Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph fixes from Sage Weil:
 "Two of Alex's patches deal with a race when reseting server
  connections for open RBD images, one demotes some non-fatal BUGs to
  WARNs, and my patch fixes a protocol feature bit failure path."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  libceph: fix protocol feature mismatch failure path
  libceph: WARN, don't BUG on unexpected connection states
  libceph: always reset osds when kicking
  libceph: move linger requests sooner in kick_requests()

1 files changed, 21 insertions, 13 deletions

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 780caf6..eb9a444 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1270,7 +1270,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
  * Requeue requests whose mapping to an OSD has changed.  If requests map to
  * no osd, request a new map.
  *
- * Caller should hold map_sem for read and request_mutex.
+ * Caller should hold map_sem for read.
  */
 static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 {
@@ -1284,6 +1284,24 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 	for (p = rb_first(&osdc->requests); p; ) {
 		req = rb_entry(p, struct ceph_osd_request, r_node);
 		p = rb_next(p);
+
+		/*
+		 * For linger requests that have not yet been
+		 * registered, move them to the linger list; they'll
+		 * be sent to the osd in the loop below.  Unregister
+		 * the request before re-registering it as a linger
+		 * request to ensure the __map_request() below
+		 * will decide it needs to be sent.
+		 */
+		if (req->r_linger && list_empty(&req->r_linger_item)) {
+			dout("%p tid %llu restart on osd%d\n",
+			     req, req->r_tid,
+			     req->r_osd ? req->r_osd->o_osd : -1);
+			__unregister_request(osdc, req);
+			__register_linger_request(osdc, req);
+			continue;
+		}
+
 		err = __map_request(osdc, req, force_resend);
 		if (err < 0)
 			continue;  /* error */
@@ -1298,17 +1316,6 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 				req->r_flags |= CEPH_OSD_FLAG_RETRY;
 			}
 		}
-		if (req->r_linger && list_empty(&req->r_linger_item)) {
-			/*
-			 * register as a linger so that we will
-			 * re-submit below and get a new tid
-			 */
-			dout("%p tid %llu restart on osd%d\n",
-			     req, req->r_tid,
-			     req->r_osd ? req->r_osd->o_osd : -1);
-			__register_linger_request(osdc, req);
-			__unregister_request(osdc, req);
-		}
 	}
 
 	list_for_each_entry_safe(req, nreq, &osdc->req_linger,
@@ -1316,6 +1323,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 		dout("linger req=%p req->r_osd=%p\n", req, req->r_osd);
 
 		err = __map_request(osdc, req, force_resend);
+		dout("__map_request returned %d\n", err);
 		if (err == 0)
 			continue;  /* no change and no osd was specified */
 		if (err < 0)
@@ -1337,6 +1345,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 		dout("%d requests for down osds, need new map\n", needmap);
 		ceph_monc_request_next_osdmap(&osdc->client->monc);
 	}
+	reset_changed_osds(osdc);
 }
 
 
@@ -1393,7 +1402,6 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 				osdc->osdmap = newmap;
 			}
 			kick_requests(osdc, 0);
-			reset_changed_osds(osdc);
 		} else {
 			dout("ignoring incremental map %u len %d\n",
 			     epoch, maplen);