From 66ee59af630fd8d5f4f56fb28162857e629aa0ab Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Feb 2015 19:56:46 +0100
Subject: [PATCH 1/5] fs: remove ki_nbytes

There is no need to pass the total request length in the kiocb, as
we already get passed in through the iov_iter argument.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c               | 34 ++++++++++++++++++----------------
 fs/ceph/file.c         |  2 +-
 fs/nfs/direct.c        |  2 +-
 fs/ocfs2/file.c        |  8 +++-----
 fs/read_write.c        |  8 --------
 fs/udf/file.c          |  2 +-
 include/linux/aio.h    |  1 -
 kernel/printk/printk.c |  2 +-
 mm/page_io.c           |  1 -
 net/socket.c           |  6 +++---
 10 files changed, 28 insertions(+), 38 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 118a2e0088d8..667054c7c067 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1344,12 +1344,13 @@ typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
 static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 				     int rw, char __user *buf,
 				     unsigned long *nr_segs,
+				     size_t *len,
 				     struct iovec **iovec,
 				     bool compat)
 {
 	ssize_t ret;
 
-	*nr_segs = kiocb->ki_nbytes;
+	*nr_segs = *len;
 
 #ifdef CONFIG_COMPAT
 	if (compat)
@@ -1364,21 +1365,22 @@ static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 	if (ret < 0)
 		return ret;
 
-	/* ki_nbytes now reflect bytes instead of segs */
-	kiocb->ki_nbytes = ret;
+	/* len now reflect bytes instead of segs */
+	*len = ret;
 	return 0;
 }
 
 static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
 				       int rw, char __user *buf,
 				       unsigned long *nr_segs,
+				       size_t len,
 				       struct iovec *iovec)
 {
-	if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
+	if (unlikely(!access_ok(!rw, buf, len)))
 		return -EFAULT;
 
 	iovec->iov_base = buf;
-	iovec->iov_len = kiocb->ki_nbytes;
+	iovec->iov_len = len;
 	*nr_segs = 1;
 	return 0;
 }
@@ -1388,7 +1390,7 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
  *	Performs the initial checks and io submission.
  */
 static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
-			    char __user *buf, bool compat)
+			    char __user *buf, size_t len, bool compat)
 {
 	struct file *file = req->ki_filp;
 	ssize_t ret;
@@ -1423,21 +1425,21 @@ rw_common:
 		if (!rw_op && !iter_op)
 			return -EINVAL;
 
-		ret = (opcode == IOCB_CMD_PREADV ||
-		       opcode == IOCB_CMD_PWRITEV)
-			? aio_setup_vectored_rw(req, rw, buf, &nr_segs,
-						&iovec, compat)
-			: aio_setup_single_vector(req, rw, buf, &nr_segs,
-						  iovec);
+		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
+			ret = aio_setup_vectored_rw(req, rw, buf, &nr_segs,
+						&len, &iovec, compat);
+		else
+			ret = aio_setup_single_vector(req, rw, buf, &nr_segs,
+						  len, iovec);
 		if (!ret)
-			ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+			ret = rw_verify_area(rw, file, &req->ki_pos, len);
 		if (ret < 0) {
 			if (iovec != inline_vecs)
 				kfree(iovec);
 			return ret;
 		}
 
-		req->ki_nbytes = ret;
+		len = ret;
 
 		/* XXX: move/kill - rw_verify_area()? */
 		/* This matches the pread()/pwrite() logic */
@@ -1450,7 +1452,7 @@ rw_common:
 			file_start_write(file);
 
 		if (iter_op) {
-			iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes);
+			iov_iter_init(&iter, rw, iovec, nr_segs, len);
 			ret = iter_op(req, &iter);
 		} else {
 			ret = rw_op(req, iovec, nr_segs, req->ki_pos);
@@ -1553,10 +1555,10 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	req->ki_obj.user = user_iocb;
 	req->ki_user_data = iocb->aio_data;
 	req->ki_pos = iocb->aio_offset;
-	req->ki_nbytes = iocb->aio_nbytes;
 
 	ret = aio_run_iocb(req, iocb->aio_lio_opcode,
 			   (char __user *)(unsigned long)iocb->aio_buf,
+			   iocb->aio_nbytes,
 			   compat);
 	if (ret)
 		goto out_put_req;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 905986dd4c3c..081c4e3f9e49 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -807,7 +807,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *filp = iocb->ki_filp;
 	struct ceph_file_info *fi = filp->private_data;
-	size_t len = iocb->ki_nbytes;
+	size_t len = iov_iter_count(to);
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct page *pinned_page = NULL;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 7077521acdf4..27cebf164070 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -265,7 +265,7 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t
 
 	return -EINVAL;
 #else
-	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
 
 	if (rw == READ)
 		return nfs_file_direct_read(iocb, iter, pos);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 46e0d4e857c7..266845de2100 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2280,7 +2280,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 		file->f_path.dentry->d_name.name,
 		(unsigned int)from->nr_segs);	/* GRRRRR */
 
-	if (iocb->ki_nbytes == 0)
+	if (count == 0)
 		return 0;
 
 	appending = file->f_flags & O_APPEND ? 1 : 0;
@@ -2330,8 +2330,7 @@ relock:
 	}
 
 	can_do_direct = direct_io;
-	ret = ocfs2_prepare_inode_for_write(file, ppos,
-					    iocb->ki_nbytes, appending,
+	ret = ocfs2_prepare_inode_for_write(file, ppos, count, appending,
 					    &can_do_direct, &has_refcount);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -2339,8 +2338,7 @@ relock:
 	}
 
 	if (direct_io && !is_sync_kiocb(iocb))
-		unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_nbytes,
-						      *ppos);
+		unaligned_dio = ocfs2_is_io_unaligned(inode, count, *ppos);
 
 	/*
 	 * We can't complete the direct I/O as requested, fall back to
diff --git a/fs/read_write.c b/fs/read_write.c
index 8e1b68786d66..f8b8fc1316ab 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -343,7 +343,6 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
 
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = iov_iter_count(iter);
 
 	iter->type |= READ;
 	ret = file->f_op->read_iter(&kiocb, iter);
@@ -366,7 +365,6 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = iov_iter_count(iter);
 
 	iter->type |= WRITE;
 	ret = file->f_op->write_iter(&kiocb, iter);
@@ -426,7 +424,6 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 
 	ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
 	if (-EIOCBQUEUED == ret)
@@ -446,7 +443,6 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 	iov_iter_init(&iter, READ, &iov, 1, len);
 
 	ret = filp->f_op->read_iter(&kiocb, &iter);
@@ -510,7 +506,6 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 
 	ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
 	if (-EIOCBQUEUED == ret)
@@ -530,7 +525,6 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 	iov_iter_init(&iter, WRITE, &iov, 1, len);
 
 	ret = filp->f_op->write_iter(&kiocb, &iter);
@@ -719,7 +713,6 @@ static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iove
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 
 	iov_iter_init(&iter, rw, iov, nr_segs, len);
 	ret = fn(&kiocb, &iter);
@@ -737,7 +730,6 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	kiocb.ki_nbytes = len;
 
 	ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
 	if (ret == -EIOCBQUEUED)
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 08f3555fbeac..9c0b6da9dbb3 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -122,7 +122,7 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	int err, pos;
-	size_t count = iocb->ki_nbytes;
+	size_t count = iov_iter_count(from);
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
 	mutex_lock(&inode->i_mutex);
diff --git a/include/linux/aio.h b/include/linux/aio.h
index d9c92daa3944..132d1ecba435 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -42,7 +42,6 @@ struct kiocb {
 
 	__u64			ki_user_data;	/* user's data for completion */
 	loff_t			ki_pos;
-	size_t			ki_nbytes;	/* copy of iocb->aio_nbytes */
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c06df7de0963..60b2aa2a2da9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -521,7 +521,7 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 	int i;
 	int level = default_message_loglevel;
 	int facility = 1;	/* LOG_USER */
-	size_t len = iocb->ki_nbytes;
+	size_t len = iov_iter_count(from);
 	ssize_t ret = len;
 
 	if (len > LOG_LINE_MAX)
diff --git a/mm/page_io.c b/mm/page_io.c
index e6045804c8d8..7ef21577856c 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -274,7 +274,6 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE);
 		init_sync_kiocb(&kiocb, swap_file);
 		kiocb.ki_pos = page_file_offset(page);
-		kiocb.ki_nbytes = PAGE_SIZE;
 
 		set_page_writeback(page);
 		unlock_page(page);
diff --git a/net/socket.c b/net/socket.c
index bbedbfcb42c2..f92145554f34 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -858,11 +858,11 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
-	if (iocb->ki_nbytes == 0)	/* Match SYS5 behaviour */
+	if (!iov_iter_count(to))	/* Match SYS5 behaviour */
 		return 0;
 
 	res = __sock_recvmsg(iocb, sock, &msg,
-			     iocb->ki_nbytes, msg.msg_flags);
+			     iov_iter_count(to), msg.msg_flags);
 	*to = msg.msg_iter;
 	return res;
 }
@@ -883,7 +883,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (sock->type == SOCK_SEQPACKET)
 		msg.msg_flags |= MSG_EOR;
 
-	res = __sock_sendmsg(iocb, sock, &msg, iocb->ki_nbytes);
+	res = __sock_sendmsg(iocb, sock, &msg, iov_iter_count(from));
 	*from = msg.msg_iter;
 	return res;
 }

From 9d5722b7777e64de2d932f46cfee7765fdcc60d6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2015 14:59:43 +0100
Subject: [PATCH 2/5] fuse: handle synchronous iocbs internally

Based on a patch from Maxim Patlasov <MPatlasov@parallels.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/fuse/file.c   | 51 +++++++++++++++++++++++++++++-------------------
 fs/fuse/fuse_i.h |  1 +
 2 files changed, 32 insertions(+), 20 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index c01ec3bdcfd8..f81d83eb9758 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -528,6 +528,17 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
 	}
 }
 
+static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
+{
+	if (io->err)
+		return io->err;
+
+	if (io->bytes >= 0 && io->write)
+		return -EIO;
+
+	return io->bytes < 0 ? io->size : io->bytes;
+}
+
 /**
  * In case of short read, the caller sets 'pos' to the position of
  * actual end of fuse request in IO request. Otherwise, if bytes_requested
@@ -546,6 +557,7 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
  */
 static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 {
+	bool is_sync = is_sync_kiocb(io->iocb);
 	int left;
 
 	spin_lock(&io->lock);
@@ -555,27 +567,21 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 		io->bytes = pos;
 
 	left = --io->reqs;
+	if (!left && is_sync)
+		complete(io->done);
 	spin_unlock(&io->lock);
 
-	if (!left) {
-		long res;
+	if (!left && !is_sync) {
+		ssize_t res = fuse_get_res_by_io(io);
 
-		if (io->err)
-			res = io->err;
-		else if (io->bytes >= 0 && io->write)
-			res = -EIO;
-		else {
-			res = io->bytes < 0 ? io->size : io->bytes;
+		if (res >= 0) {
+			struct inode *inode = file_inode(io->iocb->ki_filp);
+			struct fuse_conn *fc = get_fuse_conn(inode);
+			struct fuse_inode *fi = get_fuse_inode(inode);
 
-			if (!is_sync_kiocb(io->iocb)) {
-				struct inode *inode = file_inode(io->iocb->ki_filp);
-				struct fuse_conn *fc = get_fuse_conn(inode);
-				struct fuse_inode *fi = get_fuse_inode(inode);
-
-				spin_lock(&fc->lock);
-				fi->attr_version = ++fc->attr_version;
-				spin_unlock(&fc->lock);
-			}
+			spin_lock(&fc->lock);
+			fi->attr_version = ++fc->attr_version;
+			spin_unlock(&fc->lock);
 		}
 
 		aio_complete(io->iocb, res, 0);
@@ -2801,6 +2807,7 @@ static ssize_t
 fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 			loff_t offset)
 {
+	DECLARE_COMPLETION_ONSTACK(wait);
 	ssize_t ret = 0;
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
@@ -2852,6 +2859,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	if (!is_sync_kiocb(iocb) && (offset + count > i_size) && rw == WRITE)
 		io->async = false;
 
+	if (io->async && is_sync_kiocb(iocb))
+		io->done = &wait;
+
 	if (rw == WRITE)
 		ret = __fuse_direct_write(io, iter, &pos);
 	else
@@ -2864,11 +2874,12 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 		if (!is_sync_kiocb(iocb))
 			return -EIOCBQUEUED;
 
-		ret = wait_on_sync_kiocb(iocb);
-	} else {
-		kfree(io);
+		wait_for_completion(&wait);
+		ret = fuse_get_res_by_io(io);
 	}
 
+	kfree(io);
+
 	if (rw == WRITE) {
 		if (ret > 0)
 			fuse_write_update_size(inode, pos);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1cdfb07c1376..7354dc142a50 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -263,6 +263,7 @@ struct fuse_io_priv {
 	int err;
 	struct kiocb *iocb;
 	struct file *file;
+	struct completion *done;
 };
 
 /**

From 599bd19bdc4c6b20fd91d50f2f79dececbaf80c1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Feb 2015 19:59:44 +0100
Subject: [PATCH 3/5] fs: don't allow to complete sync iocbs through
 aio_complete

The AIO interface is fairly complex because it tries to allow
filesystems to always work async and then wakeup a synchronous
caller through aio_complete.  It turns out that basically no one
was doing this to avoid the complexity and context switches,
and we've already fixed up the remaining users and can now
get rid of this case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c            | 24 +-----------------------
 fs/ecryptfs/file.c  |  6 ------
 fs/read_write.c     | 26 ++++++++------------------
 include/linux/aio.h |  4 ----
 net/socket.c        |  9 +++------
 5 files changed, 12 insertions(+), 57 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 667054c7c067..8ca8df1c3550 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -778,22 +778,6 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 	return 0;
 }
 
-/* wait_on_sync_kiocb:
- *	Waits on the given sync kiocb to complete.
- */
-ssize_t wait_on_sync_kiocb(struct kiocb *req)
-{
-	while (!req->ki_ctx) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (req->ki_ctx)
-			break;
-		io_schedule();
-	}
-	__set_current_state(TASK_RUNNING);
-	return req->ki_user_data;
-}
-EXPORT_SYMBOL(wait_on_sync_kiocb);
-
 /*
  * exit_aio: called when the last user of mm goes away.  At this point, there is
  * no way for any new requests to be submited or any of the io_* syscalls to be
@@ -1025,13 +1009,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	 *    ref, no other paths have a way to get another ref
 	 *  - the sync task helpfully left a reference to itself in the iocb
 	 */
-	if (is_sync_kiocb(iocb)) {
-		iocb->ki_user_data = res;
-		smp_wmb();
-		iocb->ki_ctx = ERR_PTR(-EXDEV);
-		wake_up_process(iocb->ki_obj.tsk);
-		return;
-	}
+	BUG_ON(is_sync_kiocb(iocb));
 
 	if (iocb->ki_list.next) {
 		unsigned long flags;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 6f4e659f508f..a36da8841e0c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -52,12 +52,6 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
 	struct file *file = iocb->ki_filp;
 
 	rc = generic_file_read_iter(iocb, to);
-	/*
-	 * Even though this is a async interface, we need to wait
-	 * for IO to finish to update atime
-	 */
-	if (-EIOCBQUEUED == rc)
-		rc = wait_on_sync_kiocb(iocb);
 	if (rc >= 0) {
 		path = ecryptfs_dentry_to_lower_path(file->f_path.dentry);
 		touch_atime(path);
diff --git a/fs/read_write.c b/fs/read_write.c
index f8b8fc1316ab..76e324e8ce8d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -346,9 +346,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
 
 	iter->type |= READ;
 	ret = file->f_op->read_iter(&kiocb, iter);
-	if (ret == -EIOCBQUEUED)
-		ret = wait_on_sync_kiocb(&kiocb);
-
+	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
 	return ret;
@@ -368,9 +366,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 
 	iter->type |= WRITE;
 	ret = file->f_op->write_iter(&kiocb, iter);
-	if (ret == -EIOCBQUEUED)
-		ret = wait_on_sync_kiocb(&kiocb);
-
+	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
 	return ret;
@@ -426,8 +422,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 	kiocb.ki_pos = *ppos;
 
 	ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
@@ -446,8 +441,7 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p
 	iov_iter_init(&iter, READ, &iov, 1, len);
 
 	ret = filp->f_op->read_iter(&kiocb, &iter);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
@@ -508,8 +502,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 	kiocb.ki_pos = *ppos;
 
 	ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
@@ -528,8 +521,7 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo
 	iov_iter_init(&iter, WRITE, &iov, 1, len);
 
 	ret = filp->f_op->write_iter(&kiocb, &iter);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
@@ -716,8 +708,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iove
 
 	iov_iter_init(&iter, rw, iov, nr_segs, len);
 	ret = fn(&kiocb, &iter);
-	if (ret == -EIOCBQUEUED)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
@@ -732,8 +723,7 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 	kiocb.ki_pos = *ppos;
 
 	ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
-	if (ret == -EIOCBQUEUED)
-		ret = wait_on_sync_kiocb(&kiocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 132d1ecba435..f8516430490d 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -37,7 +37,6 @@ struct kiocb {
 
 	union {
 		void __user		*user;
-		struct task_struct	*tsk;
 	} ki_obj;
 
 	__u64			ki_user_data;	/* user's data for completion */
@@ -63,13 +62,11 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 	*kiocb = (struct kiocb) {
 			.ki_ctx = NULL,
 			.ki_filp = filp,
-			.ki_obj.tsk = current,
 		};
 }
 
 /* prototypes */
 #ifdef CONFIG_AIO
-extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
 extern void aio_complete(struct kiocb *iocb, long res, long res2);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
@@ -77,7 +74,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr,
 			 struct iocb __user *__user *iocbpp, bool compat);
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
-static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
 static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
 struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }
diff --git a/net/socket.c b/net/socket.c
index f92145554f34..f6c519d7b3ba 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -633,8 +633,7 @@ static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	init_sync_kiocb(&iocb, NULL);
 	ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) :
 		      __sock_sendmsg(&iocb, sock, msg, size);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
 
@@ -766,8 +765,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	init_sync_kiocb(&iocb, NULL);
 	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
 EXPORT_SYMBOL(sock_recvmsg);
@@ -780,8 +778,7 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 
 	init_sync_kiocb(&iocb, NULL);
 	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
+	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
 

From 04b2fa9f8f36ec6fb6fd1c9dc9df6fff0cd27323 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2015 14:49:06 +0100
Subject: [PATCH 4/5] fs: split generic and aio kiocb

Most callers in the kernel want to perform synchronous file I/O, but
still have to bloat the stack with a full struct kiocb.  Split out
the parts needed in filesystem code from those in the aio code, and
only allocate those needed to pass down argument on the stack.  The
aio code embedds the generic iocb in the one it allocates and can
easily get back to it by using container_of.

Also add a ->ki_complete method to struct kiocb, this is used to call
into the aio code and thus removes the dependency on aio for filesystems
impementing asynchronous operations.  It will also allow other callers
to substitute their own completion callback.

We also add a new ->ki_flags field to work around the nasty layering
violation recently introduced in commit 5e33f6 ("usb: gadget: ffs: add
eventfd notification about ffs events").

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/usb/gadget/function/f_fs.c |  5 +-
 drivers/usb/gadget/legacy/inode.c  |  5 +-
 fs/aio.c                           | 94 +++++++++++++++++++++---------
 fs/direct-io.c                     |  4 +-
 fs/fuse/file.c                     |  2 +-
 fs/nfs/direct.c                    |  2 +-
 include/linux/aio.h                | 46 ++-------------
 7 files changed, 81 insertions(+), 77 deletions(-)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 175c9956cbe3..b64538b498dc 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -655,9 +655,10 @@ static void ffs_user_copy_worker(struct work_struct *work)
 		unuse_mm(io_data->mm);
 	}
 
-	aio_complete(io_data->kiocb, ret, ret);
+	io_data->kiocb->ki_complete(io_data->kiocb, ret, ret);
 
-	if (io_data->ffs->ffs_eventfd && !io_data->kiocb->ki_eventfd)
+	if (io_data->ffs->ffs_eventfd &&
+	    !(io_data->kiocb->ki_flags & IOCB_EVENTFD))
 		eventfd_signal(io_data->ffs->ffs_eventfd, 1);
 
 	usb_ep_free_request(io_data->ep, io_data->req);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 200f9a584064..a4a80694f607 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -469,7 +469,7 @@ static void ep_user_copy_worker(struct work_struct *work)
 		ret = -EFAULT;
 
 	/* completing the iocb can drop the ctx and mm, don't touch mm after */
-	aio_complete(iocb, ret, ret);
+	iocb->ki_complete(iocb, ret, ret);
 
 	kfree(priv->buf);
 	kfree(priv->to_free);
@@ -497,7 +497,8 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req)
 		kfree(priv);
 		iocb->private = NULL;
 		/* aio_complete() reports bytes-transferred _and_ faults */
-		aio_complete(iocb, req->actual ? req->actual : req->status,
+
+		iocb->ki_complete(iocb, req->actual ? req->actual : req->status,
 				req->status);
 	} else {
 		/* ep_copy_to_user() won't report both; we hide some faults */
diff --git a/fs/aio.c b/fs/aio.c
index 8ca8df1c3550..958286536a10 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -151,6 +151,38 @@ struct kioctx {
 	unsigned		id;
 };
 
+/*
+ * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
+ * cancelled or completed (this makes a certain amount of sense because
+ * successful cancellation - io_cancel() - does deliver the completion to
+ * userspace).
+ *
+ * And since most things don't implement kiocb cancellation and we'd really like
+ * kiocb completion to be lockless when possible, we use ki_cancel to
+ * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
+ * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
+ */
+#define KIOCB_CANCELLED		((void *) (~0ULL))
+
+struct aio_kiocb {
+	struct kiocb		common;
+
+	struct kioctx		*ki_ctx;
+	kiocb_cancel_fn		*ki_cancel;
+
+	struct iocb __user	*ki_user_iocb;	/* user's aiocb */
+	__u64			ki_user_data;	/* user's data for completion */
+
+	struct list_head	ki_list;	/* the aio core uses this
+						 * for cancellation */
+
+	/*
+	 * If the aio_resfd field of the userspace iocb is not zero,
+	 * this is the underlying eventfd context to deliver events to.
+	 */
+	struct eventfd_ctx	*ki_eventfd;
+};
+
 /*------ sysctl variables----*/
 static DEFINE_SPINLOCK(aio_nr_lock);
 unsigned long aio_nr;		/* current system wide number of aio requests */
@@ -220,7 +252,7 @@ static int __init aio_setup(void)
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
 
-	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
+	kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
 	pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
@@ -480,8 +512,9 @@ static int aio_setup_ring(struct kioctx *ctx)
 #define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
 #define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
 
-void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
+void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
+	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
 	struct kioctx *ctx = req->ki_ctx;
 	unsigned long flags;
 
@@ -496,7 +529,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct kiocb *kiocb)
+static int kiocb_cancel(struct aio_kiocb *kiocb)
 {
 	kiocb_cancel_fn *old, *cancel;
 
@@ -514,7 +547,7 @@ static int kiocb_cancel(struct kiocb *kiocb)
 		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
 	} while (cancel != old);
 
-	return cancel(kiocb);
+	return cancel(&kiocb->common);
 }
 
 static void free_ioctx(struct work_struct *work)
@@ -550,13 +583,13 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 static void free_ioctx_users(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, users);
-	struct kiocb *req;
+	struct aio_kiocb *req;
 
 	spin_lock_irq(&ctx->ctx_lock);
 
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
-				       struct kiocb, ki_list);
+				       struct aio_kiocb, ki_list);
 
 		list_del_init(&req->ki_list);
 		kiocb_cancel(req);
@@ -932,9 +965,9 @@ static void user_refill_reqs_available(struct kioctx *ctx)
  *	Allocate a slot for an aio request.
  * Returns NULL if no requests are free.
  */
-static inline struct kiocb *aio_get_req(struct kioctx *ctx)
+static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 {
-	struct kiocb *req;
+	struct aio_kiocb *req;
 
 	if (!get_reqs_available(ctx)) {
 		user_refill_reqs_available(ctx);
@@ -955,10 +988,10 @@ out_put:
 	return NULL;
 }
 
-static void kiocb_free(struct kiocb *req)
+static void kiocb_free(struct aio_kiocb *req)
 {
-	if (req->ki_filp)
-		fput(req->ki_filp);
+	if (req->common.ki_filp)
+		fput(req->common.ki_filp);
 	if (req->ki_eventfd != NULL)
 		eventfd_ctx_put(req->ki_eventfd);
 	kmem_cache_free(kiocb_cachep, req);
@@ -994,8 +1027,9 @@ out:
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
-void aio_complete(struct kiocb *iocb, long res, long res2)
+static void aio_complete(struct kiocb *kiocb, long res, long res2)
 {
+	struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
 	struct io_event	*ev_page, *event;
@@ -1009,7 +1043,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	 *    ref, no other paths have a way to get another ref
 	 *  - the sync task helpfully left a reference to itself in the iocb
 	 */
-	BUG_ON(is_sync_kiocb(iocb));
+	BUG_ON(is_sync_kiocb(kiocb));
 
 	if (iocb->ki_list.next) {
 		unsigned long flags;
@@ -1035,7 +1069,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
 	event = ev_page + pos % AIO_EVENTS_PER_PAGE;
 
-	event->obj = (u64)(unsigned long)iocb->ki_obj.user;
+	event->obj = (u64)(unsigned long)iocb->ki_user_iocb;
 	event->data = iocb->ki_user_data;
 	event->res = res;
 	event->res2 = res2;
@@ -1044,7 +1078,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
 
 	pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
-		 ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
+		 ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data,
 		 res, res2);
 
 	/* after flagging the request as done, we
@@ -1091,7 +1125,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 
 	percpu_ref_put(&ctx->reqs);
 }
-EXPORT_SYMBOL(aio_complete);
 
 /* aio_read_events_ring
  *	Pull an event off of the ioctx's event ring.  Returns the number of
@@ -1480,7 +1513,7 @@ rw_common:
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {
-	struct kiocb *req;
+	struct aio_kiocb *req;
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
@@ -1503,11 +1536,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	if (unlikely(!req))
 		return -EAGAIN;
 
-	req->ki_filp = fget(iocb->aio_fildes);
-	if (unlikely(!req->ki_filp)) {
+	req->common.ki_filp = fget(iocb->aio_fildes);
+	if (unlikely(!req->common.ki_filp)) {
 		ret = -EBADF;
 		goto out_put_req;
 	}
+	req->common.ki_pos = iocb->aio_offset;
+	req->common.ki_complete = aio_complete;
+	req->common.ki_flags = 0;
 
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
@@ -1522,6 +1558,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			req->ki_eventfd = NULL;
 			goto out_put_req;
 		}
+
+		req->common.ki_flags |= IOCB_EVENTFD;
 	}
 
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1530,11 +1568,10 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		goto out_put_req;
 	}
 
-	req->ki_obj.user = user_iocb;
+	req->ki_user_iocb = user_iocb;
 	req->ki_user_data = iocb->aio_data;
-	req->ki_pos = iocb->aio_offset;
 
-	ret = aio_run_iocb(req, iocb->aio_lio_opcode,
+	ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode,
 			   (char __user *)(unsigned long)iocb->aio_buf,
 			   iocb->aio_nbytes,
 			   compat);
@@ -1623,10 +1660,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 /* lookup_kiocb
  *	Finds a given iocb for cancellation.
  */
-static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
-				  u32 key)
+static struct aio_kiocb *
+lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key)
 {
-	struct list_head *pos;
+	struct aio_kiocb *kiocb;
 
 	assert_spin_locked(&ctx->ctx_lock);
 
@@ -1634,9 +1671,8 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
 		return NULL;
 
 	/* TODO: use a hash or array, this sucks. */
-	list_for_each(pos, &ctx->active_reqs) {
-		struct kiocb *kiocb = list_kiocb(pos);
-		if (kiocb->ki_obj.user == iocb)
+	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+		if (kiocb->ki_user_iocb == iocb)
 			return kiocb;
 	}
 	return NULL;
@@ -1656,7 +1692,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 		struct io_event __user *, result)
 {
 	struct kioctx *ctx;
-	struct kiocb *kiocb;
+	struct aio_kiocb *kiocb;
 	u32 key;
 	int ret;
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index e181b6b2e297..c38b460776e6 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -265,7 +265,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 				ret = err;
 		}
 
-		aio_complete(dio->iocb, ret, 0);
+		dio->iocb->ki_complete(dio->iocb, ret, 0);
 	}
 
 	kmem_cache_free(dio_cache, dio);
@@ -1056,7 +1056,7 @@ static inline int drop_refcount(struct dio *dio)
 	 * operation.  AIO can if it was a broken operation described above or
 	 * in fact if all the bios race to complete before we get here.  In
 	 * that case dio_complete() translates the EIOCBQUEUED into the proper
-	 * return code that the caller will hand to aio_complete().
+	 * return code that the caller will hand to ->complete().
 	 *
 	 * This is managed by the bio_lock instead of being an atomic_t so that
 	 * completion paths can drop their ref and use the remaining count to
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f81d83eb9758..a5c5e38b3ff8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -584,7 +584,7 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 			spin_unlock(&fc->lock);
 		}
 
-		aio_complete(io->iocb, res, 0);
+		io->iocb->ki_complete(io->iocb, res, 0);
 		kfree(io);
 	}
 }
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 27cebf164070..5db3385fc108 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -393,7 +393,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
 		long res = (long) dreq->error;
 		if (!res)
 			res = (long) dreq->count;
-		aio_complete(dreq->iocb, res, 0);
+		dreq->iocb->ki_complete(dreq->iocb, res, 0);
 	}
 
 	complete_all(&dreq->completion);
diff --git a/include/linux/aio.h b/include/linux/aio.h
index f8516430490d..5c40b61285ac 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -14,67 +14,38 @@ struct kiocb;
 
 #define KIOCB_KEY		0
 
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED		((void *) (~0ULL))
-
 typedef int (kiocb_cancel_fn)(struct kiocb *);
 
+#define IOCB_EVENTFD		(1 << 0)
+
 struct kiocb {
 	struct file		*ki_filp;
-	struct kioctx		*ki_ctx;	/* NULL for sync ops */
-	kiocb_cancel_fn		*ki_cancel;
-	void			*private;
-
-	union {
-		void __user		*user;
-	} ki_obj;
-
-	__u64			ki_user_data;	/* user's data for completion */
 	loff_t			ki_pos;
-
-	struct list_head	ki_list;	/* the aio core uses this
-						 * for cancellation */
-
-	/*
-	 * If the aio_resfd field of the userspace iocb is not zero,
-	 * this is the underlying eventfd context to deliver events to.
-	 */
-	struct eventfd_ctx	*ki_eventfd;
+	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+	void			*private;
+	int			ki_flags;
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
 {
-	return kiocb->ki_ctx == NULL;
+	return kiocb->ki_complete == NULL;
 }
 
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
-			.ki_ctx = NULL,
 			.ki_filp = filp,
 		};
 }
 
 /* prototypes */
 #ifdef CONFIG_AIO
-extern void aio_complete(struct kiocb *iocb, long res, long res2);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
 extern long do_io_submit(aio_context_t ctx_id, long nr,
 			 struct iocb __user *__user *iocbpp, bool compat);
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
-static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
 struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }
 static inline long do_io_submit(aio_context_t ctx_id, long nr,
@@ -84,11 +55,6 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req,
 				       kiocb_cancel_fn *cancel) { }
 #endif /* CONFIG_AIO */
 
-static inline struct kiocb *list_kiocb(struct list_head *h)
-{
-	return list_entry(h, struct kiocb, ki_list);
-}
-
 /* for sysctl: */
 extern unsigned long aio_nr;
 extern unsigned long aio_max_nr;

From e2e40f2c1ed433c5e224525c8c862fd32e5d3df2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 22 Feb 2015 08:58:50 -0800
Subject: [PATCH 5/5] fs: move struct kiocb to fs.h

struct kiocb now is a generic I/O container, so move it to fs.h.
Also do a #include diet for aio.h while we're at it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/hypfs/inode.c                      |  2 +-
 drivers/char/mem.c                           |  2 +-
 drivers/char/tile-srom.c                     |  1 -
 drivers/infiniband/hw/ipath/ipath_file_ops.c |  1 -
 drivers/infiniband/hw/qib/qib_file_ops.c     |  1 -
 drivers/misc/mei/amthif.c                    |  1 -
 drivers/misc/mei/main.c                      |  1 -
 drivers/misc/mei/pci-me.c                    |  1 -
 drivers/scsi/sg.c                            |  2 +-
 drivers/staging/unisys/include/timskmod.h    |  1 -
 drivers/usb/gadget/function/f_fs.c           |  1 +
 drivers/usb/gadget/legacy/inode.c            |  1 +
 fs/9p/vfs_addr.c                             |  2 +-
 fs/affs/file.c                               |  2 +-
 fs/afs/write.c                               |  1 -
 fs/bfs/inode.c                               |  1 +
 fs/block_dev.c                               |  1 -
 fs/btrfs/file.c                              |  2 +-
 fs/btrfs/inode.c                             |  2 +-
 fs/ceph/file.c                               |  1 -
 fs/direct-io.c                               |  1 -
 fs/ecryptfs/file.c                           |  1 -
 fs/ext2/inode.c                              |  2 +-
 fs/ext3/inode.c                              |  2 +-
 fs/ext4/file.c                               |  2 +-
 fs/ext4/indirect.c                           |  2 +-
 fs/ext4/inode.c                              |  1 -
 fs/ext4/page-io.c                            |  1 -
 fs/f2fs/data.c                               |  2 +-
 fs/fat/inode.c                               |  1 -
 fs/fuse/cuse.c                               |  2 +-
 fs/fuse/dev.c                                |  1 -
 fs/fuse/file.c                               |  2 +-
 fs/gfs2/aops.c                               |  2 +-
 fs/gfs2/file.c                               |  1 -
 fs/hfs/inode.c                               |  2 +-
 fs/hfsplus/inode.c                           |  2 +-
 fs/jfs/inode.c                               |  2 +-
 fs/nfs/file.c                                |  1 -
 fs/nilfs2/inode.c                            |  2 +-
 fs/ntfs/file.c                               |  1 -
 fs/ntfs/inode.c                              |  1 -
 fs/ocfs2/aops.c                              |  1 +
 fs/ocfs2/aops.h                              |  2 +-
 fs/pipe.c                                    |  1 -
 fs/read_write.c                              |  1 -
 fs/reiserfs/inode.c                          |  2 +-
 fs/splice.c                                  |  1 -
 fs/ubifs/file.c                              |  1 -
 fs/udf/file.c                                |  2 +-
 fs/udf/inode.c                               |  2 +-
 fs/xfs/xfs_aops.c                            |  1 -
 fs/xfs/xfs_file.c                            |  1 -
 include/linux/aio.h                          | 31 +-------------------
 include/linux/fs.h                           | 22 ++++++++++++++
 include/net/sock.h                           |  1 -
 kernel/printk/printk.c                       |  2 +-
 kernel/sysctl.c                              |  1 +
 mm/filemap.c                                 |  1 -
 mm/page_io.c                                 |  2 +-
 mm/shmem.c                                   |  2 +-
 net/ipv4/raw.c                               |  1 -
 sound/core/pcm_native.c                      |  2 +-
 63 files changed, 55 insertions(+), 86 deletions(-)

diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 4c8008dd938e..ad66b07f742e 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -21,7 +21,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 297110c12635..9c4fd7a8e2e5 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -26,7 +26,7 @@
 #include <linux/pfn.h>
 #include <linux/export.h>
 #include <linux/io.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include <linux/uaccess.h>
 
diff --git a/drivers/char/tile-srom.c b/drivers/char/tile-srom.c
index 02e76ac6d282..69f6b4acc377 100644
--- a/drivers/char/tile-srom.c
+++ b/drivers/char/tile-srom.c
@@ -27,7 +27,6 @@
 #include <linux/types.h>	/* size_t */
 #include <linux/proc_fs.h>
 #include <linux/fcntl.h>	/* O_ACCMODE */
-#include <linux/aio.h>
 #include <linux/pagemap.h>
 #include <linux/hugetlb.h>
 #include <linux/uaccess.h>
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 6d7f453b4d05..aed8afee56da 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -40,7 +40,6 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
-#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <linux/cpu.h>
 #include <asm/pgtable.h>
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index b15e34eeef68..826c17ee4c7d 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -39,7 +39,6 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
-#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <asm/pgtable.h>
 #include <linux/delay.h>
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index c4cb9a984a5f..40ea639fa413 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -19,7 +19,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/ioctl.h>
 #include <linux/cdev.h>
 #include <linux/list.h>
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 3c019c0e60eb..47680c84801c 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -22,7 +22,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/ioctl.h>
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index bd3039ab8f98..af44ee26075d 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -21,7 +21,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/pci.h>
 #include <linux/poll.h>
 #include <linux/ioctl.h>
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 0cbc1fb45f10..c78a6f7bbc20 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -33,7 +33,6 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
-#include <linux/aio.h>
 #include <linux/errno.h>
 #include <linux/mtio.h>
 #include <linux/ioctl.h>
@@ -51,6 +50,7 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
+#include <linux/uio.h>
 
 #include "scsi.h"
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/staging/unisys/include/timskmod.h b/drivers/staging/unisys/include/timskmod.h
index 4019a0d63645..52648d4d9922 100644
--- a/drivers/staging/unisys/include/timskmod.h
+++ b/drivers/staging/unisys/include/timskmod.h
@@ -46,7 +46,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/seq_file.h>
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index b64538b498dc..a12315a78248 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/hid.h>
 #include <linux/module.h>
+#include <linux/uio.h>
 #include <asm/unaligned.h>
 
 #include <linux/usb/composite.h>
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a4a80694f607..662ef2c1c62b 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -26,6 +26,7 @@
 #include <linux/poll.h>
 #include <linux/mmu_context.h>
 #include <linux/aio.h>
+#include <linux/uio.h>
 
 #include <linux/device.h>
 #include <linux/moduleparam.h>
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index eb14e055ea83..ff1a5bac4200 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -33,7 +33,7 @@
 #include <linux/pagemap.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf95669..33eaa67bb026 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -12,7 +12,7 @@
  *  affs regular file handling primitives
  */
 
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "affs.h"
 
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c13cb08964ed..0714abcd7f32 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -14,7 +14,6 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
-#include <linux/aio.h>
 #include "internal.h"
 
 static int afs_write_back_from_locked_page(struct afs_writeback *wb,
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 90bc079d9982..fdcb4d69f430 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -15,6 +15,7 @@
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
+#include <linux/uio.h>
 #include <asm/uaccess.h>
 #include "bfs.h"
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 975266be67d3..2e522aed6584 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -27,7 +27,6 @@
 #include <linux/namei.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>
-#include <linux/aio.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b78bbbac900d..69c9508d2c7e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,7 +24,6 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
@@ -32,6 +31,7 @@
 #include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/btrfs.h>
+#include <linux/uio.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 54bcf639d1cf..b214ab178f3a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,7 +32,6 @@
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
-#include <linux/aio.h>
 #include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
@@ -43,6 +42,7 @@
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/uio.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 081c4e3f9e49..98e257c1b5b1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -7,7 +7,6 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
 
 #include "super.h"
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c38b460776e6..6fb00e3f1059 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -37,7 +37,6 @@
 #include <linux/uio.h>
 #include <linux/atomic.h>
 #include <linux/prefetch.h>
-#include <linux/aio.h>
 
 /*
  * How many user pages to map in one call to get_user_pages().  This determines
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index a36da8841e0c..273d36e3f0c0 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -31,7 +31,6 @@
 #include <linux/security.h>
 #include <linux/compat.h>
 #include <linux/fs_stack.h>
-#include <linux/aio.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 6434bc000125..df9d6afbc5d5 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,7 +31,7 @@
 #include <linux/mpage.h>
 #include <linux/fiemap.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xattr.h"
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2c6ccc49ba27..db07ffbe7c85 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,7 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 33a09da16c9c..598abbbe6786 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,9 +23,9 @@
 #include <linux/jbd2.h>
 #include <linux/mount.h>
 #include <linux/path.h>
-#include <linux/aio.h>
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
+#include <linux/uio.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 6b9878a24182..8611640856d3 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -20,9 +20,9 @@
  *	(sct@redhat.com), 1993, 1998
  */
 
-#include <linux/aio.h>
 #include "ext4_jbd2.h"
 #include "truncate.h"
+#include <linux/uio.h>
 
 #include <trace/events/ext4.h>
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 85404f15e53a..6325d2c1a65c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,7 +37,6 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#include <linux/aio.h>
 #include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index b24a2541a9ba..464984261e69 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -18,7 +18,6 @@
 #include <linux/pagevec.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 985ed023a750..497f8515d205 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -12,12 +12,12 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/prefetch.h>
+#include <linux/uio.h>
 
 #include "f2fs.h"
 #include "node.h"
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 497c7c5263c7..8521207de229 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -19,7 +19,6 @@
 #include <linux/mpage.h>
 #include <linux/buffer_head.h>
 #include <linux/mount.h>
-#include <linux/aio.h>
 #include <linux/vfs.h>
 #include <linux/parser.h>
 #include <linux/uio.h>
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 28d0c7abba1c..b3fa05032234 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -38,7 +38,6 @@
 #include <linux/device.h>
 #include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/aio.h>
 #include <linux/kdev_t.h>
 #include <linux/kthread.h>
 #include <linux/list.h>
@@ -48,6 +47,7 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/module.h>
+#include <linux/uio.h>
 
 #include "fuse_i.h"
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed19a7d622fa..8c92c727ddd6 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -19,7 +19,6 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/swap.h>
 #include <linux/splice.h>
-#include <linux/aio.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a5c5e38b3ff8..ff102cbf16ea 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -15,8 +15,8 @@
 #include <linux/module.h>
 #include <linux/compat.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
+#include <linux/uio.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 4ad4f94edebe..fe6634d25d1d 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -20,7 +20,7 @@
 #include <linux/swap.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/backing-dev.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <trace/events/writeback.h>
 
 #include "gfs2.h"
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3e32bb8e2d7e..f6fc412b1100 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -25,7 +25,6 @@
 #include <asm/uaccess.h>
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
-#include <linux/aio.h>
 #include <linux/delay.h>
 
 #include "gfs2.h"
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index d0929bc81782..98d4ea45bb70 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -14,7 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 0cf786f2d046..f541196d4ee9 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -14,7 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index bd3df1ca3c9b..3197aed10614 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -22,8 +22,8 @@
 #include <linux/buffer_head.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
+#include <linux/uio.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 #include "jfs_incore.h"
 #include "jfs_inode.h"
 #include "jfs_filsys.h"
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 94712fc781fa..5d8b89cb13c0 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -26,7 +26,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
-#include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 8b5969538f39..ab4987bc637f 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -26,7 +26,7 @@
 #include <linux/mpage.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "segment.h"
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 1da9b2d184dc..f16f2d8401fe 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -28,7 +28,6 @@
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 898b9949d363..1d0c21df0d80 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -28,7 +28,6 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/log2.h>
-#include <linux/aio.h>
 
 #include "aops.h"
 #include "attrib.h"
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 44db1808cdb5..e1bf18c5d25e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -29,6 +29,7 @@
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 
 #include <cluster/masklog.h>
 
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 6cae155d54df..dd59599b022d 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -22,7 +22,7 @@
 #ifndef OCFS2_AOPS_H
 #define OCFS2_AOPS_H
 
-#include <linux/aio.h>
+#include <linux/fs.h>
 
 handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
diff --git a/fs/pipe.c b/fs/pipe.c
index 21981e58e2a6..2d084f2d0b83 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -21,7 +21,6 @@
 #include <linux/audit.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
diff --git a/fs/read_write.c b/fs/read_write.c
index 76e324e8ce8d..99a6ef946d01 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,7 +9,6 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
-#include <linux/aio.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/export.h>
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index e72401e1f995..9312b7842e03 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -18,7 +18,7 @@
 #include <linux/writeback.h>
 #include <linux/quotaops.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
diff --git a/fs/splice.c b/fs/splice.c
index 7968da96bebb..4bbfa95b5bfe 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -32,7 +32,6 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
-#include <linux/aio.h>
 #include "internal.h"
 
 /*
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index e627c0acf626..c3d15fe83403 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -50,7 +50,6 @@
  */
 
 #include "ubifs.h"
-#include <linux/aio.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/slab.h>
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 9c0b6da9dbb3..7f885cc8b0b7 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -34,7 +34,7 @@
 #include <linux/errno.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index a445d599098d..9c1fbd23913d 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -38,7 +38,7 @@
 #include <linux/slab.h>
 #include <linux/crc-itu-t.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3a9b7a1b8704..4f8cdc59bc38 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -31,7 +31,6 @@
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
-#include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1cdba95c78cb..f527618cb42b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,7 +37,6 @@
 #include "xfs_log.h"
 #include "xfs_icache.h"
 
-#include <linux/aio.h>
 #include <linux/dcache.h>
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 5c40b61285ac..9eb42dbc5582 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -1,52 +1,23 @@
 #ifndef __LINUX__AIO_H
 #define __LINUX__AIO_H
 
-#include <linux/list.h>
-#include <linux/workqueue.h>
 #include <linux/aio_abi.h>
-#include <linux/uio.h>
-#include <linux/rcupdate.h>
-
-#include <linux/atomic.h>
 
 struct kioctx;
 struct kiocb;
+struct mm_struct;
 
 #define KIOCB_KEY		0
 
 typedef int (kiocb_cancel_fn)(struct kiocb *);
 
-#define IOCB_EVENTFD		(1 << 0)
-
-struct kiocb {
-	struct file		*ki_filp;
-	loff_t			ki_pos;
-	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
-	void			*private;
-	int			ki_flags;
-};
-
-static inline bool is_sync_kiocb(struct kiocb *kiocb)
-{
-	return kiocb->ki_complete == NULL;
-}
-
-static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
-{
-	*kiocb = (struct kiocb) {
-			.ki_filp = filp,
-		};
-}
-
 /* prototypes */
 #ifdef CONFIG_AIO
-struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
 extern long do_io_submit(aio_context_t ctx_id, long nr,
 			 struct iocb __user *__user *iocbpp, bool compat);
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
-struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }
 static inline long do_io_submit(aio_context_t ctx_id, long nr,
 				struct iocb __user * __user *iocbpp,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 447932aed1e1..48c1472bde4a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -314,6 +314,28 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+#define IOCB_EVENTFD		(1 << 0)
+
+struct kiocb {
+	struct file		*ki_filp;
+	loff_t			ki_pos;
+	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+	void			*private;
+	int			ki_flags;
+};
+
+static inline bool is_sync_kiocb(struct kiocb *kiocb)
+{
+	return kiocb->ki_complete == NULL;
+}
+
+static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
+{
+	*kiocb = (struct kiocb) {
+		.ki_filp = filp,
+	};
+}
+
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
diff --git a/include/net/sock.h b/include/net/sock.h
index ab186b1d31ff..71c1300025e2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -57,7 +57,6 @@
 #include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/static_key.h>
-#include <linux/aio.h>
 #include <linux/sched.h>
 
 #include <linux/filter.h>
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 60b2aa2a2da9..40d50cc4c686 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -32,7 +32,6 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
-#include <linux/aio.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
 #include <linux/kdb.h>
@@ -46,6 +45,7 @@
 #include <linux/irq_work.h>
 #include <linux/utsname.h>
 #include <linux/ctype.h>
+#include <linux/uio.h>
 
 #include <asm/uaccess.h>
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 88ea2d6e0031..83d907afb4a6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/aio.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
diff --git a/mm/filemap.c b/mm/filemap.c
index ad7242043bdb..876f4e6f3ed6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -13,7 +13,6 @@
 #include <linux/compiler.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
-#include <linux/aio.h>
 #include <linux/capability.h>
 #include <linux/kernel_stat.h>
 #include <linux/gfp.h>
diff --git a/mm/page_io.c b/mm/page_io.c
index 7ef21577856c..a96c8562d835 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -20,8 +20,8 @@
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
-#include <linux/aio.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags,
diff --git a/mm/shmem.c b/mm/shmem.c
index a63031fa3e0c..944b94079bb0 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -31,7 +31,7 @@
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 static struct vfsmount *shm_mnt;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index f027a708b7e0..4a356b7c081b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -46,7 +46,6 @@
 #include <linux/stddef.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
-#include <linux/aio.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index b03a638b420c..9ecff240a39b 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/pm_qos.h>
-#include <linux/aio.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
 #include <sound/core.h>
@@ -35,6 +34,7 @@
 #include <sound/pcm_params.h>
 #include <sound/timer.h>
 #include <sound/minors.h>
+#include <linux/uio.h>
 
 /*
  *  Compatibility