fs: introduce new ->get_poll_head and ->poll_mask methods

->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.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 220bba28f72becf7d79eb6227bd8962f4b0e5dee..6d227f9d7bd933839ce4e880e3949511df0c470f 100644 (file)
--- 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 f608180ad59d71ab2bcc2d2d818699bfaaee1470..829a7b7857a46904cfb7f02646212504a3a7f259 100644 (file)
--- 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 +903,17 @@ otherwise noted.
        activity on this file and (optionally) go to sleep until there
        is activity. Called by the select(2) and poll(2) system calls
 
+  get_poll_head: Returns the struct wait_queue_head that callers can
+  wait on.  Callers need to check the returned events using ->poll_mask
+  once woken.  Can return NULL to indicate polling is not supported,
+  or any error code using the ERR_PTR convention to indicate that a
+  grave error occured and ->poll_mask shall not be called.
+
+  poll_mask: return the mask of EPOLL* values describing the file descriptor
+  state.  Called either before going to sleep on the waitqueue returned by
+  get_poll_head, or after it has been woken.  If ->get_poll_head and
+  ->poll_mask are implemented ->poll does not need to be implement.
+
   unlocked_ioctl: called by the ioctl(2) system call.
 
   compat_ioctl: called by the ioctl(2) system call when 32 bit system calls

diff --git a/fs/select.c b/fs/select.c
index e30def680b2e58b009454d0e07367e36860ddfdb..bc3cc0f9889611446ef94cda24ec5e20892c435f 100644 (file)
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,6 +34,29 @@
 
 #include <linux/uaccess.h>
 
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+       if (file->f_op->poll) {
+               return file->f_op->poll(file, pt);
+       } else if (file_has_poll_mask(file)) {
+               unsigned int events = poll_requested_events(pt);
+               struct wait_queue_head *head;
+
+               if (pt && pt->_qproc) {
+                       head = file->f_op->get_poll_head(file, events);
+                       if (!head)
+                               return DEFAULT_POLLMASK;
+                       if (IS_ERR(head))
+                               return EPOLLERR;
+                       pt->_qproc(file, head, pt);
+               }
+
+               return file->f_op->poll_mask(file, events);
+       } else {
+               return DEFAULT_POLLMASK;
+       }
+}
+EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 760d8da1b6c7dc8b6d16703e1f65de918ec8460e..4b6045ebb2f25c348be413b152463e5a0b21afe3 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1711,6 +1711,8 @@ struct file_operations {
        int (*iterate) (struct file *, struct dir_context *);
        int (*iterate_shared) (struct file *, struct dir_context *);
        __poll_t (*poll) (struct file *, struct poll_table_struct *);
+       struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+       __poll_t (*poll_mask) (struct file *, __poll_t);
        long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
        long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
        int (*mmap) (struct file *, struct vm_area_struct *);

diff --git a/include/linux/poll.h b/include/linux/poll.h
index 7e0fdcf905d2e77b355c94a7381446927452723c..fdf86b4cbc71bacca2795107532fb75e3855c0c9 100644 (file)
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,18 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
        pt->_key   = ~(__poll_t)0; /* all events enabled */
 }
 
-static inline bool file_can_poll(struct file *file)
+static inline bool file_has_poll_mask(struct file *file)
 {
-       return file->f_op->poll;
+       return 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 bool file_can_poll(struct file *file)
 {
-       if (unlikely(!file->f_op->poll))
-               return DEFAULT_POLLMASK;
-       return file->f_op->poll(file, pt);
+       return file->f_op->poll || file_has_poll_mask(file);
 }
 
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
 struct poll_table_entry {
        struct file *filp;
        __poll_t key;