aboutsummaryrefslogtreecommitdiffstats
path: root/include/net/tcp.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r--include/net/tcp.h113
1 files changed, 74 insertions, 39 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 44e442bf23f9..14d45661a84d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -253,6 +253,8 @@ extern long sysctl_tcp_mem[3];
#define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */
extern atomic_long_t tcp_memory_allocated;
+DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc);
+
extern struct percpu_counter tcp_sockets_allocated;
extern unsigned long tcp_memory_pressure;
@@ -325,6 +327,8 @@ void tcp_remove_empty_skb(struct sock *sk);
int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
+int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
+ size_t size, struct ubuf_info *uarg);
int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
int flags);
int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
@@ -344,6 +348,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
void tcp_rcv_space_adjust(struct sock *sk);
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
void tcp_twsk_destructor(struct sock *sk);
+void tcp_twsk_purge(struct list_head *net_exit_list, int family);
ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
@@ -400,14 +405,18 @@ void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
__poll_t tcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
+int do_tcp_getsockopt(struct sock *sk, int level,
+ int optname, sockptr_t optval, sockptr_t optlen);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
bool tcp_bpf_bypass_getsockopt(int level, int optname);
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+ sockptr_t optval, unsigned int optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
void tcp_set_keepalive(struct sock *sk, int val);
void tcp_syn_ack_timeout(const struct request_sock *req);
-int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len);
int tcp_set_rcvlowat(struct sock *sk, int val);
int tcp_set_window_clamp(struct sock *sk, int val);
@@ -432,6 +441,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
struct tcphdr *th, u32 *cookie);
u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
struct tcphdr *th, u32 *cookie);
+u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss);
u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct tcphdr *th);
@@ -480,6 +490,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
+ const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct sk_buff *skb);
#ifdef CONFIG_SYN_COOKIES
@@ -620,6 +631,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
void tcp_reset(struct sock *sk, struct sk_buff *skb);
void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
void tcp_fin(struct sock *sk);
+void tcp_check_space(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
@@ -667,6 +679,9 @@ void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
+int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
+struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
+void tcp_read_done(struct sock *sk, size_t len);
void tcp_initialize_rcv_mss(struct sock *sk);
@@ -930,7 +945,7 @@ extern const struct inet_connection_sock_af_ops ipv6_specific;
INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb));
INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb));
-INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb));
+void tcp_v6_early_demux(struct sk_buff *skb);
#endif
@@ -1042,6 +1057,7 @@ struct rate_sample {
int losses; /* number of packets marked lost upon ACK */
u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
u32 prior_in_flight; /* in flight before this ACK */
+ u32 last_end_seq; /* end_seq of most recently ACKed packet */
bool is_app_limited; /* is sample from packet with bubble in pipe? */
bool is_retrans; /* is sample from retransmission? */
bool is_ack_delayed; /* is this (likely) a delayed ACK? */
@@ -1139,15 +1155,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk)
return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
}
-static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_ca_ops->set_state)
- icsk->icsk_ca_ops->set_state(sk, ca_state);
- icsk->icsk_ca_state = ca_state;
-}
-
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1156,6 +1163,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
+/* From tcp_cong.c */
+void tcp_set_ca_state(struct sock *sk, const u8 ca_state);
+
/* From tcp_rate.c */
void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
@@ -1164,6 +1174,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
bool is_sack_reneg, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);
+static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
+{
+ return t1 > t2 || (t1 == t2 && after(seq1, seq2));
+}
+
/* These functions determine how the current flow behaves in respect of SACK
* handling. SACK is negotiated with the peer, and therefore it can vary
* between different flows.
@@ -1207,9 +1222,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
#define TCP_INFINITE_SSTHRESH 0x7fffffff
+static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd;
+}
+
+static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val)
+{
+ WARN_ON_ONCE((int)val <= 0);
+ tp->snd_cwnd = val;
+}
+
static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
{
- return tp->snd_cwnd < tp->snd_ssthresh;
+ return tcp_snd_cwnd(tp) < tp->snd_ssthresh;
}
static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
@@ -1235,8 +1261,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
return tp->snd_ssthresh;
else
return max(tp->snd_ssthresh,
- ((tp->snd_cwnd >> 1) +
- (tp->snd_cwnd >> 2)));
+ ((tcp_snd_cwnd(tp) >> 1) +
+ (tcp_snd_cwnd(tp) >> 2)));
}
/* Use define here intentionally to get WARN_ON location shown at the caller */
@@ -1276,11 +1302,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
+ if (tp->is_cwnd_limited)
+ return true;
+
/* If in slow start, ensure cwnd grows to twice what was ACKed. */
if (tcp_in_slow_start(tp))
- return tp->snd_cwnd < 2 * tp->max_packets_out;
+ return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out;
- return tp->is_cwnd_limited;
+ return false;
}
/* BBR congestion control needs pacing.
@@ -1367,16 +1396,9 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
__skb_checksum_complete(skb);
}
-bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
-
-void __sk_defer_free_flush(struct sock *sk);
+bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
+ enum skb_drop_reason *reason);
-static inline void sk_defer_free_flush(struct sock *sk)
-{
- if (llist_empty(&sk->defer_list))
- return;
- __sk_defer_free_flush(sk);
-}
int tcp_filter(struct sock *sk, struct sk_buff *skb);
void tcp_set_state(struct sock *sk, int state);
@@ -1397,8 +1419,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
s32 delta;
- if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out ||
- ca_ops->cong_control)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) ||
+ tp->packets_out || ca_ops->cong_control)
return;
delta = tcp_jiffies32 - tp->lsndtime;
if (delta > inet_csk(sk)->icsk_rto)
@@ -1413,7 +1435,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
static inline int tcp_win_from_space(const struct sock *sk, int space)
{
- int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
+ int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
return tcp_adv_win_scale <= 0 ?
(space>>(-tcp_adv_win_scale)) :
@@ -1487,21 +1509,24 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
- return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl;
+ return tp->keepalive_intvl ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl);
}
static inline int keepalive_time_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
- return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time;
+ return tp->keepalive_time ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
}
static inline int keepalive_probes(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
- return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes;
+ return tp->keepalive_probes ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
}
static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
@@ -1514,7 +1539,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
static inline int tcp_fin_time(const struct sock *sk)
{
- int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
+ int fin_timeout = tcp_sk(sk)->linger2 ? :
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout);
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
@@ -1670,6 +1696,12 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index,
return __tcp_md5_do_lookup(sk, l3index, addr, family);
}
+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);
+
+
#define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key)
#else
static inline struct tcp_md5sig_key *
@@ -1678,6 +1710,14 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index,
{
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)
+{
+ return SKB_NOT_DROPPED_YET;
+}
#define tcp_twsk_md5_key(twsk) NULL
#endif
@@ -1813,11 +1853,6 @@ static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
return skb_rb_last(&sk->tcp_rtx_queue);
}
-static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
-{
- return skb_peek(&sk->sk_write_queue);
-}
-
static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
{
return skb_peek_tail(&sk->sk_write_queue);
@@ -2008,7 +2043,7 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
- return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
+ return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
}
bool tcp_stream_memory_free(const struct sock *sk, int wake);
@@ -2354,7 +2389,7 @@ static inline u32 tcp_timeout_init(struct sock *sk)
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
- return timeout;
+ return min_t(int, timeout, TCP_RTO_MAX);
}
static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.