1 files changed, 102 insertions, 70 deletions

diff --git a/kernel/fs/nfsd/nfs4state.c b/kernel/fs/nfsd/nfs4state.c
index 6b800b5b8..c7f1ce414 100644
--- a/kernel/fs/nfsd/nfs4state.c
+++ b/kernel/fs/nfsd/nfs4state.c
@@ -553,8 +553,8 @@ out:
 	return co;
 }
 
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
-					 struct kmem_cache *slab)
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *))
 {
 	struct nfs4_stid *stid;
 	int new_id;
@@ -570,6 +570,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 	idr_preload_end();
 	if (new_id < 0)
 		goto out_free;
+
+	stid->sc_free = sc_free;
 	stid->sc_client = cl;
 	stid->sc_stateid.si_opaque.so_id = new_id;
 	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
@@ -595,15 +597,12 @@ out_free:
 static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 {
 	struct nfs4_stid *stid;
-	struct nfs4_ol_stateid *stp;
 
-	stid = nfs4_alloc_stid(clp, stateid_slab);
+	stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
 	if (!stid)
 		return NULL;
 
-	stp = openlockstateid(stid);
-	stp->st_stid.sc_free = nfs4_free_ol_stateid;
-	return stp;
+	return openlockstateid(stid);
 }
 
 static void nfs4_free_deleg(struct nfs4_stid *stid)
@@ -701,11 +700,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh,
 		goto out_dec;
 	if (delegation_blocked(&current_fh->fh_handle))
 		goto out_dec;
-	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
+	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
 	if (dp == NULL)
 		goto out_dec;
 
-	dp->dl_stid.sc_free = nfs4_free_deleg;
 	/*
 	 * delegation seqid's are never incremented.  The 4.1 special
 	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -1200,27 +1198,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist)
 	}
 }
 
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-	struct nfs4_ol_stateid *stp;
-	struct list_head reaplist;
-
-	INIT_LIST_HEAD(&reaplist);
-
-	spin_lock(&clp->cl_lock);
-	unhash_lockowner_locked(lo);
-	while (!list_empty(&lo->lo_owner.so_stateids)) {
-		stp = list_first_entry(&lo->lo_owner.so_stateids,
-				struct nfs4_ol_stateid, st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
-		put_ol_stateid_locked(stp, &reaplist);
-	}
-	spin_unlock(&clp->cl_lock);
-	free_ol_stateid_reaplist(&reaplist);
-	nfs4_put_stateowner(&lo->lo_owner);
-}
-
 static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 				       struct list_head *reaplist)
 {
@@ -3452,6 +3429,10 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	struct nfs4_openowner *oo = open->op_openowner;
 	struct nfs4_ol_stateid *retstp = NULL;
 
+	/* We are moving these outside of the spinlocks to avoid the warnings */
+	mutex_init(&stp->st_mutex);
+	mutex_lock(&stp->st_mutex);
+
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
 
@@ -3467,13 +3448,17 @@ 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);
 	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
 
 out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
+	if (retstp) {
+		mutex_lock(&retstp->st_mutex);
+		/* Not that we need to, just for neatness */
+		mutex_unlock(&stp->st_mutex);
+	}
 	return retstp;
 }
 
@@ -4300,32 +4285,34 @@ 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);
+		mutex_lock(&stp->st_mutex);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 	} else {
 		stp = open->op_stp;
 		open->op_stp = NULL;
+		/*
+		 * init_open_stateid() either returns a locked stateid
+		 * it found, or initializes and locks the new one we passed in
+		 */
 		swapstp = init_open_stateid(stp, fp, open);
 		if (swapstp) {
 			nfs4_put_stid(&stp->st_stid);
 			stp = swapstp;
-			down_read(&stp->st_rwsem);
 			status = nfs4_upgrade_open(rqstp, fp, current_fh,
 						stp, open);
 			if (status) {
-				up_read(&stp->st_rwsem);
+				mutex_unlock(&stp->st_mutex);
 				goto out;
 			}
 			goto upgrade_out;
 		}
-		down_read(&stp->st_rwsem);
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			release_open_stateid(stp);
 			goto out;
 		}
@@ -4337,7 +4324,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	}
 upgrade_out:
 	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
-	up_read(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	if (nfsd4_has_session(&resp->cstate)) {
 		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4872,6 +4859,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return nfs_ok;
 }
 
+static __be32
+nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
+{
+	struct nfs4_ol_stateid *stp = openlockstateid(s);
+	__be32 ret;
+
+	mutex_lock(&stp->st_mutex);
+
+	ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
+	if (ret)
+		goto out;
+
+	ret = nfserr_locks_held;
+	if (check_for_locks(stp->st_stid.sc_file,
+			    lockowner(stp->st_stateowner)))
+		goto out;
+
+	release_lock_stateid(stp);
+	ret = nfs_ok;
+
+out:
+	mutex_unlock(&stp->st_mutex);
+	nfs4_put_stid(s);
+	return ret;
+}
+
 __be32
 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   struct nfsd4_free_stateid *free_stateid)
@@ -4879,7 +4892,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	stateid_t *stateid = &free_stateid->fr_stateid;
 	struct nfs4_stid *s;
 	struct nfs4_delegation *dp;
-	struct nfs4_ol_stateid *stp;
 	struct nfs4_client *cl = cstate->session->se_client;
 	__be32 ret = nfserr_bad_stateid;
 
@@ -4898,18 +4910,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		ret = nfserr_locks_held;
 		break;
 	case NFS4_LOCK_STID:
-		ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
-		if (ret)
-			break;
-		stp = openlockstateid(s);
-		ret = nfserr_locks_held;
-		if (check_for_locks(stp->st_stid.sc_file,
-				    lockowner(stp->st_stateowner)))
-			break;
-		WARN_ON(!unhash_lock_stateid(stp));
+		atomic_inc(&s->sc_count);
 		spin_unlock(&cl->cl_lock);
-		nfs4_put_stid(s);
-		ret = nfs_ok;
+		ret = nfsd4_free_lock_stateid(stateid, s);
 		goto out;
 	case NFS4_REVOKED_DELEG_STID:
 		dp = delegstateid(s);
@@ -4950,12 +4953,12 @@ 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);
+	mutex_lock(&stp->st_mutex);
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status == nfs_ok)
 		status = nfs4_check_fh(current_fh, &stp->st_stid);
 	if (status != nfs_ok)
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 	return status;
 }
 
@@ -5003,7 +5006,7 @@ 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);
+		mutex_unlock(&stp->st_mutex);
 		nfs4_put_stid(&stp->st_stid);
 		return nfserr_bad_stateid;
 	}
@@ -5035,12 +5038,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	oo = openowner(stp->st_stateowner);
 	status = nfserr_bad_stateid;
 	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 		goto put_stateid;
 	}
 	oo->oo_flags |= NFS4_OO_CONFIRMED;
 	nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
@@ -5116,7 +5119,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
 	status = nfs_ok;
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5169,7 +5172,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out; 
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	nfsd4_close_open_stateid(stp);
 
@@ -5391,11 +5394,10 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
-	stp->st_stid.sc_free = nfs4_free_lock_stateid;
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
-	init_rwsem(&stp->st_rwsem);
+	mutex_init(&stp->st_mutex);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -5434,7 +5436,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 	lst = find_lock_stateid(lo, fi);
 	if (lst == NULL) {
 		spin_unlock(&clp->cl_lock);
-		ns = nfs4_alloc_stid(clp, stateid_slab);
+		ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
 		if (ns == NULL)
 			return NULL;
 
@@ -5476,7 +5478,7 @@ static __be32
 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 			    struct nfs4_ol_stateid *ost,
 			    struct nfsd4_lock *lock,
-			    struct nfs4_ol_stateid **lst, bool *new)
+			    struct nfs4_ol_stateid **plst, bool *new)
 {
 	__be32 status;
 	struct nfs4_file *fi = ost->st_stid.sc_file;
@@ -5484,7 +5486,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 	struct nfs4_client *cl = oo->oo_owner.so_client;
 	struct inode *inode = d_inode(cstate->current_fh.fh_dentry);
 	struct nfs4_lockowner *lo;
+	struct nfs4_ol_stateid *lst;
 	unsigned int strhashval;
+	bool hashed;
 
 	lo = find_lockowner_str(cl, &lock->lk_new_owner);
 	if (!lo) {
@@ -5500,12 +5504,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 			goto out;
 	}
 
-	*lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
-	if (*lst == NULL) {
+retry:
+	lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
+	if (lst == NULL) {
 		status = nfserr_jukebox;
 		goto out;
 	}
+
+	mutex_lock(&lst->st_mutex);
+
+	/* See if it's still hashed to avoid race with FREE_STATEID */
+	spin_lock(&cl->cl_lock);
+	hashed = !list_empty(&lst->st_perfile);
+	spin_unlock(&cl->cl_lock);
+
+	if (!hashed) {
+		mutex_unlock(&lst->st_mutex);
+		nfs4_put_stid(&lst->st_stid);
+		goto retry;
+	}
 	status = nfs_ok;
+	*plst = lst;
 out:
 	nfs4_put_stateowner(&lo->lo_owner);
 	return status;
@@ -5564,7 +5583,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 					&open_stp, nn);
 		if (status)
 			goto out;
-		up_write(&open_stp->st_rwsem);
+		mutex_unlock(&open_stp->st_mutex);
 		open_sop = openowner(open_stp->st_stateowner);
 		status = nfserr_bad_stateid;
 		if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5572,8 +5591,6 @@ 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,
@@ -5677,7 +5694,7 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
-		up_write(&lock_stp->st_rwsem);
+		mutex_unlock(&lock_stp->st_mutex);
 
 		/*
 		 * If this is a new, never-before-used stateid, and we are
@@ -5847,7 +5864,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 fput:
 	fput(filp);
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5911,6 +5928,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfs4_client *clp;
+	LIST_HEAD (reaplist);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -5941,9 +5959,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		nfs4_get_stateowner(sop);
 		break;
 	}
+	if (!lo) {
+		spin_unlock(&clp->cl_lock);
+		return status;
+	}
+
+	unhash_lockowner_locked(lo);
+	while (!list_empty(&lo->lo_owner.so_stateids)) {
+		stp = list_first_entry(&lo->lo_owner.so_stateids,
+				       struct nfs4_ol_stateid,
+				       st_perstateowner);
+		WARN_ON(!unhash_lock_stateid(stp));
+		put_ol_stateid_locked(stp, &reaplist);
+	}
 	spin_unlock(&clp->cl_lock);
-	if (lo)
-		release_lockowner(lo);
+	free_ol_stateid_reaplist(&reaplist);
+	nfs4_put_stateowner(&lo->lo_owner);
+
 	return status;
 }