CHECKSUM_PARTIAL should only be used on plain vanilla IPv6 + UDP packets
in ip6_append_data. Some drivers don't correctly handle extension headers,
especially not ipv6 fragmentation which could result in broken checksums.
1) This patch improves the test for fragmentation and extension headers
in ip6_append_data, so we set the ip_summed mode as early as possible
to the correct value to compute the checksum during memory copy-in from
user space.
2) We always call skb_checksum_help on CHECKSUM_PARTIAL fragments in
ip6_fragment, because we don't know if the underlying hardware can deal
with ip6_fragments.
Fixes: commit 32dce968dd987 ("ipv6: Allow for partial checksums on non-ufo
packets")
See-also: commit 72e843bb09d45 ("ipv6: ip6_fragment() should check
CHECKSUM_PARTIAL")
Cc: Eric Dumazet <eduma...@google.com>
Cc: Vlad Yasevich <vyasev...@gmail.com>
Cc: Benjamin Coddington <bcodd...@redhat.com>
Signed-off-by: Hannes Frederic Sowa <han...@stressinduktion.org>
---
net/ipv6/ip6_output.c | 78 ++++++++++++++++++++++++---------------------------
1 file changed, 37 insertions(+), 41 deletions(-)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8dddb45..26d2911 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -593,6 +593,10 @@ int ip6_fragment(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);
@@ -721,10 +725,6 @@ 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 */
@@ -1260,6 +1260,7 @@ 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) {
@@ -1277,38 +1278,43 @@ 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 &&
@@ -1316,16 +1322,6 @@ 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.
--
2.4.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
