nfsd: serialize state seqid morphing operations

[ Upstream commit 35a92fe8770ce54c5eb275cd76128645bea2d200 ]

Andrew was seeing a race occur when an OPEN and OPEN_DOWNGRADE were
running in parallel. The server would receive the OPEN_DOWNGRADE first
and check its seqid, but then an OPEN would race in and bump it. The
OPEN_DOWNGRADE would then complete and bump the seqid again.  The result
was that the OPEN_DOWNGRADE would be applied after the OPEN, even though
it should have been rejected since the seqid changed.

The only recourse we have here I think is to serialize operations that
bump the seqid in a stateid, particularly when we're given a seqid in
the call. To address this, we add a new rw_semaphore to the
nfs4_ol_stateid struct. We do a down_write prior to checking the seqid
after looking up the stateid to ensure that nothing else is going to
bump it while we're operating on it.

In the case of OPEN, we do a down_read, as the call doesn't contain a
seqid. Those can run in parallel -- we just need to serialize them when
there is a concurrent OPEN_DOWNGRADE or CLOSE.

LOCK and LOCKU however always take the write lock as there is no
opportunity for parallelizing those.

Reported-and-Tested-by: Andrew W Elble <aweits@rit.edu>
Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

2 files changed, 37 insertions, 13 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index eda99c8ec3ed..b6c3a8792358 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3241,6 +3241,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = 0;
 	stp->st_openstp = NULL;
+	init_rwsem(&stp->st_rwsem);
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -4057,21 +4058,27 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 */
 	if (stp) {
 		/* Stateid was found, this is an OPEN upgrade */
+		down_read(&stp->st_rwsem);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
-		if (status)
+		if (status) {
+			up_read(&stp->st_rwsem);
 			goto out;
+		}
 	} else {
 		stp = open->op_stp;
 		open->op_stp = NULL;
 		init_open_stateid(stp, fp, open);
+		down_read(&stp->st_rwsem);
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
+			up_read(&stp->st_rwsem);
 			release_open_stateid(stp);
 			goto out;
 		}
 	}
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	up_read(&stp->st_rwsem);
 
 	if (nfsd4_has_session(&resp->cstate)) {
 		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4647,10 +4654,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 		 * revoked delegations are kept only for free_stateid.
 		 */
 		return nfserr_bad_stateid;
+	down_write(&stp->st_rwsem);
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
-	if (status)
-		return status;
-	return nfs4_check_fh(current_fh, &stp->st_stid);
+	if (status == nfs_ok)
+		status = nfs4_check_fh(current_fh, &stp->st_stid);
+	if (status != nfs_ok)
+		up_write(&stp->st_rwsem);
+	return status;
 }
 
 /* 
@@ -4697,6 +4707,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 		return status;
 	oo = openowner(stp->st_stateowner);
 	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
+		up_write(&stp->st_rwsem);
 		nfs4_put_stid(&stp->st_stid);
 		return nfserr_bad_stateid;
 	}
@@ -4727,11 +4738,14 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	oo = openowner(stp->st_stateowner);
 	status = nfserr_bad_stateid;
-	if (oo->oo_flags & NFS4_OO_CONFIRMED)
+	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
+		up_write(&stp->st_rwsem);
 		goto put_stateid;
+	}
 	oo->oo_flags |= NFS4_OO_CONFIRMED;
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	up_write(&stp->st_rwsem);
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
@@ -4810,6 +4824,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 	status = nfs_ok;
 put_stateid:
+	up_write(&stp->st_rwsem);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -4860,6 +4875,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out; 
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	up_write(&stp->st_rwsem);
 
 	nfsd4_close_open_stateid(stp);
 
@@ -5088,6 +5104,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
+	init_rwsem(&stp->st_rwsem);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -5256,6 +5273,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 					&open_stp, nn);
 		if (status)
 			goto out;
+		up_write(&open_stp->st_rwsem);
 		open_sop = openowner(open_stp->st_stateowner);
 		status = nfserr_bad_stateid;
 		if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5263,6 +5281,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			goto out;
 		status = lookup_or_create_lock_state(cstate, open_stp, lock,
 							&lock_stp, &new);
+		if (status == nfs_ok)
+			down_write(&lock_stp->st_rwsem);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
@@ -5368,6 +5388,8 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
+		up_write(&lock_stp->st_rwsem);
+
 		/*
 		 * If this is a new, never-before-used stateid, and we are
 		 * returning an error, then just go ahead and release it.
@@ -5538,6 +5560,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 fput:
 	fput(filp);
 put_stateid:
+	up_write(&stp->st_rwsem);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2712042a66b1..3ccb1046a2f9 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -506,14 +506,15 @@ struct nfs4_file {
  * Better suggestions welcome.
  */
 struct nfs4_ol_stateid {
-	struct nfs4_stid    st_stid; /* must be first field */
-	struct list_head              st_perfile;
-	struct list_head              st_perstateowner;
-	struct list_head              st_locks;
-	struct nfs4_stateowner      * st_stateowner;
-	unsigned char                 st_access_bmap;
-	unsigned char                 st_deny_bmap;
-	struct nfs4_ol_stateid         * st_openstp;
+	struct nfs4_stid		st_stid;
+	struct list_head		st_perfile;
+	struct list_head		st_perstateowner;
+	struct list_head		st_locks;
+	struct nfs4_stateowner		*st_stateowner;
+	unsigned char			st_access_bmap;
+	unsigned char			st_deny_bmap;
+	struct nfs4_ol_stateid		*st_openstp;
+	struct rw_semaphore		st_rwsem;
 };
 
 static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)