NFS: Ensure that we handle NFS4ERR_STALE_STATEID correctly

Even if the server is crazy, we should be able to mark the stateid as being
bad, to ensure it gets recovered.

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

3 files changed, 33 insertions, 14 deletions

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index ea2f41b26aea..0c6fda33d66e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -278,6 +278,7 @@ extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs4_schedule_state_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
+extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index afbfe673489b..375f0fae2c6a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -249,14 +249,14 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 			if (state == NULL)
 				break;
 			nfs4_state_mark_reclaim_nograce(clp, state);
-		case -NFS4ERR_STALE_CLIENTID:
+			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
+			if (state == NULL)
+				break;
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(clp);
-			ret = nfs4_wait_clnt_recover(clp);
-			if (ret == 0)
-				exception->retry = 1;
-			break;
+			goto do_state_recovery;
 #if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -289,6 +289,12 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 	}
 	/* We failed to handle the error */
 	return nfs4_map_errors(ret);
+do_state_recovery:
+	nfs4_schedule_state_recovery(clp);
+	ret = nfs4_wait_clnt_recover(clp);
+	if (ret == 0)
+		exception->retry = 1;
+	return ret;
 }
 
 
@@ -3420,15 +3426,14 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			if (state == NULL)
 				break;
 			nfs4_state_mark_reclaim_nograce(clp, state);
-		case -NFS4ERR_STALE_CLIENTID:
+			goto do_state_recovery;
 		case -NFS4ERR_STALE_STATEID:
+			if (state == NULL)
+				break;
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
-			rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-			nfs4_schedule_state_recovery(clp);
-			if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
-				rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
-			task->tk_status = 0;
-			return -EAGAIN;
+			goto do_state_recovery;
 #if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -3456,6 +3461,13 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 	}
 	task->tk_status = nfs4_map_errors(task->tk_status);
 	return 0;
+do_state_recovery:
+	rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
+	nfs4_schedule_state_recovery(clp);
+	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
+		rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+	task->tk_status = 0;
+	return -EAGAIN;
 }
 
 static int
@@ -4099,6 +4111,12 @@ static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_
 		   (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
 			nfs4_state_mark_reclaim_nograce(clp, state);
 		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+		break;
+	case -NFS4ERR_STALE_STATEID:
+		if (new_lock_owner != 0 ||
+		    (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+			nfs4_state_mark_reclaim_reboot(clp, state);
+		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
 	};
 }
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6d263ed79e92..c1e2733f4fa4 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -901,7 +901,7 @@ void nfs4_schedule_state_recovery(struct nfs_client *clp)
 	nfs4_schedule_state_manager(clp);
 }
 
-static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
 {
 
 	set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);