ceph: choose readdir frag based on previous readdir reply

commit b50c2de5 upstream.

The dirfragtree is lazily updated, it's not always accurate. Infinite
loops happens in following circumstance.

- client send request to read frag A
- frag A has been fragmented into frag B and C. So mds fills the reply
  with contents of frag B
- client wants to read next frag C. ceph_choose_frag(frag value of C)
  return frag A.

The fix is using previous readdir reply to calculate next readdir frag
when possible.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/ceph/dir.c

@@ -294,7 +294,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int i;
 	int err;
-	u32 ftype;
+	unsigned frag = -1;
 	struct ceph_mds_reply_info_parsed *rinfo;
 
 	dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
@@ -341,7 +341,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	/* do we have the correct frag content buffered? */
 	if (need_send_readdir(fi, ctx->pos)) {
 		struct ceph_mds_request *req;
-		unsigned frag;
 		int op = ceph_snap(inode) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
 
@@ -352,6 +351,9 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		}
 
 		if (is_hash_order(ctx->pos)) {
+			/* fragtree isn't always accurate. choose frag
+			 * based on previous reply when possible. */
+			if (frag == (unsigned)-1)
 				frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
 							NULL, NULL);
 		} else {
@@ -476,6 +478,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 		struct ceph_vino vino;
 		ino_t ino;
+		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -498,15 +501,17 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos++;
 	}
 
-	if (fi->next_offset > 2) {
 	ceph_mdsc_put_request(fi->last_readdir);
 	fi->last_readdir = NULL;
+
+	if (fi->next_offset > 2) {
+		frag = fi->frag;
 		goto more;
 	}
 
 	/* more frags? */
 	if (!ceph_frag_is_rightmost(fi->frag)) {
-		unsigned frag = ceph_frag_next(fi->frag);
+		frag = ceph_frag_next(fi->frag);
 		if (is_hash_order(ctx->pos)) {
 			loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
 							fi->next_offset, true);