ceph: Fix race between hole punch and page fault

Ceph has a following race between hole punching and page fault: CPU1 CPU2 ceph_fallocate() ... ceph_zero_pagecache_range() ceph_filemap_fault() faults in page in the range being punched ceph_zero_objects() And now we have a page in punched range with invalid data. Fix the problem by using mapping->invalidate_lock similarly to other filesystems. Note that using invalidate_lock also fixes a similar race wrt ->readpage(). CC: Jeff Layton <[email protected]> CC: [email protected] Reviewed-by: Jeff Layton <[email protected]> Signed-off-by: Jan Kara <[email protected]>
ambv · Jul 13, 2021 · 057ba5b · 057ba5b
1 parent 8bcbbe9
commit 057ba5b
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 3 deletions.
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
@@ -1395,9 +1395,11 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_SIGBUS;
 	} else {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page = find_or_create_page(mapping, 0,
-						mapping_gfp_constraint(mapping,
-						~__GFP_FS));
+		struct page *page;
+
+		filemap_invalidate_lock_shared(mapping);
+		page = find_or_create_page(mapping, 0,
+				mapping_gfp_constraint(mapping, ~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out_inline;
@@ -1418,6 +1420,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		vmf->page = page;
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
+		filemap_invalidate_unlock_shared(mapping);
 		dout("filemap_fault %p %llu read inline data ret %x\n",
 		     inode, off, ret);
 	}

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
@@ -2088,6 +2088,7 @@ static long ceph_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		goto unlock;
 
+	filemap_invalidate_lock(inode->i_mapping);
 	ceph_zero_pagecache_range(inode, offset, length);
 	ret = ceph_zero_objects(inode, offset, length);
 
@@ -2100,6 +2101,7 @@ static long ceph_fallocate(struct file *file, int mode,
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
 	}
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	ceph_put_cap_refs(ci, got);
 unlock: