Revert changes to convert to ->poll_mask() and aio IOCB_CMD_POLL

The poll() changes were not well thought out, and completely
unexplained.  They also caused a huge performance regression, because
"->poll()" was no longer a trivial file operation that just called down
to the underlying file operations, but instead did at least two indirect
calls.

Indirect calls are sadly slow now with the Spectre mitigation, but the
performance problem could at least be largely mitigated by changing the
"->get_poll_head()" operation to just have a per-file-descriptor pointer
to the poll head instead.  That gets rid of one of the new indirections.

But that doesn't fix the new complexity that is completely unwarranted
for the regular case.  The (undocumented) reason for the poll() changes
was some alleged AIO poll race fixing, but we don't make the common case
slower and more complex for some uncommon special case, so this all
really needs way more explanations and most likely a fundamental
redesign.

[ This revert is a revert of about 30 different commits, not reverted
  individually because that would just be unnecessarily messy  - Linus ]

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 19 insertions, 11 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 95b02a71fd47..e5473c03d667 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -638,8 +638,9 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
 static int unix_socketpair(struct socket *, struct socket *);
 static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll_mask(struct socket *, __poll_t);
-static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
+static __poll_t unix_dgram_poll(struct file *, struct socket *,
+				    poll_table *);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -680,7 +681,7 @@ static const struct proto_ops unix_stream_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_poll_mask,
+	.poll =		unix_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -703,7 +704,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_dgram_poll_mask,
+	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	unix_shutdown,
@@ -725,7 +726,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.socketpair =	unix_socketpair,
 	.accept =	unix_accept,
 	.getname =	unix_getname,
-	.poll_mask =	unix_dgram_poll_mask,
+	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
@@ -2629,10 +2630,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return err;
 }
 
-static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -2661,11 +2665,15 @@ static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
 	return mask;
 }
 
-static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
+				    poll_table *wait)
 {
 	struct sock *sk = sock->sk, *other;
-	int writable;
-	__poll_t mask = 0;
+	unsigned int writable;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -2691,7 +2699,7 @@ static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
 	}
 
 	/* No write status requested, avoid expensive OUT tests. */
-	if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+	if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
 		return mask;
 
 	writable = unix_writable(sk);