菜鸟笔记
提升您的技术认知

TCP连接建立系列 — TCP选项解析

本文主要分析:在收到客户端的SYN包时,服务器端是如何解析它所携带的TCP选项,并结合本端情况决定是否予以支持。

内核版本:3.6 

概述

 

收到客户端的SYN包时,需要全面的解析它携带的TCP选项,这样我们就知道客户端支持哪些选项,如果本端也支持,

那么连接就支持这些TCP选项。这些信息在连接建立的过程中,是保存在连接请求块的(request_sock、inet_request_sock、

tcp_request_sock)。

 

函数调用路径:

tcp_v4_conn_request

        |--> tcp_parse_options

 

3.6版本Linux内核支持的TCP选项包括:

NOP,用于填充。

Max Segment Size,最大分段大小。

Window Scaling,窗口扩大因子。

SACK Permit,是否允许使用SACK。

SACK,携带SACK块。

Timestamp,时间戳选项。

MD5SIG,MD5签名。

Cookie,Cookie extension,2013年3月已从内核移除。

EXP,Experimental,处于实验阶段的选项,新版本用于Fast Open。

 

实现

 

全面解析数据包的TCP选项,并保存到指定的tcp_options_received实例中。

/* Look for tcp options. Normally only called on SYN and SYNACK packets.
 * But, this can also be called on packets in the established flow when the fast version below fails.
 */

void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, const u8 **hvpp,
                       int estab, struct tcp_fastopen_cookie *foc)
{
    const unsigned char *ptr;
    const struct tcphdr *th = tcp_hdr(skb);
    int length = (th->doff * 4) - sizeof(struct tcphdr); /* 选项的总长度 */

    ptr = (const unsigned char *) (th + 1); /* 选项的起始地址 */
    opt_rx->saw_tstamp = 0; /* Saw TIMESTAMP on last packet */

    while(length > 0) {
        int opcode = *ptr++; /* 选项kind */
        int opsize; /* 选项length */

        switch(opcode) {
        case TCPOPT_EOL: /* End of options */
            return; 

        case TCPOPT_NOP: /* Padding,填充选项 */
            length--; /* 此选项只占一个字节 */
            continue;

        default:
            opsize = *ptr++; /* 选项长度 */
            if (opsize < 2) /* silly options */
                return; /* 选项长度过小 */

            if (opsize > length)
                return; /* don't parse partial options */

            switch(opcode) {
            case TCPOPT_MSS: /* MSS选项 */
                if (opsize == TCPOLEN_MSS && th->syn && ! estab) {
                    u16 in_mss = get_unaligned_be16(ptr);

                    if (in_mss) {
                        /* 如果用户指定了MSS,且比对端通告的小 */
                        if (opt_rx->user_mss && opt_rx->user_mss < in_mss)
                            in_mss = opt_rx->user_mss;

                        opt_rx->mss_clamp = in_mss; /* Maximal mss */
                    }
                }
                break;

            case TCPOPT_WINDOW: /* Window scaling */
                if (opsize == TCPOLEN_WINDOW && th->syn && ! estab &&
                    sysctl_tcp_window_scaling) {
                    __u8 snd_wscale = *(__u8 *)ptr; /* 对端的接收窗口扩大因子 */
                    opt_rx->wscale_ok = 1; /* 连接使用窗口扩大选项 */

                    if (snd_wscale > 14) {
                        net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n",
                               __func__, snd_wscale);
                        snd_wscale = 14;
                    }

                    opt_rx->snd_wscale = snd_wscale; /* 保存对端的接收窗口扩大因子 */
                }
                break;

            case TCPOPT_TIMESTAMP: /* Better RTT estimations/PAWS */
                if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) ||
                     (!estab && sysctl_tcp_timestamps))) {

                    opt_rx->saw_tstamp = 1; /* 连接支持TIMESTAMP选项 */
                    opt_rx->rcv_tsval = get_unaligned_be32(ptr); /* Time stamp value */
                    opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); /* Time stamp echo reply */
                }
                break;

            case TCPOPT_SACK_PERM: /* SACK Permitted */
                if (opsize == TCPOLEN_SACK_PERM && th->syn && !estab && sysctl_tcp_sack) {
                    opt_rx->sack_ok = TCP_SACK_SEEN; /* 连接支持SACK选项 */
                    tcp_sack_reset(opt_rx); /* 清空dsack和num_sacks变量 */
                }
                break;

            case TCPOPT_SACK: /* SACK Block */
                if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
                    !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) && opt_rx->sack_ok) {
                    /* 保存SACK选项的起始偏移地址 */
                    TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *) th; 
                }
                break;

#ifdef CONFIG_TCP_MD5SIG
            case TCPOPT_MD5SIG:
                /* The MD5 Hash has already been checked
                 * (see tcp_v{4, 6}_do_rcv()).
                 */
                break;
#endif

            /* 注意,在新版内核中此选项已被删除。Cookie extension (experimental) */
            case TCPOPT_COOKIE: 
                /* This option is variable length. */
                switch(opsize) {
                case TCPOLEN_COOKIE_BASE:
                    /* not yet implemented */
                    break;

                case TCPOLEN_COOKIE_PAIR:
                    /* not yet implemented */
                    break;

                case TCPOLEN_COOKIE_MIN + 0:
                case TCPOLEN_COOKIE_MIN + 2:
                case TCPOLEN_COOKIE_MIN + 4:
                case TCPOLEN_COOKIE_MIN + 6:
                case TCPOLEN_COOKIE_MAX:

                    /* 16-bit multple */
                    opt_rx->cookie_plus = opsize;
                    *hvpp = ptr;
                    break;

                default:
                    /* ignore option */
                    break;
                }
                break;
 
            case TCPOPT_EXP: /* Experimental */
                /* Fast Open option shares code 254 using a 16 bits magic number.
                 * It's valid only in SYN or SYN-ACK with an even size.
                 */
                if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC
                    || foc == NULL || ! th->syn || (opsize & 1))
                    break;

                foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
                if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && foc->len <= TCP_FASTOPEN_COOKIE_MAX)
                    memcpy(foc->val, ptr + 2, foc->len);
                else if (foc->len != 0)
                    foc->len = -1;
                break;
            }

            ptr += opsize - 2;
            length -= opsize;
        }
    }
}
/* TCP options */
#define TCPOPT_NOP 1 /* Padding */
#define TCPOPT_EOL 0 /* End of options */
#define TCPOPT_MSS 2 /* Segment size negotiating */
#define TCPOPT_WINDOW 3 /* Window scaling */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
#define TCPOPT_EXP 254 /* Experimental */

/* Magic number to be after the option value for sharing TCP experimental options.
 * See draft-ietf-tcpm-experimental-options-00.txt
 */
#define TCPOPT_FASTOPEN_MAGIC 0xF989

/* TCP option lengths */
#define TCPOLEN_MSS 4
#define TCPOLEN_WINDOW 3
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE + TCP_COOKIE_MIN)
#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE + TCP_COOKIE_MAX)
#define TCPOLEN_EXP_FASTOPEN_BASE 4

/* These are used to set the sack_ok field in struct tcp_options_received */
#define TCP_SACK_SEEN (1 << 0) /* peer is SACK capable */
#define TCP_FACK_ENABLED (1 << 1) /* FACK is enabled locally */
#define TCP_DSACK_SEEN (1 << 2) /* DSACK was received from peer */

/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */
#define TCP_COOKIE_MIN 8 /* 64-bits */
#define TCP_COOKIE_MAX 16 /* 128-bits */

/* TCP Fast Open */
#define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */
#define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */

/* TCP Fast Open Cookie as stored in memory */
struct tcp_fastopen_cookie {
    s8 len;
    u8 val[TCP_FASTOPEN_COOKIE_MAX];
};

static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
    rx_opt->dsack = 0;
    rx_opt->num_sacks = 0;
}

 

用于判断连接是否使用ECN。要注意的是在建立连接时,要求IP报的ECN域不能被设置,否则就禁用ECN。

/* RFC3168: 6.1.1 SYN packets must not have ECT/ECN bits set.
 *
 * If we receive a SYN packet with these bits set, it means a network is playing  bad games
 * with TOS bits. In order to avoid possible false congestion notifications, we disable
 * TCP ECN negociation.
 */
static inline void TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb)
{
    const struct tcphdr *th = tcp_hdr(skb);

    if (sysctl_tcp_ecn && th->ece && th->cwr && INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
        inet_rsk(req)->ecn_ok = 1; /* 连接支持ECN */
}

 

清零TCP选项。

static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
    rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
    rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
    rx_opt->cookie_plus = 0;
}