seccomp: Make syscall skipping and nr changes more consistent
This fixes two issues that could cause incompatibility between
kernel versions:
- If a tracer uses SECCOMP_RET_TRACE to select a syscall number
higher than the largest known syscall, emulate the unknown
vsyscall by returning -ENOSYS. (This is unlikely to make a
noticeable difference on x86-64 due to the way the system call
entry works.)
- On x86-64 with vsyscall=emulate, skipped vsyscalls were buggy.
This updates the documentation accordingly.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Will Drewry <wad@chromium.org>
Signed-off-by: James Morris <james.l.morris@oracle.com>
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ee376be..5af44b5 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -396,25 +396,29 @@
#ifdef CONFIG_SECCOMP_FILTER
case SECCOMP_MODE_FILTER: {
int data;
+ struct pt_regs *regs = task_pt_regs(current);
ret = seccomp_run_filters(this_syscall);
data = ret & SECCOMP_RET_DATA;
ret &= SECCOMP_RET_ACTION;
switch (ret) {
case SECCOMP_RET_ERRNO:
/* Set the low-order 16-bits as a errno. */
- syscall_set_return_value(current, task_pt_regs(current),
+ syscall_set_return_value(current, regs,
-data, 0);
goto skip;
case SECCOMP_RET_TRAP:
/* Show the handler the original registers. */
- syscall_rollback(current, task_pt_regs(current));
+ syscall_rollback(current, regs);
/* Let the filter pass back 16 bits of data. */
seccomp_send_sigsys(this_syscall, data);
goto skip;
case SECCOMP_RET_TRACE:
/* Skip these calls if there is no tracer. */
- if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+ syscall_set_return_value(current, regs,
+ -ENOSYS, 0);
goto skip;
+ }
/* Allow the BPF to provide the event message */
ptrace_event(PTRACE_EVENT_SECCOMP, data);
/*
@@ -425,6 +429,9 @@
*/
if (fatal_signal_pending(current))
break;
+ if (syscall_get_nr(current, regs) < 0)
+ goto skip; /* Explicit request to skip. */
+
return 0;
case SECCOMP_RET_ALLOW:
return 0;
