Merge tag 'nfsd-4.7-1' of git://linux-nfs.org/~bfields/linux

Pull nfsd bugfixes from Bruce Fields:
 "Oleg Drokin found and fixed races in the nfsd4 state code that go back
  to the big nfs4_lock_state removal around 3.17 (but that were also
  probably hard to reproduce before client changes in 3.20 allowed the
  client to perform parallel opens).

  Also fix a 4.1 backchannel crash due to rpc multipath changes in 4.6.
  Trond acked the client-side rpc fixes going through my tree"

* tag 'nfsd-4.7-1' of git://linux-nfs.org/~bfields/linux:
  nfsd: Make init_open_stateid() a bit more whole
  nfsd: Extend the mutex holding region around in nfsd4_process_open2()
  nfsd: Always lock state exclusively.
  rpc: share one xps between all backchannels
  nfsd4/rpc: move backchannel create logic into rpc code
  SUNRPC: fix xprt leak on xps allocation failure
  nfsd: Fix NFSD_MDS_PR_KEY on 32-bit by adding ULL postfix

10 files changed, 70 insertions, 57 deletions

diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index e55b5242614d..31f3df193bdb 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -290,7 +290,7 @@ out_free_buf:
 	return error;
 }
 
-#define NFSD_MDS_PR_KEY		0x0100000000000000
+#define NFSD_MDS_PR_KEY		0x0100000000000000ULL
 
 /*
  * We use the client ID as a unique key for the reservations.
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7389cb1d7409..04c68d900324 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 	}
 }
 
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
-	struct rpc_xprt *xprt;
-
-	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
-		return rpc_create(args);
-
-	xprt = args->bc_xprt->xpt_bc_xprt;
-	if (xprt) {
-		xprt_get(xprt);
-		return rpc_create_xprt(args, xprt);
-	}
-
-	return rpc_create(args);
-}
-
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	int maxtime = max_cb_time(clp->net);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
-	client = create_backchannel_client(&args);
+	client = rpc_create(&args);
 	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f5f82e145018..70d0b9b33031 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3480,12 +3480,17 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 }
 
 static struct nfs4_ol_stateid *
-init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
-		struct nfsd4_open *open)
+init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 {
 
 	struct nfs4_openowner *oo = open->op_openowner;
 	struct nfs4_ol_stateid *retstp = NULL;
+	struct nfs4_ol_stateid *stp;
+
+	stp = open->op_stp;
+	/* 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);
@@ -3493,6 +3498,8 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	retstp = nfsd4_find_existing_open(fp, open);
 	if (retstp)
 		goto out_unlock;
+
+	open->op_stp = NULL;
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
@@ -3502,14 +3509,19 @@ 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);
-	return retstp;
+	if (retstp) {
+		mutex_lock(&retstp->st_mutex);
+		/* To keep mutex tracking happy */
+		mutex_unlock(&stp->st_mutex);
+		stp = retstp;
+	}
+	return stp;
 }
 
 /*
@@ -4305,7 +4317,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
 	struct nfs4_file *fp = NULL;
 	struct nfs4_ol_stateid *stp = NULL;
-	struct nfs4_ol_stateid *swapstp = NULL;
 	struct nfs4_delegation *dp = NULL;
 	__be32 status;
 
@@ -4335,32 +4346,28 @@ 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;
-		swapstp = init_open_stateid(stp, fp, open);
-		if (swapstp) {
-			nfs4_put_stid(&stp->st_stid);
-			stp = swapstp;
-			down_read(&stp->st_rwsem);
+		/* stp is returned locked. */
+		stp = init_open_stateid(fp, open);
+		/* See if we lost the race to some other thread */
+		if (stp->st_access_bmap != 0) {
 			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;
 		}
@@ -4372,7 +4379,7 @@ 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) {
@@ -4977,12 +4984,12 @@ 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;
 }
 
@@ -5030,7 +5037,7 @@ 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;
 	}
@@ -5062,12 +5069,12 @@ 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));
 
@@ -5143,7 +5150,7 @@ 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);
@@ -5196,7 +5203,7 @@ 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);
 
@@ -5422,7 +5429,7 @@ 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);
+	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);
@@ -5591,7 +5598,7 @@ 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,
@@ -5600,7 +5607,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = lookup_or_create_lock_state(cstate, open_stp, lock,
 							&lock_stp, &new);
 		if (status == nfs_ok)
-			down_write(&lock_stp->st_rwsem);
+			mutex_lock(&lock_stp->st_mutex);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
@@ -5704,7 +5711,7 @@ 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
@@ -5874,7 +5881,7 @@ 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);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 986e51e5ceac..64053eadeb81 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -535,7 +535,7 @@ struct nfs4_ol_stateid {
 	unsigned char			st_access_bmap;
 	unsigned char			st_deny_bmap;
 	struct nfs4_ol_stateid		*st_openstp;
-	struct rw_semaphore		st_rwsem;
+	struct mutex			st_mutex;
 };
 
 static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 19c659d1c0f8..b6810c92b8bb 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -137,8 +137,6 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
-					struct rpc_xprt *xprt);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b7dabc4baafd..79ba50856707 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -84,6 +84,7 @@ struct svc_xprt {
 
 	struct net		*xpt_net;
 	struct rpc_xprt		*xpt_bc_xprt;	/* NFSv4.1 backchannel */
+	struct rpc_xprt_switch	*xpt_bc_xps;	/* NFSv4.1 backchannel */
 };
 
 static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 5aa3834619a8..5e3e1b63dbb3 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -297,6 +297,7 @@ struct xprt_create {
 	size_t			addrlen;
 	const char		*servername;
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
+	struct rpc_xprt_switch	*bc_xps;
 	unsigned int		flags;
 };
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 06b4df9faaa1..2808d550d273 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -446,16 +446,27 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 					struct rpc_xprt *xprt)
 {
 	struct rpc_clnt *clnt = NULL;
 	struct rpc_xprt_switch *xps;
 
-	xps = xprt_switch_alloc(xprt, GFP_KERNEL);
-	if (xps == NULL)
-		return ERR_PTR(-ENOMEM);
-
+	if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xps = args->bc_xprt->xpt_bc_xps;
+		xprt_switch_get(xps);
+	} else {
+		xps = xprt_switch_alloc(xprt, GFP_KERNEL);
+		if (xps == NULL) {
+			xprt_put(xprt);
+			return ERR_PTR(-ENOMEM);
+		}
+		if (xprt->bc_xprt) {
+			xprt_switch_get(xps);
+			xprt->bc_xprt->xpt_bc_xps = xps;
+		}
+	}
 	clnt = rpc_new_client(args, xps, xprt, NULL);
 	if (IS_ERR(clnt))
 		return clnt;
@@ -483,7 +494,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	return clnt;
 }
-EXPORT_SYMBOL_GPL(rpc_create_xprt);
 
 /**
  * rpc_create - create an RPC client and transport with one call
@@ -509,6 +519,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	};
 	char servername[48];
 
+	if (args->bc_xprt) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xprt = args->bc_xprt->xpt_bc_xprt;
+		if (xprt) {
+			xprt_get(xprt);
+			return rpc_create_xprt(args, xprt);
+		}
+	}
+
 	if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS)
 		xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS;
 	if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index f5572e31d518..4f01f63102ee 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -136,6 +136,8 @@ static void svc_xprt_free(struct kref *kref)
 	/* See comment on corresponding get in xs_setup_bc_tcp(): */
 	if (xprt->xpt_bc_xprt)
 		xprt_put(xprt->xpt_bc_xprt);
+	if (xprt->xpt_bc_xps)
+		xprt_switch_put(xprt->xpt_bc_xps);
 	xprt->xpt_ops->xpo_free(xprt);
 	module_put(owner);
 }
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 2d3e0c42361e..7e2b2fa189c3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -3057,6 +3057,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 		return xprt;
 
 	args->bc_xprt->xpt_bc_xprt = NULL;
+	args->bc_xprt->xpt_bc_xps = NULL;
 	xprt_put(xprt);
 	ret = ERR_PTR(-EINVAL);
 out_err: