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>

Documentation/filesystems/Locking

@@ -441,8 +441,6 @@ prototypes:
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -473,7 +471,7 @@ prototypes:
 };
 
 locking rules:
-	All except for ->poll_mask may block.
+	All may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -505,9 +503,6 @@ in sys_read() and friends.
 the lease within the individual filesystem to record the result of the
 operation
 
-->poll_mask can be called with or without the waitqueue lock for the waitqueue
-returned from ->get_poll_head.
-
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);

Documentation/filesystems/vfs.txt

@@ -857,8 +857,6 @@ struct file_operations {
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -903,17 +901,6 @@ otherwise noted.
 	activity on this file and (optionally) go to sleep until there
 	is activity. Called by the select(2) and poll(2) system calls
 
-  get_poll_head: Returns the struct wait_queue_head that callers can
-  wait on.  Callers need to check the returned events using ->poll_mask
-  once woken.  Can return NULL to indicate polling is not supported,
-  or any error code using the ERR_PTR convention to indicate that a
-  grave error occured and ->poll_mask shall not be called.
-
-  poll_mask: return the mask of EPOLL* values describing the file descriptor
-  state.  Called either before going to sleep on the waitqueue returned by
-  get_poll_head, or after it has been woken.  If ->get_poll_head and
-  ->poll_mask are implemented ->poll does not need to be implement.
-
   unlocked_ioctl: called by the ioctl(2) system call.
 
   compat_ioctl: called by the ioctl(2) system call when 32 bit system calls

crypto/af_alg.c

@@ -1060,12 +1060,19 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
+/**
+ * af_alg_poll - poll system call handler
+ */
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+			 poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	if (!ctx->more || ctx->used)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -1075,7 +1082,7 @@ __poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL_GPL(af_alg_poll_mask);
+EXPORT_SYMBOL_GPL(af_alg_poll);
 
 /**
  * af_alg_alloc_areq - allocate struct af_alg_async_req

crypto/algif_aead.c

@@ -375,7 +375,7 @@ static struct proto_ops algif_aead_ops = {
 	.sendmsg	=	aead_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	aead_recvmsg,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static int aead_check_key(struct socket *sock)
@@ -471,7 +471,7 @@ static struct proto_ops algif_aead_ops_nokey = {
 	.sendmsg	=	aead_sendmsg_nokey,
 	.sendpage	=	aead_sendpage_nokey,
 	.recvmsg	=	aead_recvmsg_nokey,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static void *aead_bind(const char *name, u32 type, u32 mask)

crypto/algif_skcipher.c

@@ -206,7 +206,7 @@ static struct proto_ops algif_skcipher_ops = {
 	.sendmsg	=	skcipher_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	skcipher_recvmsg,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static int skcipher_check_key(struct socket *sock)
@@ -302,7 +302,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
 	.sendmsg	=	skcipher_sendmsg_nokey,
 	.sendpage	=	skcipher_sendpage_nokey,
 	.recvmsg	=	skcipher_recvmsg_nokey,
-	.poll_mask	=	af_alg_poll_mask,
+	.poll		=	af_alg_poll,
 };
 
 static void *skcipher_bind(const char *name, u32 type, u32 mask)

drivers/char/random.c

@@ -402,7 +402,8 @@ static struct poolinfo {
 /*
  * Static global variables
  */
-static DECLARE_WAIT_QUEUE_HEAD(random_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -721,8 +722,8 @@ retry:
 
 		/* should we wake readers? */
 		if (entropy_bits >= random_read_wakeup_bits &&
-		    wq_has_sleeper(&random_wait)) {
-			wake_up_interruptible_poll(&random_wait, POLLIN);
+		    wq_has_sleeper(&random_read_wait)) {
+			wake_up_interruptible(&random_read_wait);
 			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 		/* If the input pool is getting full, send some
@@ -1396,7 +1397,7 @@ retry:
 	trace_debit_entropy(r->name, 8 * ibytes);
 	if (ibytes &&
 	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
-		wake_up_interruptible_poll(&random_wait, POLLOUT);
+		wake_up_interruptible(&random_write_wait);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
 	}
 
@@ -1838,7 +1839,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
 		if (nonblock)
 			return -EAGAIN;
 
-		wait_event_interruptible(random_wait,
+		wait_event_interruptible(random_read_wait,
 			ENTROPY_BITS(&input_pool) >=
 			random_read_wakeup_bits);
 		if (signal_pending(current))
@@ -1875,17 +1876,14 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 	return ret;
 }
 
-static struct wait_queue_head *
-random_get_poll_head(struct file *file, __poll_t events)
-{
-	return &random_wait;
-}
-
 static __poll_t
-random_poll_mask(struct file *file, __poll_t events)
+random_poll(struct file *file, poll_table * wait)
 {
-	__poll_t mask = 0;
+	__poll_t mask;
 
+	poll_wait(file, &random_read_wait, wait);
+	poll_wait(file, &random_write_wait, wait);
+	mask = 0;
 	if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1992,8 +1990,7 @@ static int random_fasync(int fd, struct file *filp, int on)
 const struct file_operations random_fops = {
 	.read  = random_read,
 	.write = random_write,
-	.get_poll_head  = random_get_poll_head,
-	.poll_mask  = random_poll_mask,
+	.poll  = random_poll,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
 	.llseek = noop_llseek,
@@ -2326,7 +2323,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 	 * We'll be woken up again once below random_write_wakeup_thresh,
 	 * or when the calling thread is about to terminate.
 	 */
-	wait_event_interruptible(random_wait, kthread_should_stop() ||
+	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);

drivers/isdn/mISDN/socket.c

@@ -588,7 +588,7 @@ static const struct proto_ops data_sock_ops = {
 	.getname	= data_sock_getname,
 	.sendmsg	= mISDN_sock_sendmsg,
 	.recvmsg	= mISDN_sock_recvmsg,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= data_sock_setsockopt,

drivers/net/ppp/pppoe.c

@@ -1107,7 +1107,7 @@ static const struct proto_ops pppoe_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppoe_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,

fs/aio.c

@@ -5,7 +5,6 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
- *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -165,22 +164,10 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
-struct poll_iocb {
-	struct file		*file;
-	__poll_t		events;
-	struct wait_queue_head	*head;
-
-	union {
-		struct wait_queue_entry	wait;
-		struct work_struct	work;
-	};
-};
-
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
 		struct fsync_iocb	fsync;
-		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -1590,6 +1577,7 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
 			iocb->aio_rw_flags))
 		return -EINVAL;
+
 	req->file = fget(iocb->aio_fildes);
 	if (unlikely(!req->file))
 		return -EBADF;
@@ -1604,137 +1592,6 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
-/* need to use list_del_init so we can check if item was present */
-static inline bool __aio_poll_remove(struct poll_iocb *req)
-{
-	if (list_empty(&req->wait.entry))
-		return false;
-	list_del_init(&req->wait.entry);
-	return true;
-}
-
-static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
-	fput(iocb->poll.file);
-	aio_complete(iocb, mangle_poll(mask), 0);
-}
-
-static void aio_poll_work(struct work_struct *work)
-{
-	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
-
-	if (!list_empty_careful(&iocb->ki_list))
-		aio_remove_iocb(iocb);
-	__aio_poll_complete(iocb, iocb->poll.events);
-}
-
-static int aio_poll_cancel(struct kiocb *iocb)
-{
-	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
-	struct poll_iocb *req = &aiocb->poll;
-	struct wait_queue_head *head = req->head;
-	bool found = false;
-
-	spin_lock(&head->lock);
-	found = __aio_poll_remove(req);
-	spin_unlock(&head->lock);
-
-	if (found) {
-		req->events = 0;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
-	}
-	return 0;
-}
-
-static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
-		void *key)
-{
-	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
-	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
-	struct file *file = req->file;
-	__poll_t mask = key_to_poll(key);
-
-	assert_spin_locked(&req->head->lock);
-
-	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & req->events))
-		return 0;
-
-	mask = file->f_op->poll_mask(file, req->events) & req->events;
-	if (!mask)
-		return 0;
-
-	__aio_poll_remove(req);
-
-	/*
-	 * Try completing without a context switch if we can acquire ctx_lock
-	 * without spinning.  Otherwise we need to defer to a workqueue to
-	 * avoid a deadlock due to the lock order.
-	 */
-	if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
-		list_del_init(&iocb->ki_list);
-		spin_unlock(&iocb->ki_ctx->ctx_lock);
-
-		__aio_poll_complete(iocb, mask);
-	} else {
-		req->events = mask;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
-	}
-
-	return 1;
-}
-
-static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
-{
-	struct kioctx *ctx = aiocb->ki_ctx;
-	struct poll_iocb *req = &aiocb->poll;
-	__poll_t mask;
-
-	/* reject any unknown events outside the normal event mask. */
-	if ((u16)iocb->aio_buf != iocb->aio_buf)
-		return -EINVAL;
-	/* reject fields that are not defined for poll */
-	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
-		return -EINVAL;
-
-	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
-	req->file = fget(iocb->aio_fildes);
-	if (unlikely(!req->file))
-		return -EBADF;
-	if (!file_has_poll_mask(req->file))
-		goto out_fail;
-
-	req->head = req->file->f_op->get_poll_head(req->file, req->events);
-	if (!req->head)
-		goto out_fail;
-	if (IS_ERR(req->head)) {
-		mask = EPOLLERR;
-		goto done;
-	}
-
-	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
-	aiocb->ki_cancel = aio_poll_cancel;
-
-	spin_lock_irq(&ctx->ctx_lock);
-	spin_lock(&req->head->lock);
-	mask = req->file->f_op->poll_mask(req->file, req->events) & req->events;
-	if (!mask) {
-		__add_wait_queue(req->head, &req->wait);
-		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
-	}
-	spin_unlock(&req->head->lock);
-	spin_unlock_irq(&ctx->ctx_lock);
-done:
-	if (mask)
-		__aio_poll_complete(aiocb, mask);
-	return 0;
-out_fail:
-	fput(req->file);
-	return -EINVAL; /* same as no support for IOCB_CMD_POLL */
-}
-
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
@@ -1808,9 +1665,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_FDSYNC:
 		ret = aio_fsync(&req->fsync, &iocb, true);
 		break;
-	case IOCB_CMD_POLL:
-		ret = aio_poll(req, &iocb);
-		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;

fs/eventfd.c

@@ -101,20 +101,14 @@ static int eventfd_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static struct wait_queue_head *
-eventfd_get_poll_head(struct file *file, __poll_t events)
-{
-	struct eventfd_ctx *ctx = file->private_data;
-
-	return &ctx->wqh;
-}
-
-static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 	__poll_t events = 0;
 	u64 count;
 
+	poll_wait(file, &ctx->wqh, wait);
+
 	/*
 	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
 	 * can be done outside ctx->wqh.lock because we know that poll_wait
@@ -156,11 +150,11 @@ static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
 	count = READ_ONCE(ctx->count);
 
 	if (count > 0)
-		events |= (EPOLLIN & eventmask);
+		events |= EPOLLIN;
 	if (count == ULLONG_MAX)
 		events |= EPOLLERR;
 	if (ULLONG_MAX - 1 > count)
-		events |= (EPOLLOUT & eventmask);
+		events |= EPOLLOUT;
 
 	return events;
 }
@@ -311,8 +305,7 @@ static const struct file_operations eventfd_fops = {
 	.show_fdinfo	= eventfd_show_fdinfo,
 #endif
 	.release	= eventfd_release,
-	.get_poll_head	= eventfd_get_poll_head,
-	.poll_mask	= eventfd_poll_mask,
+	.poll		= eventfd_poll,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,

fs/eventpoll.c

@@ -922,18 +922,14 @@ static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head
 	return 0;
 }
 
-static struct wait_queue_head *ep_eventpoll_get_poll_head(struct file *file,
-		__poll_t eventmask)
-{
-	struct eventpoll *ep = file->private_data;
-	return &ep->poll_wait;
-}
-
-static __poll_t ep_eventpoll_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
 {
 	struct eventpoll *ep = file->private_data;
 	int depth = 0;
 
+	/* Insert inside our poll wait queue */
+	poll_wait(file, &ep->poll_wait, wait);
+
 	/*
 	 * Proceed to find out if wanted events are really available inside
 	 * the ready list.
@@ -972,8 +968,7 @@ static const struct file_operations eventpoll_fops = {
 	.show_fdinfo	= ep_show_fdinfo,
 #endif
 	.release	= ep_eventpoll_release,
-	.get_poll_head	= ep_eventpoll_get_poll_head,
-	.poll_mask	= ep_eventpoll_poll_mask,
+	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
 };
 

fs/pipe.c

@@ -509,22 +509,19 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-static struct wait_queue_head *
-pipe_get_poll_head(struct file *filp, __poll_t events)
-{
-	struct pipe_inode_info *pipe = filp->private_data;
-
-	return &pipe->wait;
-}
-
 /* No kernel lock held - fine */
-static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+static __poll_t
+pipe_poll(struct file *filp, poll_table *wait)
 {
+	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	int nrbufs = pipe->nrbufs;
-	__poll_t mask = 0;
+	int nrbufs;
+
+	poll_wait(filp, &pipe->wait, wait);
 
 	/* Reading only -- no need for acquiring the semaphore.  */
+	nrbufs = pipe->nrbufs;
+	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
 		mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
 		if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1023,8 +1020,7 @@ const struct file_operations pipefifo_fops = {
 	.llseek		= no_llseek,
 	.read_iter	= pipe_read,
 	.write_iter	= pipe_write,
-	.get_poll_head	= pipe_get_poll_head,
-	.poll_mask	= pipe_poll_mask,
+	.poll		= pipe_poll,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
 	.fasync		= pipe_fasync,

fs/select.c

@@ -34,29 +34,6 @@
 
 #include <linux/uaccess.h>
 
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
-{
-	if (file->f_op->poll) {
-		return file->f_op->poll(file, pt);
-	} else if (file_has_poll_mask(file)) {
-		unsigned int events = poll_requested_events(pt);
-		struct wait_queue_head *head;
-
-		if (pt && pt->_qproc) {
-			head = file->f_op->get_poll_head(file, events);
-			if (!head)
-				return DEFAULT_POLLMASK;
-			if (IS_ERR(head))
-				return EPOLLERR;
-			pt->_qproc(file, head, pt);
-		}
-
-		return file->f_op->poll_mask(file, events);
-	} else {
-		return DEFAULT_POLLMASK;
-	}
-}
-EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.

fs/timerfd.c

@@ -226,20 +226,21 @@ static int timerfd_release(struct inode *inode, struct file *file)
 	kfree_rcu(ctx, rcu);
 	return 0;
 }
-	
-static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
-		__poll_t eventmask)
+
+static __poll_t timerfd_poll(struct file *file, poll_table *wait)
 {
 	struct timerfd_ctx *ctx = file->private_data;
+	__poll_t events = 0;
+	unsigned long flags;
 
-	return &ctx->wqh;
-}
+	poll_wait(file, &ctx->wqh, wait);
 
-static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
-{
-	struct timerfd_ctx *ctx = file->private_data;
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	if (ctx->ticks)
+		events |= EPOLLIN;
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
-	return ctx->ticks ? EPOLLIN : 0;
+	return events;
 }
 
 static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -363,8 +364,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 
 static const struct file_operations timerfd_fops = {
 	.release	= timerfd_release,
-	.get_poll_head	= timerfd_get_poll_head,
-	.poll_mask	= timerfd_poll_mask,
+	.poll		= timerfd_poll,
 	.read		= timerfd_read,
 	.llseek		= noop_llseek,
 	.show_fdinfo	= timerfd_show,

include/crypto/if_alg.h

@@ -245,7 +245,8 @@ ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
 			int offset, size_t size, int flags);
 void af_alg_free_resources(struct af_alg_async_req *areq);
 void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+			 poll_table *wait);
 struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
 					   unsigned int areqlen);
 int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,

include/linux/fs.h

@@ -1720,8 +1720,6 @@ struct file_operations {
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
-	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
-	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);

include/linux/net.h

@@ -147,7 +147,6 @@ struct proto_ops {
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int peer);
-	__poll_t	(*poll_mask) (struct socket *sock, __poll_t events);
 	__poll_t	(*poll)	     (struct file *file, struct socket *sock,
 				      struct poll_table_struct *wait);
 	int		(*ioctl)     (struct socket *sock, unsigned int cmd,

include/linux/poll.h

@@ -74,18 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 	pt->_key   = ~(__poll_t)0; /* all events enabled */
 }
 
-static inline bool file_has_poll_mask(struct file *file)
+static inline bool file_can_poll(struct file *file)
 {
-	return file->f_op->get_poll_head && file->f_op->poll_mask;
+	return file->f_op->poll;
 }
 
-static inline bool file_can_poll(struct file *file)
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
 {
-	return file->f_op->poll || file_has_poll_mask(file);
+	if (unlikely(!file->f_op->poll))
+		return DEFAULT_POLLMASK;
+	return file->f_op->poll(file, pt);
 }
 
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
-
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;

include/linux/skbuff.h

@@ -3252,7 +3252,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+			   struct poll_table_struct *wait);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,

include/net/bluetooth/bluetooth.h

@@ -271,7 +271,7 @@ int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		     int flags);
 int  bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags);
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
+__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
 int  bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int  bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
 int  bt_sock_wait_ready(struct sock *sk, unsigned long flags);

include/net/iucv/af_iucv.h

@@ -153,6 +153,8 @@ struct iucv_sock_list {
 	atomic_t	  autobind_name;
 };
 
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+			    poll_table *wait);
 void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
 void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
 void iucv_accept_enqueue(struct sock *parent, struct sock *sk);

include/net/sctp/sctp.h

@@ -109,7 +109,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 int sctp_inet_listen(struct socket *sock, int backlog);
 void sctp_write_space(struct sock *sk);
 void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t sctp_poll(struct file *file, struct socket *sock,
+		poll_table *wait);
 void sctp_sock_rfree(struct sk_buff *skb);
 void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 		    struct sctp_association *asoc);

include/net/tcp.h

@@ -388,7 +388,8 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t tcp_poll(struct file *file, struct socket *sock,
+		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname,

include/net/tls.h

@@ -109,7 +109,8 @@ struct tls_sw_context_rx {
 
 	struct strparser strp;
 	void (*saved_data_ready)(struct sock *sk);
-	__poll_t (*sk_poll_mask)(struct socket *sock, __poll_t events);
+	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+				struct poll_table_struct *wait);
 	struct sk_buff *recv_pkt;
 	u8 control;
 	bool decrypted;
@@ -224,7 +225,8 @@ void tls_sw_free_resources_tx(struct sock *sk);
 void tls_sw_free_resources_rx(struct sock *sk);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events);
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);

include/net/udp.h

@@ -285,7 +285,7 @@ int udp_init_sock(struct sock *sk);
 int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6);

include/uapi/linux/aio_abi.h

@@ -39,8 +39,10 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* 4 was the experimental IOCB_CMD_PREADX */
-	IOCB_CMD_POLL = 5,
+	/* These two are experimental.
+	 * IOCB_CMD_PREADX = 4,
+	 * IOCB_CMD_POLL = 5,
+	 */
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
@@ -109,7 +111,7 @@ struct iocb {
 #undef IFLITTLE
 
 struct __aio_sigset {
-	const sigset_t __user	*sigmask;
+	sigset_t __user	*sigmask;
 	size_t		sigsetsize;
 };
 

net/appletalk/ddp.c

@@ -1869,7 +1869,7 @@ static const struct proto_ops atalk_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= atalk_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= atalk_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= atalk_compat_ioctl,

net/atm/common.c

@@ -647,11 +647,16 @@ out:
 	return error;
 }
 
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
-	struct atm_vcc *vcc = ATM_SD(sock);
-	__poll_t mask = 0;
+	struct atm_vcc *vcc;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
+
+	vcc = ATM_SD(sock);
 
 	/* exceptional events */
 	if (sk->sk_err)

net/atm/common.h

@@ -17,7 +17,7 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
 int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		int flags);
 int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
+__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
 int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_setsockopt(struct socket *sock, int level, int optname,

net/atm/pvc.c

@@ -113,7 +113,7 @@ static const struct proto_ops pvc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	pvc_getname,
-	.poll_mask =	vcc_poll_mask,
+	.poll =		vcc_poll,
 	.ioctl =	vcc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = vcc_compat_ioctl,

net/atm/svc.c

@@ -636,7 +636,7 @@ static const struct proto_ops svc_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	svc_accept,
 	.getname =	svc_getname,
-	.poll_mask =	vcc_poll_mask,
+	.poll =		vcc_poll,
 	.ioctl =	svc_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	svc_compat_ioctl,

net/ax25/af_ax25.c

@@ -1941,7 +1941,7 @@ static const struct proto_ops ax25_proto_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= ax25_accept,
 	.getname	= ax25_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= ax25_ioctl,
 	.listen		= ax25_listen,
 	.shutdown	= ax25_shutdown,

net/bluetooth/af_bluetooth.c

@@ -437,13 +437,16 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t bt_sock_poll(struct file *file, struct socket *sock,
+			  poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == BT_LISTEN)
 		return bt_accept_poll(sk);
 
@@ -475,7 +478,7 @@ __poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(bt_sock_poll_mask);
+EXPORT_SYMBOL(bt_sock_poll);
 
 int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {

net/bluetooth/hci_sock.c

@@ -1975,7 +1975,7 @@ static const struct proto_ops hci_sock_ops = {
 	.sendmsg	= hci_sock_sendmsg,
 	.recvmsg	= hci_sock_recvmsg,
 	.ioctl		= hci_sock_ioctl,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= hci_sock_setsockopt,

net/bluetooth/l2cap_sock.c

@@ -1653,7 +1653,7 @@ static const struct proto_ops l2cap_sock_ops = {
 	.getname	= l2cap_sock_getname,
 	.sendmsg	= l2cap_sock_sendmsg,
 	.recvmsg	= l2cap_sock_recvmsg,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,

net/bluetooth/rfcomm/sock.c

@@ -1049,7 +1049,7 @@ static const struct proto_ops rfcomm_sock_ops = {
 	.setsockopt	= rfcomm_sock_setsockopt,
 	.getsockopt	= rfcomm_sock_getsockopt,
 	.ioctl		= rfcomm_sock_ioctl,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.socketpair	= sock_no_socketpair,
 	.mmap		= sock_no_mmap
 };

net/bluetooth/sco.c

@@ -1197,7 +1197,7 @@ static const struct proto_ops sco_sock_ops = {
 	.getname	= sco_sock_getname,
 	.sendmsg	= sco_sock_sendmsg,
 	.recvmsg	= sco_sock_recvmsg,
-	.poll_mask	= bt_sock_poll_mask,
+	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,

net/caif/caif_socket.c

@@ -934,11 +934,15 @@ static int caif_release(struct socket *sock)
 }
 
 /* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t caif_poll(struct file *file,
+			      struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
+	__poll_t mask;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
-	__poll_t mask = 0;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err)
@@ -972,7 +976,7 @@ static const struct proto_ops caif_seqpacket_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll_mask = caif_poll_mask,
+	.poll = caif_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,
@@ -993,7 +997,7 @@ static const struct proto_ops caif_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = sock_no_getname,
-	.poll_mask = caif_poll_mask,
+	.poll = caif_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = sock_no_shutdown,

net/can/bcm.c

@@ -1660,7 +1660,7 @@ static const struct proto_ops bcm_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = sock_no_getname,
-	.poll_mask     = datagram_poll_mask,
+	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,

net/can/raw.c

@@ -843,7 +843,7 @@ static const struct proto_ops raw_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = raw_getname,
-	.poll_mask     = datagram_poll_mask,
+	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,

net/core/datagram.c

@@ -819,8 +819,9 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
+ *	@file: file struct
  *	@sock: socket
- *	@events to wait for
+ *	@wait: poll table
  *
  *	Datagram poll: Again totally generic. This also handles
  *	sequenced packet sockets providing the socket receive queue
@@ -830,10 +831,14 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
  *	and you use a different write policy from sock_writeable()
  *	then please supply your own write_space callback.
  */
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
+__poll_t datagram_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 || !skb_queue_empty(&sk->sk_error_queue))
@@ -866,4 +871,4 @@ __poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(datagram_poll_mask);
+EXPORT_SYMBOL(datagram_poll);

net/dccp/dccp.h

@@ -316,7 +316,8 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		 int flags, int *addr_len);
 void dccp_shutdown(struct sock *sk, int how);
 int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+		       poll_table *wait);
 int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 void dccp_req_err(struct sock *sk, u64 seq);
 

net/dccp/ipv4.c

@@ -984,7 +984,7 @@ static const struct proto_ops inet_dccp_ops = {
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
 	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
-	.poll_mask	   = dccp_poll_mask,
+	.poll		   = dccp_poll,
 	.ioctl		   = inet_ioctl,
 	/* FIXME: work on inet_listen to rename it to sock_common_listen */
 	.listen		   = inet_dccp_listen,

net/dccp/ipv6.c

@@ -1070,7 +1070,7 @@ static const struct proto_ops inet6_dccp_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet6_getname,
-	.poll_mask	   = dccp_poll_mask,
+	.poll		   = dccp_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,

net/dccp/proto.c

@@ -312,11 +312,20 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 EXPORT_SYMBOL_GPL(dccp_disconnect);
 
-__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
+/*
+ *	Wait for a DCCP event.
+ *
+ *	Note that we don't need to lock the socket, as the upper poll layers
+ *	take care of normal races (between the test and the event) and we don't
+ *	go look at any of the socket buffers directly.
+ */
+__poll_t dccp_poll(struct file *file, struct socket *sock,
+		       poll_table *wait)
 {
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
@@ -358,7 +367,7 @@ __poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
 	return mask;
 }
 
-EXPORT_SYMBOL_GPL(dccp_poll_mask);
+EXPORT_SYMBOL_GPL(dccp_poll);
 
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {

net/decnet/af_decnet.c

@@ -1207,11 +1207,11 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer)
 }
 
 
-static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table  *wait)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 
 	if (!skb_queue_empty(&scp->other_receive_queue))
 		mask |= EPOLLRDBAND;
@@ -2331,7 +2331,7 @@ static const struct proto_ops dn_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	dn_accept,
 	.getname =	dn_getname,
-	.poll_mask =	dn_poll_mask,
+	.poll =		dn_poll,
 	.ioctl =	dn_ioctl,
 	.listen =	dn_listen,
 	.shutdown =	dn_shutdown,

net/ieee802154/socket.c

@@ -423,7 +423,7 @@ static const struct proto_ops ieee802154_raw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
@@ -969,7 +969,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = sock_no_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,

net/ipv4/af_inet.c

@@ -986,7 +986,7 @@ const struct proto_ops inet_stream_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = tcp_poll_mask,
+	.poll		   = tcp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
@@ -1021,7 +1021,7 @@ const struct proto_ops inet_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = udp_poll_mask,
+	.poll		   = udp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
@@ -1042,7 +1042,7 @@ EXPORT_SYMBOL(inet_dgram_ops);
 
 /*
  * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll_mask
+ * udp_poll
  */
 static const struct proto_ops inet_sockraw_ops = {
 	.family		   = PF_INET,
@@ -1053,7 +1053,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,

net/ipv4/tcp.c

@@ -494,21 +494,32 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 }
 
 /*
- * Socket is not locked. We are protected from async events by poll logic and
- * correct handling of state changes made by other threads is impossible in
- * any case.
+ *	Wait for a TCP event.
+ *
+ *	Note that we don't need to lock the socket, as the upper poll layers
+ *	take care of normal races (between the test and the event) and we don't
+ *	go look at any of the socket buffers directly.
  */
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
+	__poll_t mask;
 	struct sock *sk = sock->sk;
 	const struct tcp_sock *tp = tcp_sk(sk);
-	__poll_t mask = 0;
 	int state;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
+	/* Socket is not locked. We are protected from async events
+	 * by poll logic and correct handling of state changes
+	 * made by other threads is impossible in any case.
+	 */
+
+	mask = 0;
+
 	/*
 	 * EPOLLHUP is certainly not done right. But poll() doesn't
 	 * have a notion of HUP in just one direction, and for a
@@ -589,7 +600,7 @@ __poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
 
 	return mask;
 }
-EXPORT_SYMBOL(tcp_poll_mask);
+EXPORT_SYMBOL(tcp_poll);
 
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {

net/ipv4/udp.c

@@ -2591,7 +2591,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  * 	udp_poll - wait for a UDP event.
  *	@file - file struct
  *	@sock - socket
- *	@events - events to wait for
+ *	@wait - poll table
  *
  *	This is same as datagram poll, except for the special case of
  *	blocking sockets. If application is using a blocking fd
@@ -2600,23 +2600,23 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  *	but then block when reading it. Add special case code
  *	to work around these arguably broken applications.
  */
-__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
 	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Check for false positives due to checksum errors */
-	if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
+	if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll_mask);
+EXPORT_SYMBOL(udp_poll);
 
 int udp_abort(struct sock *sk, int err)
 {

net/ipv6/af_inet6.c

@@ -570,7 +570,7 @@ const struct proto_ops inet6_stream_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = inet_accept,		/* ok		*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = tcp_poll_mask,		/* ok		*/
+	.poll		   = tcp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
@@ -603,7 +603,7 @@ const struct proto_ops inet6_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = udp_poll_mask,		/* ok		*/
+	.poll		   = udp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/

net/ipv6/raw.c

@@ -1334,7 +1334,7 @@ void raw6_proc_exit(void)
 }
 #endif	/* CONFIG_PROC_FS */
 
-/* Same as inet6_dgram_ops, sans udp_poll_mask.  */
+/* Same as inet6_dgram_ops, sans udp_poll.  */
 const struct proto_ops inet6_sockraw_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
@@ -1344,7 +1344,7 @@ const struct proto_ops inet6_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = sock_no_accept,		/* a do nothing	*/
 	.getname	   = inet6_getname,
-	.poll_mask	   = datagram_poll_mask,	/* ok		*/
+	.poll		   = datagram_poll,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/

net/iucv/af_iucv.c

@@ -1488,11 +1488,14 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
+__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
+			    poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
 
@@ -2385,7 +2388,7 @@ static const struct proto_ops iucv_sock_ops = {
 	.getname	= iucv_sock_getname,
 	.sendmsg	= iucv_sock_sendmsg,
 	.recvmsg	= iucv_sock_recvmsg,
-	.poll_mask	= iucv_sock_poll_mask,
+	.poll		= iucv_sock_poll,
 	.ioctl		= sock_no_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,

net/kcm/kcmsock.c

@@ -1336,9 +1336,9 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
 	struct list_head *head;
 	int index = 0;
 
-	/* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
-	 * so  we set sk_state, otherwise epoll_wait always returns right away
-	 * with EPOLLHUP
+	/* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
+	 * we set sk_state, otherwise epoll_wait always returns right away with
+	 * EPOLLHUP
 	 */
 	kcm->sk.sk_state = TCP_ESTABLISHED;
 
@@ -1903,7 +1903,7 @@ static const struct proto_ops kcm_dgram_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -1924,7 +1924,7 @@ static const struct proto_ops kcm_seqpacket_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	sock_no_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	kcm_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,

net/key/af_key.c

@@ -3751,7 +3751,7 @@ static const struct proto_ops pfkey_ops = {
 
 	/* Now the operations that really occur. */
 	.release	=	pfkey_release,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.sendmsg	=	pfkey_sendmsg,
 	.recvmsg	=	pfkey_recvmsg,
 };

net/l2tp/l2tp_ip.c

@@ -613,7 +613,7 @@ static const struct proto_ops l2tp_ip_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,

net/l2tp/l2tp_ip6.c

@@ -754,7 +754,7 @@ static const struct proto_ops l2tp_ip6_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = l2tp_ip6_getname,
-	.poll_mask	   = datagram_poll_mask,
+	.poll		   = datagram_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,

net/l2tp/l2tp_ppp.c

@@ -1818,7 +1818,7 @@ static const struct proto_ops pppol2tp_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppol2tp_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= pppol2tp_setsockopt,

net/llc/af_llc.c

@@ -1192,7 +1192,7 @@ static const struct proto_ops llc_ui_ops = {
 	.socketpair  = sock_no_socketpair,
 	.accept      = llc_ui_accept,
 	.getname     = llc_ui_getname,
-	.poll_mask   = datagram_poll_mask,
+	.poll	     = datagram_poll,
 	.ioctl       = llc_ui_ioctl,
 	.listen      = llc_ui_listen,
 	.shutdown    = llc_ui_shutdown,

net/netlink/af_netlink.c

@@ -2658,7 +2658,7 @@ static const struct proto_ops netlink_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	netlink_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	netlink_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,

net/netrom/af_netrom.c

@@ -1355,7 +1355,7 @@ static const struct proto_ops nr_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	nr_accept,
 	.getname	=	nr_getname,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.ioctl		=	nr_ioctl,
 	.listen		=	nr_listen,
 	.shutdown	=	sock_no_shutdown,

net/nfc/llcp_sock.c

@@ -548,13 +548,16 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
+				   poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
 	pr_debug("%p\n", sk);
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
 
@@ -896,7 +899,7 @@ static const struct proto_ops llcp_sock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = llcp_sock_accept,
 	.getname        = llcp_sock_getname,
-	.poll_mask      = llcp_sock_poll_mask,
+	.poll           = llcp_sock_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = llcp_sock_listen,
 	.shutdown       = sock_no_shutdown,
@@ -916,7 +919,7 @@ static const struct proto_ops llcp_rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = llcp_sock_getname,
-	.poll_mask      = llcp_sock_poll_mask,
+	.poll           = llcp_sock_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,

net/nfc/rawsock.c

@@ -284,7 +284,7 @@ static const struct proto_ops rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll_mask      = datagram_poll_mask,
+	.poll           = datagram_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,
@@ -304,7 +304,7 @@ static const struct proto_ops rawsock_raw_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = sock_no_getname,
-	.poll_mask      = datagram_poll_mask,
+	.poll           = datagram_poll,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,

net/packet/af_packet.c

@@ -4076,11 +4076,12 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
 	return 0;
 }
 
-static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t packet_poll(struct file *file, struct socket *sock,
+				poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
-	__poll_t mask = datagram_poll_mask(sock, events);
+	__poll_t mask = datagram_poll(file, sock, wait);
 
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (po->rx_ring.pg_vec) {
@@ -4422,7 +4423,7 @@ static const struct proto_ops packet_ops_spkt = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname_spkt,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -4443,7 +4444,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname,
-	.poll_mask =	packet_poll_mask,
+	.poll =		packet_poll,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,

net/phonet/socket.c

@@ -340,12 +340,15 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 	return sizeof(struct sockaddr_pn);
 }
 
-static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
+					poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct pep_sock *pn = pep_sk(sk);
 	__poll_t mask = 0;
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_state == TCP_CLOSE)
 		return EPOLLERR;
 	if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -445,7 +448,7 @@ const struct proto_ops phonet_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pn_socket_getname,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -470,7 +473,7 @@ const struct proto_ops phonet_stream_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= pn_socket_accept,
 	.getname	= pn_socket_getname,
-	.poll_mask	= pn_socket_poll_mask,
+	.poll		= pn_socket_poll,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= pn_socket_listen,
 	.shutdown	= sock_no_shutdown,

net/qrtr/qrtr.c

@@ -1023,7 +1023,7 @@ static const struct proto_ops qrtr_proto_ops = {
 	.recvmsg	= qrtr_recvmsg,
 	.getname	= qrtr_getname,
 	.ioctl		= qrtr_ioctl,
-	.poll_mask	= datagram_poll_mask,
+	.poll		= datagram_poll,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
 	.getsockopt	= sock_no_getsockopt,

net/rose/af_rose.c

@@ -1470,7 +1470,7 @@ static const struct proto_ops rose_proto_ops = {
 	.socketpair	=	sock_no_socketpair,
 	.accept		=	rose_accept,
 	.getname	=	rose_getname,
-	.poll_mask	=	datagram_poll_mask,
+	.poll		=	datagram_poll,
 	.ioctl		=	rose_ioctl,
 	.listen		=	rose_listen,
 	.shutdown	=	sock_no_shutdown,

net/rxrpc/af_rxrpc.c

@@ -734,11 +734,15 @@ static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
 /*
  * permit an RxRPC socket to be polled
  */
-static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
-	__poll_t mask = 0;
+	__poll_t mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
 	 * queue */
@@ -945,7 +949,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
-	.poll_mask	= rxrpc_poll_mask,
+	.poll		= rxrpc_poll,
 	.ioctl		= sock_no_ioctl,
 	.listen		= rxrpc_listen,
 	.shutdown	= rxrpc_shutdown,

net/sctp/ipv6.c

@@ -1010,7 +1010,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = sctp_getname,
-	.poll_mask	   = sctp_poll_mask,
+	.poll		   = sctp_poll,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,

net/sctp/protocol.c

@@ -1016,7 +1016,7 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,	/* Semantics are different.  */
-	.poll_mask	   = sctp_poll_mask,
+	.poll		   = sctp_poll,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,	/* Looks harmless.  */

net/sctp/socket.c

@@ -7717,12 +7717,14 @@ out:
  * here, again, by modeling the current TCP/UDP code.  We don't have
  * a good way to test with it yet.
  */
-__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
+__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct sctp_sock *sp = sctp_sk(sk);
 	__poll_t mask;
 
+	poll_wait(file, sk_sleep(sk), wait);
+
 	sock_rps_record_flow(sk);
 
 	/* A TCP-style listening socket becomes readable when the accept queue

net/smc/af_smc.c

@@ -1273,7 +1273,8 @@ static __poll_t smc_accept_poll(struct sock *parent)
 	return mask;
 }
 
-static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t smc_poll(struct file *file, struct socket *sock,
+			     poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
@@ -1289,7 +1290,7 @@ static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
 	if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
 		/* delegate to CLC child sock */
 		release_sock(sk);
-		mask = smc->clcsock->ops->poll_mask(smc->clcsock, events);
+		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
 		lock_sock(sk);
 		sk->sk_err = smc->clcsock->sk->sk_err;
 		if (sk->sk_err) {
@@ -1307,6 +1308,11 @@ static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
 			}
 		}
 	} else {
+		if (sk->sk_state != SMC_CLOSED) {
+			release_sock(sk);
+			sock_poll_wait(file, sk_sleep(sk), wait);
+			lock_sock(sk);
+		}
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1619,7 +1625,7 @@ static const struct proto_ops smc_sock_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= smc_accept,
 	.getname	= smc_getname,
-	.poll_mask	= smc_poll_mask,
+	.poll		= smc_poll,
 	.ioctl		= smc_ioctl,
 	.listen		= smc_listen,
 	.shutdown	= smc_shutdown,

net/socket.c

@@ -117,10 +117,8 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
-		__poll_t events);
-static __poll_t sock_poll_mask(struct file *file, __poll_t);
-static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
+static __poll_t sock_poll(struct file *file,
+			      struct poll_table_struct *wait);
 static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_COMPAT
 static long compat_sock_ioctl(struct file *file,
@@ -143,8 +141,6 @@ static const struct file_operations socket_file_ops = {
 	.llseek =	no_llseek,
 	.read_iter =	sock_read_iter,
 	.write_iter =	sock_write_iter,
-	.get_poll_head = sock_get_poll_head,
-	.poll_mask =	sock_poll_mask,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
@@ -1130,48 +1126,14 @@ out_release:
 }
 EXPORT_SYMBOL(sock_create_lite);
 
-static struct wait_queue_head *sock_get_poll_head(struct file *file,
-		__poll_t events)
-{
-	struct socket *sock = file->private_data;
-
-	if (!sock->ops->poll_mask)
-		return NULL;
-	sock_poll_busy_loop(sock, events);
-	return sk_sleep(sock->sk);
-}
-
-static __poll_t sock_poll_mask(struct file *file, __poll_t events)
-{
-	struct socket *sock = file->private_data;
-
-	/*
-	 * We need to be sure we are in sync with the socket flags modification.
-	 *
-	 * This memory barrier is paired in the wq_has_sleeper.
-	 */
-	smp_mb();
-
-	/* this socket can poll_ll so tell the system call */
-	return sock->ops->poll_mask(sock, events) |
-		(sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
-}
-
 /* No kernel lock held - perfect */
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
 	struct socket *sock = file->private_data;
-	__poll_t events = poll_requested_events(wait), mask = 0;
-
-	if (sock->ops->poll) {
-		sock_poll_busy_loop(sock, events);
-		mask = sock->ops->poll(file, sock, wait);
-	} else if (sock->ops->poll_mask) {
-		sock_poll_wait(file, sock_get_poll_head(file, events), wait);
-		mask = sock->ops->poll_mask(sock, events);
-	}
+	__poll_t events = poll_requested_events(wait);
 
-	return mask | sock_poll_busy_flag(sock);
+	sock_poll_busy_loop(sock, events);
+	return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)

net/tipc/socket.c

@@ -692,9 +692,10 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 
 /**
- * tipc_poll - read pollmask
+ * tipc_poll - read and possibly block on pollmask
  * @file: file structure associated with the socket
  * @sock: socket for which to calculate the poll bits
+ * @wait: ???
  *
  * Returns pollmask value
  *
@@ -708,12 +709,15 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
  * imply that the operation will succeed, merely that it should be performed
  * and will not block.
  */
-static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t tipc_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
 	__poll_t revents = 0;
 
+	sock_poll_wait(file, sk_sleep(sk), wait);
+
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -3033,7 +3037,7 @@ static const struct proto_ops msg_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
@@ -3054,7 +3058,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
@@ -3075,7 +3079,7 @@ static const struct proto_ops stream_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll_mask	= tipc_poll_mask,
+	.poll		= tipc_poll,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,

net/tls/tls_main.c

@@ -712,7 +712,7 @@ static int __init tls_register(void)
 	build_protos(tls_prots[TLSV4], &tcp_prot);
 
 	tls_sw_proto_ops = inet_stream_ops;
-	tls_sw_proto_ops.poll_mask = tls_sw_poll_mask;
+	tls_sw_proto_ops.poll = tls_sw_poll;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
 
 #ifdef CONFIG_TLS_DEVICE

net/tls/tls_sw.c

@@ -919,22 +919,23 @@ splice_read_end:
 	return copied ? : err;
 }
 
-__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events)
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait)
 {
+	unsigned int ret;
 	struct sock *sk = sock->sk;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	__poll_t mask;
 
-	/* Grab EPOLLOUT and EPOLLHUP from the underlying socket */
-	mask = ctx->sk_poll_mask(sock, events);
+	/* Grab POLLOUT and POLLHUP from the underlying socket */
+	ret = ctx->sk_poll(file, sock, wait);
 
-	/* Clear EPOLLIN bits, and set based on recv_pkt */
-	mask &= ~(EPOLLIN | EPOLLRDNORM);
+	/* Clear POLLIN bits, and set based on recv_pkt */
+	ret &= ~(POLLIN | POLLRDNORM);
 	if (ctx->recv_pkt)
-		mask |= EPOLLIN | EPOLLRDNORM;
+		ret |= POLLIN | POLLRDNORM;
 
-	return mask;
+	return ret;
 }
 
 static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
@@ -1191,7 +1192,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sk->sk_data_ready = tls_data_ready;
 		write_unlock_bh(&sk->sk_callback_lock);
 
-		sw_ctx_rx->sk_poll_mask = sk->sk_socket->ops->poll_mask;
+		sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll;
 
 		strp_check_rcv(&sw_ctx_rx->strp);
 	}

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);

net/vmw_vsock/af_vsock.c

@@ -850,11 +850,18 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	return err;
 }
 
-static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t vsock_poll(struct file *file, struct socket *sock,
+			       poll_table *wait)
 {
-	struct sock *sk = sock->sk;
-	struct vsock_sock *vsk = vsock_sk(sk);
-	__poll_t mask = 0;
+	struct sock *sk;
+	__poll_t mask;
+	struct vsock_sock *vsk;
+
+	sk = sock->sk;
+	vsk = vsock_sk(sk);
+
+	poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
 
 	if (sk->sk_err)
 		/* Signify that there has been an error on this socket. */
@@ -1084,7 +1091,7 @@ static const struct proto_ops vsock_dgram_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = vsock_getname,
-	.poll_mask = vsock_poll_mask,
+	.poll = vsock_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = vsock_shutdown,
@@ -1842,7 +1849,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,
-	.poll_mask = vsock_poll_mask,
+	.poll = vsock_poll,
 	.ioctl = sock_no_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,

net/x25/af_x25.c

@@ -1750,7 +1750,7 @@ static const struct proto_ops x25_proto_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	x25_accept,
 	.getname =	x25_getname,
-	.poll_mask =	datagram_poll_mask,
+	.poll =		datagram_poll,
 	.ioctl =	x25_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_x25_ioctl,

net/xdp/xsk.c

@@ -303,9 +303,10 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 	return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
 }
 
-static __poll_t xsk_poll_mask(struct socket *sock, __poll_t events)
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+			     struct poll_table_struct *wait)
 {
-	__poll_t mask = datagram_poll_mask(sock, events);
+	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
 
@@ -696,7 +697,7 @@ static const struct proto_ops xsk_proto_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
-	.poll_mask	= xsk_poll_mask,
+	.poll		= xsk_poll,
 	.ioctl		= sock_no_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,