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 <[e-mail]>
Signed-off-by: Theodore Ts'o <[e-mail]>

fs/ext4/ext4.h

···
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
+	/*
+	 * i_mmap_sem is for serializing page faults with truncate / punch hole
+	 * operations. We have to make sure that new page cannot be faulted in
+	 * a section of the inode that is being punched. We cannot easily use
+	 * i_data_sem for this since we need protection for the whole punch
+	 * operation and i_data_sem ranks below transaction start so we have
+	 * to occasionally drop it.
+	 */
+	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
···
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);

fs/ext4/extents.c

···
 	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);
···
 	/* Call ext4_force_commit to flush all data in case of data=journal. */
 	if (ext4_should_journal_data(inode)) {
 		ret = ext4_force_commit(inode->i_sb);
-		if (ret)
-			return ret;
-	}
-
-	/*
-	 * 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;
 	}
···
 		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;
 	}
···
 		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);
···
 
 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);
···
 		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 */
···
 
 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);

fs/ext4/file.c

···
 {
 	int result;
 	handle_t *handle = NULL;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 						EXT4_DATA_TRANS_BLOCKS(sb));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
···
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
···
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 				ext4_chunk_trans_blocks(inode,
 							PMD_SIZE / PAGE_SIZE));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
···
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
 
 static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext4_get_block_dax,
-				ext4_end_io_unwritten);
+	int err;
+	struct inode *inode = file_inode(vma->vm_file);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = __dax_mkwrite(vma, vmf, ext4_get_block_dax,
+			    ext4_end_io_unwritten);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	sb_end_pagefault(inode->i_sb);
+
+	return err;
+}
+
+/*
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * handler we check for races agaist truncate. Note that since we cycle through
+ * i_mmap_sem, we are sure that also any hole punching that began before we
+ * were called is finished by now and so if it included part of the file we
+ * are working on, our pte will get unmapped and the check for pte_same() in
+ * wp_pfn_shared() fails. Thus fault gets retried and things work out as
+ * desired.
+ */
+static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
+				struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+	int ret = VM_FAULT_NOPAGE;
+	loff_t size;
+
+	sb_start_pagefault(sb);
+	file_update_time(vma->vm_file);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	sb_end_pagefault(sb);
+
+	return ret;
 }
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
 	.page_mkwrite	= ext4_dax_mkwrite,
-	.pfn_mkwrite	= dax_pfn_mkwrite,
+	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
 #define ext4_dax_vm_ops	ext4_file_vm_ops
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= ext4_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };

fs/ext4/inode.c

···
 
 	}
 
+	/* 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);
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
···
 	if (last_block_offset > first_block_offset)
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
-
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		credits = ext4_writepage_trans_blocks(inode);
···
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	/* Now release the pages again to reduce race window */
-	if (last_block_offset > first_block_offset)
-		truncate_pagecache_range(inode, first_block_offset,
-					 last_block_offset);
-
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
···
 			} else
 				ext4_wait_for_tail_page_commit(inode);
 		}
+		down_write(&EXT4_I(inode)->i_mmap_sem);
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
···
 		truncate_pagecache(inode, inode->i_size);
 		if (shrink)
 			ext4_truncate(inode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
 	if (!rc) {
···
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
···
 out_ret:
 	ret = block_page_mkwrite_return(ret);
 out:
+	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
+}
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	int err;
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_fault(vma, vmf);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+
+	return err;
 }

fs/ext4/super.c

···
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
+	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 }
 

fs/ext4/truncate.h

···
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 }
 
 /*