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 __poll_t
-random_poll(struct file *file, poll_table * wait)
+static struct wait_queue_head *
+random_get_poll_head(struct file *file, __poll_t events)
 {
-	__poll_t mask;
+	return &random_wait;
+}
+
+static __poll_t
+random_poll_mask(struct file *file, __poll_t events)
+{
+	__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/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 */