NFS client bugfixes for Linux 3.14

Highlights include stable fixes for the following bugs:
 
 - General performance regression due to NFS_INO_INVALID_LABEL being set
   when the server doesn't support labeled NFS
 - Hang in the RPC code due to a socket out-of-buffer race
 - Infinite loop when trying to establish the NFSv4 lease
 - Use-after-free bug in the RPCSEC gss code.
 - nfs4_select_rw_stateid is returning with a non-zero error value on success
 
 Other bug fixes:
 
 - Potential memory scribble in the RPC bi-directional RPC code
 - Pipe version reference leak
 - Use the correct net namespace in the new NFSv4 migration code
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJTBMBlAAoJEGcL54qWCgDyOakP+gKDh0VhKw8GziJFfY+6kHHI
 wej86M/coNnRPUv8n7s3N5TXMoV36qisYpxbIG/WQbOn6MfR3qjto6WoP7+vsrEq
 iNomtLivgEsWJePydTuIyAR/TK0du/zqP4zoPEDgdLDenucEVvkCzGIkqzg8Mddc
 duknEhIq918BkXIe3hRBWuxl+pRjwZur+TY0h/OR11oodqTYHxrE37f5PvREWOmB
 08hhjOFBFYlyEnCjD3I1SFmcXQxkKzvACavvbhTyF6u/37oL/QC1/DZKL5mSdOJ6
 novO8sv9gIpn/RhsEMOdaeYMYM5QTvkYIJQyLpKAYyaLZ42EMbRkczwNE7C0ZWyi
 F9MizDMNTie+DvsSHZPYwABTDOOQOuWPa9PO3Lyo8UtWxfmTOjYr2Rre1wyG0/+0
 ywb3JiKQCtVDPnmSHhqxFfVp9XvS7D2/vz0udgKjrCLKyDC2OMMGLVa/acnrtZmz
 s94QpPiqhjnRqIuKo251HtbK3AVaLBNQxBCPszieYwPm9aZ04P7mjsGg1WuhhB2v
 +eSa9UkicGJwKWJWtIBr54qIAOlEXu2bXY+vio5UfbDb+5qfBHe0TmNrz5QNJ53A
 x0eUBocth9VpW1cv/Rf+o30tJyZGy6Jtv8kn2hfXkJXNL3N1Gn25rD3tpb+5TtdY
 b7gtHy13/oe8yi0tK91f
 =tll2
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-3.14-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights include stable fixes for the following bugs:

   - General performance regression due to NFS_INO_INVALID_LABEL being
     set when the server doesn't support labeled NFS
   - Hang in the RPC code due to a socket out-of-buffer race
   - Infinite loop when trying to establish the NFSv4 lease
   - Use-after-free bug in the RPCSEC gss code.
   - nfs4_select_rw_stateid is returning with a non-zero error value on
     success

  Other bug fixes:

  - Potential memory scribble in the RPC bi-directional RPC code
  - Pipe version reference leak
  - Use the correct net namespace in the new NFSv4 migration code"

* tag 'nfs-for-3.14-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS fix error return in nfs4_select_rw_stateid
  NFSv4: Use the correct net namespace in nfs4_update_server
  SUNRPC: Fix a pipe_version reference leak
  SUNRPC: Ensure that gss_auth isn't freed before its upcall messages
  SUNRPC: Fix potential memory scribble in xprt_free_bc_request()
  SUNRPC: Fix races in xs_nospace()
  SUNRPC: Don't create a gss auth cache unless rpc.gssd is running
  NFS: Do not set NFS_INO_INVALID_LABEL unless server supports labeled NFS

fs/nfs/inode.c

@@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfs_fscache_invalidate(inode);
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
 	} else
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
+	nfs_zap_label_cache_locked(nfsi);
 }
 
 void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque)
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+	spin_unlock(&inode->i_lock);
+}
+
 void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					struct nfs4_label *label)
 {
@@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					__func__,
 					(char *)label->label,
 					label->len, error);
+		nfs_clear_label_invalid(inode);
 	}
 }
 
@@ -1648,7 +1655,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode->i_blocks = fattr->du.nfs2.blocks;
 
 	/* Update attrtimeo value if we're out of the unstable period */
-	if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+	if (invalid & NFS_INO_INVALID_ATTR) {
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
@@ -1661,7 +1668,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		}
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
-	invalid &= ~NFS_INO_INVALID_LABEL;
 	/* Don't invalidate the data if we were to blame */
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))

fs/nfs/internal.h

@@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server(
 extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
 						      struct nfs_fh *);
 extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
-					struct sockaddr *sap, size_t salen);
+					struct sockaddr *sap, size_t salen,
+					struct net *net);
 extern void nfs_free_server(struct nfs_server *server);
 extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
@@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label)
 	}
 	return;
 }
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+	if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+		nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
 #else
 static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
 static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */

fs/nfs/nfs4client.c

@@ -1135,6 +1135,7 @@ static int nfs_probe_destination(struct nfs_server *server)
  * @hostname: new end-point's hostname
  * @sap: new end-point's socket address
  * @salen: size of "sap"
+ * @net: net namespace
  *
  * The nfs_server must be quiescent before this function is invoked.
  * Either its session is drained (NFSv4.1+), or its transport is
@@ -1143,13 +1144,13 @@ static int nfs_probe_destination(struct nfs_server *server)
  * Returns zero on success, or a negative errno value.
  */
 int nfs4_update_server(struct nfs_server *server, const char *hostname,
-		       struct sockaddr *sap, size_t salen)
+		       struct sockaddr *sap, size_t salen, struct net *net)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct rpc_clnt *clnt = server->client;
 	struct xprt_create xargs = {
 		.ident		= clp->cl_proto,
-		.net		= &init_net,
+		.net		= net,
 		.dstaddr	= sap,
 		.addrlen	= salen,
 		.servername	= hostname,
@@ -1189,7 +1190,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_rpcclient->cl_auth->au_flavor,
 				clp->cl_proto, clnt->cl_timeout,
-				clp->cl_minorversion, clp->cl_net);
+				clp->cl_minorversion, net);
 	nfs_put_client(clp);
 	if (error != 0) {
 		nfs_server_insert_lists(server);

fs/nfs/nfs4namespace.c

@@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry,
 }
 
 static size_t nfs_parse_server_name(char *string, size_t len,
-		struct sockaddr *sa, size_t salen, struct nfs_server *server)
+		struct sockaddr *sa, size_t salen, struct net *net)
 {
-	struct net *net = rpc_net_ns(server->client);
 	ssize_t ret;
 
 	ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 				     const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	char *mnt_path;
 	unsigned int maxbuflen;
@@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 			continue;
 
 		mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
-				mountdata->addr, addr_bufsize,
-				NFS_SB(mountdata->sb));
+				mountdata->addr, addr_bufsize, net);
 		if (mountdata->addrlen == 0)
 			continue;
 
@@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 		const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(server->client);
 	struct sockaddr *sap;
 	unsigned int s;
 	size_t salen;
@@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 			continue;
 
 		salen = nfs_parse_server_name(buf->data, buf->len,
-						sap, addr_bufsize, server);
+						sap, addr_bufsize, net);
 		if (salen == 0)
 			continue;
 		rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 		if (hostname == NULL)
 			break;
 
-		error = nfs4_update_server(server, hostname, sap, salen);
+		error = nfs4_update_server(server, hostname, sap, salen, net);
 		kfree(hostname);
 		if (error == 0)
 			break;

fs/nfs/nfs4state.c

@@ -1015,8 +1015,11 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
 	if (ret == -EIO)
 		/* A lost lock - don't even consider delegations */
 		goto out;
-	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+	/* returns true if delegation stateid found and copied */
+	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+		ret = 0;
 		goto out;
+	}
 	if (ret != -ENOENT)
 		/* nfs4_copy_delegation_stateid() didn't over-write
 		 * dst, so it still has the lock stateid which we now

net/sunrpc/auth_gss/auth_gss.c

@@ -108,6 +108,7 @@ struct gss_auth {
 static DEFINE_SPINLOCK(pipe_version_lock);
 static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
+static void gss_put_auth(struct gss_auth *gss_auth);
 
 static void gss_free_ctx(struct gss_cl_ctx *);
 static const struct rpc_pipe_ops gss_upcall_ops_v0;
@@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg)
 	if (gss_msg->ctx != NULL)
 		gss_put_ctx(gss_msg->ctx);
 	rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue);
+	gss_put_auth(gss_msg->auth);
 	kfree(gss_msg);
 }
 
@@ -498,9 +500,12 @@ gss_alloc_msg(struct gss_auth *gss_auth,
 	default:
 		err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
 		if (err)
-			goto err_free_msg;
+			goto err_put_pipe_version;
 	};
+	kref_get(&gss_auth->kref);
 	return gss_msg;
+err_put_pipe_version:
+	put_pipe_version(gss_auth->net);
 err_free_msg:
 	kfree(gss_msg);
 err:
@@ -991,6 +996,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 	gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor);
 	if (gss_auth->service == 0)
 		goto err_put_mech;
+	if (!gssd_running(gss_auth->net))
+		goto err_put_mech;
 	auth = &gss_auth->rpc_auth;
 	auth->au_cslack = GSS_CRED_SLACK >> 2;
 	auth->au_rslack = GSS_VERF_SLACK >> 2;
@@ -1061,6 +1068,12 @@ gss_free_callback(struct kref *kref)
 	gss_free(gss_auth);
 }
 
+static void
+gss_put_auth(struct gss_auth *gss_auth)
+{
+	kref_put(&gss_auth->kref, gss_free_callback);
+}
+
 static void
 gss_destroy(struct rpc_auth *auth)
 {
@@ -1082,7 +1095,7 @@ gss_destroy(struct rpc_auth *auth)
 	gss_auth->gss_pipe[1] = NULL;
 	rpcauth_destroy_credcache(auth);
 
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 /*
@@ -1253,7 +1266,7 @@ gss_destroy_nullcred(struct rpc_cred *cred)
 	call_rcu(&cred->cr_rcu, gss_free_cred_callback);
 	if (ctx)
 		gss_put_ctx(ctx);
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 static void

net/sunrpc/backchannel_rqst.c

@@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req)
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	xbufp = &req->rq_snd_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
-	list_del(&req->rq_bc_pa_list);
 	kfree(req);
 }
 
@@ -168,8 +167,10 @@ out_free:
 	/*
 	 * Memory allocation failed, free the temporary list
 	 */
-	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
+	}
 
 	dprintk("RPC:       setup backchannel transport failed\n");
 	return -ENOMEM;
@@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs)
 	xprt_dec_alloc_count(xprt, max_reqs);
 	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
 		dprintk("RPC:        req=%p\n", req);
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
 		if (--max_reqs == 0)
 			break;

net/sunrpc/xprtsock.c

@@ -510,6 +510,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -527,7 +528,7 @@ static int xs_nospace(struct rpc_task *task)
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -537,6 +538,9 @@ static int xs_nospace(struct rpc_task *task)
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }