Merge branch 'work.aio-1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull aio updates from Al Viro:
 "Majority of AIO stuff this cycle. aio-fsync and aio-poll, mostly.

  The only thing I'm holding back for a day or so is Adam's aio ioprio -
  his last-minute fixup is trivial (missing stub in !CONFIG_BLOCK case),
  but let it sit in -next for decency sake..."

* 'work.aio-1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (46 commits)
  aio: sanitize the limit checking in io_submit(2)
  aio: fold do_io_submit() into callers
  aio: shift copyin of iocb into io_submit_one()
  aio_read_events_ring(): make a bit more readable
  aio: all callers of aio_{read,write,fsync,poll} treat 0 and -EIOCBQUEUED the same way
  aio: take list removal to (some) callers of aio_complete()
  aio: add missing break for the IOCB_CMD_FDSYNC case
  random: convert to ->poll_mask
  timerfd: convert to ->poll_mask
  eventfd: switch to ->poll_mask
  pipe: convert to ->poll_mask
  crypto: af_alg: convert to ->poll_mask
  net/rxrpc: convert to ->poll_mask
  net/iucv: convert to ->poll_mask
  net/phonet: convert to ->poll_mask
  net/nfc: convert to ->poll_mask
  net/caif: convert to ->poll_mask
  net/bluetooth: convert to ->poll_mask
  net/sctp: convert to ->poll_mask
  net/tipc: convert to ->poll_mask
  ...

Documentation/filesystems/Locking

@@ -440,7 +440,9 @@ prototypes:
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
-	unsigned int (*poll) (struct file *, struct poll_table_struct *);
+	__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 *);
@@ -471,7 +473,7 @@ prototypes:
 };
 
 locking rules:
-	All may block.
+	All except for ->poll_mask may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -503,6 +505,9 @@ 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

@@ -856,7 +856,9 @@ struct file_operations {
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
-	unsigned int (*poll) (struct file *, struct poll_table_struct *);
+	__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 *);
@@ -901,6 +903,17 @@ 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

arch/x86/entry/syscalls/syscall_32.tbl

@@ -396,3 +396,4 @@
 382	i386	pkey_free		sys_pkey_free			__ia32_sys_pkey_free
 383	i386	statx			sys_statx			__ia32_sys_statx
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
+385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents

arch/x86/entry/syscalls/syscall_64.tbl

@@ -341,6 +341,7 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

crypto/af_alg.c

@@ -347,7 +347,6 @@ static const struct proto_ops alg_proto_ops = {
 	.sendpage	=	sock_no_sendpage,
 	.sendmsg	=	sock_no_sendmsg,
 	.recvmsg	=	sock_no_recvmsg,
-	.poll		=	sock_no_poll,
 
 	.bind		=	alg_bind,
 	.release	=	af_alg_release,
@@ -1061,19 +1060,12 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
 }
 EXPORT_SYMBOL_GPL(af_alg_async_cb);
 
-/**
- * af_alg_poll - poll system call handler
- */
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
-			 poll_table *wait)
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	if (!ctx->more || ctx->used)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -1083,7 +1075,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL_GPL(af_alg_poll);
+EXPORT_SYMBOL_GPL(af_alg_poll_mask);
 
 /**
  * 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		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 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		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static void *aead_bind(const char *name, u32 type, u32 mask)

crypto/algif_hash.c

@@ -288,7 +288,6 @@ static struct proto_ops algif_hash_ops = {
 	.mmap		=	sock_no_mmap,
 	.bind		=	sock_no_bind,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 
 	.release	=	af_alg_release,
 	.sendmsg	=	hash_sendmsg,
@@ -396,7 +395,6 @@ static struct proto_ops algif_hash_ops_nokey = {
 	.mmap		=	sock_no_mmap,
 	.bind		=	sock_no_bind,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 
 	.release	=	af_alg_release,
 	.sendmsg	=	hash_sendmsg_nokey,

crypto/algif_rng.c

@@ -106,7 +106,6 @@ static struct proto_ops algif_rng_ops = {
 	.bind		=	sock_no_bind,
 	.accept		=	sock_no_accept,
 	.setsockopt	=	sock_no_setsockopt,
-	.poll		=	sock_no_poll,
 	.sendmsg	=	sock_no_sendmsg,
 	.sendpage	=	sock_no_sendpage,
 

crypto/algif_skcipher.c

@@ -205,7 +205,7 @@ static struct proto_ops algif_skcipher_ops = {
 	.sendmsg	=	skcipher_sendmsg,
 	.sendpage	=	af_alg_sendpage,
 	.recvmsg	=	skcipher_recvmsg,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static int skcipher_check_key(struct socket *sock)
@@ -301,7 +301,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
 	.sendmsg	=	skcipher_sendmsg_nokey,
 	.sendpage	=	skcipher_sendpage_nokey,
 	.recvmsg	=	skcipher_recvmsg_nokey,
-	.poll		=	af_alg_poll,
+	.poll_mask	=	af_alg_poll_mask,
 };
 
 static void *skcipher_bind(const char *name, u32 type, u32 mask)

drivers/char/random.c

@@ -402,8 +402,7 @@ static struct poolinfo {
 /*
  * Static global variables
  */
-static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
-static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -722,8 +721,8 @@ retry:
 
 		/* should we wake readers? */
 		if (entropy_bits >= random_read_wakeup_bits &&
-		    wq_has_sleeper(&random_read_wait)) {
-			wake_up_interruptible(&random_read_wait);
+		    wq_has_sleeper(&random_wait)) {
+			wake_up_interruptible_poll(&random_wait, POLLIN);
 			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 		/* If the input pool is getting full, send some
@@ -1397,7 +1396,7 @@ retry:
 	trace_debit_entropy(r->name, 8 * ibytes);
 	if (ibytes &&
 	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
-		wake_up_interruptible(&random_write_wait);
+		wake_up_interruptible_poll(&random_wait, POLLOUT);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
 	}
 
@@ -1839,7 +1838,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
 		if (nonblock)
 			return -EAGAIN;
 
-		wait_event_interruptible(random_read_wait,
+		wait_event_interruptible(random_wait,
 			ENTROPY_BITS(&input_pool) >=
 			random_read_wakeup_bits);
 		if (signal_pending(current))
@@ -1876,14 +1875,17 @@ 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(struct file *file, poll_table * wait)
+random_poll_mask(struct file *file, __poll_t events)
 {
-	__poll_t mask;
+	__poll_t mask = 0;
 
-	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)
@@ -1990,7 +1992,8 @@ static int random_fasync(int fd, struct file *filp, int on)
 const struct file_operations random_fops = {
 	.read  = random_read,
 	.write = random_write,
-	.poll  = random_poll,
+	.get_poll_head  = random_get_poll_head,
+	.poll_mask  = random_poll_mask,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
 	.llseek = noop_llseek,
@@ -2323,7 +2326,7 @@ 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_write_wait, kthread_should_stop() ||
+	wait_event_interruptible(random_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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= data_sock_setsockopt,
@@ -745,7 +745,6 @@ static const struct proto_ops base_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,

drivers/net/ppp/pptp.c

@@ -624,7 +624,6 @@ static const struct proto_ops pptp_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept     = sock_no_accept,
 	.getname    = pptp_getname,
-	.poll       = sock_no_poll,
 	.listen     = sock_no_listen,
 	.shutdown   = sock_no_shutdown,
 	.setsockopt = sock_no_setsockopt,

drivers/staging/comedi/drivers/serial2002.c

@@ -113,7 +113,7 @@ static void serial2002_tty_read_poll_wait(struct file *f, int timeout)
 		long elapsed;
 		__poll_t mask;
 
-		mask = f->f_op->poll(f, &table.pt);
+		mask = vfs_poll(f, &table.pt);
 		if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN |
 			    EPOLLHUP | EPOLLERR)) {
 			break;
@@ -136,7 +136,7 @@ static int serial2002_tty_read(struct file *f, int timeout)
 
 	result = -1;
 	if (!IS_ERR(f)) {
-		if (f->f_op->poll) {
+		if (file_can_poll(f)) {
 			serial2002_tty_read_poll_wait(f, timeout);
 
 			if (kernel_read(f, &ch, 1, &pos) == 1)

drivers/staging/ipx/af_ipx.c

@@ -1965,7 +1965,7 @@ static const struct proto_ops ipx_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= ipx_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= ipx_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ipx_compat_ioctl,

drivers/vfio/virqfd.c

@@ -166,7 +166,7 @@ int vfio_virqfd_enable(void *opaque,
 	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
 	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
 
-	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
+	events = vfs_poll(irqfd.file, &virqfd->pt);
 
 	/*
 	 * Check if there was an event already pending on the eventfd

drivers/vhost/vhost.c

@@ -208,7 +208,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 	if (poll->wqh)
 		return 0;
 
-	mask = file->f_op->poll(file, &poll->table);
+	mask = vfs_poll(file, &poll->table);
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
 	if (mask & EPOLLERR) {

fs/aio.c

@@ -5,6 +5,7 @@
  *	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.
  */
@@ -46,6 +47,8 @@
 
 #include "internal.h"
 
+#define KIOCB_KEY		0
+
 #define AIO_RING_MAGIC			0xa10a10a1
 #define AIO_RING_COMPAT_FEATURES	1
 #define AIO_RING_INCOMPAT_FEATURES	0
@@ -156,21 +159,29 @@ struct kioctx {
 	unsigned		id;
 };
 
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED		((void *) (~0ULL))
+struct fsync_iocb {
+	struct work_struct	work;
+	struct file		*file;
+	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 {
-	struct kiocb		common;
+	union {
+		struct kiocb		rw;
+		struct fsync_iocb	fsync;
+		struct poll_iocb	poll;
+	};
 
 	struct kioctx		*ki_ctx;
 	kiocb_cancel_fn		*ki_cancel;
@@ -264,9 +275,6 @@ static int __init aio_setup(void)
 
 	kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
-
-	pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
-
 	return 0;
 }
 __initcall(aio_setup);
@@ -552,42 +560,20 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 
 void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
+	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ctx->ctx_lock, flags);
-
-	if (!req->ki_list.next)
-		list_add(&req->ki_list, &ctx->active_reqs);
+	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
+		return;
 
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
-
 	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct aio_kiocb *kiocb)
-{
-	kiocb_cancel_fn *old, *cancel;
-
-	/*
-	 * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
-	 * actually has a cancel function, hence the cmpxchg()
-	 */
-
-	cancel = READ_ONCE(kiocb->ki_cancel);
-	do {
-		if (!cancel || cancel == KIOCB_CANCELLED)
-			return -EINVAL;
-
-		old = cancel;
-		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
-	} while (cancel != old);
-
-	return cancel(&kiocb->common);
-}
-
 /*
  * free_ioctx() should be RCU delayed to synchronize against the RCU
  * protected lookup_ioctx() and also needs process context to call
@@ -634,7 +620,7 @@ static void free_ioctx_users(struct percpu_ref *ref)
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
 				       struct aio_kiocb, ki_list);
-		kiocb_cancel(req);
+		req->ki_cancel(&req->rw);
 		list_del_init(&req->ki_list);
 	}
 
@@ -1041,7 +1027,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 		goto out_put;
 
 	percpu_ref_get(&ctx->reqs);
-
+	INIT_LIST_HEAD(&req->ki_list);
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -1049,15 +1035,6 @@ out_put:
 	return NULL;
 }
 
-static void kiocb_free(struct aio_kiocb *req)
-{
-	if (req->common.ki_filp)
-		fput(req->common.ki_filp);
-	if (req->ki_eventfd != NULL)
-		eventfd_ctx_put(req->ki_eventfd);
-	kmem_cache_free(kiocb_cachep, req);
-}
-
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
 	struct aio_ring __user *ring  = (void __user *)ctx_id;
@@ -1088,44 +1065,14 @@ out:
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
-static void aio_complete(struct kiocb *kiocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 {
-	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
 	struct io_event	*ev_page, *event;
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
-	if (kiocb->ki_flags & IOCB_WRITE) {
-		struct file *file = kiocb->ki_filp;
-
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
-		if (S_ISREG(file_inode(file)->i_mode))
-			__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
-		file_end_write(file);
-	}
-
-	/*
-	 * Special case handling for sync iocbs:
-	 *  - events go directly into the iocb for fast handling
-	 *  - the sync task with the iocb in its stack holds the single iocb
-	 *    ref, no other paths have a way to get another ref
-	 *  - the sync task helpfully left a reference to itself in the iocb
-	 */
-	BUG_ON(is_sync_kiocb(kiocb));
-
-	if (iocb->ki_list.next) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&ctx->ctx_lock, flags);
-		list_del(&iocb->ki_list);
-		spin_unlock_irqrestore(&ctx->ctx_lock, flags);
-	}
-
 	/*
 	 * Add a completion event to the ring buffer. Must be done holding
 	 * ctx->completion_lock to prevent other code from messing with the tail
@@ -1179,11 +1126,12 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 	 * eventfd. The eventfd_signal() function is safe to be called
 	 * from IRQ context.
 	 */
-	if (iocb->ki_eventfd != NULL)
+	if (iocb->ki_eventfd) {
 		eventfd_signal(iocb->ki_eventfd, 1);
+		eventfd_ctx_put(iocb->ki_eventfd);
+	}
 
-	/* everything turned out well, dispose of the aiocb. */
-	kiocb_free(iocb);
+	kmem_cache_free(kiocb_cachep, iocb);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1249,14 +1197,13 @@ static long aio_read_events_ring(struct kioctx *ctx,
 		if (head == tail)
 			break;
 
-		avail = min(avail, nr - ret);
-		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
-			    ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
-
 		pos = head + AIO_EVENTS_OFFSET;
 		page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
 		pos %= AIO_EVENTS_PER_PAGE;
 
+		avail = min(avail, nr - ret);
+		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos);
+
 		ev = kmap(page);
 		copy_ret = copy_to_user(event + ret, ev + pos,
 					sizeof(*ev) * avail);
@@ -1327,10 +1274,6 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 		wait_event_interruptible_hrtimeout(ctx->wait,
 				aio_read_events(ctx, min_nr, nr, event, &ret),
 				until);
-
-	if (!ret && signal_pending(current))
-		ret = -EINTR;
-
 	return ret;
 }
 
@@ -1446,6 +1389,58 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	return -EINVAL;
 }
 
+static void aio_remove_iocb(struct aio_kiocb *iocb)
+{
+	struct kioctx *ctx = iocb->ki_ctx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	list_del(&iocb->ki_list);
+	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+}
+
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+	if (!list_empty_careful(&iocb->ki_list))
+		aio_remove_iocb(iocb);
+
+	if (kiocb->ki_flags & IOCB_WRITE) {
+		struct inode *inode = file_inode(kiocb->ki_filp);
+
+		/*
+		 * Tell lockdep we inherited freeze protection from submission
+		 * thread.
+		 */
+		if (S_ISREG(inode->i_mode))
+			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+		file_end_write(kiocb->ki_filp);
+	}
+
+	fput(kiocb->ki_filp);
+	aio_complete(iocb, res, res2);
+}
+
+static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+{
+	int ret;
+
+	req->ki_filp = fget(iocb->aio_fildes);
+	if (unlikely(!req->ki_filp))
+		return -EBADF;
+	req->ki_complete = aio_complete_rw;
+	req->ki_pos = iocb->aio_offset;
+	req->ki_flags = iocb_flags(req->ki_filp);
+	if (iocb->aio_flags & IOCB_FLAG_RESFD)
+		req->ki_flags |= IOCB_EVENTFD;
+	req->ki_hint = file_write_hint(req->ki_filp);
+	ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
+	if (unlikely(ret))
+		fput(req->ki_filp);
+	return ret;
+}
+
 static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 		bool vectored, bool compat, struct iov_iter *iter)
 {
@@ -1465,11 +1460,11 @@ static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
 	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
 }
 
-static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 {
 	switch (ret) {
 	case -EIOCBQUEUED:
-		return ret;
+		break;
 	case -ERESTARTSYS:
 	case -ERESTARTNOINTR:
 	case -ERESTARTNOHAND:
@@ -1481,85 +1476,270 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 		ret = -EINTR;
 		/*FALLTHRU*/
 	default:
-		aio_complete(req, ret, 0);
-		return 0;
+		aio_complete_rw(req, ret, 0);
 	}
 }
 
 static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_READ)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->read_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, call_read_iter(file, req, &iter));
+		aio_rw_done(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret))
+		fput(file);
 	return ret;
 }
 
 static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		bool compat)
 {
-	struct file *file = req->ki_filp;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	struct file *file;
 	ssize_t ret;
 
+	ret = aio_prep_rw(req, iocb);
+	if (ret)
+		return ret;
+	file = req->ki_filp;
+
+	ret = -EBADF;
 	if (unlikely(!(file->f_mode & FMODE_WRITE)))
-		return -EBADF;
+		goto out_fput;
+	ret = -EINVAL;
 	if (unlikely(!file->f_op->write_iter))
-		return -EINVAL;
+		goto out_fput;
 
 	ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
 	if (ret)
-		return ret;
+		goto out_fput;
 	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret) {
-		req->ki_flags |= IOCB_WRITE;
-		file_start_write(file);
-		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
-		 * We release freeze protection in aio_complete().  Fool lockdep
-		 * by telling it the lock got released so that it doesn't
-		 * complain about held lock when we return to userspace.
+		 * Open-code file_start_write here to grab freeze protection,
+		 * which will be released by another thread in
+		 * aio_complete_rw().  Fool lockdep by telling it the lock got
+		 * released so that it doesn't complain about the held lock when
+		 * we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode))
+		if (S_ISREG(file_inode(file)->i_mode)) {
+			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		}
+		req->ki_flags |= IOCB_WRITE;
+		aio_rw_done(req, call_write_iter(file, req, &iter));
 	}
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret))
+		fput(file);
 	return ret;
 }
 
+static void aio_fsync_work(struct work_struct *work)
+{
+	struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
+	int ret;
+
+	ret = vfs_fsync(req->file, req->datasync);
+	fput(req->file);
+	aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+}
+
+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;
+	if (unlikely(!req->file->f_op->fsync)) {
+		fput(req->file);
+		return -EINVAL;
+	}
+
+	req->datasync = datasync;
+	INIT_WORK(&req->work, aio_fsync_work);
+	schedule_work(&req->work);
+	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);
+	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);
+	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,
-			 struct iocb *iocb, bool compat)
+			 bool compat)
 {
 	struct aio_kiocb *req;
-	struct file *file;
+	struct iocb iocb;
 	ssize_t ret;
 
+	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
+		return -EFAULT;
+
 	/* enforce forwards compatibility on users */
-	if (unlikely(iocb->aio_reserved2)) {
+	if (unlikely(iocb.aio_reserved2)) {
 		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
 
 	/* prevent overflows */
 	if (unlikely(
-	    (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
-	    (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
-	    ((ssize_t)iocb->aio_nbytes < 0)
+	    (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
+	    (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
+	    ((ssize_t)iocb.aio_nbytes < 0)
 	   )) {
 		pr_debug("EINVAL: overflow check\n");
 		return -EINVAL;
@@ -1569,37 +1749,19 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	if (unlikely(!req))
 		return -EAGAIN;
 
-	req->common.ki_filp = file = fget(iocb->aio_fildes);
-	if (unlikely(!req->common.ki_filp)) {
-		ret = -EBADF;
-		goto out_put_req;
-	}
-	req->common.ki_pos = iocb->aio_offset;
-	req->common.ki_complete = aio_complete;
-	req->common.ki_flags = iocb_flags(req->common.ki_filp);
-	req->common.ki_hint = file_write_hint(file);
-
-	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+	if (iocb.aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
 		 * instance of the file* now. The file descriptor must be
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
+		req->ki_eventfd = eventfd_ctx_fdget((int) iocb.aio_resfd);
 		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
 			req->ki_eventfd = NULL;
 			goto out_put_req;
 		}
-
-		req->common.ki_flags |= IOCB_EVENTFD;
-	}
-
-	ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
-	if (unlikely(ret)) {
-		pr_debug("EINVAL: aio_rw_flags\n");
-		goto out_put_req;
 	}
 
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1609,41 +1771,67 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	}
 
 	req->ki_user_iocb = user_iocb;
-	req->ki_user_data = iocb->aio_data;
+	req->ki_user_data = iocb.aio_data;
 
-	get_file(file);
-	switch (iocb->aio_lio_opcode) {
+	switch (iocb.aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = aio_read(&req->common, iocb, false, compat);
+		ret = aio_read(&req->rw, &iocb, false, compat);
 		break;
 	case IOCB_CMD_PWRITE:
-		ret = aio_write(&req->common, iocb, false, compat);
+		ret = aio_write(&req->rw, &iocb, false, compat);
 		break;
 	case IOCB_CMD_PREADV:
-		ret = aio_read(&req->common, iocb, true, compat);
+		ret = aio_read(&req->rw, &iocb, true, compat);
 		break;
 	case IOCB_CMD_PWRITEV:
-		ret = aio_write(&req->common, iocb, true, compat);
+		ret = aio_write(&req->rw, &iocb, true, compat);
+		break;
+	case IOCB_CMD_FSYNC:
+		ret = aio_fsync(&req->fsync, &iocb, false);
+		break;
+	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);
+		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
 		break;
 	}
-	fput(file);
 
-	if (ret && ret != -EIOCBQUEUED)
+	/*
+	 * If ret is 0, we'd either done aio_complete() ourselves or have
+	 * arranged for that to be done asynchronously.  Anything non-zero
+	 * means that we need to destroy req ourselves.
+	 */
+	if (ret)
 		goto out_put_req;
 	return 0;
 out_put_req:
 	put_reqs_available(ctx, 1);
 	percpu_ref_put(&ctx->reqs);
-	kiocb_free(req);
+	if (req->ki_eventfd)
+		eventfd_ctx_put(req->ki_eventfd);
+	kmem_cache_free(kiocb_cachep, req);
 	return ret;
 }
 
-static long do_io_submit(aio_context_t ctx_id, long nr,
-			  struct iocb __user *__user *iocbpp, bool compat)
+/* sys_io_submit:
+ *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
+ *	the number of iocbs queued.  May return -EINVAL if the aio_context
+ *	specified by ctx_id is invalid, if nr is < 0, if the iocb at
+ *	*iocbpp[0] is not properly initialized, if the operation specified
+ *	is invalid for the file descriptor in the iocb.  May fail with
+ *	-EFAULT if any of the data structures point to invalid data.  May
+ *	fail with -EBADF if the file descriptor specified in the first
+ *	iocb is invalid.  May fail with -EAGAIN if insufficient resources
+ *	are available to queue any iocbs.  Will return 0 if nr is 0.  Will
+ *	fail with -ENOSYS if not implemented.
+ */
+SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
+		struct iocb __user * __user *, iocbpp)
 {
 	struct kioctx *ctx;
 	long ret = 0;
@@ -1653,39 +1841,25 @@ static long do_io_submit(aio_context_t ctx_id, long nr,
 	if (unlikely(nr < 0))
 		return -EINVAL;
 
-	if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
-		nr = LONG_MAX/sizeof(*iocbpp);
-
-	if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
-		return -EFAULT;
-
 	ctx = lookup_ioctx(ctx_id);
 	if (unlikely(!ctx)) {
 		pr_debug("EINVAL: invalid context id\n");
 		return -EINVAL;
 	}
 
-	blk_start_plug(&plug);
+	if (nr > ctx->nr_events)
+		nr = ctx->nr_events;
 
-	/*
-	 * AKPM: should this return a partial result if some of the IOs were
-	 * successfully submitted?
-	 */
-	for (i=0; i<nr; i++) {
+	blk_start_plug(&plug);
+	for (i = 0; i < nr; i++) {
 		struct iocb __user *user_iocb;
-		struct iocb tmp;
 
-		if (unlikely(__get_user(user_iocb, iocbpp + i))) {
+		if (unlikely(get_user(user_iocb, iocbpp + i))) {
 			ret = -EFAULT;
 			break;
 		}
 
-		if (unlikely(copy_from_user(&tmp, user_iocb, sizeof(tmp)))) {
-			ret = -EFAULT;
-			break;
-		}
-
-		ret = io_submit_one(ctx, user_iocb, &tmp, compat);
+		ret = io_submit_one(ctx, user_iocb, false);
 		if (ret)
 			break;
 	}
@@ -1695,59 +1869,44 @@ static long do_io_submit(aio_context_t ctx_id, long nr,
 	return i ? i : ret;
 }
 
-/* sys_io_submit:
- *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
- *	the number of iocbs queued.  May return -EINVAL if the aio_context
- *	specified by ctx_id is invalid, if nr is < 0, if the iocb at
- *	*iocbpp[0] is not properly initialized, if the operation specified
- *	is invalid for the file descriptor in the iocb.  May fail with
- *	-EFAULT if any of the data structures point to invalid data.  May
- *	fail with -EBADF if the file descriptor specified in the first
- *	iocb is invalid.  May fail with -EAGAIN if insufficient resources
- *	are available to queue any iocbs.  Will return 0 if nr is 0.  Will
- *	fail with -ENOSYS if not implemented.
- */
-SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
-		struct iocb __user * __user *, iocbpp)
-{
-	return do_io_submit(ctx_id, nr, iocbpp, 0);
-}
-
 #ifdef CONFIG_COMPAT
-static inline long
-copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+		       int, nr, compat_uptr_t __user *, iocbpp)
 {
-	compat_uptr_t uptr;
-	int i;
+	struct kioctx *ctx;
+	long ret = 0;
+	int i = 0;
+	struct blk_plug plug;
 
-	for (i = 0; i < nr; ++i) {
-		if (get_user(uptr, ptr32 + i))
-			return -EFAULT;
-		if (put_user(compat_ptr(uptr), ptr64 + i))
-			return -EFAULT;
+	if (unlikely(nr < 0))
+		return -EINVAL;
+
+	ctx = lookup_ioctx(ctx_id);
+	if (unlikely(!ctx)) {
+		pr_debug("EINVAL: invalid context id\n");
+		return -EINVAL;
 	}
-	return 0;
-}
 
-#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
+	if (nr > ctx->nr_events)
+		nr = ctx->nr_events;
 
-COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
-		       int, nr, u32 __user *, iocb)
-{
-	struct iocb __user * __user *iocb64;
-	long ret;
+	blk_start_plug(&plug);
+	for (i = 0; i < nr; i++) {
+		compat_uptr_t user_iocb;
 
-	if (unlikely(nr < 0))
-		return -EINVAL;
+		if (unlikely(get_user(user_iocb, iocbpp + i))) {
+			ret = -EFAULT;
+			break;
+		}
 
-	if (nr > MAX_AIO_SUBMITS)
-		nr = MAX_AIO_SUBMITS;
+		ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
+		if (ret)
+			break;
+	}
+	blk_finish_plug(&plug);
 
-	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
-	ret = copy_iocb(nr, iocb, iocb64);
-	if (!ret)
-		ret = do_io_submit(ctx_id, nr, iocb64, 1);
-	return ret;
+	percpu_ref_put(&ctx->users);
+	return i ? i : ret;
 }
 #endif
 
@@ -1755,15 +1914,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
  *	Finds a given iocb for cancellation.
  */
 static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key)
+lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
 {
 	struct aio_kiocb *kiocb;
 
 	assert_spin_locked(&ctx->ctx_lock);
 
-	if (key != KIOCB_KEY)
-		return NULL;
-
 	/* TODO: use a hash or array, this sucks. */
 	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
 		if (kiocb->ki_user_iocb == iocb)
@@ -1787,25 +1943,24 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 {
 	struct kioctx *ctx;
 	struct aio_kiocb *kiocb;
+	int ret = -EINVAL;
 	u32 key;
-	int ret;
 
-	ret = get_user(key, &iocb->aio_key);
-	if (unlikely(ret))
+	if (unlikely(get_user(key, &iocb->aio_key)))
 		return -EFAULT;
+	if (unlikely(key != KIOCB_KEY))
+		return -EINVAL;
 
 	ctx = lookup_ioctx(ctx_id);
 	if (unlikely(!ctx))
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->ctx_lock);
-
-	kiocb = lookup_kiocb(ctx, iocb, key);
-	if (kiocb)
-		ret = kiocb_cancel(kiocb);
-	else
-		ret = -EINVAL;
-
+	kiocb = lookup_kiocb(ctx, iocb);
+	if (kiocb) {
+		ret = kiocb->ki_cancel(&kiocb->rw);
+		list_del_init(&kiocb->ki_list);
+	}
 	spin_unlock_irq(&ctx->ctx_lock);
 
 	if (!ret) {
@@ -1860,13 +2015,60 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 		struct timespec __user *, timeout)
 {
 	struct timespec64	ts;
+	int			ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
+
+SYSCALL_DEFINE6(io_pgetevents,
+		aio_context_t, ctx_id,
+		long, min_nr,
+		long, nr,
+		struct io_event __user *, events,
+		struct timespec __user *, timeout,
+		const struct __aio_sigset __user *, usig)
+{
+	struct __aio_sigset	ksig = { NULL, };
+	sigset_t		ksigmask, sigsaved;
+	struct timespec64	ts;
+	int ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
 
-	if (timeout) {
-		if (unlikely(get_timespec64(&ts, timeout)))
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ksigmask, ksig.sigmask, sizeof(ksigmask)))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -1877,13 +2079,64 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
 		       struct compat_timespec __user *, timeout)
 {
 	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
+
+
+struct __compat_aio_sigset {
+	compat_sigset_t __user	*sigmask;
+	compat_size_t		sigsetsize;
+};
+
+COMPAT_SYSCALL_DEFINE6(io_pgetevents,
+		compat_aio_context_t, ctx_id,
+		compat_long_t, min_nr,
+		compat_long_t, nr,
+		struct io_event __user *, events,
+		struct compat_timespec __user *, timeout,
+		const struct __compat_aio_sigset __user *, usig)
+{
+	struct __compat_aio_sigset ksig = { NULL, };
+	sigset_t ksigmask, sigsaved;
+	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
 
-	if (timeout) {
-		if (compat_get_timespec64(&t, timeout))
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (get_compat_sigset(&ksigmask, ksig.sigmask))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
 
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	return ret;
 }
 #endif

fs/eventfd.c

@@ -101,14 +101,20 @@ static int eventfd_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static __poll_t eventfd_poll(struct file *file, poll_table *wait)
+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)
 {
 	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
@@ -305,7 +311,8 @@ static const struct file_operations eventfd_fops = {
 	.show_fdinfo	= eventfd_show_fdinfo,
 #endif
 	.release	= eventfd_release,
-	.poll		= eventfd_poll,
+	.get_poll_head	= eventfd_get_poll_head,
+	.poll_mask	= eventfd_poll_mask,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,

fs/eventpoll.c

@@ -884,8 +884,7 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
 
 	pt->_key = epi->event.events;
 	if (!is_file_epoll(epi->ffd.file))
-		return epi->ffd.file->f_op->poll(epi->ffd.file, pt) &
-		       epi->event.events;
+		return vfs_poll(epi->ffd.file, pt) & epi->event.events;
 
 	ep = epi->ffd.file->private_data;
 	poll_wait(epi->ffd.file, &ep->poll_wait, pt);
@@ -2025,7 +2024,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 
 	/* The target file descriptor must support poll */
 	error = -EPERM;
-	if (!tf.file->f_op->poll)
+	if (!file_can_poll(tf.file))
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */

fs/pipe.c

@@ -509,19 +509,22 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-/* No kernel lock held - fine */
-static __poll_t
-pipe_poll(struct file *filp, poll_table *wait)
+static struct wait_queue_head *
+pipe_get_poll_head(struct file *filp, __poll_t events)
 {
-	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	int nrbufs;
 
-	poll_wait(filp, &pipe->wait, wait);
+	return &pipe->wait;
+}
+
+/* No kernel lock held - fine */
+static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+{
+	struct pipe_inode_info *pipe = filp->private_data;
+	int nrbufs = pipe->nrbufs;
+	__poll_t mask = 0;
 
 	/* 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)
@@ -1020,7 +1023,8 @@ const struct file_operations pipefifo_fops = {
 	.llseek		= no_llseek,
 	.read_iter	= pipe_read,
 	.write_iter	= pipe_write,
-	.poll		= pipe_poll,
+	.get_poll_head	= pipe_get_poll_head,
+	.poll_mask	= pipe_poll_mask,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
 	.fasync		= pipe_fasync,

fs/select.c

@@ -34,6 +34,29 @@
 
 #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.
@@ -233,7 +256,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
 	add_wait_queue(wait_address, &entry->wait);
 }
 
-int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
+static int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 			  ktime_t *expires, unsigned long slack)
 {
 	int rc = -EINTR;
@@ -258,7 +281,6 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
 
 	return rc;
 }
-EXPORT_SYMBOL(poll_schedule_timeout);
 
 /**
  * poll_select_set_timeout - helper function to setup the timeout value
@@ -503,14 +525,10 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 					continue;
 				f = fdget(i);
 				if (f.file) {
-					const struct file_operations *f_op;
-					f_op = f.file->f_op;
-					mask = DEFAULT_POLLMASK;
-					if (f_op->poll) {
-						wait_key_set(wait, in, out,
-							     bit, busy_flag);
-						mask = (*f_op->poll)(f.file, wait);
-					}
+					wait_key_set(wait, in, out, bit,
+						     busy_flag);
+					mask = vfs_poll(f.file, wait);
+
 					fdput(f);
 					if ((mask & POLLIN_SET) && (in & bit)) {
 						res_in |= bit;
@@ -813,34 +831,29 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
 				     bool *can_busy_poll,
 				     __poll_t busy_flag)
 {
-	__poll_t mask;
-	int fd;
-
-	mask = 0;
-	fd = pollfd->fd;
-	if (fd >= 0) {
-		struct fd f = fdget(fd);
-		mask = EPOLLNVAL;
-		if (f.file) {
-			/* userland u16 ->events contains POLL... bitmap */
-			__poll_t filter = demangle_poll(pollfd->events) |
-						EPOLLERR | EPOLLHUP;
-			mask = DEFAULT_POLLMASK;
-			if (f.file->f_op->poll) {
-				pwait->_key = filter;
-				pwait->_key |= busy_flag;
-				mask = f.file->f_op->poll(f.file, pwait);
-				if (mask & busy_flag)
-					*can_busy_poll = true;
-			}
-			/* Mask out unneeded events. */
-			mask &= filter;
-			fdput(f);
-		}
-	}
+	int fd = pollfd->fd;
+	__poll_t mask = 0, filter;
+	struct fd f;
+
+	if (fd < 0)
+		goto out;
+	mask = EPOLLNVAL;
+	f = fdget(fd);
+	if (!f.file)
+		goto out;
+
+	/* userland u16 ->events contains POLL... bitmap */
+	filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
+	pwait->_key = filter | busy_flag;
+	mask = vfs_poll(f.file, pwait);
+	if (mask & busy_flag)
+		*can_busy_poll = true;
+	mask &= filter;		/* Mask out unneeded events. */
+	fdput(f);
+
+out:
 	/* ... and so does ->revents */
 	pollfd->revents = mangle_poll(mask);
-
 	return mask;
 }
 

fs/timerfd.c

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

include/crypto/if_alg.h

@@ -245,8 +245,7 @@ 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(struct file *file, struct socket *sock,
-			 poll_table *wait);
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
 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/aio.h

@@ -8,8 +8,6 @@ struct kioctx;
 struct kiocb;
 struct mm_struct;
 
-#define KIOCB_KEY		0
-
 typedef int (kiocb_cancel_fn)(struct kiocb *);
 
 /* prototypes */

include/linux/compat.h

@@ -330,6 +330,7 @@ extern int put_compat_rusage(const struct rusage *,
 			     struct compat_rusage __user *);
 
 struct compat_siginfo;
+struct __compat_aio_sigset;
 
 struct compat_dirent {
 	u32		d_ino;
@@ -553,6 +554,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
 					compat_long_t nr,
 					struct io_event __user *events,
 					struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+					compat_long_t min_nr,
+					compat_long_t nr,
+					struct io_event __user *events,
+					struct compat_timespec __user *timeout,
+					const struct __compat_aio_sigset __user *usig);
 
 /* fs/cookies.c */
 asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);

include/linux/fs.h

@@ -1711,6 +1711,8 @@ 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

@@ -147,6 +147,7 @@ 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

@@ -74,6 +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)
+{
+	return file->f_op->get_poll_head && file->f_op->poll_mask;
+}
+
+static inline bool file_can_poll(struct file *file)
+{
+	return file->f_op->poll || file_has_poll_mask(file);
+}
+
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;
@@ -96,8 +108,6 @@ struct poll_wqueues {
 
 extern void poll_initwait(struct poll_wqueues *pwq);
 extern void poll_freewait(struct poll_wqueues *pwq);
-extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
-				 ktime_t *expires, unsigned long slack);
 extern u64 select_estimate_accuracy(struct timespec64 *tv);
 
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)

include/linux/skbuff.h

@@ -3250,8 +3250,7 @@ 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(struct file *file, struct socket *sock,
-			   struct poll_table_struct *wait);
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
 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/linux/syscalls.h

@@ -290,6 +290,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
 				long nr,
 				struct io_event __user *events,
 				struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+				long min_nr,
+				long nr,
+				struct io_event __user *events,
+				struct timespec __user *timeout,
+				const struct __aio_sigset *sig);
 
 /* fs/xattr.c */
 asmlinkage long sys_setxattr(const char __user *path, const char __user *name,

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(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
 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/busy_poll.h

@@ -121,6 +121,21 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 #endif
 }
 
+static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events)
+{
+	if (sk_can_busy_loop(sock->sk) &&
+	    events && (events & POLL_BUSY_LOOP)) {
+		/* once, only if requested by syscall */
+		sk_busy_loop(sock->sk, 1);
+	}
+}
+
+/* if this socket can poll_ll, tell the system call */
+static inline __poll_t sock_poll_busy_flag(struct socket *sock)
+{
+	return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0;
+}
+
 /* used in the NIC receive handler to mark the skb */
 static inline void skb_mark_napi_id(struct sk_buff *skb,
 				    struct napi_struct *napi)

include/net/iucv/af_iucv.h

@@ -153,8 +153,6 @@ 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

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

include/net/sock.h

@@ -1591,8 +1591,6 @@ int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
 int sock_no_accept(struct socket *, struct socket *, int, bool);
 int sock_no_getname(struct socket *, struct sockaddr *, int);
-__poll_t sock_no_poll(struct file *, struct socket *,
-			  struct poll_table_struct *);
 int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
 int sock_no_listen(struct socket *, int);
 int sock_no_shutdown(struct socket *, int);

include/net/tcp.h

@@ -388,8 +388,7 @@ 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(struct file *file, struct socket *sock,
-		      struct poll_table_struct *wait);
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
 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/udp.h

@@ -276,7 +276,7 @@ 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(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6);

include/uapi/asm-generic/unistd.h

@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 
 #undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/aio_abi.h

@@ -29,6 +29,7 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
+#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -38,10 +39,8 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* These two are experimental.
-	 * IOCB_CMD_PREADX = 4,
-	 * IOCB_CMD_POLL = 5,
-	 */
+	/* 4 was the experimental IOCB_CMD_PREADX */
+	IOCB_CMD_POLL = 5,
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
@@ -108,5 +107,10 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
+struct __aio_sigset {
+	sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 #endif /* __LINUX__AIO_ABI_H */
 

include/uapi/linux/types.h

@@ -49,11 +49,7 @@ typedef __u32 __bitwise __wsum;
 #define __aligned_be64 __be64 __attribute__((aligned(8)))
 #define __aligned_le64 __le64 __attribute__((aligned(8)))
 
-#ifdef __CHECK_POLL
 typedef unsigned __bitwise __poll_t;
-#else
-typedef unsigned __poll_t;
-#endif
 
 #endif /*  __ASSEMBLY__ */
 #endif /* _UAPI_LINUX_TYPES_H */

kernel/sys_ni.c

@@ -43,7 +43,9 @@ COND_SYSCALL(io_submit);
 COND_SYSCALL_COMPAT(io_submit);
 COND_SYSCALL(io_cancel);
 COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents);
 COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents);
 
 /* fs/xattr.c */
 

mm/memcontrol.c

@@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	if (ret)
 		goto out_put_css;
 
-	efile.file->f_op->poll(efile.file, &event->pt);
+	vfs_poll(efile.file, &event->pt);
 
 	spin_lock(&memcg->event_list_lock);
 	list_add(&event->list, &memcg->event_list);

net/9p/trans_fd.c

@@ -231,7 +231,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
 static __poll_t
 p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
 {
-	__poll_t ret, n;
+	__poll_t ret;
 	struct p9_trans_fd *ts = NULL;
 
 	if (client && client->status == Connected)
@@ -243,19 +243,9 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
 		return EPOLLERR;
 	}
 
-	if (!ts->rd->f_op->poll)
-		ret = DEFAULT_POLLMASK;
-	else
-		ret = ts->rd->f_op->poll(ts->rd, pt);
-
-	if (ts->rd != ts->wr) {
-		if (!ts->wr->f_op->poll)
-			n = DEFAULT_POLLMASK;
-		else
-			n = ts->wr->f_op->poll(ts->wr, pt);
-		ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN);
-	}
-
+	ret = vfs_poll(ts->rd, pt);
+	if (ts->rd != ts->wr)
+		ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN);
 	return ret;
 }
 

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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= atalk_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= atalk_compat_ioctl,

net/atm/common.c

@@ -648,16 +648,11 @@ out:
 	return error;
 }
 
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	struct atm_vcc *vcc;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
-
-	vcc = ATM_SD(sock);
+	struct atm_vcc *vcc = ATM_SD(sock);
+	__poll_t mask = 0;
 
 	/* 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(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
 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 =		vcc_poll,
+	.poll_mask =	vcc_poll_mask,
 	.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 =		vcc_poll,
+	.poll_mask =	vcc_poll_mask,
 	.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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= ax25_ioctl,
 	.listen		= ax25_listen,
 	.shutdown	= ax25_shutdown,

net/bluetooth/af_bluetooth.c

@@ -437,16 +437,13 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t bt_sock_poll(struct file *file, struct socket *sock,
-			  poll_table *wait)
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	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);
 
@@ -478,7 +475,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL(bt_sock_poll);
+EXPORT_SYMBOL(bt_sock_poll_mask);
 
 int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {

net/bluetooth/bnep/sock.c

@@ -175,7 +175,6 @@ static const struct proto_ops bnep_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,

net/bluetooth/cmtp/sock.c

@@ -178,7 +178,6 @@ static const struct proto_ops cmtp_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,

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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= hci_sock_setsockopt,

net/bluetooth/hidp/sock.c

@@ -208,7 +208,6 @@ static const struct proto_ops hidp_sock_ops = {
 	.getname	= sock_no_getname,
 	.sendmsg	= sock_no_sendmsg,
 	.recvmsg	= sock_no_recvmsg,
-	.poll		= sock_no_poll,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_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		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.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		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.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		= bt_sock_poll,
+	.poll_mask	= bt_sock_poll_mask,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,

net/caif/caif_socket.c

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

net/can/bcm.c

@@ -1657,7 +1657,7 @@ static const struct proto_ops bcm_ops = {
 	.socketpair    = sock_no_socketpair,
 	.accept        = sock_no_accept,
 	.getname       = sock_no_getname,
-	.poll          = datagram_poll,
+	.poll_mask     = datagram_poll_mask,
 	.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          = datagram_poll,
+	.poll_mask     = datagram_poll_mask,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,

net/core/datagram.c

@@ -819,9 +819,8 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
- *	@file: file struct
  *	@sock: socket
- *	@wait: poll table
+ *	@events to wait for
  *
  *	Datagram poll: Again totally generic. This also handles
  *	sequenced packet sockets providing the socket receive queue
@@ -831,14 +830,10 @@ 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(struct file *file, struct socket *sock,
-			   poll_table *wait)
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
-	__poll_t mask;
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-	mask = 0;
+	__poll_t mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -871,4 +866,4 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL(datagram_poll);
+EXPORT_SYMBOL(datagram_poll_mask);

net/core/sock.c

@@ -2567,12 +2567,6 @@ int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
 }
 EXPORT_SYMBOL(sock_no_getname);
 
-__poll_t sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
-{
-	return 0;
-}
-EXPORT_SYMBOL(sock_no_poll);
-
 int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	return -EOPNOTSUPP;

net/dccp/dccp.h

@@ -316,8 +316,7 @@ 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(struct file *file, struct socket *sock,
-		       poll_table *wait);
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
 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		   = dccp_poll,
+	.poll_mask	   = dccp_poll_mask,
 	.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		   = dccp_poll,
+	.poll_mask	   = dccp_poll_mask,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,

net/dccp/proto.c

@@ -312,20 +312,11 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 EXPORT_SYMBOL_GPL(dccp_disconnect);
 
-/*
- *	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 dccp_poll_mask(struct socket *sock, __poll_t events)
 {
 	__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);
 
@@ -367,7 +358,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-EXPORT_SYMBOL_GPL(dccp_poll);
+EXPORT_SYMBOL_GPL(dccp_poll_mask);
 
 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(struct file *file, struct socket *sock, poll_table  *wait)
+static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 
 	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 =		dn_poll,
+	.poll_mask =	dn_poll_mask,
 	.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		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.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		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.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		   = tcp_poll,
+	.poll_mask	   = tcp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
@@ -1018,7 +1018,7 @@ const struct proto_ops inet_dgram_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll		   = udp_poll,
+	.poll_mask	   = udp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
@@ -1039,7 +1039,7 @@ EXPORT_SYMBOL(inet_dgram_ops);
 
 /*
  * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll
+ * udp_poll_mask
  */
 static const struct proto_ops inet_sockraw_ops = {
 	.family		   = PF_INET,
@@ -1050,7 +1050,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = sock_no_accept,
 	.getname	   = inet_getname,
-	.poll		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,

net/ipv4/tcp.c

@@ -494,32 +494,21 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 }
 
 /*
- *	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.
+ * 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.
  */
-__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
 {
-	__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
@@ -600,7 +589,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	return mask;
 }
-EXPORT_SYMBOL(tcp_poll);
+EXPORT_SYMBOL(tcp_poll_mask);
 
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {

net/ipv4/udp.c

@@ -2501,7 +2501,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
  * 	udp_poll - wait for a UDP event.
  *	@file - file struct
  *	@sock - socket
- *	@wait - poll table
+ *	@events - events to wait for
  *
  *	This is same as datagram poll, except for the special case of
  *	blocking sockets. If application is using a blocking fd
@@ -2510,23 +2510,23 @@ 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(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
 {
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 	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) && !(file->f_flags & O_NONBLOCK) &&
+	if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll);
+EXPORT_SYMBOL(udp_poll_mask);
 
 int udp_abort(struct sock *sk, int err)
 {

net/ipv6/af_inet6.c

@@ -571,7 +571,7 @@ const struct proto_ops inet6_stream_ops = {
 	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
 	.accept		   = inet_accept,		/* ok		*/
 	.getname	   = inet6_getname,
-	.poll		   = tcp_poll,			/* ok		*/
+	.poll_mask	   = tcp_poll_mask,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
@@ -601,7 +601,7 @@ 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		   = udp_poll,			/* ok		*/
+	.poll_mask	   = udp_poll_mask,		/* 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.  */
+/* Same as inet6_dgram_ops, sans udp_poll_mask.  */
 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		   = datagram_poll,		/* ok		*/
+	.poll_mask	   = datagram_poll_mask,	/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/

net/iucv/af_iucv.c

@@ -1488,14 +1488,11 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
 	return 0;
 }
 
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
-			    poll_table *wait)
+static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	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);
 
@@ -2388,7 +2385,7 @@ static const struct proto_ops iucv_sock_ops = {
 	.getname	= iucv_sock_getname,
 	.sendmsg	= iucv_sock_sendmsg,
 	.recvmsg	= iucv_sock_recvmsg,
-	.poll		= iucv_sock_poll,
+	.poll_mask	= iucv_sock_poll_mask,
 	.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 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_mask 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 =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.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 =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.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		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.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		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.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		   = datagram_poll,
+	.poll_mask	   = datagram_poll_mask,
 	.ioctl		   = inet6_ioctl,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,

net/l2tp/l2tp_ppp.c

@@ -1788,7 +1788,7 @@ static const struct proto_ops pppol2tp_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pppol2tp_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.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	     = datagram_poll,
+	.poll_mask   = datagram_poll_mask,
 	.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 =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.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		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.ioctl		=	nr_ioctl,
 	.listen		=	nr_listen,
 	.shutdown	=	sock_no_shutdown,

net/nfc/llcp_sock.c

@@ -548,16 +548,13 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
 	return 0;
 }
 
-static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
-				   poll_table *wait)
+static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
 {
 	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);
 
@@ -899,7 +896,7 @@ static const struct proto_ops llcp_sock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = llcp_sock_accept,
 	.getname        = llcp_sock_getname,
-	.poll           = llcp_sock_poll,
+	.poll_mask      = llcp_sock_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = llcp_sock_listen,
 	.shutdown       = sock_no_shutdown,
@@ -919,7 +916,7 @@ static const struct proto_ops llcp_rawsock_ops = {
 	.socketpair     = sock_no_socketpair,
 	.accept         = sock_no_accept,
 	.getname        = llcp_sock_getname,
-	.poll           = llcp_sock_poll,
+	.poll_mask      = llcp_sock_poll_mask,
 	.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           = datagram_poll,
+	.poll_mask      = datagram_poll_mask,
 	.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           = datagram_poll,
+	.poll_mask      = datagram_poll_mask,
 	.ioctl          = sock_no_ioctl,
 	.listen         = sock_no_listen,
 	.shutdown       = sock_no_shutdown,

net/packet/af_packet.c

@@ -4110,12 +4110,11 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
 	return 0;
 }
 
-static __poll_t packet_poll(struct file *file, struct socket *sock,
-				poll_table *wait)
+static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(sock, events);
 
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (po->rx_ring.pg_vec) {
@@ -4457,7 +4456,7 @@ static const struct proto_ops packet_ops_spkt = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname_spkt,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -4478,7 +4477,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	packet_getname,
-	.poll =		packet_poll,
+	.poll_mask =	packet_poll_mask,
 	.ioctl =	packet_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,

net/phonet/socket.c

@@ -340,15 +340,12 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 	return sizeof(struct sockaddr_pn);
 }
 
-static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
-					poll_table *wait)
+static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
 {
 	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))
@@ -448,7 +445,7 @@ const struct proto_ops phonet_dgram_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= pn_socket_getname,
-	.poll		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.ioctl		= pn_socket_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -473,7 +470,7 @@ const struct proto_ops phonet_stream_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= pn_socket_accept,
 	.getname	= pn_socket_getname,
-	.poll		= pn_socket_poll,
+	.poll_mask	= pn_socket_poll_mask,
 	.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		= datagram_poll,
+	.poll_mask	= datagram_poll_mask,
 	.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		=	datagram_poll,
+	.poll_mask	=	datagram_poll_mask,
 	.ioctl		=	rose_ioctl,
 	.listen		=	rose_listen,
 	.shutdown	=	sock_no_shutdown,

net/rxrpc/af_rxrpc.c

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

net/sctp/socket.c

@@ -7722,14 +7722,12 @@ 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(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
 {
 	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/socket.c

@@ -117,8 +117,10 @@ 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 __poll_t sock_poll(struct file *file,
-			      struct poll_table_struct *wait);
+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 long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_COMPAT
 static long compat_sock_ioctl(struct file *file,
@@ -141,6 +143,8 @@ 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
@@ -1114,27 +1118,48 @@ out_release:
 }
 EXPORT_SYMBOL(sock_create_lite);
 
-/* No kernel lock held - perfect */
-static __poll_t sock_poll(struct file *file, poll_table *wait)
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+		__poll_t events)
 {
-	__poll_t busy_flag = 0;
-	struct socket *sock;
+	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 can't return errors to poll, so it's either yes or no.
+	 * We need to be sure we are in sync with the socket flags modification.
+	 *
+	 * This memory barrier is paired in the wq_has_sleeper.
 	 */
-	sock = file->private_data;
+	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);
+}
 
-	if (sk_can_busy_loop(sock->sk)) {
-		/* this socket can poll_ll so tell the system call */
-		busy_flag = POLL_BUSY_LOOP;
+/* 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;
 
-		/* once, only if requested by syscall */
-		if (wait && (wait->_key & POLL_BUSY_LOOP))
-			sk_busy_loop(sock->sk, 1);
+	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);
 	}
 
-	return busy_flag | sock->ops->poll(file, sock, wait);
+	return mask | sock_poll_busy_flag(sock);
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)

net/tipc/socket.c

@@ -692,10 +692,9 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 
 /**
- * tipc_poll - read and possibly block on pollmask
+ * tipc_poll - read pollmask
  * @file: file structure associated with the socket
  * @sock: socket for which to calculate the poll bits
- * @wait: ???
  *
  * Returns pollmask value
  *
@@ -709,15 +708,12 @@ 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(struct file *file, struct socket *sock,
-			      poll_table *wait)
+static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
 {
 	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)
@@ -3028,7 +3024,7 @@ static const struct proto_ops msg_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
@@ -3049,7 +3045,7 @@ static const struct proto_ops packet_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
@@ -3070,7 +3066,7 @@ static const struct proto_ops stream_ops = {
 	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
-	.poll		= tipc_poll,
+	.poll_mask	= tipc_poll_mask,
 	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,

net/unix/af_unix.c

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

net/vmw_vsock/af_vsock.c

@@ -850,18 +850,11 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	return err;
 }
 
-static __poll_t vsock_poll(struct file *file, struct socket *sock,
-			       poll_table *wait)
+static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
 {
-	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;
+	struct sock *sk = sock->sk;
+	struct vsock_sock *vsk = vsock_sk(sk);
+	__poll_t mask = 0;
 
 	if (sk->sk_err)
 		/* Signify that there has been an error on this socket. */
@@ -1091,7 +1084,7 @@ static const struct proto_ops vsock_dgram_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = sock_no_accept,
 	.getname = vsock_getname,
-	.poll = vsock_poll,
+	.poll_mask = vsock_poll_mask,
 	.ioctl = sock_no_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = vsock_shutdown,
@@ -1849,7 +1842,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,
-	.poll = vsock_poll,
+	.poll_mask = vsock_poll_mask,
 	.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 =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	x25_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_x25_ioctl,

virt/kvm/eventfd.c

@@ -397,7 +397,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * Check if there was an event already pending on the eventfd
 	 * before we registered, and trigger it as if we didn't miss it.
 	 */
-	events = f.file->f_op->poll(f.file, &irqfd->pt);
+	events = vfs_poll(f.file, &irqfd->pt);
 
 	if (events & EPOLLIN)
 		schedule_work(&irqfd->inject);