[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <1386005715-27566-1-git-send-email-paul.durrant@citrix.com>
Date: Mon, 2 Dec 2013 17:35:15 +0000
From: Paul Durrant <paul.durrant@...rix.com>
To: <xen-devel@...ts.xen.org>, <netdev@...r.kernel.org>
CC: Paul Durrant <paul.durrant@...rix.com>,
Zoltan Kiss <zoltan.kiss@...rix.com>,
Wei Liu <wei.liu2@...rix.com>,
Ian Campbell <ian.campbell@...rix.com>,
David Vrabel <david.vrabel@...rix.com>,
David Miller <davem@...emloft.net>
Subject: [PATCH net v4] xen-netback: fix fragment detection in checksum setup
The code to detect fragments in checksum_setup() was missing for IPv4 and
too eager for IPv6. (It transpires that Windows seems to send IPv6 packets
with a fragment header even if they are not a fragment - i.e. offset is zero,
and M bit is not set).
This patch also incorporates a fix to callers of maybe_pull_tail() where
skb->network_header was being erroneously added to the length argument.
Signed-off-by: Paul Durrant <paul.durrant@...rix.com>
Signed-off-by: Zoltan Kiss <zoltan.kiss@...rix.com>
Cc: Wei Liu <wei.liu2@...rix.com>
Cc: Ian Campbell <ian.campbell@...rix.com>
Cc: David Vrabel <david.vrabel@...rix.com>
cc: David Miller <davem@...emloft.net>
---
v4
- Re-work maybe_pull_tail() to have a failure path and update mac and
network header pointers on success.
- Re-work callers of maybe_pull_tail() to handle failures and allow for
movement of skb header pointers.
- Incorporate fixes from patch "Fix pull size in checksum_setup_ip" since
it also modifies callers of maybe_pull_tail().
- Remove error messages in checksum routines that could be triggered by frontends
v3
- Use defined values for 'fragment offset' and 'more fragments'
v2
- Added comments noting what fragment/offset masks mean
drivers/net/xen-netback/netback.c | 215 ++++++++++++++++++++-----------------
include/linux/ipv6.h | 1 +
include/net/ipv6.h | 3 +-
3 files changed, 120 insertions(+), 99 deletions(-)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 64f0e0d..e3d7216 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1149,49 +1149,62 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
return 0;
}
-static inline void maybe_pull_tail(struct sk_buff *skb, unsigned int len)
+static inline bool maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+ unsigned int max)
{
- if (skb_is_nonlinear(skb) && skb_headlen(skb) < len) {
- /* If we need to pullup then pullup to the max, so we
- * won't need to do it again.
- */
- int target = min_t(int, skb->len, MAX_TCP_HEADER);
- __pskb_pull_tail(skb, target - skb_headlen(skb));
- }
+ if (skb_headlen(skb) >= len)
+ return true;
+
+ /* If we need to pullup then pullup to the max, so we
+ * won't need to do it again.
+ */
+ if (max > skb->len)
+ max = skb->len;
+
+ __pskb_pull_tail(skb, max - skb_headlen(skb));
+
+ return skb_headlen(skb) >= len;
}
+/* This value should be large enough to cover a tagged ethernet header plus
+ * maximally sized IP and TCP or UDP headers.
+ */
+#define MAX_IP_HDR_LEN 128
+
static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
int recalculate_partial_csum)
{
- struct iphdr *iph = (void *)skb->data;
- unsigned int header_size;
unsigned int off;
+ bool fragment;
int err = -EPROTO;
- off = sizeof(struct iphdr);
+ fragment = false;
- header_size = skb->network_header + off + MAX_IPOPTLEN;
- maybe_pull_tail(skb, header_size);
+ if (!maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN))
+ goto out;
+
+ if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+ fragment = true;
- off = iph->ihl * 4;
+ off = ip_hdrlen(skb);
- switch (iph->protocol) {
+ switch (ip_hdr(skb)->protocol) {
case IPPROTO_TCP:
if (!skb_partial_csum_set(skb, off,
offsetof(struct tcphdr, check)))
goto out;
if (recalculate_partial_csum) {
- struct tcphdr *tcph = tcp_hdr(skb);
-
- header_size = skb->network_header +
- off +
- sizeof(struct tcphdr);
- maybe_pull_tail(skb, header_size);
-
- tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
+ if (!maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IP_HDR_LEN))
+ goto out;
+
+ tcp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
}
break;
case IPPROTO_UDP:
@@ -1200,24 +1213,19 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
goto out;
if (recalculate_partial_csum) {
- struct udphdr *udph = udp_hdr(skb);
-
- header_size = skb->network_header +
- off +
- sizeof(struct udphdr);
- maybe_pull_tail(skb, header_size);
-
- udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
+ if (!maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IP_HDR_LEN))
+ goto out;
+
+ udp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
}
break;
default:
- if (net_ratelimit())
- netdev_err(vif->dev,
- "Attempting to checksum a non-TCP/UDP packet, "
- "dropping a protocol %d packet\n",
- iph->protocol);
goto out;
}
@@ -1227,75 +1235,93 @@ out:
return err;
}
+/* This value should be large enough to cover a tagged ethernet header plus
+ * an IPv6 header, all options, and a maximal TCP or UDP header.
+ */
+#define MAX_IPV6_HDR_LEN 256
+
+#define OPT_HDR(type, skb, off) \
+ (type *)(skb_network_header(skb) + (off))
+
static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
int recalculate_partial_csum)
{
int err = -EPROTO;
- struct ipv6hdr *ipv6h = (void *)skb->data;
u8 nexthdr;
- unsigned int header_size;
unsigned int off;
+ unsigned int len;
bool fragment;
bool done;
+ fragment = false;
done = false;
off = sizeof(struct ipv6hdr);
- header_size = skb->network_header + off;
- maybe_pull_tail(skb, header_size);
+ if (!maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN))
+ goto out;
- nexthdr = ipv6h->nexthdr;
+ nexthdr = ipv6_hdr(skb)->nexthdr;
- while ((off <= sizeof(struct ipv6hdr) + ntohs(ipv6h->payload_len)) &&
- !done) {
+ len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+ while (off <= len && !done) {
switch (nexthdr) {
case IPPROTO_DSTOPTS:
case IPPROTO_HOPOPTS:
case IPPROTO_ROUTING: {
- struct ipv6_opt_hdr *hp = (void *)(skb->data + off);
+ struct ipv6_opt_hdr *hp;
- header_size = skb->network_header +
- off +
- sizeof(struct ipv6_opt_hdr);
- maybe_pull_tail(skb, header_size);
+ if (!maybe_pull_tail(skb,
+ off +
+ sizeof(struct ipv6_opt_hdr),
+ MAX_IPV6_HDR_LEN))
+ goto out;
+ hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
nexthdr = hp->nexthdr;
off += ipv6_optlen(hp);
break;
}
case IPPROTO_AH: {
- struct ip_auth_hdr *hp = (void *)(skb->data + off);
+ struct ip_auth_hdr *hp;
+
+ if (!maybe_pull_tail(skb,
+ off +
+ sizeof(struct ip_auth_hdr),
+ MAX_IPV6_HDR_LEN))
+ goto out;
+
+ hp = OPT_HDR(struct ip_auth_hdr, skb, off);
+ nexthdr = hp->nexthdr;
+ off += ipv6_authlen(hp);
+ break;
+ }
+ case IPPROTO_FRAGMENT: {
+ struct frag_hdr *hp;
+
+ if (!maybe_pull_tail(skb,
+ off +
+ sizeof(struct frag_hdr),
+ MAX_IPV6_HDR_LEN))
+ goto out;
+
+ hp = OPT_HDR(struct frag_hdr, skb, off);
- header_size = skb->network_header +
- off +
- sizeof(struct ip_auth_hdr);
- maybe_pull_tail(skb, header_size);
+ if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+ fragment = true;
nexthdr = hp->nexthdr;
- off += (hp->hdrlen+2)<<2;
+ off += sizeof(struct frag_hdr);
break;
}
- case IPPROTO_FRAGMENT:
- fragment = true;
- /* fall through */
default:
done = true;
break;
}
}
- if (!done) {
- if (net_ratelimit())
- netdev_err(vif->dev, "Failed to parse packet header\n");
+ if (!done || fragment)
goto out;
- }
-
- if (fragment) {
- if (net_ratelimit())
- netdev_err(vif->dev, "Packet is a fragment!\n");
- goto out;
- }
switch (nexthdr) {
case IPPROTO_TCP:
@@ -1304,17 +1330,16 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
goto out;
if (recalculate_partial_csum) {
- struct tcphdr *tcph = tcp_hdr(skb);
-
- header_size = skb->network_header +
- off +
- sizeof(struct tcphdr);
- maybe_pull_tail(skb, header_size);
-
- tcph->check = ~csum_ipv6_magic(&ipv6h->saddr,
- &ipv6h->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
+ if (!maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IPV6_HDR_LEN))
+ goto out;
+
+ tcp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
}
break;
case IPPROTO_UDP:
@@ -1323,25 +1348,19 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
goto out;
if (recalculate_partial_csum) {
- struct udphdr *udph = udp_hdr(skb);
-
- header_size = skb->network_header +
- off +
- sizeof(struct udphdr);
- maybe_pull_tail(skb, header_size);
-
- udph->check = ~csum_ipv6_magic(&ipv6h->saddr,
- &ipv6h->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
+ if (!maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IPV6_HDR_LEN))
+ goto out;
+
+ udp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
}
break;
default:
- if (net_ratelimit())
- netdev_err(vif->dev,
- "Attempting to checksum a non-TCP/UDP packet, "
- "dropping a protocol %d packet\n",
- nexthdr);
goto out;
}
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5d89d1b..c56c350 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -4,6 +4,7 @@
#include <uapi/linux/ipv6.h>
#define ipv6_optlen(p) (((p)->hdrlen+1) << 3)
+#define ipv6_authlen(p) (((p)->hdrlen+2) << 2)
/*
* This structure contains configuration options per IPv6 link.
*/
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index eb198ac..488316e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -110,7 +110,8 @@ struct frag_hdr {
__be32 identification;
};
-#define IP6_MF 0x0001
+#define IP6_MF 0x0001
+#define IP6_OFFSET 0xFFF8
#include <net/sock.h>
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists