net: add skb_checksum_setup

This patch adds a function to set up the partial checksum offset for IP
packets (and optionally re-calculate the pseudo-header checksum) into the
core network code.
The implementation was previously private and duplicated between xen-netback
and xen-netfront, however it is not xen-specific and is potentially useful
to any network driver.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 275 insertions, 0 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d97f2d07d02b..48b760505cb6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2893,6 +2893,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb)
 
 bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
 
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
+
 u32 __skb_get_poff(const struct sk_buff *skb);
 
 /**
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1d641e781f85..15057d29b010 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -65,6 +65,7 @@
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/checksum.h>
+#include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
 #include <asm/uaccess.h>
@@ -3549,6 +3550,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 }
 EXPORT_SYMBOL_GPL(skb_partial_csum_set);
 
+static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+                               unsigned int max)
+{
+        if (skb_headlen(skb) >= len)
+                return 0;
+
+        /* 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;
+
+        if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
+                return -ENOMEM;
+
+        if (skb_headlen(skb) < len)
+                return -EPROTO;
+
+        return 0;
+}
+
+/* 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 skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+{
+        unsigned int off;
+        bool fragment;
+        int err;
+
+        fragment = false;
+
+        err = skb_maybe_pull_tail(skb,
+                                  sizeof(struct iphdr),
+                                  MAX_IP_HDR_LEN);
+        if (err < 0)
+                goto out;
+
+        if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+                fragment = true;
+
+        off = ip_hdrlen(skb);
+
+        err = -EPROTO;
+
+        if (fragment)
+                goto out;
+
+        switch (ip_hdr(skb)->protocol) {
+        case IPPROTO_TCP:
+                err = skb_maybe_pull_tail(skb,
+                                          off + sizeof(struct tcphdr),
+                                          MAX_IP_HDR_LEN);
+                if (err < 0)
+                        goto out;
+
+                if (!skb_partial_csum_set(skb, off,
+                                          offsetof(struct tcphdr, check))) {
+                        err = -EPROTO;
+                        goto out;
+                }
+
+                if (recalculate)
+                        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:
+                err = skb_maybe_pull_tail(skb,
+                                          off + sizeof(struct udphdr),
+                                          MAX_IP_HDR_LEN);
+                if (err < 0)
+                        goto out;
+
+                if (!skb_partial_csum_set(skb, off,
+                                          offsetof(struct udphdr, check))) {
+                        err = -EPROTO;
+                        goto out;
+                }
+
+                if (recalculate)
+                        udp_hdr(skb)->check =
+                                ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+                                                   ip_hdr(skb)->daddr,
+                                                   skb->len - off,
+                                                   IPPROTO_UDP, 0);
+                break;
+        default:
+                goto out;
+        }
+
+        err = 0;
+
+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 skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
+{
+        int err;
+        u8 nexthdr;
+        unsigned int off;
+        unsigned int len;
+        bool fragment;
+        bool done;
+
+        fragment = false;
+        done = false;
+
+        off = sizeof(struct ipv6hdr);
+
+        err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
+        if (err < 0)
+                goto out;
+
+        nexthdr = ipv6_hdr(skb)->nexthdr;
+
+        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;
+
+                        err = skb_maybe_pull_tail(skb,
+                                                  off +
+                                                  sizeof(struct ipv6_opt_hdr),
+                                                  MAX_IPV6_HDR_LEN);
+                        if (err < 0)
+                                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;
+
+                        err = skb_maybe_pull_tail(skb,
+                                                  off +
+                                                  sizeof(struct ip_auth_hdr),
+                                                  MAX_IPV6_HDR_LEN);
+                        if (err < 0)
+                                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;
+
+                        err = skb_maybe_pull_tail(skb,
+                                                  off +
+                                                  sizeof(struct frag_hdr),
+                                                  MAX_IPV6_HDR_LEN);
+                        if (err < 0)
+                                goto out;
+
+                        hp = OPT_HDR(struct frag_hdr, skb, off);
+
+                        if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+                                fragment = true;
+
+                        nexthdr = hp->nexthdr;
+                        off += sizeof(struct frag_hdr);
+                        break;
+                }
+                default:
+                        done = true;
+                        break;
+                }
+        }
+
+        err = -EPROTO;
+
+        if (!done || fragment)
+                goto out;
+
+        switch (nexthdr) {
+        case IPPROTO_TCP:
+                err = skb_maybe_pull_tail(skb,
+                                          off + sizeof(struct tcphdr),
+                                          MAX_IPV6_HDR_LEN);
+                if (err < 0)
+                        goto out;
+
+                if (!skb_partial_csum_set(skb, off,
+                                          offsetof(struct tcphdr, check))) {
+                        err = -EPROTO;
+                        goto out;
+                }
+
+                if (recalculate)
+                        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:
+                err = skb_maybe_pull_tail(skb,
+                                          off + sizeof(struct udphdr),
+                                          MAX_IPV6_HDR_LEN);
+                if (err < 0)
+                        goto out;
+
+                if (!skb_partial_csum_set(skb, off,
+                                          offsetof(struct udphdr, check))) {
+                        err = -EPROTO;
+                        goto out;
+                }
+
+                if (recalculate)
+                        udp_hdr(skb)->check =
+                                ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+                                                 &ipv6_hdr(skb)->daddr,
+                                                 skb->len - off,
+                                                 IPPROTO_UDP, 0);
+                break;
+        default:
+                goto out;
+        }
+
+        err = 0;
+
+out:
+        return err;
+}
+
+/**
+ * skb_checksum_setup - set up partial checksum offset
+ * @skb: the skb to set up
+ * @recalculate: if true the pseudo-header checksum will be recalculated
+ */
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
+{
+        int err;
+
+        switch (skb->protocol) {
+        case htons(ETH_P_IP):
+                err = skb_checksum_setup_ip(skb, recalculate);
+                break;
+
+        case htons(ETH_P_IPV6):
+                err = skb_checksum_setup_ipv6(skb, recalculate);
+                break;
+
+        default:
+                err = -EPROTO;
+                break;
+        }
+
+        return err;
+}
+EXPORT_SYMBOL(skb_checksum_setup);
+
 void __skb_warn_lro_forwarding(const struct sk_buff *skb)
 {
         net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",