NFS: Support NFS4ERR_LEASE_MOVED recovery in state manager

A migration on the FSID in play for the current NFS operation
is reported via the error status code NFS4ERR_MOVED.

"Lease moved" means that a migration has occurred on some other
FSID than the one for the current operation.  It's a signal that
the client should take action immediately to handle a migration
that it may not have noticed otherwise.  This is so that the
client's lease does not expire unnoticed on the destination server.

In NFSv4.0, a moved lease is reported with the NFS4ERR_LEASE_MOVED
error status code.

To recover from NFS4ERR_LEASE_MOVED, check each FSID for that server
to see if it is still present.  Invoke nfs4_try_migration() if the
FSID is no longer present on the server.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

fs/nfs/nfs4_fs.h

@@ -30,6 +30,7 @@ enum nfs4_client_state {
 	NFS4CLNT_PURGE_STATE,
 	NFS4CLNT_BIND_CONN_TO_SESSION,
 	NFS4CLNT_MOVED,
+	NFS4CLNT_LEASE_MOVED,
 };
 
 #define NFS4_RENEW_TIMEOUT		0x01
@@ -425,6 +426,7 @@ extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
 extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern int nfs4_schedule_migration_recovery(const struct nfs_server *);
+extern void nfs4_schedule_lease_moved_recovery(struct nfs_client *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_server_scope(struct nfs_client *,
 				      struct nfs41_server_scope **);

fs/nfs/nfs4state.c

@@ -1233,6 +1233,22 @@ int nfs4_schedule_migration_recovery(const struct nfs_server *server)
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery);
 
+/**
+ * nfs4_schedule_lease_moved_recovery - start lease-moved recovery
+ *
+ * @clp: server to check for moved leases
+ *
+ */
+void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp)
+{
+	dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n",
+		__func__, clp->cl_clientid, clp->cl_hostname);
+
+	set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery);
+
 int nfs4_wait_clnt_recover(struct nfs_client *clp)
 {
 	int res;
@@ -1661,7 +1677,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 			nfs4_state_end_reclaim_reboot(clp);
 			break;
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_LEASE_MOVED:
 			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 			nfs4_state_clear_reclaim_reboot(clp);
 			nfs4_state_start_reclaim_reboot(clp);
@@ -1975,6 +1990,55 @@ restart:
 	return 0;
 }
 
+/*
+ * Test each nfs_server on the clp's cl_superblocks list to see
+ * if it's moved to another server.  Stop when the server no longer
+ * returns NFS4ERR_LEASE_MOVED.
+ */
+static int nfs4_handle_lease_moved(struct nfs_client *clp)
+{
+	const struct nfs4_state_maintenance_ops *ops =
+				clp->cl_mvops->state_renewal_ops;
+	struct nfs_server *server;
+	struct rpc_cred *cred;
+
+	dprintk("%s: lease moved reported on \"%s\"\n", __func__,
+			clp->cl_hostname);
+
+	spin_lock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred_locked(clp);
+	spin_unlock(&clp->cl_lock);
+	if (cred == NULL)
+		return -NFS4ERR_NOENT;
+
+	clp->cl_mig_gen++;
+restart:
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		struct inode *inode;
+		int status;
+
+		if (server->mig_gen == clp->cl_mig_gen)
+			continue;
+		server->mig_gen = clp->cl_mig_gen;
+
+		rcu_read_unlock();
+
+		inode = server->super->s_root->d_inode;
+		status = nfs4_proc_fsid_present(inode, cred);
+		if (status != -NFS4ERR_MOVED)
+			goto restart;	/* wasn't this one */
+		if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED)
+			goto restart;	/* there are more */
+		goto out;
+	}
+	rcu_read_unlock();
+
+out:
+	put_rpccred(cred);
+	return 0;
+}
+
 /**
  * nfs4_discover_server_trunking - Detect server IP address trunking
  *
@@ -2312,6 +2376,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
 				goto out_error;
 		}
 
+		if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) {
+			section = "lease moved";
+			status = nfs4_handle_lease_moved(clp);
+			if (status < 0)
+				goto out_error;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
 			section = "reclaim reboot";