10 files changed, 212 insertions, 43 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index caa0278d30a9..bf85d5f97032 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -772,6 +772,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
         struct sk_buff *segs = ERR_PTR(-EINVAL);
         struct ipv6hdr *ipv6h;
         struct inet6_protocol *ops;
+        int proto;
+        struct frag_hdr *fptr;
+        unsigned int unfrag_ip6hlen;
+        u8 *prevhdr;
+        int offset = 0;
 
         if (!(features & NETIF_F_V6_CSUM))
                 features &= ~NETIF_F_SG;
@@ -791,10 +796,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
         __skb_pull(skb, sizeof(*ipv6h));
         segs = ERR_PTR(-EPROTONOSUPPORT);
 
+        proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
         rcu_read_lock();
-        ops = rcu_dereference(inet6_protos[
-                ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
-
+        ops = rcu_dereference(inet6_protos[proto]);
         if (likely(ops && ops->gso_segment)) {
                 skb_reset_transport_header(skb);
                 segs = ops->gso_segment(skb, features);
@@ -808,6 +812,16 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
                 ipv6h = ipv6_hdr(skb);
                 ipv6h->payload_len = htons(skb->len - skb->mac_len -
                                            sizeof(*ipv6h));
+                if (proto == IPPROTO_UDP) {
+                        unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+                        fptr = (struct frag_hdr *)(skb_network_header(skb) +
+                                unfrag_ip6hlen);
+                        fptr->frag_off = htons(offset);
+                        if (skb->next != NULL)
+                                fptr->frag_off |= htons(IP6_MF);
+                        offset += (ntohs(ipv6h->payload_len) -
+                                   sizeof(struct frag_hdr));
+                }
         }
 
 out:
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 52ee1dced2ff..0e93ca56eb69 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -164,12 +164,6 @@ static __inline__ void rt6_release(struct rt6_info *rt)
                 dst_free(&rt->u.dst);
 }
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-#define FIB_TABLE_HASHSZ 256
-#else
-#define FIB_TABLE_HASHSZ 1
-#endif
-
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
         unsigned int h;
@@ -180,7 +174,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb)
          */
         rwlock_init(&tb->tb6_lock);
 
-        h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1);
+        h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1);
 
         /*
          * No protection necessary, this is the only list mutatation
@@ -231,7 +225,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id)
 
         if (id == 0)
                 id = RT6_TABLE_MAIN;
-        h = id & (FIB_TABLE_HASHSZ - 1);
+        h = id & (FIB6_TABLE_HASHSZ - 1);
         rcu_read_lock();
         head = &net->ipv6.fib_table_hash[h];
         hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
@@ -382,7 +376,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
         arg.net = net;
         w->args = &arg;
 
-        for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
+        for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) {
                 e = 0;
                 head = &net->ipv6.fib_table_hash[h];
                 hlist_for_each_entry(tb, node, head, tb6_hlist) {
@@ -1368,7 +1362,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
         unsigned int h;
 
         rcu_read_lock();
-        for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+        for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
                 head = &net->ipv6.fib_table_hash[h];
                 hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
                         write_lock_bh(&table->tb6_lock);
@@ -1483,7 +1477,7 @@ static int fib6_net_init(struct net *net)
         if (!net->ipv6.rt6_stats)
                 goto out_timer;
 
-        net->ipv6.fib_table_hash = kcalloc(FIB_TABLE_HASHSZ,
+        net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ,
                                            sizeof(*net->ipv6.fib_table_hash),
                                            GFP_KERNEL);
         if (!net->ipv6.fib_table_hash)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 6d6a4277c677..2d9cbaa67edb 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -63,7 +63,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 
         if (skb->pkt_type == PACKET_OTHERHOST) {
                 kfree_skb(skb);
-                return 0;
+                return NET_RX_DROP;
         }
 
         rcu_read_lock();
@@ -133,7 +133,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
                 if (ipv6_parse_hopopts(skb) < 0) {
                         IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
                         rcu_read_unlock();
-                        return 0;
+                        return NET_RX_DROP;
                 }
         }
 
@@ -149,7 +149,7 @@ err:
 drop:
         rcu_read_unlock();
         kfree_skb(skb);
-        return 0;
+        return NET_RX_DROP;
 }
 
 /*
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 87f8419a68fd..93beee944657 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -57,18 +57,6 @@
 
 static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
 
-static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr)
-{
-        static u32 ipv6_fragmentation_id = 1;
-        static DEFINE_SPINLOCK(ip6_id_lock);
-
-        spin_lock_bh(&ip6_id_lock);
-        fhdr->identification = htonl(ipv6_fragmentation_id);
-        if (++ipv6_fragmentation_id == 0)
-                ipv6_fragmentation_id = 1;
-        spin_unlock_bh(&ip6_id_lock);
-}
-
 int __ip6_local_out(struct sk_buff *skb)
 {
         int len;
@@ -706,7 +694,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                 skb_reset_network_header(skb);
                 memcpy(skb_network_header(skb), tmp_hdr, hlen);
 
-                ipv6_select_ident(skb, fh);
+                ipv6_select_ident(fh);
                 fh->nexthdr = nexthdr;
                 fh->reserved = 0;
                 fh->frag_off = htons(IP6_MF);
@@ -844,7 +832,7 @@ slow_path:
                 fh->nexthdr = nexthdr;
                 fh->reserved = 0;
                 if (!frag_id) {
-                        ipv6_select_ident(skb, fh);
+                        ipv6_select_ident(fh);
                         frag_id = fh->identification;
                 } else
                         fh->identification = frag_id;
@@ -1087,11 +1075,13 @@ static inline int ip6_ufo_append_data(struct sock *sk,
         if (!err) {
                 struct frag_hdr fhdr;
 
-                /* specify the length of each IP datagram fragment*/
-                skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
-                                            sizeof(struct frag_hdr);
+                /* Specify the length of each IPv6 datagram fragment.
+                 * It has to be a multiple of 8.
+                 */
+                skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
+                                             sizeof(struct frag_hdr)) & ~7;
                 skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-                ipv6_select_ident(skb, &fhdr);
+                ipv6_select_ident(&fhdr);
                 skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
                 __skb_queue_tail(&sk->sk_write_queue, skb);
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 51f410e7775a..a1d6045c4694 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1063,14 +1063,14 @@ ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
                 goto tx_err;
 
         t->recursion--;
-        return 0;
+        return NETDEV_TX_OK;
 
 tx_err:
         stats->tx_errors++;
         stats->tx_dropped++;
         kfree_skb(skb);
         t->recursion--;
-        return 0;
+        return NETDEV_TX_OK;
 }
 
 static void ip6_tnl_set_cap(struct ip6_tnl *t)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index c769f155c698..07ded5075b33 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -427,7 +427,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
                            MRT6MSG_WHOLEPKT);
         read_unlock(&mrt_lock);
         kfree_skb(skb);
-        return 0;
+        return NETDEV_TX_OK;
 }
 
 static const struct net_device_ops reg_vif_netdev_ops = {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 4b264ed40a8c..71c3dacec1ed 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2107,7 +2107,6 @@ static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca,
                 for (j=0; j<i; j++)
                         (void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]);
         } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) {
-                struct inet6_dev *idev = pmc->idev;
                 struct ip6_sf_list *psf;
 
                 /* filter mode change */
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 98b7327d0949..d335a306a4db 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -753,7 +753,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
                         stats->tx_dropped++;
                         dev_kfree_skb(skb);
                         tunnel->recursion--;
-                        return 0;
+                        return NETDEV_TX_OK;
                 }
                 if (skb->sk)
                         skb_set_owner_w(new_skb, skb->sk);
@@ -794,7 +794,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
         IPTUNNEL_XMIT();
         tunnel->recursion--;
-        return 0;
+        return NETDEV_TX_OK;
 
 tx_error_icmp:
         dst_link_failure(skb);
@@ -802,7 +802,7 @@ tx_error:
         stats->tx_errors++;
         dev_kfree_skb(skb);
         tunnel->recursion--;
-        return 0;
+        return NETDEV_TX_OK;
 }
 
 static void ipip6_tunnel_bind_dev(struct net_device *dev)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 33b59bd92c4d..d79fa6724451 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -638,6 +638,47 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
         }
 }
 
+/**
+ *      udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
+ *      @sk:    socket we are sending on
+ *      @skb:   sk_buff containing the filled-in UDP header
+ *              (checksum field must be zeroed out)
+ */
+static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
+                                 const struct in6_addr *saddr,
+                                 const struct in6_addr *daddr, int len)
+{
+        unsigned int offset;
+        struct udphdr *uh = udp_hdr(skb);
+        __wsum csum = 0;
+
+        if (skb_queue_len(&sk->sk_write_queue) == 1) {
+                /* Only one fragment on the socket.  */
+                skb->csum_start = skb_transport_header(skb) - skb->head;
+                skb->csum_offset = offsetof(struct udphdr, check);
+                uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0);
+        } else {
+                /*
+                 * HW-checksum won't work as there are two or more
+                 * fragments on the socket so that all csums of sk_buffs
+                 * should be together
+                 */
+                offset = skb_transport_offset(skb);
+                skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+
+                skb->ip_summed = CHECKSUM_NONE;
+
+                skb_queue_walk(&sk->sk_write_queue, skb) {
+                        csum = csum_add(csum, skb->csum);
+                }
+
+                uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
+                                            csum);
+                if (uh->check == 0)
+                        uh->check = CSUM_MANGLED_0;
+        }
+}
+
 /*
  *      Sending
  */
@@ -668,7 +709,11 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 
         if (is_udplite)
                 csum = udplite_csum_outgoing(sk, skb);
-         else
+        else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+                udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst,
+                                     up->len);
+                goto send;
+        } else
                 csum = udp_csum_outgoing(sk, skb);
 
         /* add protocol-dependent pseudo-header */
@@ -677,6 +722,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
         if (uh->check == 0)
                 uh->check = CSUM_MANGLED_0;
 
+send:
         err = ip6_push_pending_frames(sk);
 out:
         up->len = 0;
@@ -1032,9 +1078,102 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 }
 #endif
 
+static int udp6_ufo_send_check(struct sk_buff *skb)
+{
+        struct ipv6hdr *ipv6h;
+        struct udphdr *uh;
+
+        if (!pskb_may_pull(skb, sizeof(*uh)))
+                return -EINVAL;
+
+        ipv6h = ipv6_hdr(skb);
+        uh = udp_hdr(skb);
+
+        uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
+                                     IPPROTO_UDP, 0);
+        skb->csum_start = skb_transport_header(skb) - skb->head;
+        skb->csum_offset = offsetof(struct udphdr, check);
+        skb->ip_summed = CHECKSUM_PARTIAL;
+        return 0;
+}
+
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features)
+{
+        struct sk_buff *segs = ERR_PTR(-EINVAL);
+        unsigned int mss;
+        unsigned int unfrag_ip6hlen, unfrag_len;
+        struct frag_hdr *fptr;
+        u8 *mac_start, *prevhdr;
+        u8 nexthdr;
+        u8 frag_hdr_sz = sizeof(struct frag_hdr);
+        int offset;
+        __wsum csum;
+
+        mss = skb_shinfo(skb)->gso_size;
+        if (unlikely(skb->len <= mss))
+                goto out;
+
+        if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+                /* Packet is from an untrusted source, reset gso_segs. */
+                int type = skb_shinfo(skb)->gso_type;
+
+                if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+                             !(type & (SKB_GSO_UDP))))
+                        goto out;
+
+                skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+                segs = NULL;
+                goto out;
+        }
+
+        /* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+         * do checksum of UDP packets sent as multiple IP fragments.
+         */
+        offset = skb->csum_start - skb_headroom(skb);
+        csum = skb_checksum(skb, offset, skb->len- offset, 0);
+        offset += skb->csum_offset;
+        *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+        skb->ip_summed = CHECKSUM_NONE;
+
+        /* Check if there is enough headroom to insert fragment header. */
+        if ((skb_headroom(skb) < frag_hdr_sz) &&
+            pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC))
+                goto out;
+
+        /* Find the unfragmentable header and shift it left by frag_hdr_sz
+         * bytes to insert fragment header.
+         */
+        unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+        nexthdr = *prevhdr;
+        *prevhdr = NEXTHDR_FRAGMENT;
+        unfrag_len = skb_network_header(skb) - skb_mac_header(skb) +
+                     unfrag_ip6hlen;
+        mac_start = skb_mac_header(skb);
+        memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len);
+
+        skb->mac_header -= frag_hdr_sz;
+        skb->network_header -= frag_hdr_sz;
+
+        fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+        fptr->nexthdr = nexthdr;
+        fptr->reserved = 0;
+        ipv6_select_ident(fptr);
+
+        /* Fragment the skb. ipv6 header and the remaining fields of the
+         * fragment header are updated in ipv6_gso_segment()
+         */
+        segs = skb_segment(skb, features);
+
+out:
+        return segs;
+}
+
 static struct inet6_protocol udpv6_protocol = {
         .handler        =       udpv6_rcv,
         .err_handler    =       udpv6_err,
+        .gso_send_check =       udp6_ufo_send_check,
+        .gso_segment    =       udp6_ufo_fragment,
         .flags          =       INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 3a3c677bc0f2..611cffcf554f 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -306,9 +306,24 @@ static void xfrm6_policy_fini(void)
         xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo);
 }
 
+static struct ctl_table xfrm6_policy_table[] = {
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "xfrm6_gc_thresh",
+                .data           = &xfrm6_dst_ops.gc_thresh,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec,
+        },
+        { }
+};
+
+static struct ctl_table_header *sysctl_hdr;
+
 int __init xfrm6_init(void)
 {
         int ret;
+        unsigned int gc_thresh;
 
         ret = xfrm6_policy_init();
         if (ret)
@@ -317,6 +332,22 @@ int __init xfrm6_init(void)
         ret = xfrm6_state_init();
         if (ret)
                 goto out_policy;
+        /*
+         * We need a good default value for the xfrm6 gc threshold.
+         * In ipv4 we set it to the route hash table size * 8, which
+         * is half the size of the maximaum route cache for ipv4.  It
+         * would be good to do the same thing for v6, except the table is
+         * constructed differently here.  Here each table for a net namespace
+         * can have FIB_TABLE_HASHSZ entries, so lets go with the same
+         * computation that we used for ipv4 here.  Also, lets keep the initial
+         * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults
+         * to that as a minimum as well
+         */
+        gc_thresh = FIB6_TABLE_HASHSZ * 8;
+        xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh;
+
+        sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path,
+                                                xfrm6_policy_table);
 out:
         return ret;
 out_policy:
@@ -326,6 +357,8 @@ out_policy:
 
 void xfrm6_fini(void)
 {
+        if (sysctl_hdr)
+                unregister_net_sysctl_table(sysctl_hdr);
         //xfrm6_input_fini();
         xfrm6_policy_fini();
         xfrm6_state_fini();