1 files changed, 34 insertions, 66 deletions

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 7600aacf531d..51f270b479b6 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -218,7 +218,7 @@ static struct page *dio_get_page(struct dio *dio)
  * filesystems can use it to hold additional state between get_block calls and
  * dio_complete.
  */
-static int dio_complete(struct dio *dio, loff_t offset, int ret)
+static int dio_complete(struct dio *dio, loff_t offset, int ret, bool is_async)
 {
         ssize_t transferred = 0;
 
@@ -239,14 +239,6 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
                         transferred = dio->i_size - offset;
         }
 
-        if (dio->end_io && dio->result)
-                dio->end_io(dio->iocb, offset, transferred,
-                            dio->map_bh.b_private);
-
-        if (dio->flags & DIO_LOCKING)
-                /* lockdep: non-owner release */
-                up_read_non_owner(&dio->inode->i_alloc_sem);
-
         if (ret == 0)
                 ret = dio->page_errors;
         if (ret == 0)
@@ -254,6 +246,17 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
         if (ret == 0)
                 ret = transferred;
 
+        if (dio->end_io && dio->result) {
+                dio->end_io(dio->iocb, offset, transferred,
+                            dio->map_bh.b_private, ret, is_async);
+        } else if (is_async) {
+                aio_complete(dio->iocb, ret, 0);
+        }
+
+        if (dio->flags & DIO_LOCKING)
+                /* lockdep: non-owner release */
+                up_read_non_owner(&dio->inode->i_alloc_sem);
+
         return ret;
 }
 
@@ -277,8 +280,7 @@ static void dio_bio_end_aio(struct bio *bio, int error)
         spin_unlock_irqrestore(&dio->bio_lock, flags);
 
         if (remaining == 0) {
-                int ret = dio_complete(dio, dio->iocb->ki_pos, 0);
-                aio_complete(dio->iocb, ret, 0);
+                dio_complete(dio, dio->iocb->ki_pos, 0, true);
                 kfree(dio);
         }
 }
@@ -1126,7 +1128,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
         spin_unlock_irqrestore(&dio->bio_lock, flags);
 
         if (ret2 == 0) {
-                ret = dio_complete(dio, offset, ret);
+                ret = dio_complete(dio, offset, ret, false);
                 kfree(dio);
         } else
                 BUG_ON(ret != -EIOCBQUEUED);
@@ -1134,8 +1136,27 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
         return ret;
 }
 
+/*
+ * This is a library function for use by filesystem drivers.
+ *
+ * The locking rules are governed by the flags parameter:
+ *  - if the flags value contains DIO_LOCKING we use a fancy locking
+ *    scheme for dumb filesystems.
+ *    For writes this function is called under i_mutex and returns with
+ *    i_mutex held, for reads, i_mutex is not held on entry, but it is
+ *    taken and dropped again before returning.
+ *    For reads and writes i_alloc_sem is taken in shared mode and released
+ *    on I/O completion (which may happen asynchronously after returning to
+ *    the caller).
+ *
+ *  - if the flags value does NOT contain DIO_LOCKING we don't use any
+ *    internal locking but rather rely on the filesystem to synchronize
+ *    direct I/O reads/writes versus each other and truncate.
+ *    For reads and writes both i_mutex and i_alloc_sem are not held on
+ *    entry and are never taken.
+ */
 ssize_t
-__blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode,
+__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         struct block_device *bdev, const struct iovec *iov, loff_t offset, 
         unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
         dio_submit_t submit_io, int flags)
@@ -1231,57 +1252,4 @@ __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode,
 out:
         return retval;
 }
-EXPORT_SYMBOL(__blockdev_direct_IO_newtrunc);
-
-/*
- * This is a library function for use by filesystem drivers.
- *
- * The locking rules are governed by the flags parameter:
- *  - if the flags value contains DIO_LOCKING we use a fancy locking
- *    scheme for dumb filesystems.
- *    For writes this function is called under i_mutex and returns with
- *    i_mutex held, for reads, i_mutex is not held on entry, but it is
- *    taken and dropped again before returning.
- *    For reads and writes i_alloc_sem is taken in shared mode and released
- *    on I/O completion (which may happen asynchronously after returning to
- *    the caller).
- *
- *  - if the flags value does NOT contain DIO_LOCKING we don't use any
- *    internal locking but rather rely on the filesystem to synchronize
- *    direct I/O reads/writes versus each other and truncate.
- *    For reads and writes both i_mutex and i_alloc_sem are not held on
- *    entry and are never taken.
- */
-ssize_t
-__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-        struct block_device *bdev, const struct iovec *iov, loff_t offset,
-        unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
-        dio_submit_t submit_io, int flags)
-{
-        ssize_t retval;
-
-        retval = __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov,
-                        offset, nr_segs, get_block, end_io, submit_io, flags);
-        /*
-         * In case of error extending write may have instantiated a few
-         * blocks outside i_size. Trim these off again for DIO_LOCKING.
-         * NOTE: DIO_NO_LOCK/DIO_OWN_LOCK callers have to handle this in
-         * their own manner. This is a further example of where the old
-         * truncate sequence is inadequate.
-         *
-         * NOTE: filesystems with their own locking have to handle this
-         * on their own.
-         */
-        if (flags & DIO_LOCKING) {
-                if (unlikely((rw & WRITE) && retval < 0)) {
-                        loff_t isize = i_size_read(inode);
-                        loff_t end = offset + iov_length(iov, nr_segs);
-
-                        if (end > isize)
-                                vmtruncate(inode, isize);
-                }
-        }
-
-        return retval;
-}
 EXPORT_SYMBOL(__blockdev_direct_IO);