Merge branch 'csum_partial_frags'

Hannes Frederic Sowa says:

====================
net: clean up interactions of CHECKSUM_PARTIAL and fragmentation

This series fixes wrong checksums on the wire for IPv4 and IPv6. Large
send buffers and especially NFS lead to wrong checksums in both IPv4
and IPv6.

CHECKSUM_PARTIAL skbs should not receive the respective fragmentations
functions, so we add WARN_ON_ONCE to those functions to fix up those as
soon as they get reported.

Changelog:
v2: added v4 checks
v3: removed WARN_ON_ONCES (advice by Tom Herbert)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 43 insertions, 44 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 50e29737b584..4233cbe47052 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -533,6 +533,11 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 	dev = rt->dst.dev;
 
+	/* for offloaded checksums cleanup checksum before fragmentation */
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (err = skb_checksum_help(skb)))
+		goto fail;
+
 	/*
 	 *	Point into the IP datagram header.
 	 */
@@ -657,9 +662,6 @@ slow_path_clean:
 	}
 
 slow_path:
-	/* for offloaded checksums cleanup checksum before fragmentation */
-	if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb))
-		goto fail;
 	iph = ip_hdr(skb);
 
 	left = skb->len - hlen;		/* Space per frame */
@@ -911,6 +913,7 @@ static int __ip_append_data(struct sock *sk,
 	if (transhdrlen &&
 	    length + fragheaderlen <= mtu &&
 	    rt->dst.dev->features & NETIF_F_V4_CSUM &&
+	    !(flags & MSG_MORE) &&
 	    !exthdrlen)
 		csummode = CHECKSUM_PARTIAL;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3c8e9d8795cd..e6a7bd15b9b7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -603,6 +603,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
 				    &ipv6_hdr(skb)->saddr);
 
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (err = skb_checksum_help(skb)))
+		goto fail;
+
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		int first_len = skb_pagelen(skb);
@@ -731,10 +735,6 @@ slow_path_clean:
 	}
 
 slow_path:
-	if ((skb->ip_summed == CHECKSUM_PARTIAL) &&
-	    skb_checksum_help(skb))
-		goto fail;
-
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;			/* Where to start from */
 
@@ -1270,6 +1270,7 @@ static int __ip6_append_data(struct sock *sk,
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
+	unsigned int maxnonfragsize, headersize;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1287,38 +1288,43 @@ static int __ip6_append_data(struct sock *sk,
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
 		     sizeof(struct frag_hdr);
 
-	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		unsigned int maxnonfragsize, headersize;
-
-		headersize = sizeof(struct ipv6hdr) +
-			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
-			     (dst_allfrag(&rt->dst) ?
-			      sizeof(struct frag_hdr) : 0) +
-			     rt->rt6i_nfheader_len;
-
-		if (ip6_sk_ignore_df(sk))
-			maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
-		else
-			maxnonfragsize = mtu;
+	headersize = sizeof(struct ipv6hdr) +
+		     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
+		     (dst_allfrag(&rt->dst) ?
+		      sizeof(struct frag_hdr) : 0) +
+		     rt->rt6i_nfheader_len;
+
+	if (cork->length + length > mtu - headersize && dontfrag &&
+	    (sk->sk_protocol == IPPROTO_UDP ||
+	     sk->sk_protocol == IPPROTO_RAW)) {
+		ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+				sizeof(struct ipv6hdr));
+		goto emsgsize;
+	}
 
-		/* dontfrag active */
-		if ((cork->length + length > mtu - headersize) && dontfrag &&
-		    (sk->sk_protocol == IPPROTO_UDP ||
-		     sk->sk_protocol == IPPROTO_RAW)) {
-			ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
-						   sizeof(struct ipv6hdr));
-			goto emsgsize;
-		}
+	if (ip6_sk_ignore_df(sk))
+		maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+	else
+		maxnonfragsize = mtu;
 
-		if (cork->length + length > maxnonfragsize - headersize) {
+	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-			ipv6_local_error(sk, EMSGSIZE, fl6,
-					 mtu - headersize +
-					 sizeof(struct ipv6hdr));
-			return -EMSGSIZE;
-		}
+		ipv6_local_error(sk, EMSGSIZE, fl6,
+				 mtu - headersize +
+				 sizeof(struct ipv6hdr));
+		return -EMSGSIZE;
 	}
 
+	/* CHECKSUM_PARTIAL only with no extension headers and when
+	 * we are not going to fragment
+	 */
+	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
+	    headersize == sizeof(struct ipv6hdr) &&
+	    length < mtu - headersize &&
+	    !(flags & MSG_MORE) &&
+	    rt->dst.dev->features & NETIF_F_V6_CSUM)
+		csummode = CHECKSUM_PARTIAL;
+
 	if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
 		sock_tx_timestamp(sk, &tx_flags);
 		if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
@@ -1326,16 +1332,6 @@ emsgsize:
 			tskey = sk->sk_tskey++;
 	}
 
-	/* If this is the first and only packet and device
-	 * supports checksum offloading, let's use it.
-	 * Use transhdrlen, same as IPv4, because partial
-	 * sums only work when transhdrlen is set.
-	 */
-	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
-	    length + fragheaderlen < mtu &&
-	    rt->dst.dev->features & NETIF_F_V6_CSUM &&
-	    !exthdrlen)
-		csummode = CHECKSUM_PARTIAL;
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.