Hi,
One of CRIU tests fails with this patch:
https://github.com/xemul/criu/blob/master/test/zdtm/static/seccomp_filter_tsync.c
Before this patch only a thread which called a "wrong" syscall is killed.
Now a whole process is killed if one of threads called a "wrong" syscall.
Before this patch only one thread is killed:
512 seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, {len=4,
filter=0x7fffe111fb10} <unfinished ...>
484 kill(30, SIG_0) = 0
484 write(1, "Wait for zdtm/static/seccomp_filter_tsync(30) to die for
0.100000\n", 66 <unfinished ...>
512 <... seccomp resumed> ) = 0
512 futex(0x606420, FUTEX_WAKE_PRIVATE, 1 <unfinished ...>
484 <... write resumed> ) = 66
512 <... futex resumed> ) = 1
484 select(0, NULL, NULL, NULL, {tv_sec=0, tv_usec=100000} <unfinished ...>
512 futex(0x7f9e894a19d0, FUTEX_WAIT, 32, NULL <unfinished ...>
513 <... futex resumed> ) = 0
513 futex(0x606420, FUTEX_WAKE_PRIVATE, 1) = 0
513 ptrace(PTRACE_TRACEME) = ?
513 +++ killed by SIGSYS +++
512 <... futex resumed> ) = 0
After this patch a whole process is killed:
767 seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, {len=4,
filter=0x7ffdeedbcd20}) = 0
767 futex(0x606420, FUTEX_WAKE_PRIVATE, 1) = 1
768 <... futex resumed> ) = 0
767 futex(0x7fab05b229d0, FUTEX_WAIT, 32, NULL <unfinished ...>
768 futex(0x606420, FUTEX_WAKE_PRIVATE, 1) = 0
768 ptrace(PTRACE_TRACEME <unfinished ...>
767 <... futex resumed>) = ?
768 <... ptrace resumed>) = ?
768 +++ killed by SIGSYS (core dumped) +++
767 +++ killed by SIGSYS (core dumped) +++
766 <... wait4 resumed> [{WIFSIGNALED(s) && WTERMSIG(s) == SIGSYS &&
WCOREDUMP(s)}], 0, NULL) = 31
766 --- SIGCHLD {si_signo=SIGCHLD, si_code=CLD_KILLED, si_pid=31, si_
Steps to reproduce:
$ git clone git://github.com/xemul/criu
$ cd criu/test/zdtm/static/
$ make seccomp_filter_tsync.out
$ cat seccomp_filter_tsync.out
On Thu, Jan 19, 2017 at 10:28:57PM -0600, Mike Frysinger wrote:
> From: Mike Frysinger <vap...@chromium.org>
>
> The SECCOMP_RET_KILL mode is documented as immediately killing the
> process as if a SIGSYS had been sent and not caught (similar to a
> SIGKILL). However, a SIGSYS is documented as triggering a coredump
> which does not happen today.
>
> This has the advantage of being able to more easily debug a process
> that fails a seccomp filter. Today, most apps need to recompile and
> change their filter in order to get detailed info out, or manually run
> things through strace, or enable detailed kernel auditing. Now we get
> coredumps that fit into existing system-wide crash reporting setups.
>
> >From a security pov, this shouldn't be a problem. Unhandled signals
> can already be sent externally which trigger a coredump independent of
> the status of the seccomp filter. The act of dumping core itself does
> not cause change in execution of the program.
>
> URL: https://crbug.com/676357
> Signed-off-by: Mike Frysinger <vap...@chromium.org>
> Acked-by: Jorge Lucangeli Obes <jorg...@chromium.org>
> Acked-by: Kees Cook <keesc...@chromium.org>
> Acked-by: Kees Cook <keesc...@chromium.org>
> ---
> kernel/seccomp.c | 29 +++++++++++++++++++++--------
> 1 file changed, 21 insertions(+), 8 deletions(-)
>
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index f7ce79a46050..f8f88ebcb3ba 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -16,6 +16,7 @@
> #include <linux/atomic.h>
> #include <linux/audit.h>
> #include <linux/compat.h>
> +#include <linux/coredump.h>
> #include <linux/sched.h>
> #include <linux/seccomp.h>
> #include <linux/slab.h>
> @@ -486,6 +487,17 @@ void put_seccomp_filter(struct task_struct *tsk)
> }
> }
>
> +static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason)
> +{
> + memset(info, 0, sizeof(*info));
> + info->si_signo = SIGSYS;
> + info->si_code = SYS_SECCOMP;
> + info->si_call_addr = (void __user *)KSTK_EIP(current);
> + info->si_errno = reason;
> + info->si_arch = syscall_get_arch();
> + info->si_syscall = syscall;
> +}
> +
> /**
> * seccomp_send_sigsys - signals the task to allow in-process syscall
> emulation
> * @syscall: syscall number to send to userland
> @@ -496,13 +508,7 @@ void put_seccomp_filter(struct task_struct *tsk)
> static void seccomp_send_sigsys(int syscall, int reason)
> {
> struct siginfo info;
> - memset(&info, 0, sizeof(info));
> - info.si_signo = SIGSYS;
> - info.si_code = SYS_SECCOMP;
> - info.si_call_addr = (void __user *)KSTK_EIP(current);
> - info.si_errno = reason;
> - info.si_arch = syscall_get_arch();
> - info.si_syscall = syscall;
> + seccomp_init_siginfo(&info, syscall, reason);
> force_sig_info(SIGSYS, &info, current);
> }
> #endif /* CONFIG_SECCOMP_FILTER */
> @@ -634,10 +640,17 @@ static int __seccomp_filter(int this_syscall, const
> struct seccomp_data *sd,
> return 0;
>
> case SECCOMP_RET_KILL:
> - default:
> + default: {
> + siginfo_t info;
> audit_seccomp(this_syscall, SIGSYS, action);
> + /* Show the original registers in the dump. */
> + syscall_rollback(current, task_pt_regs(current));
> + /* Trigger a manual coredump since do_exit skips it. */
> + seccomp_init_siginfo(&info, this_syscall, data);
> + do_coredump(&info);
> do_exit(SIGSYS);
> }
> + }
>
> unreachable();
>
