Commit 99dc2ef0 authored by Chuck Lever's avatar Chuck Lever
Browse files

NFSD: CREATE_SESSION must never cache NFS4ERR_DELAY replies 



There are one or two cases where CREATE_SESSION returns
NFS4ERR_DELAY in order to force the client to wait a bit and try
CREATE_SESSION again. However, after commit e4469c6c ("NFSD: Fix
the NFSv4.1 CREATE_SESSION operation"), NFSD caches that response in
the CREATE_SESSION slot. Thus, when the client resends the
CREATE_SESSION, the server always returns the cached NFS4ERR_DELAY
response rather than actually executing the request and properly
recording its outcome. This blocks the client from making further
progress.

RFC 8881 Section 15.1.1.3 says:
> If NFS4ERR_DELAY is returned on an operation other than SEQUENCE
> that validly appears as the first operation of a request ... [t]he
> request can be retried in full without modification. In this case
> as well, the replier MUST avoid returning a response containing
> NFS4ERR_DELAY as the response to an initial operation of a request
> solely on the basis of its presence in the reply cache.

Neither the original NFSD code nor the discussion in section 18.36.4
refer explicitly to this important requirement, so I missed it.

Note also that not only must the server not cache NFS4ERR_DELAY, but
it has to not advance the CREATE_SESSION slot sequence number so
that it can properly recognize and accept the client's retry.

Reported-by: default avatarDai Ngo <dai.ngo@oracle.com>
Fixes: e4469c6c ("NFSD: Fix the NFSv4.1 CREATE_SESSION operation")
Tested-by: default avatarDai Ngo <dai.ngo@oracle.com>
Signed-off-by: default avatarChuck Lever <chuck.lever@oracle.com>
parent 6978bd6a

fs/nfsd/nfs4state.c

+25 −11
Original line number Diff line number Diff line
@@ -3831,15 +3831,20 @@ nfsd4_create_session(struct svc_rqst *rqstp, 
	else

		cs_slot = &unconf->cl_cs_slot;

	status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);

	if (status) {

		if (status == nfserr_replay_cache) {

	switch (status) {

	case nfs_ok:

		cs_slot->sl_seqid++;

		cr_ses->seqid = cs_slot->sl_seqid;

		break;

	case nfserr_replay_cache:

		status = nfsd4_replay_create_session(cr_ses, cs_slot);

		fallthrough;

	case nfserr_jukebox:

		/* The server MUST NOT cache NFS4ERR_DELAY */

		goto out_free_conn;

		}

	default:

		goto out_cache_error;

	}

	cs_slot->sl_seqid++;

	cr_ses->seqid = cs_slot->sl_seqid;



	/* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */

	if (conf) {
@@ -3859,10 +3864,8 @@ nfsd4_create_session(struct svc_rqst *rqstp, 
		old = find_confirmed_client_by_name(&unconf->cl_name, nn);

		if (old) {

			status = mark_client_expired_locked(old);

			if (status) {

				old = NULL;

				goto out_cache_error;

			}

			if (status)

				goto out_expired_error;

			trace_nfsd_clid_replaced(&old->cl_clientid);

		}

		move_to_confirmed(unconf);
@@ -3894,6 +3897,17 @@ nfsd4_create_session(struct svc_rqst *rqstp, 
		expire_client(old);

	return status;



out_expired_error:

	old = NULL;

	/*

	 * Revert the slot seq_nr change so the server will process

	 * the client's resend instead of returning a cached response.

	 */

	if (status == nfserr_jukebox) {

		cs_slot->sl_seqid--;

		cr_ses->seqid = cs_slot->sl_seqid;

		goto out_free_conn;

	}

out_cache_error:

	nfsd4_cache_create_session(cr_ses, cs_slot, status);

out_free_conn: