Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: viro@zeniv.linux.org.uk
Cc: Avi Kivity <avi@scylladb.com>,
	linux-aio@kvack.org, linux-fsdevel@vger.kernel.org,
	netdev@vger.kernel.org, linux-api@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 13/36] fs: introduce new ->get_poll_head and ->poll_mask methods
Date: Wed, 17 Jan 2018 20:27:19 +0100	[thread overview]
Message-ID: <20180117192742.710-14-hch@lst.de> (raw)
In-Reply-To: <20180117192742.710-1-hch@lst.de>

->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 before going to sleep to check for already pending
events, and after the wakeup to return the actual mask of events reported
by poll.  It can be called with the waitqueue lock held to gurantee
race free checking for events and to be called from the waitqueue
wake callback, but the legacy callers don't hold it yet.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/Locking |  7 ++++++-
 Documentation/filesystems/vfs.txt | 11 +++++++++++
 fs/select.c                       | 29 +++++++++++++++++++++++++++++
 include/linux/fs.h                |  2 ++
 include/linux/poll.h              | 19 +++++++++++++++----
 5 files changed, 63 insertions(+), 5 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..17e0355be7d1 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.  Can return NULL to indicate polling is not supported.
+
+  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/fs/select.c b/fs/select.c
index e96f1342c2f6..707abe79536b 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,6 +34,35 @@
 
 #include <linux/uaccess.h>
 
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+	unsigned int events = poll_requested_events(pt), mask;
+	struct wait_queue_head *head;
+
+	if (unlikely(!file_can_poll(file)))
+		return DEFAULT_POLLMASK;
+
+	if (file->f_op->poll)
+		return file->f_op->poll(file, pt);
+
+	/*
+	 * Only get the poll head and do the first mask check if we are actually
+	 * going to sleep on this file:
+	 */
+	if (pt && pt->_qproc) {
+		head = vfs_get_poll_head(file, events);
+		if (!head)
+			return DEFAULT_POLLMASK;
+		mask = file->f_op->poll_mask(file, events);
+		if (mask)
+			return mask;
+
+		pt->_qproc(file, head, pt);
+	}
+
+	return file->f_op->poll_mask(file, events);
+}
+EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.
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 7afd259c570f..7ce8b7f902cd 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -75,16 +75,27 @@ 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)
+static inline struct wait_queue_head *vfs_get_poll_head(struct file *file,
+		__poll_t events)
 {
-	if (unlikely(!file->f_op->poll))
+	if (unlikely(!file->f_op->get_poll_head || !file->f_op->poll_mask))
+		return NULL;
+	return file->f_op->get_poll_head(file, events);
+}
+
+static inline __poll_t vfs_poll_mask(struct file *file, __poll_t events)
+{
+	if (unlikely(!file->f_op->poll_mask))
 		return DEFAULT_POLLMASK;
-	return file->f_op->poll(file, pt);
+	return file->f_op->poll_mask(file, events) & events;
 }
 
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
 struct poll_table_entry {
 	struct file *filp;
 	__poll_t key;
-- 
2.14.2

  parent reply	other threads:[~2018-01-17 19:27 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-17 19:27 aio poll, io_pgetevents and a new in-kernel poll API V3 Christoph Hellwig
2018-01-17 19:27 ` [PATCH 01/36] aio: don't print the page size at boot time Christoph Hellwig
2018-01-17 19:27 ` [PATCH 02/36] aio: remove an outdated comment in aio_complete Christoph Hellwig
2018-01-17 19:27 ` [PATCH 03/36] aio: refactor read/write iocb setup Christoph Hellwig
2018-01-17 19:27 ` [PATCH 04/36] aio: sanitize ki_list handling Christoph Hellwig
2018-01-17 19:27 ` [PATCH 05/36] aio: simplify cancellation Christoph Hellwig
2018-01-17 19:27 ` [PATCH 06/36] aio: delete iocbs from the active_reqs list in kiocb_cancel Christoph Hellwig
2018-01-17 19:27 ` [PATCH 07/36] aio: add delayed cancel support Christoph Hellwig
2018-01-17 19:27 ` [PATCH 08/36] aio: implement io_pgetevents Christoph Hellwig
2018-01-17 19:27 ` [PATCH 09/36] fs: unexport poll_schedule_timeout Christoph Hellwig
2018-01-17 19:27 ` [PATCH 10/36] fs: cleanup do_pollfd Christoph Hellwig
2018-01-17 19:27 ` [PATCH 11/36] fs: update documentation for __poll_t Christoph Hellwig
2018-01-17 19:27 ` [PATCH 12/36] fs: add new vfs_poll and file_can_poll helpers Christoph Hellwig
2018-01-17 19:27 ` Christoph Hellwig [this message]
2018-01-17 19:27 ` [PATCH 14/36] aio: implement IOCB_CMD_POLL Christoph Hellwig
2018-01-17 19:27 ` [PATCH 15/36] net: refactor socket_poll Christoph Hellwig
2018-01-17 19:27 ` [PATCH 16/36] net: add support for ->poll_mask in proto_ops Christoph Hellwig
2018-01-17 19:27 ` [PATCH 17/36] net: remove sock_no_poll Christoph Hellwig
2018-01-17 19:27 ` [PATCH 18/36] net/tcp: convert to ->poll_mask Christoph Hellwig
2018-01-17 19:27 ` [PATCH 19/36] net/unix: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 20/36] net: convert datagram_poll users tp ->poll_mask Christoph Hellwig
2018-01-17 19:27 ` [PATCH 21/36] net/dccp: convert to ->poll_mask Christoph Hellwig
2018-01-17 19:27 ` [PATCH 22/36] net/atm: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 23/36] net/vmw_vsock: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 24/36] net/tipc: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 25/36] net/sctp: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 26/36] net/bluetooth: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 27/36] net/caif: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 28/36] net/nfc: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 29/36] net/phonet: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 30/36] net/iucv: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 31/36] net/rxrpc: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 32/36] crypto: af_alg: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 33/36] pipe: " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 34/36] eventfd: switch " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 35/36] timerfd: convert " Christoph Hellwig
2018-01-17 19:27 ` [PATCH 36/36] random: " Christoph Hellwig
2018-01-18 15:46 ` aio poll, io_pgetevents and a new in-kernel poll API V3 Jeff Moyer
2018-01-18 16:44   ` Jeff Moyer
2018-01-18 17:42     ` Christoph Hellwig
2018-01-18 17:59       ` Jeff Moyer
2018-01-18 17:55     ` Colin Walters
2018-01-18 18:53       ` Christoph Hellwig
2018-01-18 17:51   ` Avi Kivity
2018-01-18 17:52     ` Avi Kivity
2018-01-18 17:54     ` Jeff Moyer
2018-01-22 20:12 aio poll, io_pgetevents and a new in-kernel poll API V4 Christoph Hellwig
2018-01-22 20:12 ` [PATCH 13/36] fs: introduce new ->get_poll_head and ->poll_mask methods Christoph Hellwig
2018-03-05 21:27 aio poll, io_pgetevents and a new in-kernel poll API V5 Christoph Hellwig
2018-03-05 21:27 ` [PATCH 13/36] fs: introduce new ->get_poll_head and ->poll_mask methods Christoph Hellwig
2018-03-20  3:29   ` Darrick J. Wong
2018-03-20 15:39     ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180117192742.710-14-hch@lst.de \
    --to=hch@lst.de \
    --cc=avi@scylladb.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [PATCH 13/36] fs: introduce new ->get_poll_head and ->poll_mask methods' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).