--- zzzz-none-000/linux-3.10.107/net/ipv4/syncookies.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv4/syncookies.c 2021-02-04 17:41:59.000000000 +0000 @@ -19,33 +19,48 @@ #include #include -/* Timestamps: lowest bits store TCP options */ -#define TSBITS 6 -#define TSMASK (((__u32)1 << TSBITS) - 1) - extern int sysctl_tcp_syncookies; -__u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; -EXPORT_SYMBOL(syncookie_secret); - -static __init int init_syncookies(void) -{ - get_random_bytes(syncookie_secret, sizeof(syncookie_secret)); - return 0; -} -__initcall(init_syncookies); +static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly; #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) +/* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK + * stores TCP options: + * + * MSB LSB + * | 31 ... 6 | 5 | 4 | 3 2 1 0 | + * | Timestamp | ECN | SACK | WScale | + * + * When we receive a valid cookie-ACK, we look at the echoed tsval (if + * any) to figure out which TCP options we should use for the rebuilt + * connection. + * + * A WScale setting of '0xf' (which is an invalid scaling value) + * means that original syn did not include the TCP window scaling option. + */ +#define TS_OPT_WSCALE_MASK 0xf +#define TS_OPT_SACK BIT(4) +#define TS_OPT_ECN BIT(5) +/* There is no TS_OPT_TIMESTAMP: + * if ACK contains timestamp option, we already know it was + * requested/supported by the syn/synack exchange. + */ +#define TSBITS 6 +#define TSMASK (((__u32)1 << TSBITS) - 1) + static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch); static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) { - __u32 *tmp = __get_cpu_var(ipv4_cookie_scratch); + __u32 *tmp; + + net_get_random_once(syncookie_secret, sizeof(syncookie_secret)); + tmp = this_cpu_ptr(ipv4_cookie_scratch); memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c])); tmp[0] = (__force u32)saddr; tmp[1] = (__force u32)daddr; @@ -72,9 +87,11 @@ ireq = inet_rsk(req); - options = ireq->wscale_ok ? ireq->snd_wscale : 0xf; - options |= ireq->sack_ok << 4; - options |= ireq->ecn_ok << 5; + options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK; + if (ireq->sack_ok) + options |= TS_OPT_SACK; + if (ireq->ecn_ok) + options |= TS_OPT_ECN; ts = ts_now & ~TSMASK; ts |= options; @@ -89,8 +106,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport, - __be16 dport, __u32 sseq, __u32 count, - __u32 data) + __be16 dport, __u32 sseq, __u32 data) { /* * Compute the secure sequence number. @@ -102,7 +118,7 @@ * As an extra hack, we add a small "data" value that encodes the * MSS into the second hash value. */ - + u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) @@ -114,22 +130,21 @@ * If the syncookie is bad, the data returned will be out of * range. This must be checked by the caller. * - * The count value used to generate the cookie must be within - * "maxdiff" if the current (passed-in) "count". The return value - * is (__u32)-1 if this test fails. + * The count value used to generate the cookie must be less than + * MAX_SYNCOOKIE_AGE minutes in the past. + * The return value (__u32)-1 if this test fails. */ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, __u32 sseq, - __u32 count, __u32 maxdiff) + __be16 sport, __be16 dport, __u32 sseq) { - __u32 diff; + u32 diff, count = tcp_cookie_time(); /* Strip away the layers from the cookie */ cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; /* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */ - diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS); - if (diff >= maxdiff) + diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); + if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - @@ -138,105 +153,101 @@ } /* - * MSS Values are taken from the 2009 paper - * 'Measuring TCP Maximum Segment Size' by S. Alcock and R. Nelson: - * - values 1440 to 1460 accounted for 80% of observed mss values - * - values outside the 536-1460 range are rare (<0.2%). + * MSS Values are chosen based on the 2011 paper + * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson. + * Values .. + * .. lower than 536 are rare (< 0.2%) + * .. between 537 and 1299 account for less than < 1.5% of observed values + * .. in the 1300-1349 range account for about 15 to 20% of observed mss values + * .. exceeding 1460 are very rare (< 0.04%) * - * Table must be sorted. + * 1460 is the single most frequently announced mss value (30 to 46% depending + * on monitor location). Table must be sorted. */ static __u16 const msstab[] = { - 64, - 512, 536, - 1024, - 1440, + 1300, + 1440, /* 1440, 1452: PPPoE */ 1460, - 4312, - 8960, }; /* * Generate a syncookie. mssp points to the mss, which is returned * rounded down to the value encoded in the cookie. */ -__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) +u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, + u16 *mssp) { - const struct iphdr *iph = ip_hdr(skb); - const struct tcphdr *th = tcp_hdr(skb); int mssind; const __u16 mss = *mssp; - tcp_synq_overflow(sk); - for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) if (mss >= msstab[mssind]) break; *mssp = msstab[mssind]; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return secure_tcp_syn_cookie(iph->saddr, iph->daddr, th->source, th->dest, ntohl(th->seq), - jiffies / (HZ * 60), mssind); + mssind); +} +EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); + +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp) +{ + const struct iphdr *iph = ip_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); + + return __cookie_v4_init_sequence(iph, th, mssp); } -/* - * This (misnamed) value is the age of syncookie which is permitted. - * Its ideal value should be dependent on TCP_TIMEOUT_INIT and - * sysctl_tcp_retries1. It's a rather complicated formula (exponential - * backoff) to compute at runtime so it's currently hardcoded here. - */ -#define COUNTER_TRIES 4 /* * Check if a ack sequence number is a valid syncookie. * Return the decoded mss if it is, or 0 if not. */ -static inline int cookie_check(struct sk_buff *skb, __u32 cookie) +int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, + u32 cookie) { - const struct iphdr *iph = ip_hdr(skb); - const struct tcphdr *th = tcp_hdr(skb); __u32 seq = ntohl(th->seq) - 1; __u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr, - th->source, th->dest, seq, - jiffies / (HZ * 60), - COUNTER_TRIES); + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } +EXPORT_SYMBOL_GPL(__cookie_v4_check); -static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; + bool own_req; - child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, + NULL, &own_req); + if (child) { + atomic_set(&req->rsk_refcnt, 1); + sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } - +EXPORT_SYMBOL(tcp_get_cookie_sock); /* * when syncookies are in effect and tcp timestamps are enabled we stored * additional tcp options in the timestamp. * This extracts these options from the timestamp echo. * - * The lowest 4 bits store snd_wscale. - * next 2 bits indicate SACK and ECN support. - * - * return false if we decode an option that should not be. + * return false if we decode a tcp option that is disabled + * on the host. */ -bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, - struct net *net, bool *ecn_ok) +bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) { /* echoed timestamp, lowest bits contain options */ - u32 options = tcp_opt->rcv_tsecr & TSMASK; + u32 options = tcp_opt->rcv_tsecr; if (!tcp_opt->saw_tstamp) { tcp_clear_options(tcp_opt); @@ -246,26 +257,43 @@ if (!sysctl_tcp_timestamps) return false; - tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0; - *ecn_ok = (options >> 5) & 1; - if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn) - return false; + tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; if (tcp_opt->sack_ok && !sysctl_tcp_sack) return false; - if ((options & 0xf) == 0xf) + if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) return true; /* no window scaling */ tcp_opt->wscale_ok = 1; - tcp_opt->snd_wscale = options & 0xf; + tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; + return sysctl_tcp_window_scaling != 0; } -EXPORT_SYMBOL(cookie_check_timestamp); +EXPORT_SYMBOL(cookie_timestamp_decode); -struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, - struct ip_options *opt) +bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, + const struct net *net, const struct dst_entry *dst) { + bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN; + + if (!ecn_ok) + return false; + + if (net->ipv4.sysctl_tcp_ecn) + return true; + + return dst_feature(dst, RTAX_FEATURE_ECN); +} +EXPORT_SYMBOL(cookie_ecn_ok); + +/* On input, sk is a listener. + * Output is listener if incoming packet would not create a child + * NULL if memory could not be allocated. + */ +struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) +{ + struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct tcp_options_received tcp_opt; struct inet_request_sock *ireq; struct tcp_request_sock *treq; @@ -277,14 +305,16 @@ int mss; struct rtable *rt; __u8 rcv_wscale; - bool ecn_ok = false; struct flowi4 fl4; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; - if (tcp_synq_no_recent_overflow(sk) || - (mss = cookie_check(skb, cookie)) == 0) { + if (tcp_synq_no_recent_overflow(sk)) + goto out; + + mss = __cookie_v4_check(ip_hdr(skb), th, cookie); + if (mss == 0) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); goto out; } @@ -295,11 +325,11 @@ memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) + if (!cookie_timestamp_decode(&tcp_opt)) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */ if (!req) goto out; @@ -308,38 +338,31 @@ treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; req->mss = mss; - ireq->loc_port = th->dest; - ireq->rmt_port = th->source; - ireq->loc_addr = ip_hdr(skb)->daddr; - ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->ecn_ok = ecn_ok; + ireq->ir_num = ntohs(th->dest); + ireq->ir_rmt_port = th->source; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + ireq->ir_mark = inet_request_mark(sk, skb); ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; - treq->listener = NULL; + treq->snt_synack.v64 = 0; + treq->tfo_listener = false; + + ireq->ir_iif = sk->sk_bound_dev_if; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - if (opt && opt->optlen) { - int opt_size = sizeof(struct ip_options_rcu) + opt->optlen; - - ireq->opt = kmalloc(opt_size, GFP_ATOMIC); - if (ireq->opt != NULL && ip_options_echo(&ireq->opt->opt, skb)) { - kfree(ireq->opt); - ireq->opt = NULL; - } - } + ireq->opt = tcp_v4_save_options(skb); if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); goto out; } - req->expires = 0UL; req->num_retrans = 0; /* @@ -348,11 +371,11 @@ * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), - (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, - ireq->loc_addr, th->source, th->dest); + opt->srr ? opt->faddr : ireq->ir_rmt_addr, + ireq->ir_loc_addr, th->source, th->dest); security_req_classify_flow(req, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(sock_net(sk), &fl4); if (IS_ERR(rt)) { @@ -361,16 +384,17 @@ } /* Try to redo what tcp_v4_send_synack did. */ - req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, - &req->rcv_wnd, &req->window_clamp, + &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; + ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst); - ret = get_cookie_sock(sk, skb, req, &rt->dst); + ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */