direct-io: Implement generic deferred AIO completions

Add support to the core direct-io code to defer AIO completions to user
context using a workqueue.  This replaces opencoded and less efficient
code in XFS and ext4 (we save a memory allocation for each direct IO)
and will be needed to properly support O_(D)SYNC for AIO.

The communication between the filesystem and the direct I/O code requires
a new buffer head flag, which is a bit ugly but not avoidable until the
direct I/O code stops abusing the buffer_head structure for communicating
with the filesystems.

Currently this creates a per-superblock unbound workqueue for these
completions, which is taken from an earlier patch by Jan Kara.  I'm
not really convinced about this use and would prefer a "normal" global
workqueue with a high concurrency limit, but this needs further discussion.

JK: Fixed ext4 part, dynamic allocation of the workqueue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 5 insertions, 23 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 596ec71da00e..e11d654af786 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -86,14 +86,6 @@ xfs_destroy_ioend(
                 bh->b_end_io(bh, !ioend->io_error);
         }
 
-        if (ioend->io_iocb) {
-                inode_dio_done(ioend->io_inode);
-                if (ioend->io_isasync) {
-                        aio_complete(ioend->io_iocb, ioend->io_error ?
-                                        ioend->io_error : ioend->io_result, 0);
-                }
-        }
-
         mempool_free(ioend, xfs_ioend_pool);
 }
 
@@ -281,7 +273,6 @@ xfs_alloc_ioend(
          * all the I/O from calling the completion routine too early.
          */
         atomic_set(&ioend->io_remaining, 1);
-        ioend->io_isasync = 0;
         ioend->io_isdirect = 0;
         ioend->io_error = 0;
         ioend->io_list = NULL;
@@ -291,8 +282,6 @@ xfs_alloc_ioend(
         ioend->io_buffer_tail = NULL;
         ioend->io_offset = 0;
         ioend->io_size = 0;
-        ioend->io_iocb = NULL;
-        ioend->io_result = 0;
         ioend->io_append_trans = NULL;
 
         INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -1292,8 +1281,10 @@ __xfs_get_blocks(
                 if (create || !ISUNWRITTEN(&imap))
                         xfs_map_buffer(inode, bh_result, &imap, offset);
                 if (create && ISUNWRITTEN(&imap)) {
-                        if (direct)
+                        if (direct) {
                                 bh_result->b_private = inode;
+                                set_buffer_defer_completion(bh_result);
+                        }
                         set_buffer_unwritten(bh_result);
                 }
         }
@@ -1390,9 +1381,7 @@ xfs_end_io_direct_write(
         struct kiocb            *iocb,
         loff_t                  offset,
         ssize_t                 size,
-        void                    *private,
-        int                     ret,
-        bool                    is_async)
+        void                    *private)
 {
         struct xfs_ioend        *ioend = iocb->private;
 
@@ -1414,17 +1403,10 @@ xfs_end_io_direct_write(
 
         ioend->io_offset = offset;
         ioend->io_size = size;
-        ioend->io_iocb = iocb;
-        ioend->io_result = ret;
         if (private && size > 0)
                 ioend->io_type = XFS_IO_UNWRITTEN;
 
-        if (is_async) {
-                ioend->io_isasync = 1;
-                xfs_finish_ioend(ioend);
-        } else {
-                xfs_finish_ioend_sync(ioend);
-        }
+        xfs_finish_ioend_sync(ioend);
 }
 
 STATIC ssize_t