[SRU][Q:linux-oracle][PATCH 1/1] sunrpc: allocate a separate bvec array for socket sends

[Vinicius Peixoto]

From: Jeff Layton <jlayton at kernel.org>

BugLink: https://bugs.launchpad.net/bugs/2147073

svc_tcp_sendmsg() calls xdr_buf_to_bvec() with the second slot of
rq_bvec as the start, but doesn't reduce the array length by one, which
could lead to an array overrun. Also, rq_bvec is always rq_maxpages in
length, which can be too short in some cases, since the TCP record
marker consumes a slot.

Fix both problems by adding a separate bvec array to the svc_sock that
is specifically for sending. For TCP, make this array one slot longer
than rq_maxpages, to account for the record marker. For UDP, only
allocate as large an array as we need since it's limited to 64k of
payload.

Signed-off-by: Jeff Layton <jlayton at kernel.org>
Reviewed-by: NeilBrown <neil at brown.name>
Signed-off-by: Chuck Lever <chuck.lever at oracle.com>
(cherry picked from commit 6b3b697d65d46a0f640216a3f6c72856c159c567)
Signed-off-by: Vinicius Peixoto <vinicius.peixoto at canonical.com>
---
 include/linux/sunrpc/svcsock.h |  3 ++
 net/sunrpc/svcsock.c           | 55 +++++++++++++++++++++++++++++-----
 2 files changed, 51 insertions(+), 7 deletions(-)

diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 963bbe251e52..de37069aba90 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -26,6 +26,9 @@ struct svc_sock {
 	void			(*sk_odata)(struct sock *);
 	void			(*sk_owspace)(struct sock *);
 
+	/* For sends (protected by xpt_mutex) */
+	struct bio_vec		*sk_bvec;
+
 	/* private TCP part */
 	/* On-the-wire fragment header: */
 	__be32			sk_marker;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b396c85ff072..60cb83dc9a55 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.
  */
@@ -740,14 +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);
 	}
@@ -1237,19 +1248,19 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
 	*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);
@@ -1397,6 +1408,20 @@ 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
  */
@@ -1407,12 +1432,26 @@ 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;
@@ -1424,6 +1463,7 @@ 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);
 		}
@@ -1641,5 +1681,6 @@ 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);
 }
-- 
2.51.0