1 files changed, 99 insertions, 33 deletions

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 46c156b121db..d61cd9b40491 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -68,6 +68,17 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+/*
+ * For UDP:
+ * 1 for header page
+ * enough pages for RPCSVC_MAXPAYLOAD_UDP
+ * 1 in case payload is not aligned
+ * 1 for tail page
+ */
+enum {
+	SUNRPC_MAX_UDP_SENDPAGES = 1 + RPCSVC_MAXPAYLOAD_UDP / PAGE_SIZE + 1 + 1
+};
+
 /* To-do: to avoid tying up an nfsd thread while waiting for a
  * handshake request, the request could instead be deferred.
  */
@@ -257,20 +268,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 }
 
 static int
-svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
+svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags)
 {
 	union {
 		struct cmsghdr	cmsg;
 		u8		buf[CMSG_SPACE(sizeof(u8))];
 	} u;
-	struct socket *sock = svsk->sk_sock;
+	u8 alert[2];
+	struct kvec alert_kvec = {
+		.iov_base = alert,
+		.iov_len = sizeof(alert),
+	};
+	struct msghdr msg = {
+		.msg_flags = *msg_flags,
+		.msg_control = &u,
+		.msg_controllen = sizeof(u),
+	};
 	int ret;
 
-	msg->msg_control = &u;
-	msg->msg_controllen = sizeof(u);
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+		      alert_kvec.iov_len);
+	ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
+	if (ret > 0 &&
+	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+		iov_iter_revert(&msg.msg_iter, ret);
+		ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN);
+	}
+	return ret;
+}
+
+static int
+svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg)
+{
+	int ret;
+	struct socket *sock = svsk->sk_sock;
+
 	ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
-	if (unlikely(msg->msg_controllen != sizeof(u)))
-		ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+	if (msg->msg_flags & MSG_CTRUNC) {
+		msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+		if (ret == 0 || ret == -EIO)
+			ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags);
+	}
 	return ret;
 }
 
@@ -321,7 +359,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
 		iov_iter_advance(&msg.msg_iter, seek);
 		buflen -= seek;
 	}
-	len = svc_tcp_sock_recv_cmsg(svsk, &msg);
+	len = svc_tcp_sock_recvmsg(svsk, &msg);
 	if (len > 0)
 		svc_flush_bvec(bvec, len, seek);
 
@@ -713,14 +751,14 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
 
-	count = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, xdr);
+	count = xdr_buf_to_bvec(svsk->sk_bvec, SUNRPC_MAX_UDP_SENDPAGES, xdr);
 
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 		      count, rqstp->rq_res.len);
 	err = sock_sendmsg(svsk->sk_sock, &msg);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
-		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 			      count, rqstp->rq_res.len);
 		err = sock_sendmsg(svsk->sk_sock, &msg);
 	}
@@ -809,6 +847,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	/* data might have come in before data_ready set up */
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
+	set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 
 	/* make sure we get destination address info */
 	switch (svsk->sk_sk->sk_family) {
@@ -1018,7 +1057,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
 		iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen;
 		iov.iov_len  = want;
 		iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want);
-		len = svc_tcp_sock_recv_cmsg(svsk, &msg);
+		len = svc_tcp_sock_recvmsg(svsk, &msg);
 		if (len < 0)
 			return len;
 		svsk->sk_tcplen += len;
@@ -1034,9 +1073,10 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
 	return svc_sock_reclen(svsk);
 
 err_too_large:
-	net_notice_ratelimited("svc: %s %s RPC fragment too large: %d\n",
-			       __func__, svsk->sk_xprt.xpt_server->sv_name,
-			       svc_sock_reclen(svsk));
+	net_notice_ratelimited("svc: %s oversized RPC fragment (%u octets) from %pISpc\n",
+			       svsk->sk_xprt.xpt_server->sv_name,
+			       svc_sock_reclen(svsk),
+			       (struct sockaddr *)&svsk->sk_xprt.xpt_remote);
 	svc_xprt_deferred_close(&svsk->sk_xprt);
 err_short:
 	return -EAGAIN;
@@ -1197,7 +1237,7 @@ err_noclose:
  * that the pages backing @xdr are unchanging.
  */
 static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
-			   rpc_fraghdr marker, int *sentp)
+			   rpc_fraghdr marker)
 {
 	struct msghdr msg = {
 		.msg_flags	= MSG_SPLICE_PAGES,
@@ -1206,29 +1246,24 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
 	void *buf;
 	int ret;
 
-	*sentp = 0;
-
 	/* The stream record marker is copied into a temporary page
-	 * fragment buffer so that it can be included in rq_bvec.
+	 * fragment buffer so that it can be included in sk_bvec.
 	 */
 	buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker),
 			      GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 	memcpy(buf, &marker, sizeof(marker));
-	bvec_set_virt(rqstp->rq_bvec, buf, sizeof(marker));
+	bvec_set_virt(svsk->sk_bvec, buf, sizeof(marker));
 
-	count = xdr_buf_to_bvec(rqstp->rq_bvec + 1, rqstp->rq_maxpages,
+	count = xdr_buf_to_bvec(svsk->sk_bvec + 1, rqstp->rq_maxpages,
 				&rqstp->rq_res);
 
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
 		      1 + count, sizeof(marker) + rqstp->rq_res.len);
 	ret = sock_sendmsg(svsk->sk_sock, &msg);
 	page_frag_free(buf);
-	if (ret < 0)
-		return ret;
-	*sentp += ret;
-	return 0;
+	return ret;
 }
 
 /**
@@ -1247,7 +1282,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	struct xdr_buf *xdr = &rqstp->rq_res;
 	rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT |
 					 (u32)xdr->len);
-	int sent, err;
+	int sent;
 
 	svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
 	rqstp->rq_xprt_ctxt = NULL;
@@ -1255,9 +1290,9 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	mutex_lock(&xprt->xpt_mutex);
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
-	err = svc_tcp_sendmsg(svsk, rqstp, marker, &sent);
-	trace_svcsock_tcp_send(xprt, err < 0 ? (long)err : sent);
-	if (err < 0 || sent != (xdr->len + sizeof(marker)))
+	sent = svc_tcp_sendmsg(svsk, rqstp, marker);
+	trace_svcsock_tcp_send(xprt, sent);
+	if (sent < 0 || sent != (xdr->len + sizeof(marker)))
 		goto out_close;
 	mutex_unlock(&xprt->xpt_mutex);
 	return sent;
@@ -1266,10 +1301,10 @@ out_notconn:
 	mutex_unlock(&xprt->xpt_mutex);
 	return -ENOTCONN;
 out_close:
-	pr_notice("rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
+	pr_notice("rpc-srv/tcp: %s: %s %d when sending %zu bytes - shutting down socket\n",
 		  xprt->xpt_server->sv_name,
-		  (err < 0) ? "got error" : "sent",
-		  (err < 0) ? err : sent, xdr->len);
+		  (sent < 0) ? "got error" : "sent",
+		  sent, xdr->len + sizeof(marker));
 	svc_xprt_deferred_close(xprt);
 	mutex_unlock(&xprt->xpt_mutex);
 	return -EAGAIN;
@@ -1328,6 +1363,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	if (sk->sk_state == TCP_LISTEN) {
 		strcpy(svsk->sk_xprt.xpt_remotebuf, "listener");
 		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
+		set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 		sk->sk_data_ready = svc_tcp_listen_data_ready;
 		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 	} else {
@@ -1368,6 +1404,20 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 	spin_unlock_bh(&serv->sv_lock);
 }
 
+static int svc_sock_sendpages(struct svc_serv *serv, struct socket *sock, int flags)
+{
+	switch (sock->type) {
+	case SOCK_STREAM:
+		/* +1 for TCP record marker */
+		if (flags & SVC_SOCK_TEMPORARY)
+			return svc_serv_maxpages(serv) + 1;
+		return 0;
+	case SOCK_DGRAM:
+		return SUNRPC_MAX_UDP_SENDPAGES;
+	}
+	return -EINVAL;
+}
+
 /*
  * Initialize socket for RPC use and create svc_sock struct
  */
@@ -1378,12 +1428,26 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+	int		sendpages;
 	unsigned long	pages;
 
+	sendpages = svc_sock_sendpages(serv, sock, flags);
+	if (sendpages < 0)
+		return ERR_PTR(sendpages);
+
 	pages = svc_serv_maxpages(serv);
 	svsk = kzalloc(struct_size(svsk, sk_pages, pages), GFP_KERNEL);
 	if (!svsk)
 		return ERR_PTR(-ENOMEM);
+
+	if (sendpages) {
+		svsk->sk_bvec = kcalloc(sendpages, sizeof(*svsk->sk_bvec), GFP_KERNEL);
+		if (!svsk->sk_bvec) {
+			kfree(svsk);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
 	svsk->sk_maxpages = pages;
 
 	inet = sock->sk;
@@ -1395,6 +1459,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 				     inet->sk_protocol,
 				     ntohs(inet_sk(inet)->inet_sport));
 		if (err < 0) {
+			kfree(svsk->sk_bvec);
 			kfree(svsk);
 			return ERR_PTR(err);
 		}
@@ -1533,7 +1598,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 		ip6_sock_set_v6only(sock->sk);
 	if (type == SOCK_STREAM)
 		sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */
-	error = kernel_bind(sock, sin, len);
+	error = kernel_bind(sock, (struct sockaddr_unsized *)sin, len);
 	if (error < 0)
 		goto bummer;
 
@@ -1612,5 +1677,6 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sock_release(sock);
 
 	page_frag_cache_drain(&svsk->sk_frag_cache);
+	kfree(svsk->sk_bvec);
 	kfree(svsk);
 }