ext4: return to starting transaction in ext4_dax_huge_fault()

DAX will return to locking exceptional entry before mapping blocks for a page fault to fix possible races with concurrent writes. To avoid lock inversion between exceptional entry lock and transaction start, start the transaction already in ext4_dax_huge_fault(). Fixes: 9f141d6 Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Jan Kara <[email protected]> Cc: Ross Zwisler <[email protected]> Cc: Dan Williams <[email protected]> Cc: <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
ambv · May 12, 2017 · fb26a1c · fb26a1c
1 parent cd65637
commit fb26a1c
Showing 1 changed file with 17 additions and 4 deletions.
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
@@ -257,19 +257,32 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
 	int result;
+	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vmf->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(vmf->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);
 	}
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
+	if (!IS_ERR(handle))
+		result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
+	else
+		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;
 }