於TCP/IP協議棧的TCP協議的重傳功能是由在linux內核源碼(net/ipv4/tcp_output.c)中的函數tcp_retransmit_skb()實現的
代碼如下:
/* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { icsk->icsk_mtup.probe_size = 0; } /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ //說明在發送緩存區中消耗了許多內存去做其他的工作(比如分片等,只有1/4的緩存才是保留給這些工作的),暫時不能重傳 if (atomic_read(&sk->sk_wmem_alloc) > min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; //檢測重傳的段,接收方是否已經收到其部分或者全部,如果收到則說明有bug ,否者就調整TCP段的負荷,即刪除SKB緩存區 //前面部分已經接收到的數據 if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) BUG(); if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } //根據目的地址等條件獲取路由,如果獲取路由失敗就不能發送 if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit serves as a zero window probe. */ //如果接收方已經減小了窗口,並且帶重傳的SKB已經不在新的窗口內,則不能重傳該SKB, //有一種情況例外,就是接收方的接受窗口減少為0,在這種情況下會發送0窗口探測段 if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) && TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; if (skb->len > cur_mss) {//如果當前的SKB長度大於MSS,則要進行分段處理 if (tcp_fragment(sk, skb, cur_mss, cur_mss)) return -ENOMEM; /* We'll try again later. */ } else { int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } } tcp_retrans_try_collapse(sk, skb, cur_mss); /* Some Solaris stacks overoptimize and ignore the FIN on a * retransmit when old data is attached. So strip it off * since it is cheap to do so and saves bytes on the network. */ //有以下Solaris系統的協議棧有時候會忽略重傳SKB上帶有的FIN標志的payload,將payload全部剝離掉,節省網絡流量 if (skb->len > 0 && (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) && tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) { if (!pskb_trim(skb, 0)) { /* Reuse, even though it does some unnecessary work */ tcp_init_nondata_skb(skb, TCP_SKB_CB(skb)->end_seq - 1, TCP_SKB_CB(skb)->flags); skb->ip_summed = CHECKSUM_NONE; } } /* Make a copy, if the first transmission SKB clone we made * is still in somebody's hands, else make a clone. */ TCP_SKB_CB(skb)->when = tcp_time_stamp; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);//發送SKB if (err == 0) { /* Update global TCP statistics. */ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); tp->total_retrans++; #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { if (net_ratelimit()) printk(KERN_DEBUG "retrans_out leaked.\n"); } #endif if (!tp->retrans_out) tp->lost_retrans_low = tp->snd_nxt; TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); /* Save stamp of the first retransmit. */ if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; tp->undo_retrans += tcp_skb_pcount(skb); /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). */ TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; } return err; }我們知道,TCP的發送是有一個SKB 隊列如圖,這樣維持一個發送隊列,如果收到發送了SKB的ACK,就將對應的SKB從隊列中刪除掉,在函數
這裡注意的到函數tcp_retransmit_skb()最終的是調用函數tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);將SKB發送出去,而構造TCP的頭部信息在函
數tcp_transmit_skb()中,下面是函數tcp_transmit_skb()構造TCP頭部的片段 所以也就是說在發送隊列中的SKB是沒有頭部的,這也是方便了選擇重傳等功能
/* Build TCP header and checksum it. */ th = tcp_hdr(skb); th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->flags);