[NET]: Add software TSOv4

This patch adds the GSO implementation for IPv4 TCP.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 243 insertions, 0 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 97b0d2d1a6b0..a45bba9b8cbd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1297,6 +1297,7 @@ extern void	       skb_split(struct sk_buff *skb,
                                  struct sk_buff *skb1, const u32 len);
 
 extern void            skb_release_data(struct sk_buff *skb);
+extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
                                        int len, void *buffer)
diff --git a/include/net/protocol.h b/include/net/protocol.h
index bcaee39bd2ff..3b6dc15c68a5 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -36,6 +36,7 @@
 struct net_protocol {
         int                     (*handler)(struct sk_buff *skb);
         void                    (*err_handler)(struct sk_buff *skb, u32 info);
+        struct sk_buff         *(*gso_segment)(struct sk_buff *skb, int sg);
         int                     no_policy;
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b197a9e615c1..ca3d38dfc00b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1086,6 +1086,8 @@ extern struct request_sock_ops tcp_request_sock_ops;
 
 extern int tcp_v4_destroy_sock(struct sock *sk);
 
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg);
+
 #ifdef CONFIG_PROC_FS
 extern int  tcp4_proc_init(void);
 extern void tcp4_proc_exit(void);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 368d98578c14..8e5044ba3ab6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1842,6 +1842,132 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
+/**
+ *      skb_segment - Perform protocol segmentation on skb.
+ *      @skb: buffer to segment
+ *      @sg: whether scatter-gather can be used for generated segments
+ *
+ *      This function performs segmentation on the given skb.  It returns
+ *      the segment at the given position.  It returns NULL if there are
+ *      no more segments to generate, or when an error is encountered.
+ */
+struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
+{
+        struct sk_buff *segs = NULL;
+        struct sk_buff *tail = NULL;
+        unsigned int mss = skb_shinfo(skb)->gso_size;
+        unsigned int doffset = skb->data - skb->mac.raw;
+        unsigned int offset = doffset;
+        unsigned int headroom;
+        unsigned int len;
+        int nfrags = skb_shinfo(skb)->nr_frags;
+        int err = -ENOMEM;
+        int i = 0;
+        int pos;
+
+        __skb_push(skb, doffset);
+        headroom = skb_headroom(skb);
+        pos = skb_headlen(skb);
+
+        do {
+                struct sk_buff *nskb;
+                skb_frag_t *frag;
+                int hsize, nsize;
+                int k;
+                int size;
+
+                len = skb->len - offset;
+                if (len > mss)
+                        len = mss;
+
+                hsize = skb_headlen(skb) - offset;
+                if (hsize < 0)
+                        hsize = 0;
+                nsize = hsize + doffset;
+                if (nsize > len + doffset || !sg)
+                        nsize = len + doffset;
+
+                nskb = alloc_skb(nsize + headroom, GFP_ATOMIC);
+                if (unlikely(!nskb))
+                        goto err;
+
+                if (segs)
+                        tail->next = nskb;
+                else
+                        segs = nskb;
+                tail = nskb;
+
+                nskb->dev = skb->dev;
+                nskb->priority = skb->priority;
+                nskb->protocol = skb->protocol;
+                nskb->dst = dst_clone(skb->dst);
+                memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+                nskb->pkt_type = skb->pkt_type;
+                nskb->mac_len = skb->mac_len;
+
+                skb_reserve(nskb, headroom);
+                nskb->mac.raw = nskb->data;
+                nskb->nh.raw = nskb->data + skb->mac_len;
+                nskb->h.raw = nskb->nh.raw + (skb->h.raw - skb->nh.raw);
+                memcpy(skb_put(nskb, doffset), skb->data, doffset);
+
+                if (!sg) {
+                        nskb->csum = skb_copy_and_csum_bits(skb, offset,
+                                                            skb_put(nskb, len),
+                                                            len, 0);
+                        continue;
+                }
+
+                frag = skb_shinfo(nskb)->frags;
+                k = 0;
+
+                nskb->ip_summed = CHECKSUM_HW;
+                nskb->csum = skb->csum;
+                memcpy(skb_put(nskb, hsize), skb->data + offset, hsize);
+
+                while (pos < offset + len) {
+                        BUG_ON(i >= nfrags);
+
+                        *frag = skb_shinfo(skb)->frags[i];
+                        get_page(frag->page);
+                        size = frag->size;
+
+                        if (pos < offset) {
+                                frag->page_offset += offset - pos;
+                                frag->size -= offset - pos;
+                        }
+
+                        k++;
+
+                        if (pos + size <= offset + len) {
+                                i++;
+                                pos += size;
+                        } else {
+                                frag->size -= pos + size - (offset + len);
+                                break;
+                        }
+
+                        frag++;
+                }
+
+                skb_shinfo(nskb)->nr_frags = k;
+                nskb->data_len = len - hsize;
+                nskb->len += nskb->data_len;
+                nskb->truesize += nskb->data_len;
+        } while ((offset += len) < skb->len);
+
+        return segs;
+
+err:
+        while ((skb = segs)) {
+                segs = skb->next;
+                kfree(skb);
+        }
+        return ERR_PTR(err);
+}
+
+EXPORT_SYMBOL_GPL(skb_segment);
+
 void __init skb_init(void)
 {
         skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0a277453526b..461216b47948 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -68,6 +68,7 @@
  */
 
 #include <linux/config.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/socket.h>
@@ -1096,6 +1097,54 @@ int inet_sk_rebuild_header(struct sock *sk)
 
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
+{
+        struct sk_buff *segs = ERR_PTR(-EINVAL);
+        struct iphdr *iph;
+        struct net_protocol *ops;
+        int proto;
+        int ihl;
+        int id;
+
+        if (!pskb_may_pull(skb, sizeof(*iph)))
+                goto out;
+
+        iph = skb->nh.iph;
+        ihl = iph->ihl * 4;
+        if (ihl < sizeof(*iph))
+                goto out;
+
+        if (!pskb_may_pull(skb, ihl))
+                goto out;
+
+        skb->h.raw = __skb_pull(skb, ihl);
+        iph = skb->nh.iph;
+        id = ntohs(iph->id);
+        proto = iph->protocol & (MAX_INET_PROTOS - 1);
+        segs = ERR_PTR(-EPROTONOSUPPORT);
+
+        rcu_read_lock();
+        ops = rcu_dereference(inet_protos[proto]);
+        if (ops && ops->gso_segment)
+                segs = ops->gso_segment(skb, sg);
+        rcu_read_unlock();
+
+        if (IS_ERR(segs))
+                goto out;
+
+        skb = segs;
+        do {
+                iph = skb->nh.iph;
+                iph->id = htons(id++);
+                iph->tot_len = htons(skb->len - skb->mac_len);
+                iph->check = 0;
+                iph->check = ip_fast_csum(skb->nh.raw, iph->ihl);
+        } while ((skb = skb->next));
+
+out:
+        return segs;
+}
+
 #ifdef CONFIG_IP_MULTICAST
 static struct net_protocol igmp_protocol = {
         .handler =      igmp_rcv,
@@ -1105,6 +1154,7 @@ static struct net_protocol igmp_protocol = {
 static struct net_protocol tcp_protocol = {
         .handler =      tcp_v4_rcv,
         .err_handler =  tcp_v4_err,
+        .gso_segment =  tcp_tso_segment,
         .no_policy =    1,
 };
 
@@ -1150,6 +1200,7 @@ static int ipv4_proc_init(void);
 static struct packet_type ip_packet_type = {
         .type = __constant_htons(ETH_P_IP),
         .func = ip_rcv,
+        .gso_segment = inet_gso_segment,
 };
 
 static int __init inet_init(void)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 062dd1a0d8a8..0e029c4e2903 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -258,6 +258,7 @@
 #include <linux/random.h>
 #include <linux/bootmem.h>
 #include <linux/cache.h>
+#include <linux/err.h>
 
 #include <net/icmp.h>
 #include <net/tcp.h>
@@ -2144,6 +2145,67 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
+{
+        struct sk_buff *segs = ERR_PTR(-EINVAL);
+        struct tcphdr *th;
+        unsigned thlen;
+        unsigned int seq;
+        unsigned int delta;
+        unsigned int oldlen;
+        unsigned int len;
+
+        if (!pskb_may_pull(skb, sizeof(*th)))
+                goto out;
+
+        th = skb->h.th;
+        thlen = th->doff * 4;
+        if (thlen < sizeof(*th))
+                goto out;
+
+        if (!pskb_may_pull(skb, thlen))
+                goto out;
+
+        oldlen = ~htonl(skb->len);
+        __skb_pull(skb, thlen);
+
+        segs = skb_segment(skb, sg);
+        if (IS_ERR(segs))
+                goto out;
+
+        len = skb_shinfo(skb)->gso_size;
+        delta = csum_add(oldlen, htonl(thlen + len));
+
+        skb = segs;
+        th = skb->h.th;
+        seq = ntohl(th->seq);
+
+        do {
+                th->fin = th->psh = 0;
+
+                if (skb->ip_summed == CHECKSUM_NONE) {
+                        th->check = csum_fold(csum_partial(
+                                skb->h.raw, thlen, csum_add(skb->csum, delta)));
+                }
+
+                seq += len;
+                skb = skb->next;
+                th = skb->h.th;
+
+                th->seq = htonl(seq);
+                th->cwr = 0;
+        } while (skb->next);
+
+        if (skb->ip_summed == CHECKSUM_NONE) {
+                delta = csum_add(oldlen, htonl(skb->tail - skb->h.raw));
+                th->check = csum_fold(csum_partial(
+                        skb->h.raw, thlen, csum_add(skb->csum, delta)));
+        }
+
+out:
+        return segs;
+}
+
 extern void __skb_cb_too_small_for_tcp(int, int);
 extern struct tcp_congestion_ops tcp_reno;