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>

2 files changed, 7 insertions, 2 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 91fa9a94ae92..d77797a52b7b 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -36,6 +36,7 @@ enum bh_state_bits {
         BH_Quiet,       /* Buffer Error Prinks to be quiet */
         BH_Meta,        /* Buffer contains metadata */
         BH_Prio,        /* Buffer should be submitted with REQ_PRIO */
+        BH_Defer_Completion, /* Defer AIO completion to workqueue */
 
         BH_PrivateStart,/* not a state bit, but the first bit available
                          * for private allocation by other entities
@@ -128,6 +129,7 @@ BUFFER_FNS(Write_EIO, write_io_error)
 BUFFER_FNS(Unwritten, unwritten)
 BUFFER_FNS(Meta, meta)
 BUFFER_FNS(Prio, prio)
+BUFFER_FNS(Defer_Completion, defer_completion)
 
 #define bh_offset(bh)           ((unsigned long)(bh)->b_data & ~PAGE_MASK)
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65c9929cd340..c9013876eb29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -46,6 +46,7 @@ struct vfsmount;
 struct cred;
 struct swap_info_struct;
 struct seq_file;
+struct workqueue_struct;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -63,8 +64,7 @@ struct buffer_head;
 typedef int (get_block_t)(struct inode *inode, sector_t iblock,
                         struct buffer_head *bh_result, int create);
 typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
-                        ssize_t bytes, void *private, int ret,
-                        bool is_async);
+                        ssize_t bytes, void *private);
 
 #define MAY_EXEC                0x00000001
 #define MAY_WRITE               0x00000002
@@ -1328,6 +1328,9 @@ struct super_block {
 
         /* Being remounted read-only */
         int s_readonly_remount;
+
+        /* AIO completions deferred from interrupt context */
+        struct workqueue_struct *s_dio_done_wq;
 };
 
 /* superblock cache pruning functions */