Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull third hunk of vfs changes from Al Viro:
 "This contains the ->direct_IO() changes from Omar + saner
  generic_write_checks() + dealing with fcntl()/{read,write}() races
  (mirroring O_APPEND/O_DIRECT into iocb->ki_flags and instead of
  repeatedly looking at ->f_flags, which can be changed by fcntl(2),
  check ->ki_flags - which cannot) + infrastructure bits for dhowells'
  d_inode annotations + Christophs switch of /dev/loop to
  vfs_iter_write()"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (30 commits)
  block: loop: switch to VFS ITER_BVEC
  configfs: Fix inconsistent use of file_inode() vs file->f_path.dentry->d_inode
  VFS: Make pathwalk use d_is_reg() rather than S_ISREG()
  VFS: Fix up debugfs to use d_is_dir() in place of S_ISDIR()
  VFS: Combine inode checks with d_is_negative() and d_is_positive() in pathwalk
  NFS: Don't use d_inode as a variable name
  VFS: Impose ordering on accesses of d_inode and d_flags
  VFS: Add owner-filesystem positive/negative dentry checks
  nfs: generic_write_checks() shouldn't be done on swapout...
  ocfs2: use __generic_file_write_iter()
  mirror O_APPEND and O_DIRECT into iocb->ki_flags
  switch generic_write_checks() to iocb and iter
  ocfs2: move generic_write_checks() before the alignment checks
  ocfs2_file_write_iter: stop messing with ppos
  udf_file_write_iter: reorder and simplify
  fuse: ->direct_IO() doesn't need generic_write_checks()
  ext4_file_write_iter: move generic_write_checks() up
  xfs_file_aio_write_checks: switch to iocb/iov_iter
  generic_write_checks(): drop isblk argument
  blkdev_write_iter: expand generic_file_checks() call in there
  ...

4 files changed, 46 insertions, 44 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8a3981e..c8eb32e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2152,8 +2152,8 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-				struct iov_iter *iter, loff_t offset);
+extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				  loff_t offset);
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 7a6defc..e576d68 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -95,11 +95,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int o_direct = io_is_direct(file);
+	int o_direct = iocb->ki_flags & IOCB_DIRECT;
 	int overwrite = 0;
-	size_t length = iov_iter_count(from);
 	ssize_t ret;
-	loff_t pos = iocb->ki_pos;
 
 	/*
 	 * Unaligned direct AIO must be serialized; see comment above
@@ -108,16 +106,17 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (o_direct &&
 	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
 	    !is_sync_kiocb(iocb) &&
-	    (file->f_flags & O_APPEND ||
-	     ext4_unaligned_aio(inode, from, pos))) {
+	    (iocb->ki_flags & IOCB_APPEND ||
+	     ext4_unaligned_aio(inode, from, iocb->ki_pos))) {
 		aio_mutex = ext4_aio_mutex(inode);
 		mutex_lock(aio_mutex);
 		ext4_unwritten_wait(inode);
 	}
 
 	mutex_lock(&inode->i_mutex);
-	if (file->f_flags & O_APPEND)
-		iocb->ki_pos = pos = i_size_read(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
 
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
@@ -126,22 +125,19 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-		if ((pos > sbi->s_bitmap_maxbytes) ||
-		    (pos == sbi->s_bitmap_maxbytes && length > 0)) {
-			mutex_unlock(&inode->i_mutex);
+		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes) {
 			ret = -EFBIG;
-			goto errout;
+			goto out;
 		}
-
-		if (pos + length > sbi->s_bitmap_maxbytes)
-			iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
+		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
 	}
 
 	iocb->private = &overwrite;
 	if (o_direct) {
+		size_t length = iov_iter_count(from);
+		loff_t pos = iocb->ki_pos;
 		blk_start_plug(&plug);
 
-
 		/* check whether we do a DIO overwrite or not */
 		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
 		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
@@ -185,7 +181,12 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (o_direct)
 		blk_finish_plug(&plug);
 
-errout:
+	if (aio_mutex)
+		mutex_unlock(aio_mutex);
+	return ret;
+
+out:
+	mutex_unlock(&inode->i_mutex);
 	if (aio_mutex)
 		mutex_unlock(aio_mutex);
 	return ret;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 740c787..3580629e 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -642,8 +642,8 @@ out:
  * crashes then stale disk data _may_ be exposed inside the file. But current
  * VFS code falls back into buffered path in that case so we are safe.
  */
-ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-			   struct iov_iter *iter, loff_t offset)
+ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			   loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -654,7 +654,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	int retries = 0;
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		loff_t final_size = offset + count;
 
 		if (final_size > inode->i_size) {
@@ -676,7 +676,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+	if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) {
 		/*
 		 * Nolock dioread optimization may be dynamically disabled
 		 * via ext4_inode_block_unlocked_dio(). Check inode's state
@@ -690,23 +690,24 @@ retry:
 			goto locked;
 		}
 		if (IS_DAX(inode))
-			ret = dax_do_io(rw, iocb, inode, iter, offset,
+			ret = dax_do_io(iocb, inode, iter, offset,
 					ext4_get_block, NULL, 0);
 		else
-			ret = __blockdev_direct_IO(rw, iocb, inode,
-					inode->i_sb->s_bdev, iter, offset,
-					ext4_get_block, NULL, NULL, 0);
+			ret = __blockdev_direct_IO(iocb, inode,
+						   inode->i_sb->s_bdev, iter,
+						   offset, ext4_get_block, NULL,
+						   NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
 		if (IS_DAX(inode))
-			ret = dax_do_io(rw, iocb, inode, iter, offset,
+			ret = dax_do_io(iocb, inode, iter, offset,
 					ext4_get_block, NULL, DIO_LOCKING);
 		else
-			ret = blockdev_direct_IO(rw, iocb, inode, iter,
-					offset, ext4_get_block);
+			ret = blockdev_direct_IO(iocb, inode, iter, offset,
+						 ext4_get_block);
 
-		if (unlikely((rw & WRITE) && ret < 0)) {
+		if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 			loff_t isize = i_size_read(inode);
 			loff_t end = offset + count;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 035b7a0..b49cf6e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2952,8 +2952,8 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
  * if the machine crashes during the write.
  *
  */
-static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter, loff_t offset)
+static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				  loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -2966,8 +2966,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
-	if (rw != WRITE || final_size > inode->i_size)
-		return ext4_ind_direct_IO(rw, iocb, iter, offset);
+	if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
+		return ext4_ind_direct_IO(iocb, iter, offset);
 
 	BUG_ON(iocb->private == NULL);
 
@@ -2976,7 +2976,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	 * conversion. This also disallows race between truncate() and
 	 * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
 	 */
-	if (rw == WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		atomic_inc(&inode->i_dio_count);
 
 	/* If we do a overwrite dio, i_mutex locking can be released */
@@ -3034,10 +3034,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		dio_flags = DIO_LOCKING;
 	}
 	if (IS_DAX(inode))
-		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+		ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
 				ext4_end_io_dio, dio_flags);
 	else
-		ret = __blockdev_direct_IO(rw, iocb, inode,
+		ret = __blockdev_direct_IO(iocb, inode,
 					   inode->i_sb->s_bdev, iter, offset,
 					   get_block_func,
 					   ext4_end_io_dio, NULL, dio_flags);
@@ -3078,7 +3078,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retake_lock:
-	if (rw == WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		inode_dio_done(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
 	if (overwrite) {
@@ -3089,8 +3089,8 @@ retake_lock:
 	return ret;
 }
 
-static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter, loff_t offset)
+static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			      loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -3107,12 +3107,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
 	if (ext4_has_inline_data(inode))
 		return 0;
 
-	trace_ext4_direct_IO_enter(inode, offset, count, rw);
+	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_direct_IO(rw, iocb, iter, offset);
+		ret = ext4_ext_direct_IO(iocb, iter, offset);
 	else
-		ret = ext4_ind_direct_IO(rw, iocb, iter, offset);
-	trace_ext4_direct_IO_exit(inode, offset, count, rw, ret);
+		ret = ext4_ind_direct_IO(iocb, iter, offset);
+	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }