ext4: fix races between page faults and hole punching

Currently, page faults and hole punching are completely unsynchronized.
This can result in page fault faulting in a page into a range that we
are punching after truncate_pagecache_range() has been called and thus
we can end up with a page mapped to disk blocks that will be shortly
freed. Filesystem corruption will shortly follow. Note that the same
race is avoided for truncate by checking page fault offset against
i_size but there isn't similar mechanism available for punching holes.

Fix the problem by creating new rw semaphore i_mmap_sem in inode and
grab it for writing over truncate, hole punching, and other functions
removing blocks from extent tree and for read over page faults. We
cannot easily use i_data_sem for this since that ranks below transaction
start and we need something ranking above it so that it can be held over
the whole truncate / hole punching operation. Also remove various
workarounds we had in the code to reduce race window when page fault
could have created pages with stale mapping information.

Signed-off-by: Jan Kara <jack@suse.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 30 insertions, 24 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 551353b..5be9ca5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4770,7 +4770,6 @@ 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);
@@ -4786,17 +4785,6 @@ 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
@@ -4856,16 +4844,22 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
 			  EXT4_EX_NOCACHE);
 
-		/* 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);
 
+		/*
+		 * Prevent page faults from reinstantiating pages we have
+		 * released from page cache.
+		 */
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+		/* 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);
+
 		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;
 	}
@@ -5524,17 +5518,22 @@ 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);
+	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_dio;
+		goto out_mmap;
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -5573,7 +5572,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
@@ -5660,17 +5660,22 @@ 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);
+	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_dio;
+		goto out_mmap;
 	}
 
 	/* Expand file to avoid data loss if there is error while shifting */
@@ -5741,7 +5746,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);