ceph: Fix i_size update race

ceph_aio_write() has an optimization that marks cap EPH_CAP_FILE_WR
dirty before data is copied to page cache and inode size is updated.
If ceph_check_caps() flushes the dirty cap before the inode size is
updated, MDS can miss the new inode size. The fix is move
ceph_{get,put}_cap_refs() into ceph_write_{begin,end}() and call
__ceph_mark_dirty_caps() after inode size is updated.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Sage Weil <sage@inktank.com>

1 files changed, 47 insertions, 4 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 22b6e45..21a0718 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1078,23 +1078,51 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_file_info *fi = file->private_data;
 	struct page *page;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	int r;
+	int r, want, got = 0;
+
+	if (fi->fmode & CEPH_FILE_MODE_LAZY)
+		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
+	else
+		want = CEPH_CAP_FILE_BUFFER;
+
+	dout("write_begin %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
+	     inode, ceph_vinop(inode), pos, len, inode->i_size);
+	r = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos+len);
+	if (r < 0)
+		return r;
+	dout("write_begin %p %llx.%llx %llu~%u  got cap refs on %s\n",
+	     inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
+	if (!(got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO))) {
+		ceph_put_cap_refs(ci, got);
+		return -EAGAIN;
+	}
 
 	do {
 		/* get a page */
 		page = grab_cache_page_write_begin(mapping, index, 0);
-		if (!page)
-			return -ENOMEM;
-		*pagep = page;
+		if (!page) {
+			r = -ENOMEM;
+			break;
+		}
 
 		dout("write_begin file %p inode %p page %p %d~%d\n", file,
 		     inode, page, (int)pos, (int)len);
 
 		r = ceph_update_writeable_page(file, pos, len, page);
+		if (r)
+			page_cache_release(page);
 	} while (r == -EAGAIN);
 
+	if (r) {
+		ceph_put_cap_refs(ci, got);
+	} else {
+		*pagep = page;
+		*(int *)fsdata = got;
+	}
 	return r;
 }
 
@@ -1108,10 +1136,12 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
 	int check_cap = 0;
+	int got = (unsigned long)fsdata;
 
 	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
 	     inode, page, (int)pos, (int)copied, (int)len);
@@ -1134,6 +1164,19 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 	up_read(&mdsc->snap_rwsem);
 	page_cache_release(page);
 
+	if (copied > 0) {
+		int dirty;
+		spin_lock(&ci->i_ceph_lock);
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+		spin_unlock(&ci->i_ceph_lock);
+		if (dirty)
+			__mark_inode_dirty(inode, dirty);
+	}
+
+	dout("write_end %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
+	     inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
+	ceph_put_cap_refs(ci, got);
+
 	if (check_cap)
 		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);