diff options
Diffstat (limited to 'include/net/tcp.h')
| -rw-r--r-- | include/net/tcp.h | 380 |
1 files changed, 330 insertions, 50 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 91688d0dadcd..d2f0736b76b8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -37,6 +37,7 @@ #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> +#include <net/tcp_ao.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> @@ -131,6 +132,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ +static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); + #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) @@ -141,6 +144,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ + +#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ + #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the @@ -161,7 +167,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) +/* Ensure that TCP PAWS checks are relaxed after ~2147 seconds + * to avoid overflows. This assumes a clock smaller than 1 Mhz. + * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. + */ +#define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC) + #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN @@ -184,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_AO 29 /* Authentication Option (RFC5925) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ @@ -348,12 +360,14 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); -static inline void tcp_dec_quickack_mode(struct sock *sk, - const unsigned int pkts) +static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { + /* How many ACKs S/ACKing new data have we sent? */ + const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; + if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ @@ -424,7 +438,6 @@ int tcp_mmap(struct file *file, struct socket *sock, void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); -const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * BPF SKB-less helpers @@ -718,8 +731,10 @@ static inline void tcp_fast_path_check(struct sock *sk) tcp_fast_path_on(tp); } +u32 tcp_delack_max(const struct sock *sk); + /* Compute the actual rto_min value */ -static inline u32 tcp_rto_min(struct sock *sk) +static inline u32 tcp_rto_min(const struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = inet_csk(sk)->icsk_rto_min; @@ -729,7 +744,7 @@ static inline u32 tcp_rto_min(struct sock *sk) return rto_min; } -static inline u32 tcp_rto_min_us(struct sock *sk) +static inline u32 tcp_rto_min_us(const struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } @@ -789,22 +804,31 @@ static inline u64 tcp_clock_us(void) return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } -/* This should only be used in contexts where tp->tcp_mstamp is up to date */ -static inline u32 tcp_time_stamp(const struct tcp_sock *tp) +static inline u64 tcp_clock_ms(void) { - return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return div_u64(tcp_clock_ns(), NSEC_PER_MSEC); } -/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ -static inline u32 tcp_ns_to_ts(u64 ns) +/* TCP Timestamp included in TS option (RFC 1323) can either use ms + * or usec resolution. Each socket carries a flag to select one or other + * resolution, as the route attribute could change anytime. + * Each flow must stick to initial resolution. + */ +static inline u32 tcp_clock_ts(bool usec_ts) { - return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); + return usec_ts ? tcp_clock_us() : tcp_clock_ms(); } -/* Could use tcp_clock_us() / 1000, but this version uses a single divide */ -static inline u32 tcp_time_stamp_raw(void) +static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { - return tcp_ns_to_ts(tcp_clock_ns()); + return div_u64(tp->tcp_mstamp, USEC_PER_MSEC); +} + +static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) +{ + if (tp->tcp_usec_ts) + return tp->tcp_mstamp; + return tcp_time_stamp_ms(tp); } void tcp_mstamp_refresh(struct tcp_sock *tp); @@ -814,17 +838,30 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) return max_t(s64, t1 - t0, 0); } -static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) -{ - return tcp_ns_to_ts(skb->skb_mstamp_ns); -} - /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } +/* Provide skb TSval in usec or ms unit */ +static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) +{ + if (usec_ts) + return tcp_skb_timestamp_us(skb); + + return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC); +} + +static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) +{ + return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset; +} + +static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) +{ + return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off; +} #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) @@ -1453,13 +1490,15 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } +/* Assume a conservative default of 1200 bytes of payload per 4K page. + * This may be adjusted later in tcp_measure_rcv_mss(). + */ +#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \ + SKB_TRUESIZE(4096)) + static inline void tcp_scaling_ratio_init(struct sock *sk) { - /* Assume a conservative default of 1200 bytes of payload per 4K page. - * This may be adjusted later in tcp_measure_rcv_mss(). - */ - tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) / - SKB_TRUESIZE(4096); + tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; } /* Note: caller must be prepared to deal with negative returns */ @@ -1590,7 +1629,7 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), - rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) + rx_opt->ts_recent_stamp + TCP_PAWS_WRAP))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, @@ -1650,12 +1689,7 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) tp->retransmit_skb_hint = NULL; } -union tcp_md5_addr { - struct in_addr a4; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr a6; -#endif -}; +#define tcp_md5_addr tcp_ao_addr /* - key database */ struct tcp_md5sig_key { @@ -1699,12 +1733,39 @@ union tcp_md5sum_block { #endif }; -/* - pool: digest algorithm, hash description and scratch buffer */ -struct tcp_md5sig_pool { - struct ahash_request *md5_req; - void *scratch; +/* + * struct tcp_sigpool - per-CPU pool of ahash_requests + * @scratch: per-CPU temporary area, that can be used between + * tcp_sigpool_start() and tcp_sigpool_end() to perform + * crypto request + * @req: pre-allocated ahash request + */ +struct tcp_sigpool { + void *scratch; + struct ahash_request *req; }; +int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); +void tcp_sigpool_get(unsigned int id); +void tcp_sigpool_release(unsigned int id); +int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, + const struct sk_buff *skb, + unsigned int header_len); + +/** + * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash + * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() + * @c: returned tcp_sigpool for usage (uninitialized on failure) + * + * Returns 0 on success, error otherwise. + */ +int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); +/** + * tcp_sigpool_end - enable bh and stop using tcp_sigpool + * @c: tcp_sigpool context that was returned by tcp_sigpool_start() + */ +void tcp_sigpool_end(struct tcp_sigpool *c); +size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); @@ -1717,6 +1778,7 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); +void tcp_clear_md5_list(struct sock *sk); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); @@ -1725,20 +1787,29 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, extern struct static_key_false_deferred tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, - int family); + int family, bool any_l3index); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; - return __tcp_md5_do_lookup(sk, l3index, addr, family); + return __tcp_md5_do_lookup(sk, l3index, addr, family, false); +} + +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup_any_l3index(const struct sock *sk, + const union tcp_md5_addr *addr, int family) +{ + if (!static_branch_unlikely(&tcp_md5_needed.key)) + return NULL; + return __tcp_md5_do_lookup(sk, 0, addr, family, true); } enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, - int family, int dif, int sdif); + int family, int l3index, const __u8 *hash_location); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) @@ -1750,27 +1821,29 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, return NULL; } +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup_any_l3index(const struct sock *sk, + const union tcp_md5_addr *addr, int family) +{ + return NULL; +} + static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, - int family, int dif, int sdif) + int family, int l3index, const __u8 *hash_location) { return SKB_NOT_DROPPED_YET; } #define tcp_twsk_md5_key(twsk) NULL #endif -bool tcp_alloc_md5sig_pool(void); - -struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); -static inline void tcp_put_md5sig_pool(void) -{ - local_bh_enable(); -} +int tcp_md5_alloc_sigpool(void); +void tcp_md5_release_sigpool(void); +void tcp_md5_add_sigpool(void); +extern int tcp_md5_sigpool_id; -int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, - unsigned int header_len); -int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, +int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ @@ -2075,7 +2148,11 @@ INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)) INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); +#ifdef CONFIG_INET void tcp_gro_complete(struct sk_buff *skb); +#else +static inline void tcp_gro_complete(struct sk_buff *skb) { } +#endif void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); @@ -2115,6 +2192,18 @@ struct tcp_sock_af_ops { sockptr_t optval, int optlen); #endif +#ifdef CONFIG_TCP_AO + int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); + struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, + struct sock *addr_sk, + int sndid, int rcvid); + int (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send); + int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao, + const struct sock *sk, const struct sk_buff *skb, + const u8 *tkey, int hash_offset, u32 sne); +#endif }; struct tcp_request_sock_ops { @@ -2127,6 +2216,15 @@ struct tcp_request_sock_ops { const struct sock *sk, const struct sk_buff *skb); #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, + struct request_sock *req, + int sndid, int rcvid); + int (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); + int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt, + struct request_sock *req, const struct sk_buff *skb, + int hash_offset, u32 sne); +#endif #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); @@ -2167,6 +2265,76 @@ static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, } #endif +struct tcp_key { + union { + struct { + struct tcp_ao_key *ao_key; + char *traffic_key; + u32 sne; + u8 rcv_next; + }; + struct tcp_md5sig_key *md5_key; + }; + enum { + TCP_KEY_NONE = 0, + TCP_KEY_MD5, + TCP_KEY_AO, + } type; +}; + +static inline void tcp_get_current_key(const struct sock *sk, + struct tcp_key *out) +{ +#if defined(CONFIG_TCP_AO) || defined(CONFIG_TCP_MD5SIG) + const struct tcp_sock *tp = tcp_sk(sk); +#endif + +#ifdef CONFIG_TCP_AO + if (static_branch_unlikely(&tcp_ao_needed.key)) { + struct tcp_ao_info *ao; + + ao = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)); + if (ao) { + out->ao_key = READ_ONCE(ao->current_key); + out->type = TCP_KEY_AO; + return; + } + } +#endif +#ifdef CONFIG_TCP_MD5SIG + if (static_branch_unlikely(&tcp_md5_needed.key) && + rcu_access_pointer(tp->md5sig_info)) { + out->md5_key = tp->af_specific->md5_lookup(sk, sk); + if (out->md5_key) { + out->type = TCP_KEY_MD5; + return; + } + } +#endif + out->type = TCP_KEY_NONE; +} + +static inline bool tcp_key_is_md5(const struct tcp_key *key) +{ +#ifdef CONFIG_TCP_MD5SIG + if (static_branch_unlikely(&tcp_md5_needed.key) && + key->type == TCP_KEY_MD5) + return true; +#endif + return false; +} + +static inline bool tcp_key_is_ao(const struct tcp_key *key) +{ +#ifdef CONFIG_TCP_AO + if (static_branch_unlikely(&tcp_ao_needed.key) && + key->type == TCP_KEY_AO) + return true; +#endif + return false; +} + int tcpv4_offload_init(void); void tcp_v4_init(void); @@ -2525,4 +2693,116 @@ static inline u64 tcp_transmit_time(const struct sock *sk) return 0; } +static inline int tcp_parse_auth_options(const struct tcphdr *th, + const u8 **md5_hash, const struct tcp_ao_hdr **aoh) +{ + const u8 *md5_tmp, *ao_tmp; + int ret; + + ret = tcp_do_parse_auth_options(th, &md5_tmp, &ao_tmp); + if (ret) + return ret; + + if (md5_hash) + *md5_hash = md5_tmp; + + if (aoh) { + if (!ao_tmp) + *aoh = NULL; + else + *aoh = (struct tcp_ao_hdr *)(ao_tmp - 2); + } + + return 0; +} + +static inline bool tcp_ao_required(struct sock *sk, const void *saddr, + int family, int l3index, bool stat_inc) +{ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao_info; + struct tcp_ao_key *ao_key; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return false; + + ao_info = rcu_dereference_check(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao_info) + return false; + + ao_key = tcp_ao_do_lookup(sk, l3index, saddr, family, -1, -1); + if (ao_info->ao_required || ao_key) { + if (stat_inc) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED); + atomic64_inc(&ao_info->counters.ao_required); + } + return true; + } +#endif + return false; +} + +/* Called with rcu_read_lock() */ +static inline enum skb_drop_reason +tcp_inbound_hash(struct sock *sk, const struct request_sock *req, + const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif) +{ + const struct tcphdr *th = tcp_hdr(skb); + const struct tcp_ao_hdr *aoh; + const __u8 *md5_location; + int l3index; + + /* Invalid option or two times meet any of auth options */ + if (tcp_parse_auth_options(th, &md5_location, &aoh)) { + tcp_hash_fail("TCP segment has incorrect auth options set", + family, skb, ""); + return SKB_DROP_REASON_TCP_AUTH_HDR; + } + + if (req) { + if (tcp_rsk_used_ao(req) != !!aoh) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + tcp_hash_fail("TCP connection can't start/end using TCP-AO", + family, skb, "%s", + !aoh ? "missing AO" : "AO signed"); + return SKB_DROP_REASON_TCP_AOFAILURE; + } + } + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + /* Fast path: unsigned segments */ + if (likely(!md5_location && !aoh)) { + /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid + * for the remote peer. On TCP-AO established connection + * the last key is impossible to remove, so there's + * always at least one current_key. + */ + if (tcp_ao_required(sk, saddr, family, l3index, true)) { + tcp_hash_fail("AO hash is required, but not found", + family, skb, "L3 index %d", l3index); + return SKB_DROP_REASON_TCP_AONOTFOUND; + } + if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + tcp_hash_fail("MD5 Hash not found", + family, skb, "L3 index %d", l3index); + return SKB_DROP_REASON_TCP_MD5NOTFOUND; + } + return SKB_NOT_DROPPED_YET; + } + + if (aoh) + return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); + + return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, + l3index, md5_location); +} + #endif /* _TCP_H */ |