1 files changed, 60 insertions, 73 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3578b25fccfd..551353b1b17a 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4685,6 +4685,10 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	if (len <= EXT_UNWRITTEN_MAX_LEN)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
@@ -4748,6 +4752,8 @@ retry:
 		goto retry;
 	}
 
+	ext4_inode_resume_unlocked_dio(inode);
+
 	return ret > 0 ? ret2 : ret;
 }
 
@@ -4764,6 +4770,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
+	struct address_space *mapping = inode->i_mapping;
 	unsigned int blkbits = inode->i_blkbits;
 
 	trace_ext4_zero_range(inode, offset, len, mode);
@@ -4779,6 +4786,17 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	/*
+	 * Write out all dirty pages to avoid race conditions
+	 * Then release them.
+	 */
+	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		ret = filemap_write_and_wait_range(mapping, offset,
+						   offset + len - 1);
+		if (ret)
+			return ret;
+	}
+
+	/*
 	 * Round up offset. This is not fallocate, we neet to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
@@ -4821,10 +4839,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
-
 	/* Preallocate the range including the unaligned edges */
 	if (partial_begin || partial_end) {
 		ret = ext4_alloc_file_blocks(file,
@@ -4833,7 +4847,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 				 round_down(offset, 1 << blkbits)) >> blkbits,
 				new_size, flags, mode);
 		if (ret)
-			goto out_dio;
+			goto out_mutex;
 
 	}
 
@@ -4842,23 +4856,16 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
 			  EXT4_EX_NOCACHE);
 
-		/*
-		 * Prevent page faults from reinstantiating pages we have
-		 * released from page cache.
-		 */
-		down_write(&EXT4_I(inode)->i_mmap_sem);
-		ret = ext4_update_disksize_before_punch(inode, offset, len);
-		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
-			goto out_dio;
-		}
-		/* Now release the pages and zero block aligned part of pages */
+		/* Now release the pages and zero block aligned part of pages*/
 		truncate_pagecache_range(inode, start, end - 1);
 		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
+		/* Wait all existing dio workers, newcomers will block on i_mutex */
+		ext4_inode_block_unlocked_dio(inode);
+		inode_dio_wait(inode);
+
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags, mode);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
 		if (ret)
 			goto out_dio;
 	}
@@ -4991,13 +4998,8 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
-
 	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 				     flags, mode);
-	ext4_inode_resume_unlocked_dio(inode);
 	if (ret)
 		goto out;
 
@@ -5492,7 +5494,21 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
+	/*
+	 * Need to round down offset to be aligned with page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+
+	/* Write out all dirty pages */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+					   LLONG_MAX);
+	if (ret)
+		return ret;
+
+	/* Take mutex lock */
 	mutex_lock(&inode->i_mutex);
+
 	/*
 	 * There is no need to overlap collapse range with EOF, in which case
 	 * it is effectively a truncate operation
@@ -5508,43 +5524,17 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
+	truncate_pagecache(inode, ioffset);
+
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
-	/*
-	 * Prevent page faults from reinstantiating pages we have released from
-	 * page cache.
-	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
-	/*
-	 * Need to round down offset to be aligned with page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-	/*
-	 * Write tail of the last page before removed range since it will get
-	 * removed from the page cache below.
-	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
-	if (ret)
-		goto out_mmap;
-	/*
-	 * Write data that will be shifted to preserve them when discarding
-	 * page cache below. We are also protected from pages becoming dirty
-	 * by i_mmap_sem.
-	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
-					   LLONG_MAX);
-	if (ret)
-		goto out_mmap;
-	truncate_pagecache(inode, ioffset);
-
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_mmap;
+		goto out_dio;
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -5583,8 +5573,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+out_dio:
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
@@ -5638,7 +5627,21 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
+	/*
+	 * Need to round down to align start offset to page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+
+	/* Write out all dirty pages */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+			LLONG_MAX);
+	if (ret)
+		return ret;
+
+	/* Take mutex lock */
 	mutex_lock(&inode->i_mutex);
+
 	/* Currently just for extent based files */
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		ret = -EOPNOTSUPP;
@@ -5657,32 +5660,17 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
+	truncate_pagecache(inode, ioffset);
+
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
-	/*
-	 * Prevent page faults from reinstantiating pages we have released from
-	 * page cache.
-	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
-	/*
-	 * Need to round down to align start offset to page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-			LLONG_MAX);
-	if (ret)
-		goto out_mmap;
-	truncate_pagecache(inode, ioffset);
-
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_mmap;
+		goto out_dio;
 	}
 
 	/* Expand file to avoid data loss if there is error while shifting */
@@ -5753,8 +5741,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+out_dio:
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);