Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: partial revert to fix double brelse WARNING()
  ext4: Fix return value of ext4_split_unwritten_extents() to fix direct I/O
  ext4: code clean up for dio fallocate handling
  ext4: skip conversion of uninit extents after direct IO if there isn't any
  ext4: fix ext4_ext_direct_IO()'s return value after converting uninit extents
  ext4: discard preallocation when restarting a transaction during truncate

4 files changed, 45 insertions, 32 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 00d153f..8825515 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -322,6 +322,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 #define EXT4_STATE_NO_EXPAND		0x00000008 /* No space for expansion */
 #define EXT4_STATE_DA_ALLOC_CLOSE	0x00000010 /* Alloc DA blks on close */
 #define EXT4_STATE_EXT_MIGRATE		0x00000020 /* Inode is migrating */
+#define EXT4_STATE_DIO_UNWRITTEN	0x00000040 /* need convert on dio done*/
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext4_new_group_input {
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 10539e3..715264b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2807,6 +2807,8 @@ fix_extent_len:
  * into three uninitialized extent(at most). After IO complete, the part
  * being filled will be convert to initialized by the end_io callback function
  * via ext4_convert_unwritten_extents().
+ *
+ * Returns the size of uninitialized extent to be written on success.
  */
 static int ext4_split_unwritten_extents(handle_t *handle,
 					struct inode *inode,
@@ -2824,7 +2826,6 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 	unsigned int allocated, ee_len, depth;
 	ext4_fsblk_t newblock;
 	int err = 0;
-	int ret = 0;
 
 	ext_debug("ext4_split_unwritten_extents: inode %lu,"
 		  "iblock %llu, max_blocks %u\n", inode->i_ino,
@@ -2842,12 +2843,12 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 	ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
 
 	/*
- 	 * if the entire unintialized extent length less than
- 	 * the size of extent to write, there is no need to split
- 	 * uninitialized extent
+ 	 * If the uninitialized extent begins at the same logical
+ 	 * block where the write begins, and the write completely
+ 	 * covers the extent, then we don't need to split it.
  	 */
- 	if (allocated <= max_blocks)
-		return ret;
+	if ((iblock == ee_block) && (allocated <= max_blocks))
+		return allocated;
 
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
@@ -3048,12 +3049,18 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		ret = ext4_split_unwritten_extents(handle,
 						inode, path, iblock,
 						max_blocks, flags);
-		/* flag the io_end struct that we need convert when IO done */
+		/*
+		 * Flag the inode(non aio case) or end_io struct (aio case)
+		 * that this IO needs to convertion to written when IO is
+		 * completed
+		 */
 		if (io)
 			io->flag = DIO_AIO_UNWRITTEN;
+		else
+			EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
 		goto out;
 	}
-	/* DIO end_io complete, convert the filled extent to written */
+	/* async DIO end_io complete, convert the filled extent to written */
 	if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
 		ret = ext4_convert_unwritten_extents_dio(handle, inode,
 							path);
@@ -3295,10 +3302,16 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 		 * To avoid unecessary convertion for every aio dio rewrite
 		 * to the mid of file, here we flag the IO that is really
 		 * need the convertion.
-		 *
+		 * For non asycn direct IO case, flag the inode state
+		 * that we need to perform convertion when IO is done.
 		 */
-		if (io && flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT)
-			io->flag = DIO_AIO_UNWRITTEN;
+		if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+			if (io)
+				io->flag = DIO_AIO_UNWRITTEN;
+			else
+				EXT4_I(inode)->i_state |=
+					EXT4_STATE_DIO_UNWRITTEN;;
+		}
 	}
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err) {
@@ -3519,6 +3532,7 @@ retry:
  *
  * This function is called from the direct IO end io call back
  * function, to convert the fallocated extents after IO is completed.
+ * Returns 0 on success.
  */
 int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 				    loff_t len)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5c5bc5d..2c8caa5 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -193,7 +193,7 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
  * so before we call here everything must be consistently dirtied against
  * this transaction.
  */
- int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
 				 int nblocks)
 {
 	int ret;
@@ -209,6 +209,7 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
 	down_write(&EXT4_I(inode)->i_data_sem);
+	ext4_discard_preallocations(inode);
 
 	return ret;
 }
@@ -3445,8 +3446,6 @@ out:
 	return ret;
 }
 
-/* Maximum number of blocks we map for direct IO at once. */
-
 static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create)
 {
@@ -3654,13 +3653,14 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
         ext4_io_end_t *io_end = iocb->private;
 	struct workqueue_struct *wq;
 
+	/* if not async direct IO or dio with 0 bytes write, just return */
+	if (!io_end || !size)
+		return;
+
 	ext_debug("ext4_end_io_dio(): io_end 0x%p"
 		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
  		  iocb->private, io_end->inode->i_ino, iocb, offset,
 		  size);
-	/* if not async direct IO or dio with 0 bytes write, just return */
-	if (!io_end || !size)
-		return;
 
 	/* if not aio dio with unwritten extents, just free io and return */
 	if (io_end->flag != DIO_AIO_UNWRITTEN){
@@ -3771,13 +3771,19 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
 			ext4_free_io_end(iocb->private);
 			iocb->private = NULL;
-		} else if (ret > 0)
+		} else if (ret > 0 && (EXT4_I(inode)->i_state &
+				       EXT4_STATE_DIO_UNWRITTEN)) {
+			int err;
 			/*
 			 * for non AIO case, since the IO is already
 			 * completed, we could do the convertion right here
 			 */
-			ret = ext4_convert_unwritten_extents(inode,
-								offset, ret);
+			err = ext4_convert_unwritten_extents(inode,
+							     offset, ret);
+			if (err < 0)
+				ret = err;
+			EXT4_I(inode)->i_state &= ~EXT4_STATE_DIO_UNWRITTEN;
+		}
 		return ret;
 	}
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 7c8fe80..6d2c1b8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1518,12 +1518,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 			return retval;
 
 		if (blocks == 1 && !dx_fallback &&
-		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
-			retval = make_indexed_dir(handle, dentry, inode, bh);
-			if (retval == -ENOSPC)
-				brelse(bh);
-			return retval;
-		}
+		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
+			return make_indexed_dir(handle, dentry, inode, bh);
 		brelse(bh);
 	}
 	bh = ext4_append(handle, dir, &block, &retval);
@@ -1532,10 +1528,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	de->inode = 0;
 	de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
-	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
-	if (retval == -ENOSPC)
-		brelse(bh);
-	return retval;
+	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
 
 /*
@@ -1664,8 +1657,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	if (!de)
 		goto cleanup;
 	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
-	if (err != -ENOSPC)
-		bh = NULL;
+	bh = NULL;
 	goto cleanup;
 
 journal_error: