[11/12] ceph: Fix race between hole punch and page fault

Commit Message

Jan Kara April 23, 2021, 5:29 p.m. UTC

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 <[e-mail]>
CC: [e-mail]
Signed-off-by: Jan Kara <[e-mail]>
---
 fs/ceph/addr.c | 9 ++++++---
 fs/ceph/file.c | 2 ++
 2 files changed, 8 insertions(+), 3 deletions(-)

Patch

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 26e66436f005..4f45e9754b5a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1519,9 +1519,11 @@  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;
+
+		down_read(&mapping->invalidate_lock);
+		page = find_or_create_page(mapping, 0,
+				mapping_gfp_constraint(mapping, ~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out_inline;
@@ -1542,6 +1544,7 @@  static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		vmf->page = page;
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
+		up_read(&mapping->invalidate_lock);
 		dout("filemap_fault %p %llu~%zd read inline data ret %x\n",
 		     inode, off, (size_t)PAGE_SIZE, ret);
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 209535d5b8d3..40fee8ff5cf9 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2087,6 +2087,7 @@  static long ceph_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		goto unlock;
 
+	down_write(&inode->i_mapping->invalidate_lock);
 	ceph_zero_pagecache_range(inode, offset, length);
 	ret = ceph_zero_objects(inode, offset, length);
 
@@ -2099,6 +2100,7 @@  static long ceph_fallocate(struct file *file, int mode,
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
 	}
+	up_write(&inode->i_mapping->invalidate_lock);
 
 	ceph_put_cap_refs(ci, got);
 unlock: