signal: remove the wrong signal_pending() check in restore_user_sigmask()

commit 97abc889ee296faf95ca0e978340fb7b942a3e32 upstream.

This is the minimal fix for stable, I'll send cleanups later.

Commit 854a6ed56839 ("signal: Add restore_user_sigmask()") introduced
the visible change which breaks user-space: a signal temporary unblocked
by set_user_sigmask() can be delivered even if the caller returns
success or timeout.

Change restore_user_sigmask() to accept the additional "interrupted"
argument which should be used instead of signal_pending() check, and
update the callers.

Eric said:

: For clarity.  I don't think this is required by posix, or fundamentally to
: remove the races in select.  It is what linux has always done and we have
: applications who care so I agree this fix is needed.
:
: Further in any case where the semantic change that this patch rolls back
: (aka where allowing a signal to be delivered and the select like call to
: complete) would be advantage we can do as well if not better by using
: signalfd.
:
: Michael is there any chance we can get this guarantee of the linux
: implementation of pselect and friends clearly documented.  The guarantee
: that if the system call completes successfully we are guaranteed that no
: signal that is unblocked by using sigmask will be delivered?

Link: http://lkml.kernel.org/r/20190604134117.GA29963@redhat.com
Fixes: 854a6ed56839a40f6b5d02a2962f48841482eec4 ("signal: Add restore_user_sigmask()")
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Reported-by: NEric Wong <e@80x24.org>
Tested-by: NEric Wong <e@80x24.org>
Acked-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NDeepa Dinamani <deepa.kernel@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: <stable@vger.kernel.org>	[5.0+]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NJoseph Qi <joseph.qi@linux.alibaba.com>
Reviewed-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>

fs/aio.c

@@ -2096,6 +2096,7 @@ SYSCALL_DEFINE6(io_pgetevents,
 	struct __aio_sigset	ksig = { NULL, };
 	sigset_t		ksigmask, sigsaved;
 	struct timespec64	ts;
+	bool interrupted;
 	int ret;
 
 	if (timeout && unlikely(get_timespec64(&ts, timeout)))
@@ -2110,8 +2111,10 @@ SYSCALL_DEFINE6(io_pgetevents,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;
@@ -2153,6 +2156,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 	struct __compat_aio_sigset ksig = { NULL, };
 	sigset_t ksigmask, sigsaved;
 	struct timespec64 t;
+	bool interrupted;
 	int ret;
 
 	if (timeout && compat_get_timespec64(&t, timeout))
@@ -2166,8 +2170,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;

fs/eventpoll.c

@@ -2229,7 +2229,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
 
 	error = do_epoll_wait(epfd, events, maxevents, timeout);
 
-	restore_user_sigmask(sigmask, &sigsaved);
+	restore_user_sigmask(sigmask, &sigsaved, error == -EINTR);
 
 	return error;
 }
@@ -2254,7 +2254,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
 
 	err = do_epoll_wait(epfd, events, maxevents, timeout);
 
-	restore_user_sigmask(sigmask, &sigsaved);
+	restore_user_sigmask(sigmask, &sigsaved, err == -EINTR);
 
 	return err;
 }

fs/io_uring.c

@@ -2356,11 +2356,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	}
 
 	ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events);
-	if (ret == -ERESTARTSYS)
-		ret = -EINTR;
 
 	if (sig)
-		restore_user_sigmask(sig, &sigsaved);
+		restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS);
+
+	if (ret == -ERESTARTSYS)
+		ret = -EINTR;
 
 	return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0;
 }

fs/select.c

@@ -722,10 +722,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
 		return ret;
 
 	ret = core_sys_select(n, inp, outp, exp, to);
+	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
 	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
 	return ret;
 }
 
@@ -1048,8 +1047,7 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;
@@ -1292,10 +1290,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp,
 		return ret;
 
 	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
 	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
 	return ret;
 }
 
@@ -1341,8 +1338,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;

include/linux/signal.h

@@ -266,7 +266,7 @@ extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set,
 	sigset_t *oldset, size_t sigsetsize);
 extern void restore_user_sigmask(const void __user *usigmask,
-				 sigset_t *sigsaved);
+				 sigset_t *sigsaved, bool interrupted);
 extern void set_current_blocked(sigset_t *);
 extern void __set_current_blocked(const sigset_t *);
 extern int show_unhandled_signals;

kernel/signal.c

@@ -2793,7 +2793,8 @@ EXPORT_SYMBOL(set_compat_user_sigmask);
  * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
  * epoll_pwait where a new sigmask is passed in from userland for the syscalls.
  */
-void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
+void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved,
+				bool interrupted)
 {
 
 	if (!usigmask)
@@ -2803,7 +2804,7 @@ void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
 	 * Restoring sigmask here can lead to delivering signals that the above
 	 * syscalls are intended to block because of the sigmask passed in.
 	 */
-	if (signal_pending(current)) {
+	if (interrupted) {
 		current->saved_sigmask = *sigsaved;
 		set_restore_sigmask();
 		return;