1 files changed, 55 insertions, 91 deletions

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index a51c9b989d58..e43f26382411 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock)
 #endif
 
 /**
- * svc_tcp_release_rqst - Release transport-related resources
- * @rqstp: request structure with resources to be released
+ * svc_tcp_release_ctxt - Release transport-related resources
+ * @xprt: the transport which owned the context
+ * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
  *
  */
-static void svc_tcp_release_rqst(struct svc_rqst *rqstp)
+static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
 {
 }
 
 /**
- * svc_udp_release_rqst - Release transport-related resources
- * @rqstp: request structure with resources to be released
+ * svc_udp_release_ctxt - Release transport-related resources
+ * @xprt: the transport which owned the context
+ * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
  *
  */
-static void svc_udp_release_rqst(struct svc_rqst *rqstp)
+static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
 {
-	struct sk_buff *skb = rqstp->rq_xprt_ctxt;
+	struct sk_buff *skb = ctxt;
 
-	if (skb) {
-		rqstp->rq_xprt_ctxt = NULL;
+	if (skb)
 		consume_skb(skb);
-	}
 }
 
 union svc_pktinfo_u {
@@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 	unsigned int sent;
 	int err;
 
-	svc_udp_release_rqst(rqstp);
+	svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
+	rqstp->rq_xprt_ctxt = NULL;
 
 	svc_set_cmsg_data(rqstp, cmh);
 
@@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
 	.xpo_result_payload = svc_sock_result_payload,
-	.xpo_release_rqst = svc_udp_release_rqst,
+	.xpo_release_ctxt = svc_udp_release_ctxt,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
 	.xpo_has_wspace = svc_udp_has_wspace,
@@ -825,12 +826,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
 
 	trace_sk_data_ready(sk);
 
-	if (svsk) {
-		/* Refer to svc_setup_socket() for details. */
-		rmb();
-		svsk->sk_odata(sk);
-	}
-
 	/*
 	 * This callback may called twice when a new connection
 	 * is established as a child socket inherits everything
@@ -839,13 +834,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
 	 *    when one of child sockets become ESTABLISHED.
 	 * 2) data_ready method of the child socket may be called
 	 *    when it receives data before the socket is accepted.
-	 * In case of 2, we should ignore it silently.
+	 * In case of 2, we should ignore it silently and DO NOT
+	 * dereference svsk.
 	 */
-	if (sk->sk_state == TCP_LISTEN) {
-		if (svsk) {
-			set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
-			svc_xprt_enqueue(&svsk->sk_xprt);
-		}
+	if (sk->sk_state != TCP_LISTEN)
+		return;
+
+	if (svsk) {
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
+		svsk->sk_odata(sk);
+		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 }
 
@@ -886,15 +886,13 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 	err = kernel_accept(sock, &newsock, O_NONBLOCK);
 	if (err < 0) {
-		if (err == -ENOMEM)
-			printk(KERN_WARNING "%s: no more sockets!\n",
-			       serv->sv_name);
-		else if (err != -EAGAIN)
-			net_warn_ratelimited("%s: accept failed (err %d)!\n",
-					     serv->sv_name, -err);
-		trace_svcsock_accept_err(xprt, serv->sv_name, err);
+		if (err != -EAGAIN)
+			trace_svcsock_accept_err(xprt, serv->sv_name, err);
 		return NULL;
 	}
+	if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL)))
+		return NULL;
+
 	set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 
 	err = kernel_getpeername(newsock, sin);
@@ -935,7 +933,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	return &newsvsk->sk_xprt;
 
 failed:
-	sock_release(newsock);
+	sockfd_put(newsock);
 	return NULL;
 }
 
@@ -1199,13 +1197,14 @@ err_noclose:
 static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
 			      int flags)
 {
-	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
-			       offset_in_page(vec->iov_base),
-			       vec->iov_len, flags);
+	struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | flags, };
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, vec, 1, vec->iov_len);
+	return sock_sendmsg(sock, &msg);
 }
 
 /*
- * kernel_sendpage() is used exclusively to reduce the number of
+ * MSG_SPLICE_PAGES is used exclusively to reduce the number of
  * copy operations in this path. Therefore the caller must ensure
  * that the pages backing @xdr are unchanging.
  *
@@ -1245,28 +1244,13 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 	if (ret != head->iov_len)
 		goto out;
 
-	if (xdr->page_len) {
-		unsigned int offset, len, remaining;
-		struct bio_vec *bvec;
-
-		bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
-		offset = offset_in_page(xdr->page_base);
-		remaining = xdr->page_len;
-		while (remaining > 0) {
-			len = min(remaining, bvec->bv_len - offset);
-			ret = kernel_sendpage(sock, bvec->bv_page,
-					      bvec->bv_offset + offset,
-					      len, 0);
-			if (ret < 0)
-				return ret;
-			*sentp += ret;
-			if (ret != len)
-				goto out;
-			remaining -= len;
-			offset = 0;
-			bvec++;
-		}
-	}
+	msg.msg_flags = MSG_SPLICE_PAGES;
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
+		      xdr_buf_pagecount(xdr), xdr->page_len);
+	ret = sock_sendmsg(sock, &msg);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
 
 	if (tail->iov_len) {
 		ret = svc_tcp_send_kvec(sock, tail, 0);
@@ -1298,7 +1282,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	unsigned int sent;
 	int err;
 
-	svc_tcp_release_rqst(rqstp);
+	svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
+	rqstp->rq_xprt_ctxt = NULL;
 
 	atomic_inc(&svsk->sk_sendqlen);
 	mutex_lock(&xprt->xpt_mutex);
@@ -1343,7 +1328,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
 	.xpo_result_payload = svc_sock_result_payload,
-	.xpo_release_rqst = svc_tcp_release_rqst,
+	.xpo_release_ctxt = svc_tcp_release_ctxt,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
 	.xpo_has_wspace = svc_tcp_has_wspace,
@@ -1430,7 +1415,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 						struct socket *sock,
 						int flags)
 {
-	struct file	*filp = NULL;
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
@@ -1439,14 +1423,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	if (!svsk)
 		return ERR_PTR(-ENOMEM);
 
-	if (!sock->file) {
-		filp = sock_alloc_file(sock, O_NONBLOCK, NULL);
-		if (IS_ERR(filp)) {
-			kfree(svsk);
-			return ERR_CAST(filp);
-		}
-	}
-
 	inet = sock->sk;
 
 	if (pmap_register) {
@@ -1456,8 +1432,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 				     inet->sk_protocol,
 				     ntohs(inet_sk(inet)->inet_sport));
 		if (err < 0) {
-			if (filp)
-				fput(filp);
 			kfree(svsk);
 			return ERR_PTR(err);
 		}
@@ -1470,7 +1444,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	svsk->sk_owspace = inet->sk_write_space;
 	/*
 	 * This barrier is necessary in order to prevent race condition
-	 * with svc_data_ready(), svc_listen_data_ready() and others
+	 * with svc_data_ready(), svc_tcp_listen_data_ready(), and others
 	 * when calling callbacks above.
 	 */
 	wmb();
@@ -1482,29 +1456,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	else
 		svc_tcp_init(svsk, serv);
 
-	trace_svcsock_new_socket(sock);
+	trace_svcsock_new(svsk, sock);
 	return svsk;
 }
 
-bool svc_alien_sock(struct net *net, int fd)
-{
-	int err;
-	struct socket *sock = sockfd_lookup(fd, &err);
-	bool ret = false;
-
-	if (!sock)
-		goto out;
-	if (sock_net(sock->sk) != net)
-		ret = true;
-	sockfd_put(sock);
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(svc_alien_sock);
-
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
+ * @net: caller's network namespace
  * @fd: file descriptor of the new listener
  * @name_return: pointer to buffer to fill in with name of listener
  * @len: size of the buffer
@@ -1514,8 +1473,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock);
  * Name is terminated with '\n'.  On error, returns a negative errno
  * value.
  */
-int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
-		const size_t len, const struct cred *cred)
+int svc_addsock(struct svc_serv *serv, struct net *net, const int fd,
+		char *name_return, const size_t len, const struct cred *cred)
 {
 	int err = 0;
 	struct socket *so = sockfd_lookup(fd, &err);
@@ -1526,6 +1485,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 
 	if (!so)
 		return err;
+	err = -EINVAL;
+	if (sock_net(so->sk) != net)
+		goto out;
 	err = -EAFNOSUPPORT;
 	if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
 		goto out;
@@ -1675,6 +1637,8 @@ static void svc_sock_free(struct svc_xprt *xprt)
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 	struct socket *sock = svsk->sk_sock;
 
+	trace_svcsock_free(svsk, sock);
+
 	tls_handshake_cancel(sock->sk);
 	if (sock->file)
 		sockfd_put(sock);