ext4: revert to old read/write/aio interface for 3.18 backport

Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 176 insertions, 5 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8131be8c0..5833ccfc4 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -64,6 +64,7 @@ static void ext4_unwritten_wait(struct inode *inode)
 	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
 }
 
+#if 0
 /*
  * This tests whether the IO in question is block-aligned or not.
  * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
@@ -190,10 +191,147 @@ errout:
 		mutex_unlock(aio_mutex);
 	return ret;
 }
+#endif
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete.  Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block.  If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+		   unsigned long nr_segs, loff_t pos)
+{
+	struct super_block *sb = inode->i_sb;
+	int blockmask = sb->s_blocksize - 1;
+	size_t count = iov_length(iov, nr_segs);
+	loff_t final_size = pos + count;
+
+	if (pos >= i_size_read(inode))
+		return 0;
+
+	if ((pos & blockmask) || (final_size & blockmask))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t
+ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
+		    unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct blk_plug plug;
+	int unaligned_aio = 0;
+	ssize_t ret;
+	int overwrite = 0;
+	size_t length = iov_length(iov, nr_segs);
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	    !is_sync_kiocb(iocb))
+		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+
+	/* Unaligned direct AIO must be serialized; see comment above */
+	if (unaligned_aio) {
+		mutex_lock(ext4_aio_mutex(inode));
+		ext4_unwritten_wait(inode);
+	}
+
+	BUG_ON(iocb->ki_pos != pos);
+
+	mutex_lock(&inode->i_mutex);
+	blk_start_plug(&plug);
+
+	iocb->private = &overwrite;
+
+	/* check whether we do a DIO overwrite or not */
+	if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
+	    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+		struct ext4_map_blocks map;
+		unsigned int blkbits = inode->i_blkbits;
+		int err, len;
+
+		map.m_lblk = pos >> blkbits;
+		map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+			- map.m_lblk;
+		len = map.m_len;
+
+		err = ext4_map_blocks(NULL, inode, &map, 0);
+		/*
+		 * 'err==len' means that all of blocks has been preallocated no
+		 * matter they are initialized or not.  For excluding
+		 * uninitialized extents, we need to check m_flags.  There are
+		 * two conditions that indicate for initialized extents.
+		 * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
+		 * 2) If we do a real lookup, non-flags are returned.
+		 * So we should check these two conditions.
+		 */
+		if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+			overwrite = 1;
+	}
+
+	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (ret > 0 || ret == -EIOCBQUEUED) {
+		ssize_t err;
+
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
+			ret = err;
+	}
+	blk_finish_plug(&plug);
+
+	if (unaligned_aio)
+		mutex_unlock(ext4_aio_mutex(inode));
+
+	return ret;
+}
+
+static ssize_t
+ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
+		unsigned long nr_segs, loff_t pos)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+		size_t length = iov_length(iov, nr_segs);
+
+		if ((pos > sbi->s_bitmap_maxbytes ||
+		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
+			return -EFBIG;
+
+		if (pos + length > sbi->s_bitmap_maxbytes) {
+			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
+					      sbi->s_bitmap_maxbytes - pos);
+		}
+	}
+
+	if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
+		ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
+	else
+		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+	return ret;
+}
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
+#if 0
 	.map_pages	= filemap_map_pages,
+#endif
 	.page_mkwrite   = ext4_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
@@ -402,6 +540,37 @@ out:
 	return found;
 }
 
+static inline int unsigned_offsets(struct file *file)
+{
+	return file->f_mode & FMODE_UNSIGNED_OFFSET;
+}
+
+/**
+ * vfs_setpos - update the file offset for lseek
+ * @file:	file structure in question
+ * @offset:	file offset to seek to
+ * @maxsize:	maximum file size
+ *
+ * This is a low-level filesystem helper for updating the file offset to
+ * the value specified by @offset if the given offset is valid and it is
+ * not equal to the current file offset.
+ *
+ * Return the specified offset on success and -EINVAL on invalid offset.
+ */
+static loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
+{
+	if (offset < 0 && !unsigned_offsets(file))
+		return -EINVAL;
+	if (offset > maxsize)
+		return -EINVAL;
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	return offset;
+}
+
 /*
  * ext4_seek_data() retrieves the offset for SEEK_DATA.
  */
@@ -583,10 +752,10 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 
 const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
-	.read		= new_sync_read,
-	.write		= new_sync_write,
-	.read_iter	= generic_file_read_iter,
-	.write_iter	= ext4_file_write_iter,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= ext4_file_write,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
@@ -596,7 +765,7 @@ const struct file_operations ext4_file_operations = {
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= iter_file_splice_write,
+	.splice_write	= generic_file_splice_write,
 	.fallocate	= ext4_fallocate,
 };
 
@@ -608,7 +777,9 @@ const struct inode_operations ext4_file_inode_operations = {
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
 	.get_acl	= ext4_get_acl,
+#if 0
 	.set_acl	= ext4_set_acl,
+#endif
 	.fiemap		= ext4_fiemap,
 };