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 01/35] 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 02/35] 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 03/35] 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 04/35] 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 94b5d2621aef59271c53cd13ecf9249e24b3d4df Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Feb 2015 19:38:03 -0500
Subject: [PATCH 05/35] getname_flags(): clean up a bit

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 53 +++++++++++++++++++++++++----------------------------
 1 file changed, 25 insertions(+), 28 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c83145af4bfc..a5421a12bb92 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -124,10 +124,9 @@
 struct filename *
 getname_flags(const char __user *filename, int flags, int *empty)
 {
-	struct filename *result, *err;
-	int len;
-	long max;
+	struct filename *result;
 	char *kname;
+	int len;
 
 	result = audit_reusename(filename);
 	if (result)
@@ -136,7 +135,6 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	result = __getname();
 	if (unlikely(!result))
 		return ERR_PTR(-ENOMEM);
-	result->refcnt = 1;
 
 	/*
 	 * First, try to embed the struct filename inside the names_cache
@@ -145,13 +143,11 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	kname = (char *)result + sizeof(*result);
 	result->name = kname;
 	result->separate = false;
-	max = EMBEDDED_NAME_MAX;
 
-recopy:
-	len = strncpy_from_user(kname, filename, max);
+	len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
 	if (unlikely(len < 0)) {
-		err = ERR_PTR(len);
-		goto error;
+		__putname(result);
+		return ERR_PTR(len);
 	}
 
 	/*
@@ -160,43 +156,44 @@ recopy:
 	 * names_cache allocation for the pathname, and re-do the copy from
 	 * userland.
 	 */
-	if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) {
+	if (unlikely(len == EMBEDDED_NAME_MAX)) {
 		kname = (char *)result;
 
 		result = kzalloc(sizeof(*result), GFP_KERNEL);
-		if (!result) {
-			err = ERR_PTR(-ENOMEM);
-			result = (struct filename *)kname;
-			goto error;
+		if (unlikely(!result)) {
+			__putname(kname);
+			return ERR_PTR(-ENOMEM);
 		}
 		result->name = kname;
 		result->separate = true;
-		result->refcnt = 1;
-		max = PATH_MAX;
-		goto recopy;
+		len = strncpy_from_user(kname, filename, PATH_MAX);
+		if (unlikely(len < 0)) {
+			__putname(kname);
+			kfree(result);
+			return ERR_PTR(len);
+		}
+		if (unlikely(len == PATH_MAX)) {
+			__putname(kname);
+			kfree(result);
+			return ERR_PTR(-ENAMETOOLONG);
+		}
 	}
 
+	result->refcnt = 1;
 	/* The empty path is special. */
 	if (unlikely(!len)) {
 		if (empty)
 			*empty = 1;
-		err = ERR_PTR(-ENOENT);
-		if (!(flags & LOOKUP_EMPTY))
-			goto error;
+		if (!(flags & LOOKUP_EMPTY)) {
+			putname(result);
+			return ERR_PTR(-ENOENT);
+		}
 	}
 
-	err = ERR_PTR(-ENAMETOOLONG);
-	if (unlikely(len >= PATH_MAX))
-		goto error;
-
 	result->uptr = filename;
 	result->aname = NULL;
 	audit_getname(result);
 	return result;
-
-error:
-	putname(result);
-	return err;
 }
 
 struct filename *

From 5eb6b495c60ef865324a81898eeb18062fd81662 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Feb 2015 19:40:53 -0500
Subject: [PATCH 06/35] switch path_lookupat() to struct filename

all callers were passing it ->name of some struct filename

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index a5421a12bb92..92b1f00cc05a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1969,7 +1969,7 @@ static inline int lookup_last(struct nameidata *nd, struct path *path)
 }
 
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int path_lookupat(int dfd, const char *name,
+static int path_lookupat(int dfd, const struct filename *name,
 				unsigned int flags, struct nameidata *nd)
 {
 	struct path path;
@@ -1989,7 +1989,7 @@ static int path_lookupat(int dfd, const char *name,
 	 * be handled by restarting a traditional ref-walk (which will always
 	 * be able to complete).
 	 */
-	err = path_init(dfd, name, flags, nd);
+	err = path_init(dfd, name->name, flags, nd);
 	if (!err && !(flags & LOOKUP_PARENT)) {
 		err = lookup_last(nd, &path);
 		while (err > 0) {
@@ -2024,12 +2024,11 @@ static int path_lookupat(int dfd, const char *name,
 static int filename_lookup(int dfd, struct filename *name,
 				unsigned int flags, struct nameidata *nd)
 {
-	int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd);
+	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
 	if (unlikely(retval == -ECHILD))
-		retval = path_lookupat(dfd, name->name, flags, nd);
+		retval = path_lookupat(dfd, name, flags, nd);
 	if (unlikely(retval == -ESTALE))
-		retval = path_lookupat(dfd, name->name,
-						flags | LOOKUP_REVAL, nd);
+		retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
 
 	if (likely(!retval))
 		audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
@@ -3153,7 +3152,7 @@ static int do_tmpfile(int dfd, struct filename *pathname,
 	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *dentry, *child;
 	struct inode *dir;
-	int error = path_lookupat(dfd, pathname->name,
+	int error = path_lookupat(dfd, pathname,
 				  flags | LOOKUP_DIRECTORY, nd);
 	if (unlikely(error))
 		return error;

From 668696dcbb1b184f8758ba9903c373c4960174a9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Feb 2015 19:44:00 -0500
Subject: [PATCH 07/35] switch path_mountpoint() to struct filename

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 92b1f00cc05a..e1d18522db31 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2337,12 +2337,13 @@ out:
  * Returns 0 and "path" will be valid on success; Returns error otherwise.
  */
 static int
-path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags)
+path_mountpoint(int dfd, const struct filename *name, struct path *path,
+		unsigned int flags)
 {
 	struct nameidata nd;
 	int err;
 
-	err = path_init(dfd, name, flags, &nd);
+	err = path_init(dfd, name->name, flags, &nd);
 	if (unlikely(err))
 		goto out;
 
@@ -2366,20 +2367,20 @@ out:
 }
 
 static int
-filename_mountpoint(int dfd, struct filename *s, struct path *path,
+filename_mountpoint(int dfd, struct filename *name, struct path *path,
 			unsigned int flags)
 {
 	int error;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-	error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+	error = path_mountpoint(dfd, name, path, flags | LOOKUP_RCU);
 	if (unlikely(error == -ECHILD))
-		error = path_mountpoint(dfd, s->name, path, flags);
+		error = path_mountpoint(dfd, name, path, flags);
 	if (unlikely(error == -ESTALE))
-		error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL);
+		error = path_mountpoint(dfd, name, path, flags | LOOKUP_REVAL);
 	if (likely(!error))
-		audit_inode(s, path->dentry, 0);
-	putname(s);
+		audit_inode(name, path->dentry, 0);
+	putname(name);
 	return error;
 }
 

From 6e8a1f8741d6f1179cb3b03991caeac9e4bfd9e2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Feb 2015 19:46:04 -0500
Subject: [PATCH 08/35] switch path_init() to struct filename

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index e1d18522db31..2c4b68c12550 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1848,7 +1848,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 	return err;
 }
 
-static int path_init(int dfd, const char *name, unsigned int flags,
+static int path_init(int dfd, const struct filename *name, unsigned int flags,
 		     struct nameidata *nd)
 {
 	int retval = 0;
@@ -1860,7 +1860,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
-		if (*name) {
+		if (name->name[0]) {
 			if (!d_can_lookup(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
@@ -1882,7 +1882,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	nd->root.mnt = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
-	if (*name=='/') {
+	if (name->name[0] == '/') {
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
 			nd->seq = set_root_rcu(nd);
@@ -1916,7 +1916,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 		dentry = f.file->f_path.dentry;
 
-		if (*name) {
+		if (name->name[0]) {
 			if (!d_can_lookup(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
@@ -1946,7 +1946,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	return -ECHILD;
 done:
 	current->total_link_count = 0;
-	return link_path_walk(name, nd);
+	return link_path_walk(name->name, nd);
 }
 
 static void path_cleanup(struct nameidata *nd)
@@ -1989,7 +1989,7 @@ static int path_lookupat(int dfd, const struct filename *name,
 	 * be handled by restarting a traditional ref-walk (which will always
 	 * be able to complete).
 	 */
-	err = path_init(dfd, name->name, flags, nd);
+	err = path_init(dfd, name, flags, nd);
 	if (!err && !(flags & LOOKUP_PARENT)) {
 		err = lookup_last(nd, &path);
 		while (err > 0) {
@@ -2343,7 +2343,7 @@ path_mountpoint(int dfd, const struct filename *name, struct path *path,
 	struct nameidata nd;
 	int err;
 
-	err = path_init(dfd, name->name, flags, &nd);
+	err = path_init(dfd, name, flags, &nd);
 	if (unlikely(err))
 		goto out;
 
@@ -3226,7 +3226,7 @@ static struct file *path_openat(int dfd, struct filename *pathname,
 		goto out;
 	}
 
-	error = path_init(dfd, pathname->name, flags, nd);
+	error = path_init(dfd, pathname, flags, nd);
 	if (unlikely(error))
 		goto out;
 

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 09/35] 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

From bc917be8105993c256338ad1189650364a741483 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 17:45:43 -0400
Subject: [PATCH 10/35] saner iov_iter initialization primitives

iovec-backed iov_iter instances are assumed to satisfy several properties:
	* no more than UIO_MAXIOV elements in iovec array
	* total size of all ranges is no more than MAX_RW_COUNT
	* all ranges pass access_ok().

The problem is, invariants of data structures should be established in the
primitives creating those data structures, not in the code using those
primitives.  And iov_iter_init() violates that principle.  For a while we
managed to get away with that, but once the use of iov_iter started to
spread, it didn't take long for shit to hit the fan - missed check in
sys_sendto() had introduced a roothole.

We _do_ have primitives for importing and validating iovecs (both native and
compat ones) and those primitives are almost always followed by shoving the
resulting iovec into iov_iter.  Life would be considerably simpler (and safer)
if we combined those primitives with initializing iov_iter.

That gives us two new primitives - import_iovec() and compat_import_iovec().
Calling conventions:
	iovec = iov_array;
	err = import_iovec(direction, uvec, nr_segs,
			   ARRAY_SIZE(iov_array), &iovec,
			   &iter);
imports user vector into kernel space (into iov_array if it fits, allocated
if it doesn't fit or if iovec was NULL), validates it and sets iter up to
refer to it.  On success 0 is returned and allocated kernel copy (or NULL
if the array had fit into caller-supplied one) is returned via iovec.
On failure all allocations are undone and -E... is returned.  If the total
size of ranges exceeds MAX_RW_COUNT, the excess is silently truncated.

compat_import_iovec() expects uvec to be a pointer to user array of compat_iovec;
otherwise it's identical to import_iovec().

Finally, import_single_range() sets iov_iter backed by single-element iovec
covering a user-supplied range -

	err = import_single_range(direction, address, size, iovec, &iter);

does validation and sets iter up.  Again, size in excess of MAX_RW_COUNT gets
silently truncated.

Next commits will be switching the things up to use of those and reducing
the amount of iov_iter_init() instances.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h | 14 +++++++++++
 lib/iov_iter.c      | 57 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 71880299ed48..1f4a37f1f025 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -139,4 +139,18 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
+int import_iovec(int type, const struct iovec __user * uvector,
+		 unsigned nr_segs, unsigned fast_segs,
+		 struct iovec **iov, struct iov_iter *i);
+
+#ifdef CONFIG_COMPAT
+struct compat_iovec;
+int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
+		 unsigned nr_segs, unsigned fast_segs,
+		 struct iovec **iov, struct iov_iter *i);
+#endif
+
+int import_single_range(int type, void __user *buf, size_t len,
+		 struct iovec *iov, struct iov_iter *i);
+
 #endif
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 9d96e283520c..fc6e33f6b7f3 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -766,3 +766,60 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 				   flags);
 }
 EXPORT_SYMBOL(dup_iter);
+
+int import_iovec(int type, const struct iovec __user * uvector,
+		 unsigned nr_segs, unsigned fast_segs,
+		 struct iovec **iov, struct iov_iter *i)
+{
+	ssize_t n;
+	struct iovec *p;
+	n = rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
+				  *iov, &p);
+	if (n < 0) {
+		if (p != *iov)
+			kfree(p);
+		*iov = NULL;
+		return n;
+	}
+	iov_iter_init(i, type, p, nr_segs, n);
+	*iov = p == *iov ? NULL : p;
+	return 0;
+}
+EXPORT_SYMBOL(import_iovec);
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+
+int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
+		 unsigned nr_segs, unsigned fast_segs,
+		 struct iovec **iov, struct iov_iter *i)
+{
+	ssize_t n;
+	struct iovec *p;
+	n = compat_rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
+				  *iov, &p);
+	if (n < 0) {
+		if (p != *iov)
+			kfree(p);
+		*iov = NULL;
+		return n;
+	}
+	iov_iter_init(i, type, p, nr_segs, n);
+	*iov = p == *iov ? NULL : p;
+	return 0;
+}
+#endif
+
+int import_single_range(int rw, void __user *buf, size_t len,
+		 struct iovec *iov, struct iov_iter *i)
+{
+	if (len > MAX_RW_COUNT)
+		len = MAX_RW_COUNT;
+	if (unlikely(!access_ok(!rw, buf, len)))
+		return -EFAULT;
+
+	iov->iov_base = buf;
+	iov->iov_len = len;
+	iov_iter_init(i, rw, iov, 1, len);
+	return 0;
+}

From fd2f7cb5bcac58b63717cd45366bff9a6ab961c6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Feb 2015 20:07:13 -0500
Subject: [PATCH 11/35] kill struct filename.separate

just make const char iname[] the last member and compare name->name with
name->iname instead of checking name->separate

We need to make sure that out-of-line name doesn't end up allocated adjacent
to struct filename refering to it; fortunately, it's easy to achieve - just
allocate that struct filename with one byte in ->iname[], so that ->iname[0]
will be inside the same object and thus have an address different from that
of out-of-line name [spotted by Boqun Feng <boqun.feng@gmail.com>]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c         | 29 ++++++++++++++++-------------
 include/linux/fs.h |  2 +-
 2 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 2c4b68c12550..6218e62a0534 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -119,7 +119,7 @@
  * PATH_MAX includes the nul terminator --RR.
  */
 
-#define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))
+#define EMBEDDED_NAME_MAX	(PATH_MAX - offsetof(struct filename, iname))
 
 struct filename *
 getname_flags(const char __user *filename, int flags, int *empty)
@@ -140,9 +140,8 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	 * First, try to embed the struct filename inside the names_cache
 	 * allocation
 	 */
-	kname = (char *)result + sizeof(*result);
+	kname = (char *)result->iname;
 	result->name = kname;
-	result->separate = false;
 
 	len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
 	if (unlikely(len < 0)) {
@@ -157,15 +156,20 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	 * userland.
 	 */
 	if (unlikely(len == EMBEDDED_NAME_MAX)) {
+		const size_t size = offsetof(struct filename, iname[1]);
 		kname = (char *)result;
 
-		result = kzalloc(sizeof(*result), GFP_KERNEL);
+		/*
+		 * size is chosen that way we to guarantee that
+		 * result->iname[0] is within the same object and that
+		 * kname can't be equal to result->iname, no matter what.
+		 */
+		result = kzalloc(size, GFP_KERNEL);
 		if (unlikely(!result)) {
 			__putname(kname);
 			return ERR_PTR(-ENOMEM);
 		}
 		result->name = kname;
-		result->separate = true;
 		len = strncpy_from_user(kname, filename, PATH_MAX);
 		if (unlikely(len < 0)) {
 			__putname(kname);
@@ -213,8 +217,7 @@ getname_kernel(const char * filename)
 		return ERR_PTR(-ENOMEM);
 
 	if (len <= EMBEDDED_NAME_MAX) {
-		result->name = (char *)(result) + sizeof(*result);
-		result->separate = false;
+		result->name = (char *)result->iname;
 	} else if (len <= PATH_MAX) {
 		struct filename *tmp;
 
@@ -224,7 +227,6 @@ getname_kernel(const char * filename)
 			return ERR_PTR(-ENOMEM);
 		}
 		tmp->name = (char *)result;
-		tmp->separate = true;
 		result = tmp;
 	} else {
 		__putname(result);
@@ -246,7 +248,7 @@ void putname(struct filename *name)
 	if (--name->refcnt > 0)
 		return;
 
-	if (name->separate) {
+	if (name->name != name->iname) {
 		__putname(name->name);
 		kfree(name);
 	} else
@@ -1852,6 +1854,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 		     struct nameidata *nd)
 {
 	int retval = 0;
+	const char *s = name->name;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
@@ -1860,7 +1863,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
-		if (name->name[0]) {
+		if (*s) {
 			if (!d_can_lookup(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
@@ -1882,7 +1885,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 	nd->root.mnt = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
-	if (name->name[0] == '/') {
+	if (*s == '/') {
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
 			nd->seq = set_root_rcu(nd);
@@ -1916,7 +1919,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 
 		dentry = f.file->f_path.dentry;
 
-		if (name->name[0]) {
+		if (*s) {
 			if (!d_can_lookup(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
@@ -1946,7 +1949,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 	return -ECHILD;
 done:
 	current->total_link_count = 0;
-	return link_path_walk(name->name, nd);
+	return link_path_walk(s, nd);
 }
 
 static void path_cleanup(struct nameidata *nd)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b4d71b5e1ff2..d70e333988f1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2144,7 +2144,7 @@ struct filename {
 	const __user char	*uptr;	/* original userland pointer */
 	struct audit_names	*aname;
 	int			refcnt;
-	bool			separate; /* should "name" be freed? */
+	const char		iname[];
 };
 
 extern long vfs_truncate(struct path *, loff_t);

From 74eb8cc5a5f8ec85b8f6b8daebbce05a27e77e2a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 23 Feb 2015 02:44:36 -0500
Subject: [PATCH 12/35] namei.c: fold do_path_lookup() into both callers

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 48 ++++++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 6218e62a0534..9b00dad73219 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2038,19 +2038,6 @@ static int filename_lookup(int dfd, struct filename *name,
 	return retval;
 }
 
-static int do_path_lookup(int dfd, const char *name,
-				unsigned int flags, struct nameidata *nd)
-{
-	struct filename *filename = getname_kernel(name);
-	int retval = PTR_ERR(filename);
-
-	if (!IS_ERR(filename)) {
-		retval = filename_lookup(dfd, filename, flags, nd);
-		putname(filename);
-	}
-	return retval;
-}
-
 /* does lookup, returns the object with parent locked */
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
@@ -2088,9 +2075,15 @@ out:
 int kern_path(const char *name, unsigned int flags, struct path *path)
 {
 	struct nameidata nd;
-	int res = do_path_lookup(AT_FDCWD, name, flags, &nd);
-	if (!res)
-		*path = nd.path;
+	struct filename *filename = getname_kernel(name);
+	int res = PTR_ERR(filename);
+
+	if (!IS_ERR(filename)) {
+		res = filename_lookup(AT_FDCWD, filename, flags, &nd);
+		putname(filename);
+		if (!res)
+			*path = nd.path;
+	}
 	return res;
 }
 EXPORT_SYMBOL(kern_path);
@@ -2107,15 +2100,22 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		    const char *name, unsigned int flags,
 		    struct path *path)
 {
-	struct nameidata nd;
-	int err;
-	nd.root.dentry = dentry;
-	nd.root.mnt = mnt;
+	struct filename *filename = getname_kernel(name);
+	int err = PTR_ERR(filename);
+
 	BUG_ON(flags & LOOKUP_PARENT);
-	/* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
-	err = do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, &nd);
-	if (!err)
-		*path = nd.path;
+
+	/* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */
+	if (!IS_ERR(filename)) {
+		struct nameidata nd;
+		nd.root.dentry = dentry;
+		nd.root.mnt = mnt;
+		err = filename_lookup(AT_FDCWD, filename,
+				      flags | LOOKUP_ROOT, &nd);
+		if (!err)
+			*path = nd.path;
+		putname(filename);
+	}
 	return err;
 }
 EXPORT_SYMBOL(vfs_path_lookup);

From 9e7543e9398ddd9679fbc81748a3e62eff4ab105 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 23 Feb 2015 02:49:48 -0500
Subject: [PATCH 13/35] remove incorrect comment in lookup_one_len()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 9b00dad73219..76fb76a0818b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2137,9 +2137,7 @@ static struct dentry *lookup_hash(struct nameidata *nd)
  * @len:	maximum length @len should be interpreted to
  *
  * Note that this routine is purely a helper for filesystem usage and should
- * not be called by generic code.  Also note that by using this function the
- * nameidata argument is passed to the filesystem methods and a filesystem
- * using this helper needs to be prepared for that.
+ * not be called by generic code.
  */
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {

From a555ad450f973528825201a5fedbe46374f86644 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 23 Feb 2015 03:21:31 -0500
Subject: [PATCH 14/35] whack-a-mole: no need to set_fs(USER_DS) in
 {start,flush}_thread()

flush_old_exec() has already done that.  Back on 2011 a bunch of
instances like that had been kicked out, but that hadn't taken
care of then-out-of-tree architectures, obviously, and they served
as reinfection vector...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arc/kernel/process.c          | 2 --
 arch/c6x/kernel/process.c          | 1 -
 arch/hexagon/kernel/process.c      | 2 --
 arch/metag/include/asm/processor.h | 1 -
 arch/nios2/kernel/process.c        | 1 -
 arch/openrisc/kernel/process.c     | 1 -
 6 files changed, 8 deletions(-)

diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 98c00a2d4dd9..f46efd14059d 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -155,8 +155,6 @@ int copy_thread(unsigned long clone_flags,
  */
 void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp)
 {
-	set_fs(USER_DS); /* user space */
-
 	regs->sp = usp;
 	regs->ret = pc;
 
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index 57d2ea8d1977..3ae9f5a166a0 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -101,7 +101,6 @@ void start_thread(struct pt_regs *regs, unsigned int pc, unsigned long usp)
 	 */
 	usp -= 8;
 
-	set_fs(USER_DS);
 	regs->pc  = pc;
 	regs->sp  = usp;
 	regs->tsr |= 0x40; /* set user mode */
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 0a0dd5c05b46..a9ebd471823a 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -37,8 +37,6 @@
  */
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 {
-	/* Set to run with user-mode data segmentation */
-	set_fs(USER_DS);
 	/* We want to zero all data-containing registers. Is this overkill? */
 	memset(regs, 0, sizeof(*regs));
 	/* We might want to also zero all Processor registers here */
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index 13272fd5a5ba..0838ca699764 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -111,7 +111,6 @@ struct thread_struct {
  */
 #define start_thread(regs, pc, usp) do {				   \
 	unsigned int *argc = (unsigned int *) bprm->exec;		   \
-	set_fs(USER_DS);						   \
 	current->thread.int_depth = 1;					   \
 	/* Force this process down to user land */			   \
 	regs->ctx.SaveMask = TBICTX_PRIV_BIT;				   \
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 0e075b5ad2a5..2f8c74f93e70 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -94,7 +94,6 @@ void show_regs(struct pt_regs *regs)
 
 void flush_thread(void)
 {
-	set_fs(USER_DS);
 }
 
 int copy_thread(unsigned long clone_flags,
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 386af258591d..7095dfe7666b 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -197,7 +197,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 {
 	unsigned long sr = mfspr(SPR_SR) & ~SPR_SR_SM;
 
-	set_fs(USER_DS);
 	memset(regs, 0, sizeof(struct pt_regs));
 
 	regs->pc = pc;

From 74008b365dcb921781f7430c1fc279be7778327b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 23 Feb 2015 05:46:21 -0500
Subject: [PATCH 15/35] whack-a-mole: there's no point doing set_fs(USER_DS) in
 sigframe setup

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/frv/kernel/signal.c        | 4 ----
 arch/m32r/kernel/signal.c       | 2 --
 arch/microblaze/kernel/signal.c | 2 --
 arch/sh/kernel/signal_32.c      | 4 ----
 arch/sh/kernel/signal_64.c      | 4 ----
 arch/xtensa/kernel/signal.c     | 5 -----
 6 files changed, 21 deletions(-)

diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index 336713ab4745..85ca6727ca07 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -176,8 +176,6 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set)
 	struct sigframe __user *frame;
 	int rsig, sig = ksig->sig;
 
-	set_fs(USER_DS);
-
 	frame = get_sigframe(ksig, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
@@ -257,8 +255,6 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set)
 	struct rt_sigframe __user *frame;
 	int rsig, sig = ksig->sig;
 
-	set_fs(USER_DS);
-
 	frame = get_sigframe(ksig, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 7736c6660a15..8c25e0c8f6a5 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -214,8 +214,6 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->r2 = (unsigned long)&frame->uc;
 	regs->bpc = (unsigned long)ksig->ka.sa.sa_handler;
 
-	set_fs(USER_DS);
-
 #if DEBUG_SIG
 	printk("SIG deliver (%s:%d): sp=%p pc=%p\n",
 		current->comm, current->pid, frame, regs->pc);
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index a1cbaf90e2ea..20ccd4e2baa5 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -236,8 +236,6 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	/* Offset to handle microblaze rtid r14, 0 */
 	regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
 
-	set_fs(USER_DS);
-
 #ifdef DEBUG_SIG
 	pr_info("SIG deliver (%s:%d): sp=%p pc=%08lx\n",
 		current->comm, current->pid, frame, regs->pc);
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 0b34f2a704fe..97292890b51b 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -329,8 +329,6 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	if (err)
 		return -EFAULT;
 
-	set_fs(USER_DS);
-
 	pr_debug("SIG deliver (%s:%d): sp=%p pc=%08lx pr=%08lx\n",
 		 current->comm, task_pid_nr(current), frame, regs->pc, regs->pr);
 
@@ -408,8 +406,6 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	if (err)
 		return -EFAULT;
 
-	set_fs(USER_DS);
-
 	pr_debug("SIG deliver (%s:%d): sp=%p pc=%08lx pr=%08lx\n",
 		 current->comm, task_pid_nr(current), frame, regs->pc, regs->pr);
 
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index 71993c6a7d94..0462995d4d7f 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -457,8 +457,6 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs
 
 	regs->pc = neff_sign_extend((unsigned long)ksig->ka.sa.sa_handler);
 
-	set_fs(USER_DS);
-
 	/* Broken %016Lx */
 	pr_debug("SIG deliver (#%d,%s:%d): sp=%p pc=%08Lx%08Lx link=%08Lx%08Lx\n",
 		 signal, current->comm, current->pid, frame,
@@ -547,8 +545,6 @@ static int setup_rt_frame(struct ksignal *kig, sigset_t *set,
 	regs->regs[REG_ARG3] = (unsigned long long)(unsigned long)(signed long)&frame->uc.uc_mcontext;
 	regs->pc = neff_sign_extend((unsigned long)ksig->ka.sa.sa_handler);
 
-	set_fs(USER_DS);
-
 	pr_debug("SIG deliver (#%d,%s:%d): sp=%p pc=%08Lx%08Lx link=%08Lx%08Lx\n",
 		 signal, current->comm, current->pid, frame,
 		 regs->pc >> 32, regs->pc & 0xffffffff,
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 3d733ba16f28..6b3790445cbe 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -405,11 +405,6 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	regs->areg[8] = (unsigned long) &frame->uc;
 	regs->threadptr = tp;
 
-	/* Set access mode to USER_DS.  Nomenclature is outdated, but
-	 * functionality is used in uaccess.h
-	 */
-	set_fs(USER_DS);
-
 #if DEBUG_SIG
 	printk("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08x\n",
 		current->comm, current->pid, signal, frame, regs->pc);

From 2247386243747500977dc92b1ab833401303f9f0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Mar 2015 19:24:30 -0400
Subject: [PATCH 16/35] constify tomoyo_realpath_from_path()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 security/tomoyo/common.h   | 2 +-
 security/tomoyo/realpath.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
index b897d4862016..6627102c24af 100644
--- a/security/tomoyo/common.h
+++ b/security/tomoyo/common.h
@@ -945,7 +945,7 @@ char *tomoyo_encode2(const char *str, int str_len);
 char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt,
 		      va_list args);
 char *tomoyo_read_token(struct tomoyo_acl_param *param);
-char *tomoyo_realpath_from_path(struct path *path);
+char *tomoyo_realpath_from_path(const struct path *path);
 char *tomoyo_realpath_nofollow(const char *pathname);
 const char *tomoyo_get_exe(void);
 const char *tomoyo_yesno(const unsigned int value);
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index bed745c8b1a3..1e0d480ff6a6 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -89,7 +89,7 @@ char *tomoyo_encode(const char *str)
  *
  * If dentry is a directory, trailing '/' is appended.
  */
-static char *tomoyo_get_absolute_path(struct path *path, char * const buffer,
+static char *tomoyo_get_absolute_path(const struct path *path, char * const buffer,
 				      const int buflen)
 {
 	char *pos = ERR_PTR(-ENOMEM);
@@ -216,7 +216,7 @@ out:
  *
  * Returns the buffer.
  */
-static char *tomoyo_get_socket_name(struct path *path, char * const buffer,
+static char *tomoyo_get_socket_name(const struct path *path, char * const buffer,
 				    const int buflen)
 {
 	struct inode *inode = path->dentry->d_inode;
@@ -247,7 +247,7 @@ static char *tomoyo_get_socket_name(struct path *path, char * const buffer,
  * These functions use kzalloc(), so the caller must call kfree()
  * if these functions didn't return NULL.
  */
-char *tomoyo_realpath_from_path(struct path *path)
+char *tomoyo_realpath_from_path(const struct path *path)
 {
 	char *buf = NULL;
 	char *name = NULL;

From 3f7036a071b879da017eddaedb10fba173fdf1ff Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Mar 2015 19:28:30 -0400
Subject: [PATCH 17/35] switch security_inode_getattr() to struct path *

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c                  |  2 +-
 include/linux/security.h   |  7 +++----
 security/apparmor/lsm.c    |  6 +++---
 security/capability.c      |  2 +-
 security/security.c        |  6 +++---
 security/selinux/hooks.c   | 12 +++---------
 security/smack/smack_lsm.c | 13 +++++--------
 security/tomoyo/common.h   |  2 +-
 security/tomoyo/file.c     |  4 ++--
 security/tomoyo/tomoyo.c   |  5 ++---
 10 files changed, 24 insertions(+), 35 deletions(-)

diff --git a/fs/stat.c b/fs/stat.c
index ae0c3cef9927..19636af5e75c 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -66,7 +66,7 @@ int vfs_getattr(struct path *path, struct kstat *stat)
 {
 	int retval;
 
-	retval = security_inode_getattr(path->mnt, path->dentry);
+	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
 	return vfs_getattr_nosec(path, stat);
diff --git a/include/linux/security.h b/include/linux/security.h
index a1b7dbd127ff..4e14e3d6309f 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1556,7 +1556,7 @@ struct security_operations {
 	int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd);
 	int (*inode_permission) (struct inode *inode, int mask);
 	int (*inode_setattr)	(struct dentry *dentry, struct iattr *attr);
-	int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry);
+	int (*inode_getattr) (const struct path *path);
 	int (*inode_setxattr) (struct dentry *dentry, const char *name,
 			       const void *value, size_t size, int flags);
 	void (*inode_post_setxattr) (struct dentry *dentry, const char *name,
@@ -1843,7 +1843,7 @@ int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask);
 int security_inode_setattr(struct dentry *dentry, struct iattr *attr);
-int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry);
+int security_inode_getattr(const struct path *path);
 int security_inode_setxattr(struct dentry *dentry, const char *name,
 			    const void *value, size_t size, int flags);
 void security_inode_post_setxattr(struct dentry *dentry, const char *name,
@@ -2259,8 +2259,7 @@ static inline int security_inode_setattr(struct dentry *dentry,
 	return 0;
 }
 
-static inline int security_inode_getattr(struct vfsmount *mnt,
-					  struct dentry *dentry)
+static inline int security_inode_getattr(const struct path *path)
 {
 	return 0;
 }
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 107db88b1d5f..dd56bffd6500 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -364,12 +364,12 @@ static int apparmor_path_chown(struct path *path, kuid_t uid, kgid_t gid)
 	return common_perm(OP_CHOWN, path, AA_MAY_CHOWN, &cond);
 }
 
-static int apparmor_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+static int apparmor_inode_getattr(const struct path *path)
 {
-	if (!mediated_filesystem(dentry))
+	if (!mediated_filesystem(path->dentry))
 		return 0;
 
-	return common_perm_mnt_dentry(OP_GETATTR, mnt, dentry,
+	return common_perm_mnt_dentry(OP_GETATTR, path->mnt, path->dentry,
 				      AA_MAY_META_READ);
 }
 
diff --git a/security/capability.c b/security/capability.c
index 070dd46f62f4..bdf22034a961 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -225,7 +225,7 @@ static int cap_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	return 0;
 }
 
-static int cap_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+static int cap_inode_getattr(const struct path *path)
 {
 	return 0;
 }
diff --git a/security/security.c b/security/security.c
index e81d5bbe7363..ed890c6d31c5 100644
--- a/security/security.c
+++ b/security/security.c
@@ -608,11 +608,11 @@ int security_inode_setattr(struct dentry *dentry, struct iattr *attr)
 }
 EXPORT_SYMBOL_GPL(security_inode_setattr);
 
-int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+int security_inode_getattr(const struct path *path)
 {
-	if (unlikely(IS_PRIVATE(dentry->d_inode)))
+	if (unlikely(IS_PRIVATE(path->dentry->d_inode)))
 		return 0;
-	return security_ops->inode_getattr(mnt, dentry);
+	return security_ops->inode_getattr(path);
 }
 
 int security_inode_setxattr(struct dentry *dentry, const char *name,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4d1a54190388..e119cdcffc87 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1623,7 +1623,7 @@ static inline int dentry_has_perm(const struct cred *cred,
    the path to help the auditing code to more easily generate the
    pathname if needed. */
 static inline int path_has_perm(const struct cred *cred,
-				struct path *path,
+				const struct path *path,
 				u32 av)
 {
 	struct inode *inode = path->dentry->d_inode;
@@ -2954,15 +2954,9 @@ static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	return dentry_has_perm(cred, dentry, av);
 }
 
-static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+static int selinux_inode_getattr(const struct path *path)
 {
-	const struct cred *cred = current_cred();
-	struct path path;
-
-	path.dentry = dentry;
-	path.mnt = mnt;
-
-	return path_has_perm(cred, &path, FILE__GETATTR);
+	return path_has_perm(current_cred(), path, FILE__GETATTR);
 }
 
 static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name)
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index c934311812f1..1511965549b8 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1034,19 +1034,16 @@ static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
  *
  * Returns 0 if access is permitted, an error code otherwise
  */
-static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+static int smack_inode_getattr(const struct path *path)
 {
 	struct smk_audit_info ad;
-	struct path path;
+	struct inode *inode = path->dentry->d_inode;
 	int rc;
 
-	path.dentry = dentry;
-	path.mnt = mnt;
-
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
-	smk_ad_setfield_u_fs_path(&ad, path);
-	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
-	rc = smk_bu_inode(dentry->d_inode, MAY_READ, rc);
+	smk_ad_setfield_u_fs_path(&ad, *path);
+	rc = smk_curacc(smk_of_inode(inode), MAY_READ, &ad);
+	rc = smk_bu_inode(inode, MAY_READ, rc);
 	return rc;
 }
 
diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
index 6627102c24af..f9c9fb1d56b4 100644
--- a/security/tomoyo/common.h
+++ b/security/tomoyo/common.h
@@ -978,7 +978,7 @@ int tomoyo_path2_perm(const u8 operation, struct path *path1,
 		      struct path *path2);
 int tomoyo_path_number_perm(const u8 operation, struct path *path,
 			    unsigned long number);
-int tomoyo_path_perm(const u8 operation, struct path *path,
+int tomoyo_path_perm(const u8 operation, const struct path *path,
 		     const char *target);
 unsigned int tomoyo_poll_control(struct file *file, poll_table *wait);
 unsigned int tomoyo_poll_log(struct file *file, poll_table *wait);
diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c
index c151a1869597..2367b100cc62 100644
--- a/security/tomoyo/file.c
+++ b/security/tomoyo/file.c
@@ -145,7 +145,7 @@ static void tomoyo_add_slash(struct tomoyo_path_info *buf)
  *
  * Returns true on success, false otherwise.
  */
-static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, struct path *path)
+static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path)
 {
 	buf->name = tomoyo_realpath_from_path(path);
 	if (buf->name) {
@@ -782,7 +782,7 @@ int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
  *
  * Returns 0 on success, negative value otherwise.
  */
-int tomoyo_path_perm(const u8 operation, struct path *path, const char *target)
+int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target)
 {
 	struct tomoyo_request_info r;
 	struct tomoyo_obj_info obj = {
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index f0b756e27fed..57c88d52ffa5 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -144,10 +144,9 @@ static int tomoyo_bprm_check_security(struct linux_binprm *bprm)
  *
  * Returns 0 on success, negative value otherwise.
  */
-static int tomoyo_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+static int tomoyo_inode_getattr(const struct path *path)
 {
-	struct path path = { mnt, dentry };
-	return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, &path, NULL);
+	return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, path, NULL);
 }
 
 /**

From e5b811e38af7540b385c898d83eb0198310343fd Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Mar 2015 23:36:51 -0400
Subject: [PATCH 18/35] drop bogus check in file_open_root()

For one thing, LOOKUP_DIRECTORY will be dealt with in do_last().
For another, name can be an empty string, but not NULL - no callers
pass that and it would oops immediately if they would.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index 33f9cbf2610b..ebcc7df0c9b6 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -988,9 +988,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 		return ERR_PTR(err);
 	if (flags & O_CREAT)
 		return ERR_PTR(-EINVAL);
-	if (!filename && (flags & O_DIRECTORY))
-		if (!dentry->d_inode->i_op->lookup)
-			return ERR_PTR(-ENOTDIR);
 	return do_file_open_root(dentry, mnt, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);

From 171a02032bf1e1bb35442a38d6e25e0dcbb85c63 Mon Sep 17 00:00:00 2001
From: Anton Altaparmakov <anton@tuxera.com>
Date: Wed, 11 Mar 2015 10:43:31 -0400
Subject: [PATCH 19/35] VFS: Add iov_iter_fault_in_multipages_readable()

simillar to iov_iter_fault_in_readable() but differs in that it is
not limited to faulting in the first iovec and instead faults in
"bytes" bytes iterating over the iovecs as necessary.

Also, instead of only faulting in the first and last page of the
range, all pages are faulted in.

This function is needed by NTFS when it does multi page file
writes.

Signed-off-by: Anton Altaparmakov <anton@tuxera.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  1 +
 lib/iov_iter.c      | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 71880299ed48..a69ed25af07f 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -76,6 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 9d96e283520c..b80f84376b91 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -317,6 +317,32 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 }
 EXPORT_SYMBOL(iov_iter_fault_in_readable);
 
+/*
+ * Fault in one or more iovecs of the given iov_iter, to a maximum length of
+ * bytes.  For each iovec, fault in each page that constitutes the iovec.
+ *
+ * Return 0 on success, or non-zero if the memory could not be accessed (i.e.
+ * because it is an invalid address).
+ */
+int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes)
+{
+	size_t skip = i->iov_offset;
+	const struct iovec *iov;
+	int err;
+	struct iovec v;
+
+	if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
+		iterate_iovec(i, bytes, v, iov, skip, ({
+			err = fault_in_multipages_readable(v.iov_base,
+					v.iov_len);
+			if (unlikely(err))
+			return err;
+		0;}))
+	}
+	return 0;
+}
+EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable);
+
 void iov_iter_init(struct iov_iter *i, int direction,
 			const struct iovec *iov, unsigned long nr_segs,
 			size_t count)

From a632f5593041305c8adbf4727bc1ccdf0b45178b Mon Sep 17 00:00:00 2001
From: Anton Altaparmakov <anton@tuxera.com>
Date: Wed, 11 Mar 2015 10:43:32 -0400
Subject: [PATCH 20/35] NTFS: Version 2.1.32 - Update file write from aio_write
 to write_iter.

Signed-off-by: Anton Altaparmakov <anton@tuxera.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ntfs/Makefile |   2 +-
 fs/ntfs/file.c   | 783 +++++++++++++++++++----------------------------
 2 files changed, 308 insertions(+), 477 deletions(-)

diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index 36ae529511c4..2ff263e6d363 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -8,7 +8,7 @@ ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
 
 ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
 
-ccflags-y := -DNTFS_VERSION=\"2.1.31\"
+ccflags-y := -DNTFS_VERSION=\"2.1.32\"
 ccflags-$(CONFIG_NTFS_DEBUG)	+= -DDEBUG
 ccflags-$(CONFIG_NTFS_RW)	+= -DNTFS_RW
 
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 1da9b2d184dc..29139ffb4328 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
  * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc.
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -329,62 +329,168 @@ err_out:
 	return err;
 }
 
-/**
- * ntfs_fault_in_pages_readable -
- *
- * Fault a number of userspace pages into pagetables.
- *
- * Unlike include/linux/pagemap.h::fault_in_pages_readable(), this one copes
- * with more than two userspace pages as well as handling the single page case
- * elegantly.
- *
- * If you find this difficult to understand, then think of the while loop being
- * the following code, except that we do without the integer variable ret:
- *
- *	do {
- *		ret = __get_user(c, uaddr);
- *		uaddr += PAGE_SIZE;
- *	} while (!ret && uaddr < end);
- *
- * Note, the final __get_user() may well run out-of-bounds of the user buffer,
- * but _not_ out-of-bounds of the page the user buffer belongs to, and since
- * this is only a read and not a write, and since it is still in the same page,
- * it should not matter and this makes the code much simpler.
- */
-static inline void ntfs_fault_in_pages_readable(const char __user *uaddr,
-		int bytes)
+static ssize_t ntfs_prepare_file_for_write(struct file *file, loff_t *ppos,
+		size_t *count)
 {
-	const char __user *end;
-	volatile char c;
+	loff_t pos;
+	s64 end, ll;
+	ssize_t err;
+	unsigned long flags;
+	struct inode *vi = file_inode(file);
+	ntfs_inode *base_ni, *ni = NTFS_I(vi);
+	ntfs_volume *vol = ni->vol;
 
-	/* Set @end to the first byte outside the last page we care about. */
-	end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes);
-
-	while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end))
-		;
-}
-
-/**
- * ntfs_fault_in_pages_readable_iovec -
- *
- * Same as ntfs_fault_in_pages_readable() but operates on an array of iovecs.
- */
-static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov,
-		size_t iov_ofs, int bytes)
-{
-	do {
-		const char __user *buf;
-		unsigned len;
-
-		buf = iov->iov_base + iov_ofs;
-		len = iov->iov_len - iov_ofs;
-		if (len > bytes)
-			len = bytes;
-		ntfs_fault_in_pages_readable(buf, len);
-		bytes -= len;
-		iov++;
-		iov_ofs = 0;
-	} while (bytes);
+	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
+			"0x%llx, count 0x%lx.", vi->i_ino,
+			(unsigned)le32_to_cpu(ni->type),
+			(unsigned long long)*ppos, (unsigned long)*count);
+	/* We can write back this queue in page reclaim. */
+	current->backing_dev_info = inode_to_bdi(vi);
+	err = generic_write_checks(file, ppos, count, S_ISBLK(vi->i_mode));
+	if (unlikely(err))
+		goto out;
+	/*
+	 * All checks have passed.  Before we start doing any writing we want
+	 * to abort any totally illegal writes.
+	 */
+	BUG_ON(NInoMstProtected(ni));
+	BUG_ON(ni->type != AT_DATA);
+	/* If file is encrypted, deny access, just like NT4. */
+	if (NInoEncrypted(ni)) {
+		/* Only $DATA attributes can be encrypted. */
+		/*
+		 * Reminder for later: Encrypted files are _always_
+		 * non-resident so that the content can always be encrypted.
+		 */
+		ntfs_debug("Denying write access to encrypted file.");
+		err = -EACCES;
+		goto out;
+	}
+	if (NInoCompressed(ni)) {
+		/* Only unnamed $DATA attribute can be compressed. */
+		BUG_ON(ni->name_len);
+		/*
+		 * Reminder for later: If resident, the data is not actually
+		 * compressed.  Only on the switch to non-resident does
+		 * compression kick in.  This is in contrast to encrypted files
+		 * (see above).
+		 */
+		ntfs_error(vi->i_sb, "Writing to compressed files is not "
+				"implemented yet.  Sorry.");
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+	if (*count == 0)
+		goto out;
+	base_ni = ni;
+	if (NInoAttr(ni))
+		base_ni = ni->ext.base_ntfs_ino;
+	err = file_remove_suid(file);
+	if (unlikely(err))
+		goto out;
+	/*
+	 * Our ->update_time method always succeeds thus file_update_time()
+	 * cannot fail either so there is no need to check the return code.
+	 */
+	file_update_time(file);
+	pos = *ppos;
+	/* The first byte after the last cluster being written to. */
+	end = (pos + *count + vol->cluster_size_mask) &
+			~(u64)vol->cluster_size_mask;
+	/*
+	 * If the write goes beyond the allocated size, extend the allocation
+	 * to cover the whole of the write, rounded up to the nearest cluster.
+	 */
+	read_lock_irqsave(&ni->size_lock, flags);
+	ll = ni->allocated_size;
+	read_unlock_irqrestore(&ni->size_lock, flags);
+	if (end > ll) {
+		/*
+		 * Extend the allocation without changing the data size.
+		 *
+		 * Note we ensure the allocation is big enough to at least
+		 * write some data but we do not require the allocation to be
+		 * complete, i.e. it may be partial.
+		 */
+		ll = ntfs_attr_extend_allocation(ni, end, -1, pos);
+		if (likely(ll >= 0)) {
+			BUG_ON(pos >= ll);
+			/* If the extension was partial truncate the write. */
+			if (end > ll) {
+				ntfs_debug("Truncating write to inode 0x%lx, "
+						"attribute type 0x%x, because "
+						"the allocation was only "
+						"partially extended.",
+						vi->i_ino, (unsigned)
+						le32_to_cpu(ni->type));
+				*count = ll - pos;
+			}
+		} else {
+			err = ll;
+			read_lock_irqsave(&ni->size_lock, flags);
+			ll = ni->allocated_size;
+			read_unlock_irqrestore(&ni->size_lock, flags);
+			/* Perform a partial write if possible or fail. */
+			if (pos < ll) {
+				ntfs_debug("Truncating write to inode 0x%lx "
+						"attribute type 0x%x, because "
+						"extending the allocation "
+						"failed (error %d).",
+						vi->i_ino, (unsigned)
+						le32_to_cpu(ni->type),
+						(int)-err);
+				*count = ll - pos;
+			} else {
+				if (err != -ENOSPC)
+					ntfs_error(vi->i_sb, "Cannot perform "
+							"write to inode "
+							"0x%lx, attribute "
+							"type 0x%x, because "
+							"extending the "
+							"allocation failed "
+							"(error %ld).",
+							vi->i_ino, (unsigned)
+							le32_to_cpu(ni->type),
+							(long)-err);
+				else
+					ntfs_debug("Cannot perform write to "
+							"inode 0x%lx, "
+							"attribute type 0x%x, "
+							"because there is not "
+							"space left.",
+							vi->i_ino, (unsigned)
+							le32_to_cpu(ni->type));
+				goto out;
+			}
+		}
+	}
+	/*
+	 * If the write starts beyond the initialized size, extend it up to the
+	 * beginning of the write and initialize all non-sparse space between
+	 * the old initialized size and the new one.  This automatically also
+	 * increments the vfs inode->i_size to keep it above or equal to the
+	 * initialized_size.
+	 */
+	read_lock_irqsave(&ni->size_lock, flags);
+	ll = ni->initialized_size;
+	read_unlock_irqrestore(&ni->size_lock, flags);
+	if (pos > ll) {
+		/*
+		 * Wait for ongoing direct i/o to complete before proceeding.
+		 * New direct i/o cannot start as we hold i_mutex.
+		 */
+		inode_dio_wait(vi);
+		err = ntfs_attr_extend_initialized(ni, pos);
+		if (unlikely(err < 0))
+			ntfs_error(vi->i_sb, "Cannot perform write to inode "
+					"0x%lx, attribute type 0x%x, because "
+					"extending the initialized size "
+					"failed (error %d).", vi->i_ino,
+					(unsigned)le32_to_cpu(ni->type),
+					(int)-err);
+	}
+out:
+	return err;
 }
 
 /**
@@ -421,8 +527,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 					goto err_out;
 				}
 			}
-			err = add_to_page_cache_lru(*cached_page, mapping, index,
-					GFP_KERNEL);
+			err = add_to_page_cache_lru(*cached_page, mapping,
+					index, GFP_KERNEL);
 			if (unlikely(err)) {
 				if (err == -EEXIST)
 					continue;
@@ -1268,180 +1374,6 @@ rl_not_mapped_enoent:
 	return err;
 }
 
-/*
- * Copy as much as we can into the pages and return the number of bytes which
- * were successfully copied.  If a fault is encountered then clear the pages
- * out to (ofs + bytes) and return the number of bytes which were copied.
- */
-static inline size_t ntfs_copy_from_user(struct page **pages,
-		unsigned nr_pages, unsigned ofs, const char __user *buf,
-		size_t bytes)
-{
-	struct page **last_page = pages + nr_pages;
-	char *addr;
-	size_t total = 0;
-	unsigned len;
-	int left;
-
-	do {
-		len = PAGE_CACHE_SIZE - ofs;
-		if (len > bytes)
-			len = bytes;
-		addr = kmap_atomic(*pages);
-		left = __copy_from_user_inatomic(addr + ofs, buf, len);
-		kunmap_atomic(addr);
-		if (unlikely(left)) {
-			/* Do it the slow way. */
-			addr = kmap(*pages);
-			left = __copy_from_user(addr + ofs, buf, len);
-			kunmap(*pages);
-			if (unlikely(left))
-				goto err_out;
-		}
-		total += len;
-		bytes -= len;
-		if (!bytes)
-			break;
-		buf += len;
-		ofs = 0;
-	} while (++pages < last_page);
-out:
-	return total;
-err_out:
-	total += len - left;
-	/* Zero the rest of the target like __copy_from_user(). */
-	while (++pages < last_page) {
-		bytes -= len;
-		if (!bytes)
-			break;
-		len = PAGE_CACHE_SIZE;
-		if (len > bytes)
-			len = bytes;
-		zero_user(*pages, 0, len);
-	}
-	goto out;
-}
-
-static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr,
-		const struct iovec *iov, size_t iov_ofs, size_t bytes)
-{
-	size_t total = 0;
-
-	while (1) {
-		const char __user *buf = iov->iov_base + iov_ofs;
-		unsigned len;
-		size_t left;
-
-		len = iov->iov_len - iov_ofs;
-		if (len > bytes)
-			len = bytes;
-		left = __copy_from_user_inatomic(vaddr, buf, len);
-		total += len;
-		bytes -= len;
-		vaddr += len;
-		if (unlikely(left)) {
-			total -= left;
-			break;
-		}
-		if (!bytes)
-			break;
-		iov++;
-		iov_ofs = 0;
-	}
-	return total;
-}
-
-static inline void ntfs_set_next_iovec(const struct iovec **iovp,
-		size_t *iov_ofsp, size_t bytes)
-{
-	const struct iovec *iov = *iovp;
-	size_t iov_ofs = *iov_ofsp;
-
-	while (bytes) {
-		unsigned len;
-
-		len = iov->iov_len - iov_ofs;
-		if (len > bytes)
-			len = bytes;
-		bytes -= len;
-		iov_ofs += len;
-		if (iov->iov_len == iov_ofs) {
-			iov++;
-			iov_ofs = 0;
-		}
-	}
-	*iovp = iov;
-	*iov_ofsp = iov_ofs;
-}
-
-/*
- * This has the same side-effects and return value as ntfs_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s
- * single-segment behaviour.
- *
- * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both when
- * atomic and when not atomic.  This is ok because it calls
- * __copy_from_user_inatomic() and it is ok to call this when non-atomic.  In
- * fact, the only difference between __copy_from_user_inatomic() and
- * __copy_from_user() is that the latter calls might_sleep() and the former
- * should not zero the tail of the buffer on error.  And on many architectures
- * __copy_from_user_inatomic() is just defined to __copy_from_user() so it
- * makes no difference at all on those architectures.
- */
-static inline size_t ntfs_copy_from_user_iovec(struct page **pages,
-		unsigned nr_pages, unsigned ofs, const struct iovec **iov,
-		size_t *iov_ofs, size_t bytes)
-{
-	struct page **last_page = pages + nr_pages;
-	char *addr;
-	size_t copied, len, total = 0;
-
-	do {
-		len = PAGE_CACHE_SIZE - ofs;
-		if (len > bytes)
-			len = bytes;
-		addr = kmap_atomic(*pages);
-		copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
-				*iov, *iov_ofs, len);
-		kunmap_atomic(addr);
-		if (unlikely(copied != len)) {
-			/* Do it the slow way. */
-			addr = kmap(*pages);
-			copied = __ntfs_copy_from_user_iovec_inatomic(addr +
-					ofs, *iov, *iov_ofs, len);
-			if (unlikely(copied != len))
-				goto err_out;
-			kunmap(*pages);
-		}
-		total += len;
-		ntfs_set_next_iovec(iov, iov_ofs, len);
-		bytes -= len;
-		if (!bytes)
-			break;
-		ofs = 0;
-	} while (++pages < last_page);
-out:
-	return total;
-err_out:
-	BUG_ON(copied > len);
-	/* Zero the rest of the target like __copy_from_user(). */
-	memset(addr + ofs + copied, 0, len - copied);
-	kunmap(*pages);
-	total += copied;
-	ntfs_set_next_iovec(iov, iov_ofs, copied);
-	while (++pages < last_page) {
-		bytes -= len;
-		if (!bytes)
-			break;
-		len = PAGE_CACHE_SIZE;
-		if (len > bytes)
-			len = bytes;
-		zero_user(*pages, 0, len);
-	}
-	goto out;
-}
-
 static inline void ntfs_flush_dcache_pages(struct page **pages,
 		unsigned nr_pages)
 {
@@ -1762,86 +1694,83 @@ err_out:
 	return err;
 }
 
-static void ntfs_write_failed(struct address_space *mapping, loff_t to)
+/*
+ * Copy as much as we can into the pages and return the number of bytes which
+ * were successfully copied.  If a fault is encountered then clear the pages
+ * out to (ofs + bytes) and return the number of bytes which were copied.
+ */
+static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages,
+		unsigned ofs, struct iov_iter *i, size_t bytes)
 {
-	struct inode *inode = mapping->host;
+	struct page **last_page = pages + nr_pages;
+	size_t total = 0;
+	struct iov_iter data = *i;
+	unsigned len, copied;
 
-	if (to > inode->i_size) {
-		truncate_pagecache(inode, inode->i_size);
-		ntfs_truncate_vfs(inode);
-	}
+	do {
+		len = PAGE_CACHE_SIZE - ofs;
+		if (len > bytes)
+			len = bytes;
+		copied = iov_iter_copy_from_user_atomic(*pages, &data, ofs,
+				len);
+		total += copied;
+		bytes -= copied;
+		if (!bytes)
+			break;
+		iov_iter_advance(&data, copied);
+		if (copied < len)
+			goto err;
+		ofs = 0;
+	} while (++pages < last_page);
+out:
+	return total;
+err:
+	/* Zero the rest of the target like __copy_from_user(). */
+	len = PAGE_CACHE_SIZE - copied;
+	do {
+		if (len > bytes)
+			len = bytes;
+		zero_user(*pages, copied, len);
+		bytes -= len;
+		copied = 0;
+		len = PAGE_CACHE_SIZE;
+	} while (++pages < last_page);
+	goto out;
 }
 
 /**
- * ntfs_file_buffered_write -
- *
- * Locking: The vfs is holding ->i_mutex on the inode.
+ * ntfs_perform_write - perform buffered write to a file
+ * @file:	file to write to
+ * @i:		iov_iter with data to write
+ * @pos:	byte offset in file at which to begin writing to
  */
-static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
-		const struct iovec *iov, unsigned long nr_segs,
-		loff_t pos, loff_t *ppos, size_t count)
+static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
+		loff_t pos)
 {
-	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *vi = mapping->host;
 	ntfs_inode *ni = NTFS_I(vi);
 	ntfs_volume *vol = ni->vol;
 	struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER];
 	struct page *cached_page = NULL;
-	char __user *buf = NULL;
-	s64 end, ll;
 	VCN last_vcn;
 	LCN lcn;
-	unsigned long flags;
-	size_t bytes, iov_ofs = 0;	/* Offset in the current iovec. */
-	ssize_t status, written;
+	size_t bytes;
+	ssize_t status, written = 0;
 	unsigned nr_pages;
-	int err;
 
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
-			"pos 0x%llx, count 0x%lx.",
-			vi->i_ino, (unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)pos, (unsigned long)count);
-	if (unlikely(!count))
-		return 0;
-	BUG_ON(NInoMstProtected(ni));
-	/*
-	 * If the attribute is not an index root and it is encrypted or
-	 * compressed, we cannot write to it yet.  Note we need to check for
-	 * AT_INDEX_ALLOCATION since this is the type of both directory and
-	 * index inodes.
-	 */
-	if (ni->type != AT_INDEX_ALLOCATION) {
-		/* If file is encrypted, deny access, just like NT4. */
-		if (NInoEncrypted(ni)) {
-			/*
-			 * Reminder for later: Encrypted files are _always_
-			 * non-resident so that the content can always be
-			 * encrypted.
-			 */
-			ntfs_debug("Denying write access to encrypted file.");
-			return -EACCES;
-		}
-		if (NInoCompressed(ni)) {
-			/* Only unnamed $DATA attribute can be compressed. */
-			BUG_ON(ni->type != AT_DATA);
-			BUG_ON(ni->name_len);
-			/*
-			 * Reminder for later: If resident, the data is not
-			 * actually compressed.  Only on the switch to non-
-			 * resident does compression kick in.  This is in
-			 * contrast to encrypted files (see above).
-			 */
-			ntfs_error(vi->i_sb, "Writing to compressed files is "
-					"not implemented yet.  Sorry.");
-			return -EOPNOTSUPP;
-		}
-	}
+	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
+			"0x%llx, count 0x%lx.", vi->i_ino,
+			(unsigned)le32_to_cpu(ni->type),
+			(unsigned long long)pos,
+			(unsigned long)iov_iter_count(i));
 	/*
 	 * If a previous ntfs_truncate() failed, repeat it and abort if it
 	 * fails again.
 	 */
 	if (unlikely(NInoTruncateFailed(ni))) {
+		int err;
+
 		inode_dio_wait(vi);
 		err = ntfs_truncate(vi);
 		if (err || NInoTruncateFailed(ni)) {
@@ -1855,81 +1784,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 			return err;
 		}
 	}
-	/* The first byte after the write. */
-	end = pos + count;
-	/*
-	 * If the write goes beyond the allocated size, extend the allocation
-	 * to cover the whole of the write, rounded up to the nearest cluster.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (end > ll) {
-		/* Extend the allocation without changing the data size. */
-		ll = ntfs_attr_extend_allocation(ni, end, -1, pos);
-		if (likely(ll >= 0)) {
-			BUG_ON(pos >= ll);
-			/* If the extension was partial truncate the write. */
-			if (end > ll) {
-				ntfs_debug("Truncating write to inode 0x%lx, "
-						"attribute type 0x%x, because "
-						"the allocation was only "
-						"partially extended.",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-				end = ll;
-				count = ll - pos;
-			}
-		} else {
-			err = ll;
-			read_lock_irqsave(&ni->size_lock, flags);
-			ll = ni->allocated_size;
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			/* Perform a partial write if possible or fail. */
-			if (pos < ll) {
-				ntfs_debug("Truncating write to inode 0x%lx, "
-						"attribute type 0x%x, because "
-						"extending the allocation "
-						"failed (error code %i).",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type), err);
-				end = ll;
-				count = ll - pos;
-			} else {
-				ntfs_error(vol->sb, "Cannot perform write to "
-						"inode 0x%lx, attribute type "
-						"0x%x, because extending the "
-						"allocation failed (error "
-						"code %i).", vi->i_ino,
-						(unsigned)
-						le32_to_cpu(ni->type), err);
-				return err;
-			}
-		}
-	}
-	written = 0;
-	/*
-	 * If the write starts beyond the initialized size, extend it up to the
-	 * beginning of the write and initialize all non-sparse space between
-	 * the old initialized size and the new one.  This automatically also
-	 * increments the vfs inode->i_size to keep it above or equal to the
-	 * initialized_size.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (pos > ll) {
-		err = ntfs_attr_extend_initialized(ni, pos);
-		if (err < 0) {
-			ntfs_error(vol->sb, "Cannot perform write to inode "
-					"0x%lx, attribute type 0x%x, because "
-					"extending the initialized size "
-					"failed (error code %i).", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-			status = err;
-			goto err_out;
-		}
-	}
 	/*
 	 * Determine the number of pages per cluster for non-resident
 	 * attributes.
@@ -1937,10 +1791,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 	nr_pages = 1;
 	if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni))
 		nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT;
-	/* Finally, perform the actual write. */
 	last_vcn = -1;
-	if (likely(nr_segs == 1))
-		buf = iov->iov_base;
 	do {
 		VCN vcn;
 		pgoff_t idx, start_idx;
@@ -1965,10 +1816,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 						vol->cluster_size_bits, false);
 				up_read(&ni->runlist.lock);
 				if (unlikely(lcn < LCN_HOLE)) {
-					status = -EIO;
 					if (lcn == LCN_ENOMEM)
 						status = -ENOMEM;
-					else
+					else {
+						status = -EIO;
 						ntfs_error(vol->sb, "Cannot "
 							"perform write to "
 							"inode 0x%lx, "
@@ -1977,6 +1828,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 							"is corrupt.",
 							vi->i_ino, (unsigned)
 							le32_to_cpu(ni->type));
+					}
 					break;
 				}
 				if (lcn == LCN_HOLE) {
@@ -1989,8 +1841,9 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 				}
 			}
 		}
-		if (bytes > count)
-			bytes = count;
+		if (bytes > iov_iter_count(i))
+			bytes = iov_iter_count(i);
+again:
 		/*
 		 * Bring in the user page(s) that we will copy from _first_.
 		 * Otherwise there is a nasty deadlock on copying from the same
@@ -1999,10 +1852,10 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 		 * pages being swapped out between us bringing them into memory
 		 * and doing the actual copying.
 		 */
-		if (likely(nr_segs == 1))
-			ntfs_fault_in_pages_readable(buf, bytes);
-		else
-			ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes);
+		if (unlikely(iov_iter_fault_in_multipages_readable(i, bytes))) {
+			status = -EFAULT;
+			break;
+		}
 		/* Get and lock @do_pages starting at index @start_idx. */
 		status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages,
 				pages, &cached_page);
@@ -2018,56 +1871,57 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 			status = ntfs_prepare_pages_for_non_resident_write(
 					pages, do_pages, pos, bytes);
 			if (unlikely(status)) {
-				loff_t i_size;
-
 				do {
 					unlock_page(pages[--do_pages]);
 					page_cache_release(pages[do_pages]);
 				} while (do_pages);
-				/*
-				 * The write preparation may have instantiated
-				 * allocated space outside i_size.  Trim this
-				 * off again.  We can ignore any errors in this
-				 * case as we will just be waisting a bit of
-				 * allocated space, which is not a disaster.
-				 */
-				i_size = i_size_read(vi);
-				if (pos + bytes > i_size) {
-					ntfs_write_failed(mapping, pos + bytes);
-				}
 				break;
 			}
 		}
 		u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index;
-		if (likely(nr_segs == 1)) {
-			copied = ntfs_copy_from_user(pages + u, do_pages - u,
-					ofs, buf, bytes);
-			buf += copied;
-		} else
-			copied = ntfs_copy_from_user_iovec(pages + u,
-					do_pages - u, ofs, &iov, &iov_ofs,
-					bytes);
+		copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs,
+					i, bytes);
 		ntfs_flush_dcache_pages(pages + u, do_pages - u);
-		status = ntfs_commit_pages_after_write(pages, do_pages, pos,
-				bytes);
-		if (likely(!status)) {
-			written += copied;
-			count -= copied;
-			pos += copied;
-			if (unlikely(copied != bytes))
-				status = -EFAULT;
+		status = 0;
+		if (likely(copied == bytes)) {
+			status = ntfs_commit_pages_after_write(pages, do_pages,
+					pos, bytes);
+			if (!status)
+				status = bytes;
 		}
 		do {
 			unlock_page(pages[--do_pages]);
 			page_cache_release(pages[do_pages]);
 		} while (do_pages);
-		if (unlikely(status))
+		if (unlikely(status < 0))
 			break;
-		balance_dirty_pages_ratelimited(mapping);
+		copied = status;
 		cond_resched();
-	} while (count);
-err_out:
-	*ppos = pos;
+		if (unlikely(!copied)) {
+			size_t sc;
+
+			/*
+			 * We failed to copy anything.  Fall back to single
+			 * segment length write.
+			 *
+			 * This is needed to avoid possible livelock in the
+			 * case that all segments in the iov cannot be copied
+			 * at once without a pagefault.
+			 */
+			sc = iov_iter_single_seg_count(i);
+			if (bytes > sc)
+				bytes = sc;
+			goto again;
+		}
+		iov_iter_advance(i, copied);
+		pos += copied;
+		written += copied;
+		balance_dirty_pages_ratelimited(mapping);
+		if (fatal_signal_pending(current)) {
+			status = -EINTR;
+			break;
+		}
+	} while (iov_iter_count(i));
 	if (cached_page)
 		page_cache_release(cached_page);
 	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
@@ -2077,59 +1931,56 @@ err_out:
 }
 
 /**
- * ntfs_file_aio_write_nolock -
+ * ntfs_file_write_iter_nolock - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @from:	iov_iter with data to write
+ *
+ * Basically the same as __generic_file_write_iter() except that it ends
+ * up calling ntfs_perform_write() instead of generic_perform_write() and that
+ * O_DIRECT is not implemented.
  */
-static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
-		const struct iovec *iov, unsigned long nr_segs, loff_t *ppos)
+static ssize_t ntfs_file_write_iter_nolock(struct kiocb *iocb,
+		struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	loff_t pos;
-	size_t count;		/* after file limit checks */
-	ssize_t written, err;
+	loff_t pos = iocb->ki_pos;
+	ssize_t written = 0;
+	ssize_t err;
+	size_t count = iov_iter_count(from);
 
-	count = iov_length(iov, nr_segs);
-	pos = *ppos;
-	/* We can write back this queue in page reclaim. */
-	current->backing_dev_info = inode_to_bdi(inode);
-	written = 0;
-	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
-	if (err)
-		goto out;
-	if (!count)
-		goto out;
-	err = file_remove_suid(file);
-	if (err)
-		goto out;
-	err = file_update_time(file);
-	if (err)
-		goto out;
-	written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos,
-			count);
-out:
+	err = ntfs_prepare_file_for_write(file, &pos, &count);
+	if (count && !err) {
+		iov_iter_truncate(from, count);
+		written = ntfs_perform_write(file, from, pos);
+		if (likely(written >= 0))
+			iocb->ki_pos = pos + written;
+	}
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
 
 /**
- * ntfs_file_aio_write -
+ * ntfs_file_write_iter - simple wrapper for ntfs_file_write_iter_nolock()
+ * @iocb:	IO state structure
+ * @from:	iov_iter with data to write
+ *
+ * Basically the same as generic_file_write_iter() except that it ends up
+ * calling ntfs_file_write_iter_nolock() instead of
+ * __generic_file_write_iter().
  */
-static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
+	struct inode *vi = file_inode(file);
 	ssize_t ret;
 
-	BUG_ON(iocb->ki_pos != pos);
-
-	mutex_lock(&inode->i_mutex);
-	ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
-	mutex_unlock(&inode->i_mutex);
+	mutex_lock(&vi->i_mutex);
+	ret = ntfs_file_write_iter_nolock(iocb, from);
+	mutex_unlock(&vi->i_mutex);
 	if (ret > 0) {
-		int err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		ssize_t err;
+
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}
@@ -2197,37 +2048,17 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 #endif /* NTFS_RW */
 
 const struct file_operations ntfs_file_ops = {
-	.llseek		= generic_file_llseek,	 /* Seek inside file. */
-	.read		= new_sync_read,	 /* Read from file. */
-	.read_iter	= generic_file_read_iter, /* Async read from file. */
+	.llseek		= generic_file_llseek,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
 #ifdef NTFS_RW
-	.write		= do_sync_write,	 /* Write to file. */
-	.aio_write	= ntfs_file_aio_write,	 /* Async write to file. */
-	/*.release	= ,*/			 /* Last file is closed.  See
-						    fs/ext2/file.c::
-						    ext2_release_file() for
-						    how to use this to discard
-						    preallocated space for
-						    write opened files. */
-	.fsync		= ntfs_file_fsync,	 /* Sync a file to disk. */
-	/*.aio_fsync	= ,*/			 /* Sync all outstanding async
-						    i/o operations on a
-						    kiocb. */
+	.write		= new_sync_write,
+	.write_iter	= ntfs_file_write_iter,
+	.fsync		= ntfs_file_fsync,
 #endif /* NTFS_RW */
-	/*.ioctl	= ,*/			 /* Perform function on the
-						    mounted filesystem. */
-	.mmap		= generic_file_mmap,	 /* Mmap file. */
-	.open		= ntfs_file_open,	 /* Open file. */
-	.splice_read	= generic_file_splice_read /* Zero-copy data send with
-						    the data source being on
-						    the ntfs partition.  We do
-						    not need to care about the
-						    data destination. */
-	/*.sendpage	= ,*/			 /* Zero-copy data send with
-						    the data destination being
-						    on the ntfs partition.  We
-						    do not need to care about
-						    the data source. */
+	.mmap		= generic_file_mmap,
+	.open		= ntfs_file_open,
+	.splice_read	= generic_file_splice_read,
 };
 
 const struct inode_operations ntfs_file_inode_ops = {

From 3d330dc175d3faf518cf035be5ae6a39bf256e6e Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 10 Feb 2015 10:55:53 -0500
Subject: [PATCH 21/35] dcache: return -ESTALE not -EBUSY on distributed fs
 race

On a distributed filesystem it's possible for lookup to discover that a
directory it just found is already cached elsewhere in the directory
heirarchy.  The dcache won't let us keep the directory in both places,
so we have to move the dentry to the new location from the place we
previously had it cached.

If the parent has changed, then this requires all the same locks as we'd
need to do a cross-directory rename.  But we're already in lookup
holding one parent's i_mutex, so it's too late to acquire those locks in
the right order.

The (unreliable) solution in __d_unalias is to trylock() the required
locks and return -EBUSY if it fails.

I see no particular reason for returning -EBUSY, and -ESTALE is already
the result of some other lookup races on NFS.  I think -ESTALE is the
more helpful error return.  It also allows us to take advantage of the
logic Jeff Layton added in c6a9428401c0 "vfs: fix renameat to retry on
ESTALE errors" and ancestors, which hopefully resolves some of these
errors before they're returned to userspace.

I can reproduce these cases using NFS with:

	ssh root@$client '
		mount -olookupcache=pos '$server':'$export' /mnt/
		mkdir /mnt/TO
		mkdir /mnt/DIR
		touch /mnt/DIR/test.txt
		while true; do
			strace -e open cat /mnt/DIR/test.txt 2>&1 | grep EBUSY
		done
	'
	ssh root@$server '
		while true; do
			mv $export/DIR $export/TO/DIR
			mv $export/TO/DIR $export/DIR
		done
	'

It also helps to add some other concurrent use of the directory on the
client (e.g., "ls /mnt/TO").  And you can replace the server-side mv's
by client-side mv's that are repeatedly killed.  (If the client is
interrupted while waiting for the RENAME response then it's left with a
dentry that has to go under one parent or the other, but it doesn't yet
know which.)

Acked-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index c71e3732e53b..d99736a63e3c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2690,7 +2690,7 @@ static int __d_unalias(struct inode *inode,
 		struct dentry *dentry, struct dentry *alias)
 {
 	struct mutex *m1 = NULL, *m2 = NULL;
-	int ret = -EBUSY;
+	int ret = -ESTALE;
 
 	/* If alias and dentry share a parent, then no extra locks required */
 	if (alias->d_parent == dentry->d_parent)

From c1b8940b42bb6487b10f2267a96b486276ce9ff7 Mon Sep 17 00:00:00 2001
From: Andrew Elble <aweits@rit.edu>
Date: Mon, 23 Feb 2015 08:51:24 -0500
Subject: [PATCH 22/35] NFS: fix BUG() crash in notify_change() with patch to
 chown_common()

We have observed a BUG() crash in fs/attr.c:notify_change(). The crash
occurs during an rsync into a filesystem that is exported via NFS.

1.) fs/attr.c:notify_change() modifies the caller's version of attr.
2.) 6de0ec00ba8d ("VFS: make notify_change pass ATTR_KILL_S*ID to
    setattr operations") introduced a BUG() restriction such that "no
    function will ever call notify_change() with both ATTR_MODE and
    ATTR_KILL_S*ID set". Under some circumstances though, it will have
    assisted in setting the caller's version of attr to this very
    combination.
3.) 27ac0ffeac80 ("locks: break delegations on any attribute
    modification") introduced code to handle breaking
    delegations. This can result in notify_change() being re-called. attr
    _must_ be explicitly reset to avoid triggering the BUG() established
    in #2.
4.) The path that that triggers this is via fs/open.c:chmod_common().
    The combination of attr flags set here and in the first call to
    notify_change() along with a later failed break_deleg_wait()
    results in notify_change() being called again via retry_deleg
    without resetting attr.

Solution is to move retry_deleg in chmod_common() a bit further up to
ensure attr is completely reset.

There are other places where this seemingly could occur, such as
fs/utimes.c:utimes_common(), but the attr flags are not initially
set in such a way to trigger this.

Fixes: 27ac0ffeac80 ("locks: break delegations on any attribute modification")
Reported-by: Eric Meddaugh <etmsys@rit.edu>
Tested-by: Eric Meddaugh <etmsys@rit.edu>
Signed-off-by: Andrew Elble <aweits@rit.edu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/open.c b/fs/open.c
index ebcc7df0c9b6..6a83c47d5904 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -570,6 +570,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	uid = make_kuid(current_user_ns(), user);
 	gid = make_kgid(current_user_ns(), group);
 
+retry_deleg:
 	newattrs.ia_valid =  ATTR_CTIME;
 	if (user != (uid_t) -1) {
 		if (!uid_valid(uid))
@@ -586,7 +587,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
-retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chown(path, uid, gid);
 	if (!error)

From ac15ac0669d5f5ce7fddec0d9cf3721c42d77a2c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 20 Mar 2015 20:10:21 -0400
Subject: [PATCH 23/35] lift iov_iter into {compat_,}do_readv_writev()

get it closer to matching {compat_,}rw_copy_check_uvector().

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c | 54 +++++++++++++++++++++----------------------------
 1 file changed, 23 insertions(+), 31 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 99a6ef946d01..11980f164432 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -695,25 +695,23 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 }
 EXPORT_SYMBOL(iov_shorten);
 
-static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iovec *iov,
-		unsigned long nr_segs, size_t len, loff_t *ppos, iter_fn_t fn)
+static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
+		loff_t *ppos, iter_fn_t fn)
 {
 	struct kiocb kiocb;
-	struct iov_iter iter;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
 
-	iov_iter_init(&iter, rw, iov, nr_segs, len);
-	ret = fn(&kiocb, &iter);
+	ret = fn(&kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
 
-static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
-		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
+static ssize_t do_sync_readv_writev(struct file *filp, struct iov_iter *iter,
+		loff_t *ppos, iov_fn_t fn)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
@@ -721,30 +719,23 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
 
-	ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
+	ret = fn(&kiocb, iter->iov, iter->nr_segs, kiocb.ki_pos);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
 }
 
 /* Do it by hand, with file-ops */
-static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
-		unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
+static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
+		loff_t *ppos, io_fn_t fn)
 {
-	struct iovec *vector = iov;
 	ssize_t ret = 0;
 
-	while (nr_segs > 0) {
-		void __user *base;
-		size_t len;
+	while (iov_iter_count(iter)) {
+		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
 
-		base = vector->iov_base;
-		len = vector->iov_len;
-		vector++;
-		nr_segs--;
-
-		nr = fn(filp, base, len, ppos);
+		nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
 
 		if (nr < 0) {
 			if (!ret)
@@ -752,8 +743,9 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
 			break;
 		}
 		ret += nr;
-		if (nr != len)
+		if (nr != iovec.iov_len)
 			break;
+		iov_iter_advance(iter, nr);
 	}
 
 	return ret;
@@ -844,6 +836,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
+	struct iov_iter iter;
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
@@ -853,6 +846,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 				    ARRAY_SIZE(iovstack), iovstack, &iov);
 	if (ret <= 0)
 		goto out;
+	iov_iter_init(&iter, type, iov, nr_segs, ret);
 
 	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
@@ -872,13 +866,11 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
-						pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
 	else if (fnv)
-		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
-						pos, fnv);
+		ret = do_sync_readv_writev(file, &iter, pos, fnv);
 	else
-		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn);
 
 	if (type != READ)
 		file_end_write(file);
@@ -1024,6 +1016,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
+	struct iov_iter iter;
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
@@ -1033,6 +1026,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 					       UIO_FASTIOV, iovstack, &iov);
 	if (ret <= 0)
 		goto out;
+	iov_iter_init(&iter, type, iov, nr_segs, ret);
 
 	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
@@ -1052,13 +1046,11 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
-						pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
 	else if (fnv)
-		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
-						pos, fnv);
+		ret = do_sync_readv_writev(file, &iter, pos, fnv);
 	else
-		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn);
 
 	if (type != READ)
 		file_end_write(file);

From 4c185ce06dca14f5cea192f5a2c981ef50663f2b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 20 Mar 2015 20:17:32 -0400
Subject: [PATCH 24/35] aio: lift iov_iter_init() into aio_setup_..._rw()

the only non-trivial detail is that we do it before rw_verify_area(),
so we'd better cap the length ourselves in aio_setup_single_rw()
case (for vectored case rw_copy_check_uvector() will do that for us).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 435ca29eca31..7816e8ec3c0e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1357,7 +1357,8 @@ static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 				     unsigned long *nr_segs,
 				     size_t *len,
 				     struct iovec **iovec,
-				     bool compat)
+				     bool compat,
+				     struct iov_iter *iter)
 {
 	ssize_t ret;
 
@@ -1378,6 +1379,7 @@ static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 
 	/* len now reflect bytes instead of segs */
 	*len = ret;
+	iov_iter_init(iter, rw, *iovec, *nr_segs, *len);
 	return 0;
 }
 
@@ -1385,14 +1387,18 @@ 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)
+				       struct iovec *iovec,
+				       struct iov_iter *iter)
 {
+	if (len > MAX_RW_COUNT)
+		len = MAX_RW_COUNT;
 	if (unlikely(!access_ok(!rw, buf, len)))
 		return -EFAULT;
 
 	iovec->iov_base = buf;
 	iovec->iov_len = len;
 	*nr_segs = 1;
+	iov_iter_init(iter, rw, iovec, *nr_segs, len);
 	return 0;
 }
 
@@ -1438,10 +1444,10 @@ rw_common:
 
 		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
 			ret = aio_setup_vectored_rw(req, rw, buf, &nr_segs,
-						&len, &iovec, compat);
+						&len, &iovec, compat, &iter);
 		else
 			ret = aio_setup_single_vector(req, rw, buf, &nr_segs,
-						  len, iovec);
+						  len, iovec, &iter);
 		if (!ret)
 			ret = rw_verify_area(rw, file, &req->ki_pos, len);
 		if (ret < 0) {
@@ -1463,10 +1469,9 @@ rw_common:
 			file_start_write(file);
 
 		if (iter_op) {
-			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);
+			ret = rw_op(req, iter.iov, iter.nr_segs, req->ki_pos);
 		}
 
 		if (rw == WRITE)

From a96114fa1acaabca1091a27aacebd945a5733075 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 20 Mar 2015 20:40:18 -0400
Subject: [PATCH 25/35] aio: simplify arguments of aio_setup_..._rw()

We don't need req in either of those.  We don't need nr_segs in caller.
We don't really need len in caller either - iov_iter_count(&iter) will do.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c | 45 +++++++++++++++++----------------------------
 1 file changed, 17 insertions(+), 28 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 7816e8ec3c0e..2ba172cfdeba 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1352,43 +1352,33 @@ typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
 			    unsigned long, loff_t);
 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,
-				     struct iov_iter *iter)
+static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
+				 struct iovec **iovec,
+				 bool compat,
+				 struct iov_iter *iter)
 {
 	ssize_t ret;
 
-	*nr_segs = *len;
-
 #ifdef CONFIG_COMPAT
 	if (compat)
 		ret = compat_rw_copy_check_uvector(rw,
 				(struct compat_iovec __user *)buf,
-				*nr_segs, UIO_FASTIOV, *iovec, iovec);
+				len, UIO_FASTIOV, *iovec, iovec);
 	else
 #endif
 		ret = rw_copy_check_uvector(rw,
 				(struct iovec __user *)buf,
-				*nr_segs, UIO_FASTIOV, *iovec, iovec);
+				len, UIO_FASTIOV, *iovec, iovec);
 	if (ret < 0)
 		return ret;
 
-	/* len now reflect bytes instead of segs */
-	*len = ret;
-	iov_iter_init(iter, rw, *iovec, *nr_segs, *len);
+	iov_iter_init(iter, rw, *iovec, 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,
-				       struct iov_iter *iter)
+static int aio_setup_single_vector(int rw, char __user *buf, size_t len,
+				   struct iovec *iovec,
+				   struct iov_iter *iter)
 {
 	if (len > MAX_RW_COUNT)
 		len = MAX_RW_COUNT;
@@ -1397,8 +1387,7 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
 
 	iovec->iov_base = buf;
 	iovec->iov_len = len;
-	*nr_segs = 1;
-	iov_iter_init(iter, rw, iovec, *nr_segs, len);
+	iov_iter_init(iter, rw, iovec, 1, len);
 	return 0;
 }
 
@@ -1411,7 +1400,6 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 {
 	struct file *file = req->ki_filp;
 	ssize_t ret;
-	unsigned long nr_segs;
 	int rw;
 	fmode_t mode;
 	aio_rw_op *rw_op;
@@ -1443,13 +1431,14 @@ rw_common:
 			return -EINVAL;
 
 		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
-			ret = aio_setup_vectored_rw(req, rw, buf, &nr_segs,
-						&len, &iovec, compat, &iter);
+			ret = aio_setup_vectored_rw(rw, buf, len,
+						&iovec, compat, &iter);
 		else
-			ret = aio_setup_single_vector(req, rw, buf, &nr_segs,
-						  len, iovec, &iter);
+			ret = aio_setup_single_vector(rw, buf, len,
+						iovec, &iter);
 		if (!ret)
-			ret = rw_verify_area(rw, file, &req->ki_pos, len);
+			ret = rw_verify_area(rw, file, &req->ki_pos,
+					     iov_iter_count(&iter));
 		if (ret < 0) {
 			if (iovec != inline_vecs)
 				kfree(iovec);

From d4fb392f4c5e57197a43b729e6fad5e02e5acaca Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 19:11:55 -0400
Subject: [PATCH 26/35] kill aio_setup_single_vector()

identical to import_single_range()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 2ba172cfdeba..3dba5a70ad97 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1376,21 +1376,6 @@ static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
 	return 0;
 }
 
-static int aio_setup_single_vector(int rw, char __user *buf, size_t len,
-				   struct iovec *iovec,
-				   struct iov_iter *iter)
-{
-	if (len > MAX_RW_COUNT)
-		len = MAX_RW_COUNT;
-	if (unlikely(!access_ok(!rw, buf, len)))
-		return -EFAULT;
-
-	iovec->iov_base = buf;
-	iovec->iov_len = len;
-	iov_iter_init(iter, rw, iovec, 1, len);
-	return 0;
-}
-
 /*
  * aio_run_iocb:
  *	Performs the initial checks and io submission.
@@ -1434,8 +1419,7 @@ rw_common:
 			ret = aio_setup_vectored_rw(rw, buf, len,
 						&iovec, compat, &iter);
 		else
-			ret = aio_setup_single_vector(rw, buf, len,
-						iovec, &iter);
+			ret = import_single_range(rw, buf, len, iovec, &iter);
 		if (!ret)
 			ret = rw_verify_area(rw, file, &req->ki_pos,
 					     iov_iter_count(&iter));

From 345995fa48c599210fd339a768eb68dead430b79 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 19:17:55 -0400
Subject: [PATCH 27/35] vmsplice_to_user(): switch to import_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/splice.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/fs/splice.c b/fs/splice.c
index 4bbfa95b5bfe..41cbb16299e0 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1533,34 +1533,29 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	ssize_t count;
 
 	pipe = get_pipe_info(file);
 	if (!pipe)
 		return -EBADF;
 
-	ret = rw_copy_check_uvector(READ, uiov, nr_segs,
-				    ARRAY_SIZE(iovstack), iovstack, &iov);
-	if (ret <= 0)
-		goto out;
-
-	count = ret;
-	iov_iter_init(&iter, READ, iov, nr_segs, count);
+	ret = import_iovec(READ, uiov, nr_segs,
+			   ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		return ret;
 
+	sd.total_len = iov_iter_count(&iter);
 	sd.len = 0;
-	sd.total_len = count;
 	sd.flags = flags;
 	sd.u.data = &iter;
 	sd.pos = 0;
 
-	pipe_lock(pipe);
-	ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
-	pipe_unlock(pipe);
-
-out:
-	if (iov != iovstack)
-		kfree(iov);
+	if (sd.total_len) {
+		pipe_lock(pipe);
+		ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
+		pipe_unlock(pipe);
+	}
 
+	kfree(iov);
 	return ret;
 }
 

From 32a56afa23e157b444b6c2b943322ea0d119517b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 19:34:53 -0400
Subject: [PATCH 28/35] aio_setup_vectored_rw(): switch to
 {compat_,}import_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 3dba5a70ad97..3b8467aeb5ee 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1357,23 +1357,14 @@ static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
 				 bool compat,
 				 struct iov_iter *iter)
 {
-	ssize_t ret;
-
 #ifdef CONFIG_COMPAT
 	if (compat)
-		ret = compat_rw_copy_check_uvector(rw,
+		return compat_import_iovec(rw,
 				(struct compat_iovec __user *)buf,
-				len, UIO_FASTIOV, *iovec, iovec);
-	else
+				len, UIO_FASTIOV, iovec, iter);
 #endif
-		ret = rw_copy_check_uvector(rw,
-				(struct iovec __user *)buf,
-				len, UIO_FASTIOV, *iovec, iovec);
-	if (ret < 0)
-		return ret;
-
-	iov_iter_init(iter, rw, *iovec, len, ret);
-	return 0;
+	return import_iovec(rw, (struct iovec __user *)buf,
+				len, UIO_FASTIOV, iovec, iter);
 }
 
 /*
@@ -1418,14 +1409,15 @@ rw_common:
 		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
 			ret = aio_setup_vectored_rw(rw, buf, len,
 						&iovec, compat, &iter);
-		else
+		else {
 			ret = import_single_range(rw, buf, len, iovec, &iter);
+			iovec = NULL;
+		}
 		if (!ret)
 			ret = rw_verify_area(rw, file, &req->ki_pos,
 					     iov_iter_count(&iter));
 		if (ret < 0) {
-			if (iovec != inline_vecs)
-				kfree(iovec);
+			kfree(iovec);
 			return ret;
 		}
 
@@ -1449,6 +1441,7 @@ rw_common:
 
 		if (rw == WRITE)
 			file_end_write(file);
+		kfree(iovec);
 		break;
 
 	case IOCB_CMD_FDSYNC:
@@ -1470,9 +1463,6 @@ rw_common:
 		return -EINVAL;
 	}
 
-	if (iovec != inline_vecs)
-		kfree(iovec);
-
 	if (ret != -EIOCBQUEUED) {
 		/*
 		 * There's no easy way to restart the syscall since other AIO's

From 0504c074b546651f19f23a214b76d145d3a0f5af Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 19:40:11 -0400
Subject: [PATCH 29/35] switch {compat_,}do_readv_writev() to
 {compat_,}import_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 11980f164432..69128b378646 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -842,13 +842,14 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	iov_fn_t fnv;
 	iter_fn_t iter_fn;
 
-	ret = rw_copy_check_uvector(type, uvector, nr_segs,
-				    ARRAY_SIZE(iovstack), iovstack, &iov);
-	if (ret <= 0)
-		goto out;
-	iov_iter_init(&iter, type, iov, nr_segs, ret);
+	ret = import_iovec(type, uvector, nr_segs,
+			   ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		return ret;
 
-	tot_len = ret;
+	tot_len = iov_iter_count(&iter);
+	if (!tot_len)
+		goto out;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
@@ -876,8 +877,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 		file_end_write(file);
 
 out:
-	if (iov != iovstack)
-		kfree(iov);
+	kfree(iov);
 	if ((ret + (type == READ)) > 0) {
 		if (type == READ)
 			fsnotify_access(file);
@@ -1022,13 +1022,14 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	iov_fn_t fnv;
 	iter_fn_t iter_fn;
 
-	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
-					       UIO_FASTIOV, iovstack, &iov);
-	if (ret <= 0)
-		goto out;
-	iov_iter_init(&iter, type, iov, nr_segs, ret);
+	ret = compat_import_iovec(type, uvector, nr_segs,
+				  UIO_FASTIOV, &iov, &iter);
+	if (ret < 0)
+		return ret;
 
-	tot_len = ret;
+	tot_len = iov_iter_count(&iter);
+	if (!tot_len)
+		goto out;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
@@ -1056,8 +1057,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 		file_end_write(file);
 
 out:
-	if (iov != iovstack)
-		kfree(iov);
+	kfree(iov);
 	if ((ret + (type == READ)) > 0) {
 		if (type == READ)
 			fsnotify_access(file);

From b353a1f7bbd6c015e8563e902f7c78710348e28f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 17 Mar 2015 09:59:38 -0400
Subject: [PATCH 30/35] switch keyctl_instantiate_key_common() to iov_iter

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 security/keys/compat.c   | 27 +++++---------
 security/keys/internal.h |  5 +--
 security/keys/keyctl.c   | 78 ++++++++++++++--------------------------
 3 files changed, 39 insertions(+), 71 deletions(-)

diff --git a/security/keys/compat.c b/security/keys/compat.c
index 347896548ad3..25430a3aa7f7 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -31,30 +31,21 @@ static long compat_keyctl_instantiate_key_iov(
 	key_serial_t ringid)
 {
 	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	struct iov_iter from;
 	long ret;
 
-	if (!_payload_iov || !ioc)
-		goto no_payload;
+	if (!_payload_iov)
+		ioc = 0;
 
-	ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc,
-					   ARRAY_SIZE(iovstack),
-					   iovstack, &iov);
+	ret = compat_import_iovec(WRITE, _payload_iov, ioc,
+				  ARRAY_SIZE(iovstack), &iov,
+				  &from);
 	if (ret < 0)
-		goto err;
-	if (ret == 0)
-		goto no_payload_free;
+		return ret;
 
-	ret = keyctl_instantiate_key_common(id, iov, ioc, ret, ringid);
-err:
-	if (iov != iovstack)
-		kfree(iov);
+	ret = keyctl_instantiate_key_common(id, &from, ringid);
+	kfree(iov);
 	return ret;
-
-no_payload_free:
-	if (iov != iovstack)
-		kfree(iov);
-no_payload:
-	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
 }
 
 /*
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 200e37867336..5105c2c2da75 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -243,9 +243,10 @@ extern long keyctl_instantiate_key_iov(key_serial_t,
 				       unsigned, key_serial_t);
 extern long keyctl_invalidate_key(key_serial_t);
 
+struct iov_iter;
 extern long keyctl_instantiate_key_common(key_serial_t,
-					  const struct iovec *,
-					  unsigned, size_t, key_serial_t);
+					  struct iov_iter *,
+					  key_serial_t);
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 extern long keyctl_get_persistent(uid_t, key_serial_t);
 extern unsigned persistent_keyring_expiry;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 4743d71e4aa6..0b9ec78a7a7a 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -997,21 +997,6 @@ static int keyctl_change_reqkey_auth(struct key *key)
 	return commit_creds(new);
 }
 
-/*
- * Copy the iovec data from userspace
- */
-static long copy_from_user_iovec(void *buffer, const struct iovec *iov,
-				 unsigned ioc)
-{
-	for (; ioc > 0; ioc--) {
-		if (copy_from_user(buffer, iov->iov_base, iov->iov_len) != 0)
-			return -EFAULT;
-		buffer += iov->iov_len;
-		iov++;
-	}
-	return 0;
-}
-
 /*
  * Instantiate a key with the specified payload and link the key into the
  * destination keyring if one is given.
@@ -1022,20 +1007,21 @@ static long copy_from_user_iovec(void *buffer, const struct iovec *iov,
  * If successful, 0 will be returned.
  */
 long keyctl_instantiate_key_common(key_serial_t id,
-				   const struct iovec *payload_iov,
-				   unsigned ioc,
-				   size_t plen,
+				   struct iov_iter *from,
 				   key_serial_t ringid)
 {
 	const struct cred *cred = current_cred();
 	struct request_key_auth *rka;
 	struct key *instkey, *dest_keyring;
+	size_t plen = from ? iov_iter_count(from) : 0;
 	void *payload;
 	long ret;
-	bool vm = false;
 
 	kenter("%d,,%zu,%d", id, plen, ringid);
 
+	if (!plen)
+		from = NULL;
+
 	ret = -EINVAL;
 	if (plen > 1024 * 1024 - 1)
 		goto error;
@@ -1054,20 +1040,19 @@ long keyctl_instantiate_key_common(key_serial_t id,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
-	if (payload_iov) {
+	if (from) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
 		if (!payload) {
 			if (plen <= PAGE_SIZE)
 				goto error;
-			vm = true;
 			payload = vmalloc(plen);
 			if (!payload)
 				goto error;
 		}
 
-		ret = copy_from_user_iovec(payload, payload_iov, ioc);
-		if (ret < 0)
+		ret = -EFAULT;
+		if (copy_from_iter(payload, plen, from) != plen)
 			goto error2;
 	}
 
@@ -1089,10 +1074,7 @@ long keyctl_instantiate_key_common(key_serial_t id,
 		keyctl_change_reqkey_auth(NULL);
 
 error2:
-	if (!vm)
-		kfree(payload);
-	else
-		vfree(payload);
+	kvfree(payload);
 error:
 	return ret;
 }
@@ -1112,15 +1094,19 @@ long keyctl_instantiate_key(key_serial_t id,
 			    key_serial_t ringid)
 {
 	if (_payload && plen) {
-		struct iovec iov[1] = {
-			[0].iov_base = (void __user *)_payload,
-			[0].iov_len  = plen
-		};
+		struct iovec iov;
+		struct iov_iter from;
+		int ret;
 
-		return keyctl_instantiate_key_common(id, iov, 1, plen, ringid);
+		ret = import_single_range(WRITE, (void __user *)_payload, plen,
+					  &iov, &from);
+		if (unlikely(ret))
+			return ret;
+
+		return keyctl_instantiate_key_common(id, &from, ringid);
 	}
 
-	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
+	return keyctl_instantiate_key_common(id, NULL, ringid);
 }
 
 /*
@@ -1138,29 +1124,19 @@ long keyctl_instantiate_key_iov(key_serial_t id,
 				key_serial_t ringid)
 {
 	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	struct iov_iter from;
 	long ret;
 
-	if (!_payload_iov || !ioc)
-		goto no_payload;
+	if (!_payload_iov)
+		ioc = 0;
 
-	ret = rw_copy_check_uvector(WRITE, _payload_iov, ioc,
-				    ARRAY_SIZE(iovstack), iovstack, &iov);
+	ret = import_iovec(WRITE, _payload_iov, ioc,
+				    ARRAY_SIZE(iovstack), &iov, &from);
 	if (ret < 0)
-		goto err;
-	if (ret == 0)
-		goto no_payload_free;
-
-	ret = keyctl_instantiate_key_common(id, iov, ioc, ret, ringid);
-err:
-	if (iov != iovstack)
-		kfree(iov);
+		return ret;
+	ret = keyctl_instantiate_key_common(id, &from, ringid);
+	kfree(iov);
 	return ret;
-
-no_payload_free:
-	if (iov != iovstack)
-		kfree(iov);
-no_payload:
-	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
 }
 
 /*

From 17d17e728224f69311675e2ff312e992b7cc7b1e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 14:47:11 -0400
Subject: [PATCH 31/35] process_vm_access: switch to {compat_,}import_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 mm/process_vm_access.c | 35 ++++++++++++-----------------------
 1 file changed, 12 insertions(+), 23 deletions(-)

diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index b1597690530c..e88d071648c2 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -257,22 +257,18 @@ static ssize_t process_vm_rw(pid_t pid,
 	struct iovec *iov_r = iovstack_r;
 	struct iov_iter iter;
 	ssize_t rc;
+	int dir = vm_write ? WRITE : READ;
 
 	if (flags != 0)
 		return -EINVAL;
 
 	/* Check iovecs */
-	if (vm_write)
-		rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV,
-					   iovstack_l, &iov_l);
-	else
-		rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV,
-					   iovstack_l, &iov_l);
-	if (rc <= 0)
+	rc = import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter);
+	if (rc < 0)
+		return rc;
+	if (!iov_iter_count(&iter))
 		goto free_iovecs;
 
-	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
-
 	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
 				   iovstack_r, &iov_r);
 	if (rc <= 0)
@@ -283,8 +279,7 @@ static ssize_t process_vm_rw(pid_t pid,
 free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
-	if (iov_l != iovstack_l)
-		kfree(iov_l);
+	kfree(iov_l);
 
 	return rc;
 }
@@ -320,21 +315,16 @@ compat_process_vm_rw(compat_pid_t pid,
 	struct iovec *iov_r = iovstack_r;
 	struct iov_iter iter;
 	ssize_t rc = -EFAULT;
+	int dir = vm_write ? WRITE : READ;
 
 	if (flags != 0)
 		return -EINVAL;
 
-	if (vm_write)
-		rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
-						  UIO_FASTIOV, iovstack_l,
-						  &iov_l);
-	else
-		rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt,
-						  UIO_FASTIOV, iovstack_l,
-						  &iov_l);
-	if (rc <= 0)
+	rc = compat_import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter);
+	if (rc < 0)
+		return rc;
+	if (!iov_iter_count(&iter))
 		goto free_iovecs;
-	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
 	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
 					  UIO_FASTIOV, iovstack_r,
 					  &iov_r);
@@ -346,8 +336,7 @@ compat_process_vm_rw(compat_pid_t pid,
 free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
-	if (iov_l != iovstack_l)
-		kfree(iov_l);
+	kfree(iov_l);
 	return rc;
 }
 

From e272b89ff8fb63902294ba6eadd14729e2880ade Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 20:02:55 -0400
Subject: [PATCH 32/35] sg_io(): use import_iovec()

... and don't skip access_ok() validation.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/scsi_ioctl.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index e1f71c396193..55b6f15dac90 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -335,16 +335,14 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 
-		ret = rw_copy_check_uvector(-1, hdr->dxferp, hdr->iovec_count,
-					    0, NULL, &iov);
-		if (ret < 0) {
-			kfree(iov);
+		ret = import_iovec(rq_data_dir(rq),
+				   hdr->dxferp, hdr->iovec_count,
+				   0, &iov, &i);
+		if (ret < 0)
 			goto out_free_cdb;
-		}
 
 		/* SG_IO howto says that the shorter of the two wins */
-		iov_iter_init(&i, rq_data_dir(rq), iov, hdr->iovec_count,
-			      min_t(unsigned, ret, hdr->dxfer_len));
+		iov_iter_truncate(&i, hdr->dxfer_len);
 
 		ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL);
 		kfree(iov);

From 8f7e885a4cc167f8b1931800fa1319772ae4b11d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 20:06:04 -0400
Subject: [PATCH 33/35] blk_rq_map_user(): use import_single_range()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/blk-map.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index b8d2725324a6..da310a105429 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -124,10 +124,10 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 {
 	struct iovec iov;
 	struct iov_iter i;
+	int ret = import_single_range(rq_data_dir(rq), ubuf, len, &iov, &i);
 
-	iov.iov_base = ubuf;
-	iov.iov_len = len;
-	iov_iter_init(&i, rq_data_dir(rq), &iov, 1, len);
+	if (unlikely(ret < 0))
+		return ret;
 
 	return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask);
 }

From 451a2886b6bf90e2fb378f7c46c655450fb96e81 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 20:08:18 -0400
Subject: [PATCH 34/35] sg_start_req(): make sure that there's not too many
 elements in iovec

unfortunately, allowing an arbitrary 16bit value means a possibility of
overflow in the calculation of total number of pages in bio_map_user_iov() -
we rely on there being no more than PAGE_SIZE members of sum in the
first loop there.  If that sum wraps around, we end up allocating
too small array of pointers to pages and it's easy to overflow it in
the second loop.

X-Coverup: TINC (and there's no lumber cartel either)
Cc: stable@vger.kernel.org # way, way back
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/scsi/sg.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index d383f84869aa..b5a4db883223 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1744,6 +1744,9 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			md->from_user = 0;
 	}
 
+	if (unlikely(iov_count > MAX_UIOVEC))
+		return -EINVAL;
+
 	if (iov_count) {
 		int size = sizeof(struct iovec) * iov_count;
 		struct iovec *iov;

From fdc81f45e9f57858da6351836507fbcf1b7583ee Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Mar 2015 20:25:30 -0400
Subject: [PATCH 35/35] sg_start_req(): use import_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/scsi/sg.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index b5a4db883223..9d7b7db75e4b 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1744,21 +1744,15 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			md->from_user = 0;
 	}
 
-	if (unlikely(iov_count > MAX_UIOVEC))
-		return -EINVAL;
-
 	if (iov_count) {
-		int size = sizeof(struct iovec) * iov_count;
-		struct iovec *iov;
+		struct iovec *iov = NULL;
 		struct iov_iter i;
 
-		iov = memdup_user(hp->dxferp, size);
-		if (IS_ERR(iov))
-			return PTR_ERR(iov);
+		res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
+		if (res < 0)
+			return res;
 
-		iov_iter_init(&i, rw, iov, iov_count,
-			      min_t(size_t, hp->dxfer_len,
-				    iov_length(iov, iov_count)));
+		iov_iter_truncate(&i, hp->dxfer_len);
 
 		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
 		kfree(iov);