【Linux4.1.12源码分析】二层报文发送之报文GSO分段（TCP）

TCP报文GSO分段的入口函数是tcp4_gso_segment，在tcpv4_offload对象中定义。

1、tcp4_gso_segment函数

static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
					netdev_features_t features)
{
	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		return ERR_PTR(-EINVAL);

	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {	
		const struct iphdr *iph = ip_hdr(skb);
		struct tcphdr *th = tcp_hdr(skb);	//ip层报文保证了transport header值

		/* Set up checksum pseudo header, usually expect stack to
		 * have done this already.
		 */

		th->check = 0;
		skb->ip_summed = CHECKSUM_PARTIAL;
		__tcp_v4_send_check(skb, iph->saddr, iph->daddr);	//计算伪头check值
	}

	return tcp_gso_segment(skb, features);	//TCP GSO分段
}

2、tcp_gso_segment函数

struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
				netdev_features_t features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	unsigned int sum_truesize = 0;
	struct tcphdr *th;
	unsigned int thlen;
	unsigned int seq;
	__be32 delta;
	unsigned int oldlen;
	unsigned int mss;
	struct sk_buff *gso_skb = skb;
	__sum16 newcheck;
	bool ooo_okay, copy_destructor;

	th = tcp_hdr(skb);
	thlen = th->doff * 4;		//得到tcp头的长度
	if (thlen < sizeof(*th))
		goto out;

	if (!pskb_may_pull(skb, thlen))
		goto out;

	oldlen = (u16)~skb->len;
	__skb_pull(skb, thlen);		//skb移动到用户数据区（payload）

	mss = tcp_skb_mss(skb);		//得到mss值
	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_TCPV4 |
			       SKB_GSO_DODGY |
			       SKB_GSO_TCP_ECN |
			       SKB_GSO_TCPV6 |
			       SKB_GSO_GRE |
			       SKB_GSO_GRE_CSUM |
			       SKB_GSO_IPIP |
			       SKB_GSO_SIT |
			       SKB_GSO_UDP_TUNNEL |
			       SKB_GSO_UDP_TUNNEL_CSUM |
			       SKB_GSO_TUNNEL_REMCSUM |
			       0) ||
			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
			goto out;

		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); //如果报文来源不可信，则重新计算segs，返回

		segs = NULL;
		goto out;
	}

	copy_destructor = gso_skb->destructor == tcp_wfree;
	ooo_okay = gso_skb->ooo_okay;
	/* All segments but the first should have ooo_okay cleared */
	skb->ooo_okay = 0;

	segs = skb_segment(skb, features);	//调用payload根据mss值分段
	if (IS_ERR(segs))
		goto out;

	/* Only first segment might have ooo_okay set */
	segs->ooo_okay = ooo_okay;

	delta = htonl(oldlen + (thlen + mss));	//TCP头+mss - 原始报文，该值为负值

	skb = segs;
	th = tcp_hdr(skb);	//skb_segment分段后，可以直接从skb中获取tcp头， skb_segment或udp4_ufo_fragment保证
	seq = ntohl(th->seq);

	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
		tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);

	newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +	//第一个报文基于原先值，根据delta快速计算
					       (__force u32)delta));

	do {	//刷新分段后报文的TCP头设置
		th->fin = th->psh = 0;
		th->check = newcheck;

		if (skb->ip_summed != CHECKSUM_PARTIAL)	   
			th->check = gso_make_checksum(skb, ~th->check);	 //重新计算check值

		seq += mss;
		if (copy_destructor) {
			skb->destructor = gso_skb->destructor;
			skb->sk = gso_skb->sk;
			sum_truesize += skb->truesize;
		}
		skb = skb->next;
		th = tcp_hdr(skb);

		th->seq = htonl(seq);
		th->cwr = 0;
	} while (skb->next);

	/* Following permits TCP Small Queues to work well with GSO :
	 * The callback to TCP stack will be called at the time last frag
	 * is freed at TX completion, and not right now when gso_skb
	 * is freed by GSO engine
	 */
	if (copy_destructor) {
		swap(gso_skb->sk, skb->sk);
		swap(gso_skb->destructor, skb->destructor);
		sum_truesize += skb->truesize;
		atomic_add(sum_truesize - gso_skb->truesize,
			   &skb->sk->sk_wmem_alloc);
	}

	delta = htonl(oldlen + (skb_tail_pointer(skb) -
				skb_transport_header(skb)) +	//最后一个报文的delta值不同
		      skb->data_len);
	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
				(__force u32)delta));
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		th->check = gso_make_checksum(skb, ~th->check);	//重新计算check值
out:
	return segs;
}