timers: Prevent union confusion from unexpected restart_syscall()

The nanosleep syscalls use the restart_block mechanism, with a quirk:
The `type` and `rmtp`/`compat_rmtp` fields are set up unconditionally on
syscall entry, while the rest of the restart_block is only set up in the
unlikely case that the syscall is actually interrupted by a signal (or
pseudo-signal) that doesn't have a signal handler.

If the restart_block was set up by a previous syscall (futex(...,
FUTEX_WAIT, ...) or poll()) and hasn't been invalidated somehow since then,
this will clobber some of the union fields used by futex_wait_restart() and
do_restart_poll().

If userspace afterwards wrongly calls the restart_syscall syscall,
futex_wait_restart()/do_restart_poll() will read struct fields that have
been clobbered.

This doesn't actually lead to anything particularly interesting because
none of the union fields contain trusted kernel data, and
futex(..., FUTEX_WAIT, ...) and poll() aren't syscalls where it makes much
sense to apply seccomp filters to their arguments.

So the current consequences are just of the "if userspace does bad stuff,
it can damage itself, and that's not a problem" flavor.

But still, it seems like a hazard for future developers, so invalidate the
restart_block when partly setting it up in the nanosleep syscalls.

Signed-off-by: Jann Horn <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: thejh

kernel/time/hrtimer.c

@@ -2126,6 +2126,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
 	if (!timespec64_valid(&tu))
 		return -EINVAL;
 
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 	return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
@@ -2147,6 +2148,7 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
 	if (!timespec64_valid(&tu))
 		return -EINVAL;
 
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;
 	return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,

kernel/time/posix-stubs.c

@@ -147,6 +147,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 	texp = timespec64_to_ktime(t);
@@ -240,6 +241,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;
 	texp = timespec64_to_ktime(t);

kernel/time/posix-timers.c

@@ -1270,6 +1270,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 
@@ -1297,6 +1298,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;