aio poll, io_pgetevents and a new in-kernel poll API

aio poll, io_pgetevents and a new in-kernel poll API

[Christoph Hellwig]

Hi all,

this series adds support for the IOCB_CMD_POLL operation to poll for the
readyness of file descriptors using the aio subsystem.  The API is based
on patches that existed in RHAS2.1 and RHEL3, which means it already is
supported by libaio.  To implement the poll support efficiently new
methods to poll are introduced in struct file_operations:  get_poll_head
and poll_mask.  The first one returns a wait_queue_head to wait on
(lifetime is bound by the file), and the second does a non-blocking
check for the POLL* events.  This allows aio poll to work without
any additional context switches, unlike epoll.

To make the interface fully useful a new io_pgetevents system call is
added, which atomically saves and restores the signal mask over the
io_pgetevents system call.  It it the logical equivalent to pselect and
ppoll for io_pgetevents.

The corresponding libaio changes for io_pgetevents support and
documentation, as well as a test case will be posted in a separate
series.

The changes were sponsored by Scylladb, and improve performance
of the seastar framework up to 10%, while also removing the need
for a privileged SCHED_FIFO epoll listener thread.

The patches are on top of Als __poll_t annoations, so I've also
prepared a git branch on top of those here:

    git://git.infradead.org/users/hch/vfs.git aio-poll

Gitweb:

    http://git.infradead.org/users/hch/vfs.git/shortlog/refs/heads/aio-poll

Libaio changes:

    http://git.infradead.org/users/hch/libaio.git/shortlog/refs/heads/aio-poll

Seastar changes:

    https://github.com/avikivity/seastar/commits/aio

[PATCH 01/31] fs: update documentation for __poll_t

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/Locking | 2 +-
 Documentation/filesystems/vfs.txt | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75d2d57e2c44..220bba28f72b 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -439,7 +439,7 @@ prototypes:
 	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 *);
 	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 *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5fd325df59e2..f608180ad59d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -856,7 +856,7 @@ 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 *);
 	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 *);
-- 
2.14.2

[PATCH 02/31] fs: add new vfs_poll and file_can_poll helpers

[Christoph Hellwig]

These abstract out calls to the poll method in preparation for changes to
those methods.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/staging/comedi/drivers/serial2002.c |  4 ++--
 drivers/vfio/virqfd.c                       |  2 +-
 drivers/vhost/vhost.c                       |  2 +-
 fs/eventpoll.c                              |  5 ++---
 fs/select.c                                 | 10 ++++------
 include/linux/poll.h                        | 10 ++++++++++
 mm/memcontrol.c                             |  2 +-
 net/9p/trans_fd.c                           |  8 ++++----
 virt/kvm/eventfd.c                          |  2 +-
 9 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/staging/comedi/drivers/serial2002.c b/drivers/staging/comedi/drivers/serial2002.c
index a557be8a5076..5e2a2dc372e0 100644
--- a/drivers/staging/comedi/drivers/serial2002.c
+++ b/drivers/staging/comedi/drivers/serial2002.c
@@ -121,7 +121,7 @@ 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 & (POLLRDNORM | POLLRDBAND | POLLIN |
 			    POLLHUP | POLLERR)) {
 			break;
@@ -144,7 +144,7 @@ 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)
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 8cc4b48ff127..ef539a07a08c 100644
--- a/drivers/vfio/virqfd.c
+++ b/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
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3bbeabff505a..b6311dc74d71 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -209,7 +209,7 @@ 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 & POLLERR) {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 42e35a6977c9..7d65f628810e 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -882,8 +882,7 @@ static unsigned int 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);
@@ -2015,7 +2014,7 @@ 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 */
diff --git a/fs/select.c b/fs/select.c
index ec14171dd78a..c96ebf020e5a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -503,13 +503,11 @@ 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) {
+					if (file_can_poll(f.file)) {
 						wait_key_set(wait, in, out,
 							     bit, busy_flag);
-						mask = (*f_op->poll)(f.file, wait);
+						mask = vfs_poll(f.file, wait);
 					}
 					fdput(f);
 					if ((mask & POLLIN_SET) && (in & bit)) {
@@ -820,10 +818,10 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
 			__poll_t filter = demangle_poll(pollfd->events) |
 						POLLERR | POLLHUP;
 			mask = DEFAULT_POLLMASK;
-			if (f.file->f_op->poll) {
+			if (file_can_poll(f.file)) {
 				pwait->_key = filter;
 				pwait->_key |= busy_flag;
-				mask = f.file->f_op->poll(f.file, pwait);
+				mask = vfs_poll(f.file, pwait);
 				if (mask & busy_flag)
 					*can_busy_poll = true;
 			}
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 04781a753326..6e4b2ddd4e82 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -73,6 +73,16 @@ 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_can_poll(struct file *file)
+{
+	return file->f_op->poll;
+}
+
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+	return file->f_op->poll(file, pt);
+}
+
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9011997d8a5c..284e69f345f8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3928,7 +3928,7 @@ 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);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index d6f7f7cb79c4..e5d98e144b22 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -243,16 +243,16 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
 		return POLLERR;
 	}
 
-	if (!ts->rd->f_op->poll)
+	if (!file_can_poll(ts->rd))
 		ret = DEFAULT_POLLMASK;
 	else
-		ret = ts->rd->f_op->poll(ts->rd, pt);
+		ret = vfs_poll(ts->rd, pt);
 
 	if (ts->rd != ts->wr) {
-		if (!ts->wr->f_op->poll)
+		if (!file_can_poll(ts->wr))
 			n = DEFAULT_POLLMASK;
 		else
-			n = ts->wr->f_op->poll(ts->wr, pt);
+			n = vfs_poll(ts->wr, pt);
 		ret = (ret & ~POLLOUT) | (n & ~POLLIN);
 	}
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index a334399fafec..df8a23cbf457 100644
--- a/virt/kvm/eventfd.c
+++ b/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 & POLLIN)
 		schedule_work(&irqfd->inject);
-- 
2.14.2

[PATCH 03/31] fs: introduce new ->get_poll_head and ->poll_mask methods

[Christoph Hellwig]

->get_poll_head returns the waitqueue that the poll operation is going
to sleep on.  Note that this means we can only use a single waitqueue
for the poll, unlike some current drivers that use two waitqueues for
different events.  But now that we have keyed wakeups and heavily use
those for poll there aren't that many good reason left to keep the
multiple waitqueues, and if there are any ->poll is still around, the
driver just won't support aio poll.

->poll_mask is called after the wakeup to return the actual mask of
events reported by poll.  It can be called with the waitqueue lock
held in some cases.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/Locking |  7 ++++++-
 Documentation/filesystems/vfs.txt | 11 +++++++++++
 include/linux/fs.h                |  2 ++
 include/linux/poll.h              | 16 ++++++++++++++--
 4 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 220bba28f72b..6d227f9d7bd9 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -440,6 +440,8 @@ prototypes:
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -470,7 +472,7 @@ 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
@@ -498,6 +500,9 @@ 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 *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f608180ad59d..bafb5c749443 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -857,6 +857,8 @@ struct file_operations {
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
+	struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+	__poll_t (*poll_mask) (struct file *, __poll_t);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
@@ -901,6 +903,15 @@ 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 poll, select,
+  epoll or aio poll should wait on in case this instance only has single
+  waitqueue.
+
+  poll_mask: return the mask of POLL* values describing the file descriptor
+  state.  Called before going to sleep on the waitqueue returned by
+  get_poll_head, and 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
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 34c0434511c7..f7dd8eb1eb85 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1699,6 +1699,8 @@ 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 *);
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 6e4b2ddd4e82..90b1a282f626 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -75,12 +75,24 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 
 static inline bool file_can_poll(struct file *file)
 {
-	return file->f_op->poll;
+	return file->f_op->poll ||
+		(file->f_op->get_poll_head && file->f_op->poll_mask);
 }
 
 static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
 {
-	return file->f_op->poll(file, pt);
+	unsigned int events = poll_requested_events(pt);
+
+	if (file->f_op->poll)
+		return file->f_op->poll(file, pt);
+
+	poll_wait(file, file->f_op->get_poll_head(file, events), pt);
+	return file->f_op->poll_mask(file, events);
+}
+
+static inline __poll_t vfs_poll_mask(struct file *file, __poll_t events)
+{
+	return file->f_op->poll_mask(file, events) & events;
 }
 
 struct poll_table_entry {
-- 
2.14.2

[PATCH 04/31] net: add support for ->poll_mask in proto_ops

[Christoph Hellwig]

The socket file operations still implement ->poll until all protocols are
switched over.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/net.h |  3 +++
 net/socket.c        | 61 +++++++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 60 insertions(+), 4 deletions(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index c2d468cb9821..94d65de30cb7 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -147,6 +147,9 @@ struct proto_ops {
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int *sockaddr_len, int peer);
+	void		(*pre_poll)  (const struct sock *sk);
+	__poll_t	(*poll_mask) (struct file *file, 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,
diff --git a/net/socket.c b/net/socket.c
index 092baa464afc..69b2a5444558 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -118,8 +118,10 @@ 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,
@@ -142,6 +144,8 @@ 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
@@ -1094,10 +1098,48 @@ int sock_create_lite(int family, int type, int protocol, struct socket **res)
 }
 EXPORT_SYMBOL(sock_create_lite);
 
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+		__poll_t events)
+{
+	struct socket *sock = file->private_data;
+
+	if (!sock->ops->poll_mask)
+		return NULL;
+
+	/* once, only if requested by syscall */
+	if (sk_can_busy_loop(sock->sk) &&
+	    (events && (events & POLL_BUSY_LOOP)))
+		sk_busy_loop(sock->sk, 1);
+
+	if (sock->ops->pre_poll)
+		sock->ops->pre_poll(sock->sk);
+
+	return sk_sleep(sock->sk);
+}
+
+static __poll_t sock_poll_mask(struct file *file, __poll_t events)
+{
+	struct socket *sock = file->private_data;
+	__poll_t busy_flag = 0;
+
+	/*
+	 * We need to be sure we are in sync with the socket flags modification.
+	 *
+	 * This memory barrier is paired in the wq_has_sleeper.
+	 */
+	smp_mb();
+
+	/* this socket can poll_ll so tell the system call */
+	if (sk_can_busy_loop(sock->sk))
+		busy_flag = POLL_BUSY_LOOP;
+
+	return busy_flag | sock->ops->poll_mask(file, sock, events);
+}
+
 /* No kernel lock held - perfect */
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
-	__poll_t busy_flag = 0;
+	__poll_t busy_flag = 0, mask = 0;
 	struct socket *sock;
 
 	/*
@@ -1114,7 +1156,18 @@ static __poll_t sock_poll(struct file *file, poll_table *wait)
 			sk_busy_loop(sock->sk, 1);
 	}
 
-	return busy_flag | sock->ops->poll(file, sock, wait);
+	if (sock->ops->poll) {
+		mask = sock->ops->poll(file, sock, wait);
+	} else if (sock->ops->poll_mask) {
+		unsigned int events = poll_requested_events(wait);
+
+		if (sock->ops->pre_poll)
+			sock->ops->pre_poll(sock->sk);
+		sock_poll_wait(file, sk_sleep(sock->sk), wait);
+		mask = sock->ops->poll_mask(file, sock, events);
+	}
+
+	return busy_flag | mask;
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
-- 
2.14.2

[PATCH 05/31] net: remove sock_no_poll

[Christoph Hellwig]

Now that sock_poll handles a NULL ->poll or ->poll_mask there is no need
for a stub.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 crypto/af_alg.c             | 1 -
 crypto/algif_hash.c         | 2 --
 crypto/algif_rng.c          | 1 -
 drivers/isdn/mISDN/socket.c | 1 -
 drivers/net/ppp/pptp.c      | 1 -
 include/net/sock.h          | 2 --
 net/bluetooth/bnep/sock.c   | 1 -
 net/bluetooth/cmtp/sock.c   | 1 -
 net/bluetooth/hidp/sock.c   | 1 -
 net/core/sock.c             | 6 ------
 10 files changed, 17 deletions(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 05b084e216ac..592797ec8075 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -345,7 +345,6 @@ 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,
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 76d2e716c792..d5f323c1efc5 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -293,7 +293,6 @@ 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,
@@ -401,7 +400,6 @@ 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,
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 150c2b6480ed..22df3799a17b 100644
--- a/crypto/algif_rng.c
+++ b/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,
 
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index c5603d1a07d6..c84270e16bdd 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -746,7 +746,6 @@ 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,
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..87f892f1d0fe 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -627,7 +627,6 @@ 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,
diff --git a/include/net/sock.h b/include/net/sock.h
index f90685441143..1a5c31d1893a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1578,8 +1578,6 @@ 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 *, 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);
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index b5116fa9835e..00deacdcb51c 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/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,
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index ce86a7bae844..e08f28fadd65 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/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,
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 008ba439bd62..1eaac01f85de 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/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,
diff --git a/net/core/sock.c b/net/core/sock.c
index 1211159718ad..1943a79befea 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2496,12 +2496,6 @@ 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;
-- 
2.14.2

[PATCH 06/31] net/tcp: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/net/tcp.h   |  3 +--
 net/ipv4/af_inet.c  |  3 ++-
 net/ipv4/tcp.c      | 25 ++++++-------------------
 net/ipv6/af_inet6.c |  3 ++-
 4 files changed, 11 insertions(+), 23 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 50b21a49d870..b2f288db2db6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -387,8 +387,7 @@ 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 file *file, 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,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f00499a46927..8567f31bdad9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -934,7 +934,8 @@ const struct proto_ops inet_stream_ops = {
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = inet_accept,
 	.getname	   = inet_getname,
-	.poll		   = tcp_poll,
+	.pre_poll	   = sock_rps_record_flow,
+	.poll_mask	   = tcp_poll_mask,
 	.ioctl		   = inet_ioctl,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4a7ee7f6721..2912daf8e619 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -487,34 +487,21 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 }
 
 /*
- *	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 file *file, 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_rps_record_flow(sk);
-
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	state = 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;
-
 	/*
 	 * POLLHUP is certainly not done right. But poll() doesn't
 	 * have a notion of HUP in just one direction, and for a
@@ -595,7 +582,7 @@ __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)
 {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c9441ca45399..aa3ee8617bac 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -544,7 +544,8 @@ 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		*/
+	.pre_poll	   = sock_rps_record_flow,
+	.poll_mask	   = tcp_poll_mask,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
-- 
2.14.2

[PATCH 07/31] net/unix: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/unix/af_unix.c | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6b7678df41e5..01f0d2318113 100644
--- a/net/unix/af_unix.c
+++ b/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 *, 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 file *, struct socket *, __poll_t);
+static __poll_t unix_dgram_poll_mask(struct file *, 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,
@@ -2640,13 +2639,11 @@ 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 file *file, 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)
@@ -2675,15 +2672,12 @@ 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 file *file, 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))
@@ -2709,7 +2703,7 @@ 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) & (POLLWRBAND|POLLWRNORM|POLLOUT)))
+	if (!(events & (POLLWRBAND|POLLWRNORM|POLLOUT)))
 		return mask;
 
 	writable = unix_writable(sk);
-- 
2.14.2

[PATCH 08/31] net: convert datagram_poll users tp ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/isdn/mISDN/socket.c        |  2 +-
 drivers/net/ppp/pppoe.c            |  2 +-
 drivers/staging/irda/net/af_irda.c |  6 +++---
 include/linux/skbuff.h             |  4 ++--
 include/net/udp.h                  |  2 +-
 net/appletalk/ddp.c                |  2 +-
 net/ax25/af_ax25.c                 |  2 +-
 net/bluetooth/hci_sock.c           |  2 +-
 net/can/bcm.c                      |  2 +-
 net/can/raw.c                      |  2 +-
 net/core/datagram.c                | 13 +++++--------
 net/decnet/af_decnet.c             |  7 ++++---
 net/ieee802154/socket.c            |  4 ++--
 net/ipv4/af_inet.c                 |  6 +++---
 net/ipv4/udp.c                     |  8 ++++----
 net/ipv6/af_inet6.c                |  2 +-
 net/ipv6/raw.c                     |  4 ++--
 net/ipx/af_ipx.c                   |  2 +-
 net/kcm/kcmsock.c                  |  4 ++--
 net/key/af_key.c                   |  2 +-
 net/l2tp/l2tp_ip.c                 |  2 +-
 net/l2tp/l2tp_ip6.c                |  2 +-
 net/l2tp/l2tp_ppp.c                |  2 +-
 net/llc/af_llc.c                   |  2 +-
 net/netlink/af_netlink.c           |  2 +-
 net/netrom/af_netrom.c             |  2 +-
 net/nfc/rawsock.c                  |  4 ++--
 net/packet/af_packet.c             | 10 +++++-----
 net/phonet/socket.c                |  2 +-
 net/qrtr/qrtr.c                    |  2 +-
 net/rose/af_rose.c                 |  2 +-
 net/x25/af_x25.c                   |  2 +-
 32 files changed, 55 insertions(+), 57 deletions(-)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index c84270e16bdd..61d6e4c9e7d1 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -589,7 +589,7 @@ 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,
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 4e1da1645b15..93280e99ec63 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1119,7 +1119,7 @@ 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,
diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c
index f1d128b2dae9..ad1256695282 100644
--- a/drivers/staging/irda/net/af_irda.c
+++ b/drivers/staging/irda/net/af_irda.c
@@ -2600,7 +2600,7 @@ static const struct proto_ops irda_seqpacket_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	irda_accept,
 	.getname =	irda_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	irda_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	irda_compat_ioctl,
@@ -2624,7 +2624,7 @@ static const struct proto_ops irda_dgram_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	irda_accept,
 	.getname =	irda_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	irda_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	irda_compat_ioctl,
@@ -2649,7 +2649,7 @@ static const struct proto_ops irda_ultra_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	irda_getname,
-	.poll =		datagram_poll,
+	.poll_mask =	datagram_poll_mask,
 	.ioctl =	irda_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	irda_compat_ioctl,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a87e43d16f44..b2d1b360b61e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3241,8 +3241,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
-__poll_t datagram_poll(struct file *file, struct socket *sock,
-			   struct poll_table_struct *wait);
+__poll_t datagram_poll_mask(struct file *file, 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,
diff --git a/include/net/udp.h b/include/net/udp.h
index 850a8e581cce..b4e710a4d444 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -275,7 +275,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_init_sock(struct sock *sk);
 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 file *file, struct socket *sock, __poll_t events);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 03a9fc0771c0..3ea5631fee29 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1870,7 +1870,7 @@ 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,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 06eac1f50c5e..a91314e33396 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1955,7 +1955,7 @@ 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,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 923e9a271872..46a547e4a0c8 100644
--- a/net/bluetooth/hci_sock.c
+++ b/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,
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 13690334efa3..468de0cbd495 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1670,7 +1670,7 @@ 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,
diff --git a/net/can/raw.c b/net/can/raw.c
index 864c80dbdb72..3be75dff9802 100644
--- a/net/can/raw.c
+++ b/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,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b7d9293940b5..e3ad11953493 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -821,7 +821,7 @@ 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 +831,11 @@ 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 file *file, 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 +868,4 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 
 	return mask;
 }
-EXPORT_SYMBOL(datagram_poll);
+EXPORT_SYMBOL(datagram_poll_mask);
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 9c2dde819817..df76a3b72e85 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1209,11 +1209,12 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len
 }
 
 
-static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table  *wait)
+static __poll_t dn_poll_mask(struct file *file, 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(file, sock, events);
 
 	if (!skb_queue_empty(&scp->other_receive_queue))
 		mask |= POLLRDBAND;
@@ -2343,7 +2344,7 @@ 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,
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a60658c85a9a..a0768d2759b8 100644
--- a/net/ieee802154/socket.c
+++ b/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,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8567f31bdad9..065d18032714 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -967,7 +967,7 @@ 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,
@@ -988,7 +988,7 @@ 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,
@@ -999,7 +999,7 @@ 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,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ef45adfc0edb..befd649d8a97 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2493,7 +2493,7 @@ 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
@@ -2502,9 +2502,9 @@ 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 file *file, struct socket *sock, __poll_t events)
 {
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = datagram_poll_mask(file, sock, events);
 	struct sock *sk = sock->sk;
 
 	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
@@ -2520,7 +2520,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll);
+EXPORT_SYMBOL(udp_poll_mask);
 
 int udp_abort(struct sock *sk, int err)
 {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index aa3ee8617bac..84c4b9ad6cd9 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -575,7 +575,7 @@ 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		*/
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 761a473a07c5..f3055ff978d3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1344,7 +1344,7 @@ 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,
@@ -1354,7 +1354,7 @@ 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		*/
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index d21a9d128d3e..3373f7f67d35 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1967,7 +1967,7 @@ 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,
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index d4e98f20fc2a..574b2b7a1f2b 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1872,7 +1872,7 @@ 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,
@@ -1893,7 +1893,7 @@ 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,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 3dffb892d52c..7614091ea695 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3716,7 +3716,7 @@ 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,
 };
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ff61124fdf59..aa3fced17a75 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -618,7 +618,7 @@ 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,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 192344688c06..8ca5486ce952 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -757,7 +757,7 @@ 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,
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index b412fc3351dc..48ef494f4e0d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1787,7 +1787,7 @@ 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,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..67e5db6157ef 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1180,7 +1180,7 @@ 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,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 79cc1bf36e4a..37d2808f64db 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2633,7 +2633,7 @@ 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,
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 7ed9d4422a73..b2908e7f12de 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1367,7 +1367,7 @@ 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,
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index e2188deb08dc..60c322531c49 100644
--- a/net/nfc/rawsock.c
+++ b/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,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3b4d6a3cf190..14817deb0247 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4073,12 +4073,12 @@ 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 file *file, 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(file, sock, events);
 
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (po->rx_ring.pg_vec) {
@@ -4423,7 +4423,7 @@ 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,
@@ -4444,7 +4444,7 @@ 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,
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 44417480dab7..7563b0ac8386 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -449,7 +449,7 @@ 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,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 77ab05e23001..32c892993b56 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1024,7 +1024,7 @@ 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,
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 6a5c4992cf61..6794d0ae727d 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1484,7 +1484,7 @@ 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,
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 562cc11131f6..b94b8f3339f3 100644
--- a/net/x25/af_x25.c
+++ b/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,
-- 
2.14.2

[PATCH 09/31] net/dccp: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/dccp/dccp.h  |  4 ++--
 net/dccp/ipv4.c  |  2 +-
 net/dccp/ipv6.c  |  2 +-
 net/dccp/proto.c | 14 +++-----------
 4 files changed, 7 insertions(+), 15 deletions(-)

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index f91e3816806b..23b0cbdb1c6f 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -316,8 +316,8 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		 int flags, int *addr_len);
 void dccp_shutdown(struct sock *sk, int how);
 int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll(struct file *file, struct socket *sock,
-		       poll_table *wait);
+__poll_t dccp_poll_mask(struct file *file, 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);
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index e65fcb45c3f6..e8476f319efd 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -983,7 +983,7 @@ 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,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5df7857fc0f3..f0aac8e4b888 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1069,7 +1069,7 @@ 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,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 8b8db3d481bd..4d8b6bc9b5f3 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -311,20 +311,12 @@ 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 file *file, 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);
 
@@ -366,7 +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)
 {
-- 
2.14.2

[PATCH 10/31] net/atm: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/atm/common.c | 11 +++--------
 net/atm/common.h |  2 +-
 net/atm/pvc.c    |  2 +-
 net/atm/svc.c    |  2 +-
 4 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/net/atm/common.c b/net/atm/common.c
index 8f12f1c6fa14..427ef7f6779c 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -648,16 +648,11 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 	return error;
 }
 
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t vcc_poll_mask(struct file *file, 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)
diff --git a/net/atm/common.h b/net/atm/common.h
index 5850649068bb..8cf062f32570 100644
--- a/net/atm/common.h
+++ b/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 file *file, 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,
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index e1140b3bdcaa..930651c5e77c 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -114,7 +114,7 @@ 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,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index c458adcbc177..ad0e6ffb9cfe 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -637,7 +637,7 @@ 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,
-- 
2.14.2

[PATCH 11/31] net/vmw_vsock: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/vmw_vsock/af_vsock.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index bbd97d3bd8fb..bfd59b1da741 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -850,18 +850,12 @@ 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 file *file, 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 +1085,7 @@ 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 +1843,7 @@ 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,
-- 
2.14.2

[PATCH 12/31] net/tipc: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/tipc/socket.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index fcbd6489a8b5..87f8d59614d0 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -693,10 +693,9 @@ 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
  *
@@ -710,16 +709,14 @@ 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 file *file, struct socket *sock,
+		__poll_t events)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_group *grp = tsk->group;
 	__poll_t revents = 0;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
-
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= POLLRDHUP | POLLIN | POLLRDNORM;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -3005,7 +3002,7 @@ 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,
@@ -3026,7 +3023,7 @@ 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,
@@ -3047,7 +3044,7 @@ 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,
-- 
2.14.2

[PATCH 13/31] net/sctp: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/net/sctp/sctp.h | 4 ++--
 net/sctp/ipv6.c         | 2 +-
 net/sctp/protocol.c     | 2 +-
 net/sctp/socket.c       | 4 +---
 4 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 608d123ef25f..b378d978d272 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -107,8 +107,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 int sctp_inet_listen(struct socket *sock, int backlog);
 void sctp_write_space(struct sock *sk);
 void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll(struct file *file, struct socket *sock,
-		poll_table *wait);
+__poll_t sctp_poll_mask(struct file *file, 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);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3b18085e3b10..aa1261216b51 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -971,7 +971,7 @@ 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,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6a38c2503649..13b7daafcca7 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1026,7 +1026,7 @@ 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.  */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 03d9d24b38ba..1f3392d6cb6d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7500,14 +7500,12 @@ int sctp_inet_listen(struct socket *sock, int backlog)
  * 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 file *file, 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
-- 
2.14.2

[PATCH 14/31] net/bluetooth: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/net/bluetooth/bluetooth.h | 3 ++-
 net/bluetooth/af_bluetooth.c      | 8 +++-----
 net/bluetooth/l2cap_sock.c        | 2 +-
 net/bluetooth/rfcomm/sock.c       | 2 +-
 net/bluetooth/sco.c               | 2 +-
 5 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ec9d6bc65855..f54fac510cee 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -271,7 +271,8 @@ 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 file *file, 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);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 671b907ba678..c4596a1b4c25 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -437,16 +437,14 @@ 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 file *file, 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 +476,7 @@ __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)
 {
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 67a8642f57ea..d20b33daa80f 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1654,7 +1654,7 @@ 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,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 1aaccf637479..b4dc96481d92 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/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
 };
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 08df57665e1f..b2bf5c767b3e 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1198,7 +1198,7 @@ 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,
-- 
2.14.2

[PATCH 15/31] net/caif: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/caif/caif_socket.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 64048cec41e0..bf34e9446384 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -934,15 +934,12 @@ 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 file *file, 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 +973,7 @@ 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 +994,7 @@ 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,
-- 
2.14.2

[PATCH 16/31] net/nfc: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/nfc/llcp_sock.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 985909f105eb..11b05d0ed19b 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -549,16 +549,14 @@ 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 file *file, 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);
 
@@ -900,7 +898,7 @@ 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,
@@ -920,7 +918,7 @@ 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,
-- 
2.14.2

[PATCH 17/31] net/phonet: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/phonet/socket.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 7563b0ac8386..5b7b87c1a409 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -341,15 +341,13 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 	return 0;
 }
 
-static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
-					poll_table *wait)
+static __poll_t pn_socket_poll_mask(struct file *file, 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 POLLERR;
 	if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -474,7 +472,7 @@ 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,
-- 
2.14.2

[PATCH 18/31] net/iucv: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/net/iucv/af_iucv.h | 2 --
 net/iucv/af_iucv.c         | 8 +++-----
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index f4c21b5a1242..b0eaeb02d46d 100644
--- a/include/net/iucv/af_iucv.h
+++ b/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);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 64331158d693..9d28c3faf46c 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1489,14 +1489,12 @@ 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 file *file, 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);
 
@@ -2389,7 +2387,7 @@ 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,
-- 
2.14.2

[PATCH 19/31] net/rxrpc: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 net/rxrpc/af_rxrpc.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 21ad6a3a465c..83d9bf60eb22 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -729,15 +729,12 @@ 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 file *file, 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 */
@@ -940,7 +937,7 @@ 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,
-- 
2.14.2

[PATCH 20/31] pipe: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/pipe.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index a449ca0ec0c6..33a32d13b83d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -514,19 +514,22 @@ 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) ? POLLIN | POLLRDNORM : 0;
 		if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1010,7 +1013,8 @@ 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,
-- 
2.14.2

[PATCH 21/31] eventfd: switch to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/eventfd.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/fs/eventfd.c b/fs/eventfd.c
index 6318a9b57e53..2bbbf13cb816 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -114,14 +114,20 @@ 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
@@ -341,7 +347,8 @@ 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,
-- 
2.14.2

[PATCH 22/31] timerfd: convert to ->poll_mask

[Christoph Hellwig]

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/timerfd.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/timerfd.c b/fs/timerfd.c
index 0510717f3a53..ee36bb5b2698 100644
--- a/fs/timerfd.c
+++ b/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 |= POLLIN;
-	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 ? POLLIN : 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,
-- 
2.14.2

[PATCH 23/31] aio: don't print the page size at boot time

[Christoph Hellwig]

The page size is in no way related to the aio code, and printing it in
the (debug) dmesg at every boot serves no purpose.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index a062d75109cb..03d59593912d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -264,9 +264,6 @@ 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);
-- 
2.14.2

[PATCH 24/31] aio: remove an outdated comment in aio_complete

[Christoph Hellwig]

These days we don't treat sync iocbs special in the aio completion code as
they never use it.  Remove the old comment, and move the BUG_ON for a sync
iocb to the top of the function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 03d59593912d..41fc8ce6bc7f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1088,6 +1088,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
+	BUG_ON(is_sync_kiocb(kiocb));
+
 	if (kiocb->ki_flags & IOCB_WRITE) {
 		struct file *file = kiocb->ki_filp;
 
@@ -1100,15 +1102,6 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 		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;
 
-- 
2.14.2

[PATCH 25/31] aio: refactor read/write iocb setup

[Christoph Hellwig]

Don't reference the kiocb structure from the common aio code, and move
any use of it into helper specific to the read/write path.  This is in
preparation for aio_poll support that wants to use the space for different
fields.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 172 ++++++++++++++++++++++++++++++++++++---------------------------
 1 file changed, 98 insertions(+), 74 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 41fc8ce6bc7f..496b50f9e9b1 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -170,7 +170,9 @@ struct kioctx {
 #define KIOCB_CANCELLED		((void *) (~0ULL))
 
 struct aio_kiocb {
-	struct kiocb		common;
+	union {
+		struct kiocb		rw;
+	};
 
 	struct kioctx		*ki_ctx;
 	kiocb_cancel_fn		*ki_cancel;
@@ -549,7 +551,7 @@ 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;
 
@@ -582,7 +584,7 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
 		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
 	} while (cancel != old);
 
-	return cancel(&kiocb->common);
+	return cancel(&kiocb->rw);
 }
 
 static void free_ioctx(struct work_struct *work)
@@ -1040,15 +1042,6 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 	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;
@@ -1079,29 +1072,14 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 /* 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;
 
-	BUG_ON(is_sync_kiocb(kiocb));
-
-	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);
-	}
-
 	if (iocb->ki_list.next) {
 		unsigned long flags;
 
@@ -1163,11 +1141,12 @@ 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
@@ -1430,6 +1409,48 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	return -EINVAL;
 }
 
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+	WARN_ON_ONCE(is_sync_kiocb(kiocb));
+
+	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_flags = 0;
+	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)
 {
@@ -1449,7 +1470,7 @@ 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 ssize_t aio_rw_ret(struct kiocb *req, ssize_t ret)
 {
 	switch (ret) {
 	case -EIOCBQUEUED:
@@ -1465,7 +1486,7 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 		ret = -EINTR;
 		/*FALLTHRU*/
 	default:
-		aio_complete(req, ret, 0);
+		aio_complete_rw(req, ret, 0);
 		return 0;
 	}
 }
@@ -1473,56 +1494,78 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
 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));
+		ret = aio_rw_ret(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret && ret != -EIOCBQUEUED))
+		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) {
+		struct inode *inode = file_inode(file);
+
 		req->ki_flags |= IOCB_WRITE;
 		file_start_write(file);
-		ret = aio_ret(req, call_write_iter(file, req, &iter));
+		ret = aio_rw_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.
+		 * We release freeze protection in aio_complete_rw().  Fool
+		 * lockdep by telling it the lock got released so that it
+		 * doesn't complain about held lock when we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode))
-			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		if (S_ISREG(inode->i_mode))
+			__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
 	}
 	kfree(iovec);
+out_fput:
+	if (unlikely(ret && ret != -EIOCBQUEUED))
+		fput(file);
 	return ret;
 }
 
@@ -1530,7 +1573,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {
 	struct aio_kiocb *req;
-	struct file *file;
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
@@ -1553,16 +1595,6 @@ 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 the IOCB_FLAG_RESFD flag of aio_flags is set, get an
@@ -1576,14 +1608,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			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);
@@ -1595,26 +1619,24 @@ 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;
 
-	get_file(file);
 	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;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
 		ret = -EINVAL;
 		break;
 	}
-	fput(file);
 
 	if (ret && ret != -EIOCBQUEUED)
 		goto out_put_req;
@@ -1622,7 +1644,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 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;
 }
 
-- 
2.14.2

[PATCH 26/31] aio: sanitize ki_list handling

[Christoph Hellwig]

Instead of handcoded non-null checks always initialize ki_list to an
empty list and use list_empty / list_empty_careful on it.  While we're
at it also error out on a double call to kiocb_set_cancel_fn instead
of ignoring it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 496b50f9e9b1..fe241b5b44b2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -555,13 +555,12 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 	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);
@@ -1034,7 +1033,7 @@ 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:
@@ -1080,7 +1079,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
-	if (iocb->ki_list.next) {
+	if (!list_empty_careful(iocb->ki_list.next)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&ctx->ctx_lock, flags);
-- 
2.14.2

[PATCH 27/31] aio: simplify cancellation

[Christoph Hellwig]

With the current aio code there is no need for the magic KIOCB_CANCELLED
value, as a cancelation just kicks the driver to queue the completion
ASAP, with all actual completion handling done in another thread. Given
that both the completion path and cancelation take the context lock there
is no need for magic cmpxchg loops either.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 37 +++++++++----------------------------
 1 file changed, 9 insertions(+), 28 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index fe241b5b44b2..6204c1b81a36 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -156,19 +156,6 @@ 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 aio_kiocb {
 	union {
 		struct kiocb		rw;
@@ -565,24 +552,18 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
+/*
+ * Only cancel if there ws a ki_cancel function to start with, and we
+ * are the one how managed to clear it (to protect against simulatinious
+ * cancel calls).
+ */
 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);
+	kiocb_cancel_fn *cancel = kiocb->ki_cancel;
 
+	if (!cancel)
+		return -EINVAL;
+	kiocb->ki_cancel = NULL;
 	return cancel(&kiocb->rw);
 }
 
-- 
2.14.2

[PATCH 28/31] aio: delete iocbs from the active_reqs list in kiocb_cancel

[Christoph Hellwig]

One we cancel an iocb there is no reason to keep it on the active_reqs
list, given that the list is only used to look for cancelation candidates.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 6204c1b81a36..99c1d2ad67e9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -561,6 +561,8 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
 {
 	kiocb_cancel_fn *cancel = kiocb->ki_cancel;
 
+	list_del_init(&kiocb->ki_list);
+
 	if (!cancel)
 		return -EINVAL;
 	kiocb->ki_cancel = NULL;
@@ -607,8 +609,6 @@ 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);
-
-		list_del_init(&req->ki_list);
 		kiocb_cancel(req);
 	}
 
-- 
2.14.2

[PATCH 29/31] aio: add delayed cancel support

[Christoph Hellwig]

The upcoming aio poll support would like to be able to complete the
iocb inline from the cancellation context, but that would cause
a lock order reversal.  Add support for optionally moving the cancelation
outside the context lock to avoid this reversal.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c | 49 ++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 38 insertions(+), 11 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 99c1d2ad67e9..6fca1408a8a8 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -170,6 +170,10 @@ struct aio_kiocb {
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
 
+	unsigned int		flags;		/* protected by ctx->ctx_lock */
+#define AIO_IOCB_DELAYED_CANCEL	(1 << 0)
+#define AIO_IOCB_CANCELLED	(1 << 1)
+
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
 	 * this is the underlying eventfd context to deliver events to.
@@ -536,9 +540,9 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 #define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
 #define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
 
-void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
+static void __kiocb_set_cancel_fn(struct aio_kiocb *req,
+		kiocb_cancel_fn *cancel, unsigned int iocb_flags)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 
@@ -548,8 +552,15 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 	spin_lock_irqsave(&ctx->ctx_lock, flags);
 	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
+	req->flags |= iocb_flags;
 	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
 }
+
+void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
+{
+	return __kiocb_set_cancel_fn(container_of(iocb, struct aio_kiocb, rw),
+			cancel, 0);
+}
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
 /*
@@ -603,17 +614,27 @@ static void free_ioctx_users(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, users);
 	struct aio_kiocb *req;
+	LIST_HEAD(list);
 
 	spin_lock_irq(&ctx->ctx_lock);
-
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
 				       struct aio_kiocb, ki_list);
-		kiocb_cancel(req);
-	}
 
+		if (req->flags & AIO_IOCB_DELAYED_CANCEL) {
+			req->flags |= AIO_IOCB_CANCELLED;
+			list_move_tail(&req->ki_list, &list);
+		} else {
+			kiocb_cancel(req);
+		}
+	}
 	spin_unlock_irq(&ctx->ctx_lock);
 
+	while (!list_empty(&list)) {
+		req = list_first_entry(&list, struct aio_kiocb, ki_list);
+		kiocb_cancel(req);
+	}
+
 	percpu_ref_kill(&ctx->reqs);
 	percpu_ref_put(&ctx->reqs);
 }
@@ -1786,15 +1807,22 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 	if (unlikely(!ctx))
 		return -EINVAL;
 
-	spin_lock_irq(&ctx->ctx_lock);
+	ret = -EINVAL;
 
+	spin_lock_irq(&ctx->ctx_lock);
 	kiocb = lookup_kiocb(ctx, iocb, key);
+	if (kiocb) {
+		if (kiocb->flags & AIO_IOCB_DELAYED_CANCEL) {
+			kiocb->flags |= AIO_IOCB_CANCELLED;
+		} else {
+			ret = kiocb_cancel(kiocb);
+			kiocb = NULL;
+		}
+	}
+	spin_unlock_irq(&ctx->ctx_lock);
+
 	if (kiocb)
 		ret = kiocb_cancel(kiocb);
-	else
-		ret = -EINVAL;
-
-	spin_unlock_irq(&ctx->ctx_lock);
 
 	if (!ret) {
 		/*
@@ -1806,7 +1834,6 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 	}
 
 	percpu_ref_put(&ctx->users);
-
 	return ret;
 }
 
-- 
2.14.2

[PATCH 30/31] aio: implement IOCB_CMD_POLL

[Christoph Hellwig]

Simple one-shot poll through the io_submit() interface.  To poll for
a file descriptor the application should submit an iocb of type
IOCB_CMD_POLL.  It will poll the fd for the events specified in the
the first 32 bits of the aio_buf field of the iocb.

Unlike poll or epoll without EPOLLONESHOT this interface always works
in one shot mode, that is once the iocb is completed, it will have to be
resubmitted.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c                     | 103 +++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/aio_abi.h |   6 +--
 2 files changed, 105 insertions(+), 4 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 6fca1408a8a8..cae90ac6e4a3 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -156,9 +156,17 @@ struct kioctx {
 	unsigned		id;
 };
 
+struct poll_iocb {
+	struct file		*file;
+	__poll_t		events;
+	struct wait_queue_head	*head;
+	struct wait_queue_entry	wait;
+};
+
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
+		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -1570,6 +1578,98 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 	return ret;
 }
 
+static void __aio_complete_poll(struct poll_iocb *req, __poll_t mask)
+{
+	fput(req->file);
+	aio_complete(container_of(req, struct aio_kiocb, poll),
+			mangle_poll(mask), 0);
+}
+
+static void aio_complete_poll(struct poll_iocb *req, __poll_t mask)
+{
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+
+	if (!(iocb->flags & AIO_IOCB_CANCELLED))
+		__aio_complete_poll(req, mask);
+}
+
+static int aio_poll_cancel(struct kiocb *rw)
+{
+	struct aio_kiocb *iocb = container_of(rw, struct aio_kiocb, rw);
+
+	remove_wait_queue(iocb->poll.head, &iocb->poll.wait);
+	__aio_complete_poll(&iocb->poll, 0); /* no events to report */
+	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 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 = vfs_poll_mask(file, req->events);
+	if (!mask)
+		return 0;
+
+	__remove_wait_queue(req->head, &req->wait);
+	aio_complete_poll(req, mask);
+	return 1;
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+	struct poll_iocb *req = &aiocb->poll;
+	struct file *file;
+	unsigned long flags;
+	__poll_t mask;
+	int ret;
+
+	/* reject any unknown events outside the normal event mask. */
+	if (unlikely((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) | POLLERR | POLLHUP;
+	req->file = file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+
+	ret = -EOPNOTSUPP;
+	if (unlikely(!file->f_op->get_poll_head || !file->f_op->poll_mask))
+		goto out_fput;
+	req->head = file->f_op->get_poll_head(file, req->events);
+	if (!req->head)
+		goto out_fput;
+
+	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+
+	spin_lock_irqsave(&req->head->lock, flags);
+	mask = vfs_poll_mask(file, req->events);
+	if (!mask) {
+		__kiocb_set_cancel_fn(aiocb, aio_poll_cancel,
+				AIO_IOCB_DELAYED_CANCEL);
+		__add_wait_queue(req->head, &req->wait);
+	}
+	spin_unlock_irqrestore(&req->head->lock, flags);
+
+	if (mask)
+		aio_complete_poll(req, mask);
+	return -EIOCBQUEUED;
+out_fput:
+	fput(file);
+	return ret;
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {
@@ -1633,6 +1733,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_PWRITEV:
 		ret = aio_write(&req->rw, iocb, true, compat);
 		break;
+	case IOCB_CMD_POLL:
+		ret = aio_poll(req, iocb);
+		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
 		ret = -EINVAL;
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc70ddf..28330105a4b6 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -38,10 +38,8 @@ 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,
-- 
2.14.2

[PATCH 31/31] aio: implement io_pgetevents

[Christoph Hellwig]

This is the io_getevents equivalent of ppoll/pselect and allows to
properly mix signals and aio completions (especially with IOCB_CMD_POLL)
and atomically executes the following sequence:

	sigset_t origmask;

	pthread_sigmask(SIG_SETMASK, &sigmask, &origmask);
	ret = io_getevents(ctx, min_nr, nr, events, timeout);
	pthread_sigmask(SIG_SETMASK, &origmask, NULL);

Note that unlike many other signal related calls we do not pass a sigmask
size, as that would get us to 7 arguments, which aren't easily supported
by the syscall infrastructure.  It seems a lot less painful to just add a
new syscall variant in the unlikely case we're going to increase the
sigset size.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/x86/entry/syscalls/syscall_32.tbl |  1 +
 arch/x86/entry/syscalls/syscall_64.tbl |  1 +
 fs/aio.c                               | 96 ++++++++++++++++++++++++++++++----
 include/linux/compat.h                 |  6 +++
 include/linux/syscalls.h               |  6 +++
 include/uapi/asm-generic/unistd.h      |  4 +-
 kernel/sys_ni.c                        |  2 +
 7 files changed, 105 insertions(+), 11 deletions(-)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 448ac2161112..5997c3e9ac3e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -391,3 +391,4 @@
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
 384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+385	i386	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183e2f85..e995cd2b4e65 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -339,6 +339,7 @@
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
 332	common	statx			sys_statx
+333	common	io_pgetevents		sys_io_pgetevents
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/aio.c b/fs/aio.c
index cae90ac6e4a3..57a4e8d89f78 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1299,10 +1299,6 @@ 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;
 }
 
@@ -1978,13 +1974,54 @@ 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;
 
-	if (timeout) {
-		if (unlikely(get_timespec64(&ts, timeout)))
+	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 sigset_t __user *, sigmask)
+{
+	sigset_t		ksigmask, sigsaved;
+	struct timespec64	ts;
+	int ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	if (sigmask) {
+		if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (signal_pending(current)) {
+		if (sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	}
+
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -1995,13 +2032,52 @@ 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;
+}
+
+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 compat_sigset_t __user *, sigmask)
+{
+	sigset_t ksigmask, sigsaved;
+	struct timespec64 t;
+	int ret;
 
-	if (timeout) {
-		if (compat_get_timespec64(&t, timeout))
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	if (sigmask) {
+		if (get_compat_sigset(&ksigmask, 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 (sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	return ret;
 }
 #endif
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 0fc36406f32c..a4cda98073f1 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -536,6 +536,12 @@ 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 compat_sigset_t __user *sigmask);
 asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr,
 				     u32 __user *iocb);
 asmlinkage long compat_sys_mount(const char __user *dev_name,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a78186d826d7..3bc9a130f4a9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -539,6 +539,12 @@ 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 sigset_t __user *sigmask);
 asmlinkage long sys_io_submit(aio_context_t, long,
 				struct iocb __user * __user *);
 asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8b87de067bc7..ce2ebbeece10 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/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
 
 /*
  * All syscalls below here should go away really,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index b5189762d275..8f7705559b38 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -151,9 +151,11 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_io_pgetevents);
 cond_syscall(compat_sys_io_setup);
 cond_syscall(compat_sys_io_submit);
 cond_syscall(compat_sys_io_getevents);
+cond_syscall(compat_sys_io_pgetevents);
 cond_syscall(sys_sysfs);
 cond_syscall(sys_syslog);
 cond_syscall(sys_process_vm_readv);
-- 
2.14.2

Re: aio poll, io_pgetevents and a new in-kernel poll API

[Christoph Hellwig]

And of coure I should have added linux-api to the series.

Note that the libaio patches include documenting io_pgetevents in the
io_getevents man page.

On Thu, Jan 04, 2018 at 09:00:12AM +0100, Christoph Hellwig wrote:
> Hi all,
> 
> this series adds support for the IOCB_CMD_POLL operation to poll for the
> readyness of file descriptors using the aio subsystem.  The API is based
> on patches that existed in RHAS2.1 and RHEL3, which means it already is
> supported by libaio.  To implement the poll support efficiently new
> methods to poll are introduced in struct file_operations:  get_poll_head
> and poll_mask.  The first one returns a wait_queue_head to wait on
> (lifetime is bound by the file), and the second does a non-blocking
> check for the POLL* events.  This allows aio poll to work without
> any additional context switches, unlike epoll.
> 
> To make the interface fully useful a new io_pgetevents system call is
> added, which atomically saves and restores the signal mask over the
> io_pgetevents system call.  It it the logical equivalent to pselect and
> ppoll for io_pgetevents.
> 
> The corresponding libaio changes for io_pgetevents support and
> documentation, as well as a test case will be posted in a separate
> series.
> 
> The changes were sponsored by Scylladb, and improve performance
> of the seastar framework up to 10%, while also removing the need
> for a privileged SCHED_FIFO epoll listener thread.
> 
> The patches are on top of Als __poll_t annoations, so I've also
> prepared a git branch on top of those here:
> 
>     git://git.infradead.org/users/hch/vfs.git aio-poll
> 
> Gitweb:
> 
>     http://git.infradead.org/users/hch/vfs.git/shortlog/refs/heads/aio-poll
> 
> Libaio changes:
> 
>     http://git.infradead.org/users/hch/libaio.git/shortlog/refs/heads/aio-poll
> 
> Seastar changes:
> 
>     https://github.com/avikivity/seastar/commits/aio
---end quoted text---

Re: [PATCH 02/31] fs: add new vfs_poll and file_can_poll helpers

[Al Viro]

On Thu, Jan 04, 2018 at 09:00:14AM +0100, Christoph Hellwig wrote:
> These abstract out calls to the poll method in preparation for changes to
> those methods.

FWIW, I would make vfs_poll()

static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
{
	if (unlikely(!file->f_op->poll))
		return DEFAULT_POLLMASK;
	return file->f_op->poll(file, pt);
}

That's safe for any struct file, some of the callers already do just that,
the ones that have vfs_poll() under the check for file_can_poll() will
simply optimize that piece away and the few that rely upon the knowledge
of file_operations they are dealing with (vhost, etc.) can bloody well
cope with the cost of the check.

Re: [PATCH 03/31] fs: introduce new ->get_poll_head and ->poll_mask methods

[Al Viro]

On Thu, Jan 04, 2018 at 09:00:15AM +0100, Christoph Hellwig wrote:
> ->get_poll_head returns the waitqueue that the poll operation is going
> to sleep on.  Note that this means we can only use a single waitqueue
> for the poll, unlike some current drivers that use two waitqueues for
> different events.  But now that we have keyed wakeups and heavily use
> those for poll there aren't that many good reason left to keep the
> multiple waitqueues, and if there are any ->poll is still around, the
> driver just won't support aio poll.

*UGH*

Gotta love the optimism, but have you actually done the conversion?
I'm particularly suspicious about the locking rules here...

Re: [PATCH 04/31] net: add support for ->poll_mask in proto_ops

[Al Viro]

On Thu, Jan 04, 2018 at 09:00:16AM +0100, Christoph Hellwig wrote:
> The socket file operations still implement ->poll until all protocols are
> switched over.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  include/linux/net.h |  3 +++
>  net/socket.c        | 61 +++++++++++++++++++++++++++++++++++++++++++++++++----
>  2 files changed, 60 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/net.h b/include/linux/net.h
> index c2d468cb9821..94d65de30cb7 100644
> --- a/include/linux/net.h
> +++ b/include/linux/net.h
> @@ -147,6 +147,9 @@ struct proto_ops {
>  	int		(*getname)   (struct socket *sock,
>  				      struct sockaddr *addr,
>  				      int *sockaddr_len, int peer);
> +	void		(*pre_poll)  (const struct sock *sk);

Description?  Or more descriptive name, for that matter...

> +	__poll_t	(*poll_mask) (struct file *file, struct socket *sock,
> +				      __poll_t events);

Does that sucker need struct file?

Re: [PATCH 02/31] fs: add new vfs_poll and file_can_poll helpers

[Christoph Hellwig]

On Sat, Jan 06, 2018 at 07:08:53PM +0000, Al Viro wrote:
> On Thu, Jan 04, 2018 at 09:00:14AM +0100, Christoph Hellwig wrote:
> > These abstract out calls to the poll method in preparation for changes to
> > those methods.
> 
> FWIW, I would make vfs_poll()
> 
> static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
> {
> 	if (unlikely(!file->f_op->poll))
> 		return DEFAULT_POLLMASK;
> 	return file->f_op->poll(file, pt);
> }
> 
> That's safe for any struct file, some of the callers already do just that,
> the ones that have vfs_poll() under the check for file_can_poll() will
> simply optimize that piece away and the few that rely upon the knowledge
> of file_operations they are dealing with (vhost, etc.) can bloody well
> cope with the cost of the check.

Sure, works for me.

Re: [PATCH 03/31] fs: introduce new ->get_poll_head and ->poll_mask methods

[Christoph Hellwig]

On Sat, Jan 06, 2018 at 07:12:42PM +0000, Al Viro wrote:
> On Thu, Jan 04, 2018 at 09:00:15AM +0100, Christoph Hellwig wrote:
> > ->get_poll_head returns the waitqueue that the poll operation is going
> > to sleep on.  Note that this means we can only use a single waitqueue
> > for the poll, unlike some current drivers that use two waitqueues for
> > different events.  But now that we have keyed wakeups and heavily use
> > those for poll there aren't that many good reason left to keep the
> > multiple waitqueues, and if there are any ->poll is still around, the
> > driver just won't support aio poll.
> 
> *UGH*
> 
> Gotta love the optimism, but have you actually done the conversion?
> I'm particularly suspicious about the locking rules here...

I've done just about everything but random drivers.  Which is the ones
where people care about performance and thus aio poll.  I suspect that
we will have various odd cruft drivers that will be left alone.

Re: [PATCH 04/31] net: add support for ->poll_mask in proto_ops

[Christoph Hellwig]

On Sat, Jan 06, 2018 at 07:16:22PM +0000, Al Viro wrote:
> On Thu, Jan 04, 2018 at 09:00:16AM +0100, Christoph Hellwig wrote:
> > The socket file operations still implement ->poll until all protocols are
> > switched over.
> > 
> > Signed-off-by: Christoph Hellwig <hch@lst.de>
> > ---
> >  include/linux/net.h |  3 +++
> >  net/socket.c        | 61 +++++++++++++++++++++++++++++++++++++++++++++++++----
> >  2 files changed, 60 insertions(+), 4 deletions(-)
> > 
> > diff --git a/include/linux/net.h b/include/linux/net.h
> > index c2d468cb9821..94d65de30cb7 100644
> > --- a/include/linux/net.h
> > +++ b/include/linux/net.h
> > @@ -147,6 +147,9 @@ struct proto_ops {
> >  	int		(*getname)   (struct socket *sock,
> >  				      struct sockaddr *addr,
> >  				      int *sockaddr_len, int peer);
> > +	void		(*pre_poll)  (const struct sock *sk);
> 
> Description?  Or more descriptive name, for that matter...

One option might be to have the same get_poll_head semantics as
the file operation.  Which might actually be useful for the weird
things smc is doing, if they make any sense at all to start with.

> 
> > +	__poll_t	(*poll_mask) (struct file *file, struct socket *sock,
> > +				      __poll_t events);
> 
> Does that sucker need struct file?

Not really.  Especially as we could get that from sock->file if needed.
I'll drop it for the next version.

Re: aio poll, io_pgetevents and a new in-kernel poll API

[Christoph Hellwig]

On Thu, Jan 04, 2018 at 09:00:12AM +0100, Christoph Hellwig wrote:
> The changes were sponsored by Scylladb, and improve performance
> of the seastar framework up to 10%, while also removing the need
> for a privileged SCHED_FIFO epoll listener thread.

Due to the current events:

With KPTI enabled the aio poll code is almost 16% faster than epoll
with the special SCHED_FIFO listener thread.

The Scylladb https example is still more than 4% faster with KPTI
and aio poll vs non-KPTI with epoll.

Re: [PATCH 04/31] net: add support for ->poll_mask in proto_ops

[Christoph Hellwig]

On Sat, Jan 06, 2018 at 07:16:22PM +0000, Al Viro wrote:
> > +	__poll_t	(*poll_mask) (struct file *file, struct socket *sock,
> > +				      __poll_t events);
> 
> Does that sucker need struct file?

It turns out udp needs it:

	/* Check for false positives due to checksum errors */
	if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
		mask &= ~(POLLIN | POLLRDNORM);

Re: [PATCH 04/31] net: add support for ->poll_mask in proto_ops

[Christoph Hellwig]

On Tue, Jan 09, 2018 at 05:32:37PM +0100, Christoph Hellwig wrote:
> On Sat, Jan 06, 2018 at 07:16:22PM +0000, Al Viro wrote:
> > > +	__poll_t	(*poll_mask) (struct file *file, struct socket *sock,
> > > +				      __poll_t events);
> > 
> > Does that sucker need struct file?
> 
> It turns out udp needs it:

But as mentioned in my last mail it can simply use sock->file.

Sigh, time for more coffee.

Re: [PATCH 23/31] aio: don't print the page size at boot time

[Jeff Moyer]

Christoph Hellwig <hch@lst.de> writes:

> The page size is in no way related to the aio code, and printing it in
> the (debug) dmesg at every boot serves no purpose.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Acked-by: Jeff Moyer <jmoyer@redhat.com>

Re: [PATCH 24/31] aio: remove an outdated comment in aio_complete

[Jeff Moyer]

Christoph Hellwig <hch@lst.de> writes:

> These days we don't treat sync iocbs special in the aio completion code as
> they never use it.  Remove the old comment, and move the BUG_ON for a sync
> iocb to the top of the function.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Right, this should have been part of commit 599bd19bdc4c6 ("fs: don't
allow to complete sync iocbs through aio_complete").

Reviewed-by: Jeff Moyer <jmoyer@redhat.com>


> ---
>  fs/aio.c | 11 ++---------
>  1 file changed, 2 insertions(+), 9 deletions(-)
>
> diff --git a/fs/aio.c b/fs/aio.c
> index 03d59593912d..41fc8ce6bc7f 100644
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -1088,6 +1088,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
>  	unsigned tail, pos, head;
>  	unsigned long	flags;
>  
> +	BUG_ON(is_sync_kiocb(kiocb));
> +
>  	if (kiocb->ki_flags & IOCB_WRITE) {
>  		struct file *file = kiocb->ki_filp;
>  
> @@ -1100,15 +1102,6 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
>  		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;

Re: [PATCH 31/31] aio: implement io_pgetevents

[Arnd Bergmann]

On Thu, Jan 4, 2018 at 9:00 AM, Christoph Hellwig <hch@lst.de> wrote:

> +}
> +
> +SYSCALL_DEFINE6(io_pgetevents,
> +               aio_context_t, ctx_id,
> +               long, min_nr,
> +               long, nr,
> +               struct io_event __user *, events,
> +               struct timespec __user *, timeout,
> +               const sigset_t __user *, sigmask)
> +{

> +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 compat_sigset_t __user *, sigmask)
> +{

Hmm, these two new syscall entry points turn into four when we add in
support for 64-bit time_t, as we'd have to support all combinations of 32/64
bit aio_context_t and time_t.

Would it be better to start this interface out by defining it using a 64-bit
timeout structure? The downside would be that the user space syscall
wrappers have to start out with a conversion, if we don't do it, then
the opposite conversion would have to get added later.

      Arnd

Re: [PATCH 31/31] aio: implement io_pgetevents

[Christoph Hellwig]

On Tue, Jan 09, 2018 at 11:16:16PM +0100, Arnd Bergmann wrote:
> Hmm, these two new syscall entry points turn into four when we add in
> support for 64-bit time_t, as we'd have to support all combinations of 32/64
> bit aio_context_t and time_t.

At least they'll also replace plain old io_getevents :)

> Would it be better to start this interface out by defining it using a 64-bit
> timeout structure? The downside would be that the user space syscall
> wrappers have to start out with a conversion, if we don't do it, then
> the opposite conversion would have to get added later.

Which structure do you want?  In the end applications using libaio
or even the syscalls directly (like seastar) are a special bread, so
they could probably just deal with whatever structure we want to pass.

Re: [PATCH 31/31] aio: implement io_pgetevents

[Arnd Bergmann]

On Wed, Jan 10, 2018 at 9:11 AM, Christoph Hellwig <hch@lst.de> wrote:
> On Tue, Jan 09, 2018 at 11:16:16PM +0100, Arnd Bergmann wrote:
>> Hmm, these two new syscall entry points turn into four when we add in
>> support for 64-bit time_t, as we'd have to support all combinations of 32/64
>> bit aio_context_t and time_t.
>
> At least they'll also replace plain old io_getevents :)

Ah, right, so we'd save two other calls in the process: the native 32-bit
io_getevents with compat_timespec, and the compat io_getevents with
64-bit timespec.

>> Would it be better to start this interface out by defining it using a 64-bit
>> timeout structure? The downside would be that the user space syscall
>> wrappers have to start out with a conversion, if we don't do it, then
>> the opposite conversion would have to get added later.
>
> Which structure do you want?  In the end applications using libaio
> or even the syscalls directly (like seastar) are a special bread, so
> they could probably just deal with whatever structure we want to pass.

I'd suggest passing a variant of timespec with two 64-bit members.
Deepa has posted patches for this structure in the past and was planning
to do a new version (with minor changes from review) soon, but we
can just well use it in your patch if that gets merged first.

If we merge io_pgetevents quickly (before the bulk of the y2038 syscall
conversion), I'd say we should use

struct __kernel_timespec64 {
         __s64 tv_sec;
         __s64 tv_nsec;
};

The tv_nsec type is unfortunately much trickier than it should be:
C99 requires it to be 'long', so user space needs to define the 64-bit
'struct timespec' with internal padding in the right places depending
on endianess, and the kernel has to be careful about either zeroing
the upper half or checking it for being zeroed by user space depending
on whether we come from a 32-bit or 64-bit task, but I'm fairly sure
we have that part worked out by now.

      Arnd

Re: [PATCH 31/31] aio: implement io_pgetevents

[Christoph Hellwig]

On Wed, Jan 10, 2018 at 12:03:24PM +0100, Arnd Bergmann wrote:
> I'd suggest passing a variant of timespec with two 64-bit members.
> Deepa has posted patches for this structure in the past and was planning
> to do a new version (with minor changes from review) soon, but we
> can just well use it in your patch if that gets merged first.
> 
> If we merge io_pgetevents quickly (before the bulk of the y2038 syscall
> conversion), I'd say we should use
> 
> struct __kernel_timespec64 {
>          __s64 tv_sec;
>          __s64 tv_nsec;
> };
> 
> The tv_nsec type is unfortunately much trickier than it should be:
> C99 requires it to be 'long', so user space needs to define the 64-bit
> 'struct timespec' with internal padding in the right places depending
> on endianess, and the kernel has to be careful about either zeroing
> the upper half or checking it for being zeroed by user space depending
> on whether we come from a 32-bit or 64-bit task, but I'm fairly sure
> we have that part worked out by now.

Eww.  Being the ginea pig is never good, and in this the fact that
the aio syscalls aren't in glibc is just going to make things worse
in chances of diverging from the future 'standard'.

I'm tempted to say I'd rather deal with the new 64-bit time_t version
later, especially as that should only affect 32-bit ports.

Re: [PATCH 31/31] aio: implement io_pgetevents

[Arnd Bergmann]

On Wed, Jan 10, 2018 at 3:59 PM, Christoph Hellwig <hch@lst.de> wrote:
> On Wed, Jan 10, 2018 at 12:03:24PM +0100, Arnd Bergmann wrote:
>> I'd suggest passing a variant of timespec with two 64-bit members.
>> Deepa has posted patches for this structure in the past and was planning
>> to do a new version (with minor changes from review) soon, but we
>> can just well use it in your patch if that gets merged first.
>>
>> If we merge io_pgetevents quickly (before the bulk of the y2038 syscall
>> conversion), I'd say we should use
>>
>> struct __kernel_timespec64 {
>>          __s64 tv_sec;
>>          __s64 tv_nsec;
>> };
>>
>> The tv_nsec type is unfortunately much trickier than it should be:
>> C99 requires it to be 'long', so user space needs to define the 64-bit
>> 'struct timespec' with internal padding in the right places depending
>> on endianess, and the kernel has to be careful about either zeroing
>> the upper half or checking it for being zeroed by user space depending
>> on whether we come from a 32-bit or 64-bit task, but I'm fairly sure
>> we have that part worked out by now.
>
> Eww.  Being the ginea pig is never good, and in this the fact that
> the aio syscalls aren't in glibc is just going to make things worse
> in chances of diverging from the future 'standard'.
>
> I'm tempted to say I'd rather deal with the new 64-bit time_t version
> later, especially as that should only affect 32-bit ports.

Ok, fair enough. Given that the old version gets obsoleted by this
one, it shouldn't get much uglier than it already is here when you
start out with a regular timespec. We just need to be aware of possible
clashes when we get the patches merged at the same time.

      Arnd

Re: [PATCH 31/31] aio: implement io_pgetevents

[Christoph Hellwig]

On Wed, Jan 10, 2018 at 04:48:05PM +0100, Arnd Bergmann wrote:
> Ok, fair enough. Given that the old version gets obsoleted by this
> one, it shouldn't get much uglier than it already is here when you
> start out with a regular timespec. We just need to be aware of possible
> clashes when we get the patches merged at the same time.

I still hope to get this into 4.15.  If it gets delayed and we
have a coherent 64-bit time_t abi around already I can reconsider
the decision.

Re: [PATCH 31/31] aio: implement io_pgetevents

[Christoph Hellwig]

On Wed, Jan 10, 2018 at 04:49:04PM +0100, Christoph Hellwig wrote:
> On Wed, Jan 10, 2018 at 04:48:05PM +0100, Arnd Bergmann wrote:
> > Ok, fair enough. Given that the old version gets obsoleted by this
> > one, it shouldn't get much uglier than it already is here when you
> > start out with a regular timespec. We just need to be aware of possible
> > clashes when we get the patches merged at the same time.
> 
> I still hope to get this into 4.15.  If it gets delayed and we
> have a coherent 64-bit time_t abi around already I can reconsider
> the decision.

s/4.15/4.16/ of course.

Re: [PATCH 03/31] fs: introduce new ->get_poll_head and ->poll_mask methods

[Al Viro]

On Mon, Jan 08, 2018 at 11:45:13AM +0100, Christoph Hellwig wrote:
> On Sat, Jan 06, 2018 at 07:12:42PM +0000, Al Viro wrote:
> > On Thu, Jan 04, 2018 at 09:00:15AM +0100, Christoph Hellwig wrote:
> > > ->get_poll_head returns the waitqueue that the poll operation is going
> > > to sleep on.  Note that this means we can only use a single waitqueue
> > > for the poll, unlike some current drivers that use two waitqueues for
> > > different events.  But now that we have keyed wakeups and heavily use
> > > those for poll there aren't that many good reason left to keep the
> > > multiple waitqueues, and if there are any ->poll is still around, the
> > > driver just won't support aio poll.
> > 
> > *UGH*
> > 
> > Gotta love the optimism, but have you actually done the conversion?
> > I'm particularly suspicious about the locking rules here...
> 
> I've done just about everything but random drivers.  Which is the ones
> where people care about performance and thus aio poll.  I suspect that
> we will have various odd cruft drivers that will be left alone.

*snort*

Seeing that random drivers are, by far, the majority of instances...
What I wonder is how many of them conform to that pattern and how
many can be massaged to that form.

How painful would it be, to pick an instance with more than one wait
queue involved, to convert drivers/char/random.c to that form?

FWIW, I agree that it's very common.  Which makes the departures from
that pattern worth looking into - they might be buggy.  And "more than
one queue to wait on" is not all - there's also e.g.
static unsigned int vtpm_proxy_fops_poll(struct file *filp, poll_table *wait)
{
        struct proxy_dev *proxy_dev = filp->private_data;
        unsigned ret;

        poll_wait(filp, &proxy_dev->wq, wait);

        ret = POLLOUT;

        mutex_lock(&proxy_dev->buf_lock);

        if (proxy_dev->req_len)
                ret |= POLLIN | POLLRDNORM;

        if (!(proxy_dev->state & STATE_OPENED_FLAG))
                ret |= POLLHUP;

        mutex_unlock(&proxy_dev->buf_lock);

        return ret;
} 
(mainline drivers/char/tpm/tpm_vtpm_proxy.c)

Is that mutex_lock() in there a bug?  Another fun case is dma_buf_poll()...

The reason why I went looking at ->poll() in the first place had been
recurring bugs in the instances; e.g. "oh, I've got something odd,
let's return -Esomething".  Or "was it POLLIN or POLL_IN?"

I'd really like to get the interfaces right and get rid of the bitrot
source; turning it into moldering corpse in the corner is fine, as
long as we have a realistic chance of getting rid of that body in not
too distant future...

Re: [PATCH 03/31] fs: introduce new ->get_poll_head and ->poll_mask methods

[Christoph Hellwig]

[-- Attachment #1: Type: text/plain, Size: 1496 bytes --]

On Wed, Jan 10, 2018 at 04:31:35PM +0000, Al Viro wrote:
> *snort*
> 
> Seeing that random drivers are, by far, the majority of instances...
> What I wonder is how many of them conform to that pattern and how
> many can be massaged to that form.
> 
> How painful would it be, to pick an instance with more than one wait
> queue involved, to convert drivers/char/random.c to that form?

Attached.  Not very painful at all.  Would be even nicer if we had a
wait_event version that can deal with keys, but I can look into that.

> static unsigned int vtpm_proxy_fops_poll(struct file *filp, poll_table *wait)
> {
>         struct proxy_dev *proxy_dev = filp->private_data;
>         unsigned ret;
> 
>         poll_wait(filp, &proxy_dev->wq, wait);
> 
>         ret = POLLOUT;
> 
>         mutex_lock(&proxy_dev->buf_lock);
> 
>         if (proxy_dev->req_len)
>                 ret |= POLLIN | POLLRDNORM;
> 
>         if (!(proxy_dev->state & STATE_OPENED_FLAG))
>                 ret |= POLLHUP;
> 
>         mutex_unlock(&proxy_dev->buf_lock);
> 
>         return ret;
> } 
> (mainline drivers/char/tpm/tpm_vtpm_proxy.c)

Yeah.  And what exactly is the lock protecting given that each
of them checks a single smaller than register sized variable?

> Is that mutex_lock() in there a bug?  Another fun case is dma_buf_poll()...

Right now it is not a bug, but it is not very helpful behavior.  We
actually have quite a few of those, and not allowing ->poll_mask to
is a good thing to catch these.

[-- Attachment #2: 0001-random-convert-to-poll_mask.patch --]
[-- Type: text/x-patch, Size: 3746 bytes --]

>From 5f5549dc78b39799db01d48dc346d14561ec2003 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 10 Jan 2018 18:37:51 +0100
Subject: random: convert to ->poll_mask

The big change is that random_read_wait and random_write_wait are merged
into a single waitqueue that uses keyed wakeups.  Because wait_event_*
doesn't know about that this will lead to occassional spurious wakeups
in _random_read and add_hwgenerator_randomness, but wait_event_* is
designed to handle these and were are not in a a hot path there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/char/random.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 64b59562c872..9a1b85928de3 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -401,8 +401,7 @@ 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);
@@ -710,7 +709,7 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
 
 		/* should we wake readers? */
 		if (entropy_bits >= random_read_wakeup_bits) {
-			wake_up_interruptible(&random_read_wait);
+			wake_up_interruptible_poll(&random_wait, POLLIN);
 			kill_fasync(&fasync, SIGIO, POLL_IN);
 		}
 		/* If the input pool is getting full, send some
@@ -1293,7 +1292,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 	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);
 	}
 
@@ -1748,7 +1747,7 @@ _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))
@@ -1784,14 +1783,17 @@ 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 |= POLLIN | POLLRDNORM;
 	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1890,7 +1892,8 @@ 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,
@@ -2223,7 +2226,7 @@ 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);
-- 
2.14.2