- SIGCHLD (Child exited) @ 0 (0) ---
kill(2026, SIGKILL) = -1 ESRCH (No such process)
wait4(-1, NULL, __WALL, NULL) = -1 ECHILD (No child processes)
exit_group(1)
Also, I could not reproduce the problem in kernels without utrace.
Thanks,
CAI Qian
