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, 0 insertions, 16 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b59373b625e9..5db4f0df8174 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -762,9 +762,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_unregister_li_request(sb);
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	flush_workqueue(sbi->unrsv_conversion_wq);
 	flush_workqueue(sbi->rsv_conversion_wq);
-	destroy_workqueue(sbi->unrsv_conversion_wq);
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
@@ -875,14 +873,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 #endif
 	ei->jinode = NULL;
 	INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
-	INIT_LIST_HEAD(&ei->i_unrsv_conversion_list);
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
-	INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work);
 
 	return &ei->vfs_inode;
 }
@@ -3954,14 +3950,6 @@ no_journal:
 		goto failed_mount4;
 	}
 
-	EXT4_SB(sb)->unrsv_conversion_wq =
-		alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
-	if (!EXT4_SB(sb)->unrsv_conversion_wq) {
-		printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
-		ret = -ENOMEM;
-		goto failed_mount4;
-	}
-
 	/*
 	 * The jbd2_journal_load will have done any necessary log recovery,
 	 * so we can safely mount the rest of the filesystem now.
@@ -4115,8 +4103,6 @@ failed_mount4:
 	ext4_msg(sb, KERN_ERR, "mount failed");
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
-	if (EXT4_SB(sb)->unrsv_conversion_wq)
-		destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
 failed_mount_wq:
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -4564,7 +4550,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
-	flush_workqueue(sbi->unrsv_conversion_wq);
 	/*
 	 * Writeback quota in non-journalled quota case - journalled quota has
 	 * no dirty dquots
@@ -4600,7 +4585,6 @@ static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
-	flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
 	dquot_writeback_dquots(sb, -1);
 	if (wait && test_opt(sb, BARRIER))
 		ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);