aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/include/net/inet_connection_sock.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/net/inet_connection_sock.h')
-rw-r--r--include/net/inet_connection_sock.h115
1 files changed, 68 insertions, 47 deletions
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7338b3865a2a..1735db332aab 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -25,6 +25,7 @@
#undef INET_CSK_CLEAR_TIMERS
struct inet_bind_bucket;
+struct inet_bind2_bucket;
struct tcp_congestion_ops;
/*
@@ -43,13 +44,10 @@ struct inet_connection_sock_af_ops {
struct request_sock *req_unhash,
bool *own_req);
u16 net_header_len;
- u16 net_frag_header_len;
- u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
- void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
void (*mtu_reduced)(struct sock *sk);
};
@@ -57,7 +55,7 @@ struct inet_connection_sock_af_ops {
*
* @icsk_accept_queue: FIFO of established children
* @icsk_bind_hash: Bind node
- * @icsk_timeout: Timeout
+ * @icsk_bind2_hash: Bind node in the bhash2 table
* @icsk_retransmit_timer: Resend (no ack)
* @icsk_rto: Retransmit timeout
* @icsk_pmtu_cookie Last pmtu seen by socket
@@ -65,8 +63,6 @@ struct inet_connection_sock_af_ops {
* @icsk_af_ops Operations which are AF_INET{4,6} specific
* @icsk_ulp_ops Pluggable ULP control hook
* @icsk_ulp_data ULP private data
- * @icsk_clean_acked Clean acked data hook
- * @icsk_listen_portaddr_node hash to the portaddr listener hashtable
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
@@ -76,25 +72,26 @@ struct inet_connection_sock_af_ops {
* @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options)
* @icsk_ack: Delayed ACK control data
* @icsk_mtup; MTU probing control data
+ * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack)
+ * @icsk_user_timeout: TCP_USER_TIMEOUT value
*/
struct inet_connection_sock {
/* inet_sock has to be the first member! */
struct inet_sock icsk_inet;
struct request_sock_queue icsk_accept_queue;
struct inet_bind_bucket *icsk_bind_hash;
- unsigned long icsk_timeout;
+ struct inet_bind2_bucket *icsk_bind2_hash;
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
__u32 icsk_rto_min;
+ u32 icsk_rto_max;
__u32 icsk_delack_max;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
const struct tcp_ulp_ops *icsk_ulp_ops;
void __rcu *icsk_ulp_data;
- void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
- struct hlist_node icsk_listen_portaddr_node;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:5,
icsk_ca_initialized:1,
@@ -111,41 +108,41 @@ struct inet_connection_sock {
__u8 quick; /* Scheduled number of quick acks */
__u8 pingpong; /* The session is interactive */
__u8 retry; /* Number of attempts */
- __u32 ato; /* Predicted tick of soft clock */
- unsigned long timeout; /* Currently scheduled timeout */
+ #define ATO_BITS 8
+ __u32 ato:ATO_BITS, /* Predicted tick of soft clock */
+ lrcv_flowlabel:20, /* last received ipv6 flowlabel */
+ dst_quick_ack:1, /* cache dst RTAX_QUICKACK */
+ unused:3;
__u32 lrcvtime; /* timestamp of last received data packet */
__u16 last_seg_size; /* Size of last incoming segment */
__u16 rcv_mss; /* MSS used for delayed ACK decisions */
} icsk_ack;
struct {
- int enabled;
-
/* Range of MTUs to search */
int search_high;
int search_low;
/* Information on the current probe. */
- int probe_size;
+ u32 probe_size:31,
+ /* Is the MTUP feature enabled for this connection? */
+ enabled:1;
u32 probe_timestamp;
} icsk_mtup;
+ u32 icsk_probes_tstamp;
u32 icsk_user_timeout;
u64 icsk_ca_priv[104 / sizeof(u64)];
-#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64))
+#define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv)
};
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
-#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */
#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */
#define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */
-static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
-{
- return (struct inet_connection_sock *)sk;
-}
+#define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk)
static inline void *inet_csk_ca(const struct sock *sk)
{
@@ -161,7 +158,8 @@ enum inet_csk_ack_state_t {
ICSK_ACK_TIMER = 2,
ICSK_ACK_PUSHED = 4,
ICSK_ACK_PUSHED2 = 8,
- ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
+ ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */
+ ICSK_ACK_NOMEM = 32,
};
void inet_csk_init_xmit_timers(struct sock *sk,
@@ -169,6 +167,7 @@ void inet_csk_init_xmit_timers(struct sock *sk,
void (*delack_handler)(struct timer_list *),
void (*keepalive_handler)(struct timer_list *));
void inet_csk_clear_xmit_timers(struct sock *sk);
+void inet_csk_clear_xmit_timers_sync(struct sock *sk);
static inline void inet_csk_schedule_ack(struct sock *sk)
{
@@ -185,20 +184,29 @@ static inline void inet_csk_delack_init(struct sock *sk)
memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}
-void inet_csk_delete_keepalive_timer(struct sock *sk);
-void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
+static inline unsigned long
+icsk_timeout(const struct inet_connection_sock *icsk)
+{
+ return READ_ONCE(icsk->icsk_retransmit_timer.expires);
+}
+
+static inline unsigned long
+icsk_delack_timeout(const struct inet_connection_sock *icsk)
+{
+ return READ_ONCE(icsk->icsk_delack_timer.expires);
+}
static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
- icsk->icsk_pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
} else if (what == ICSK_TIME_DACK) {
- icsk->icsk_ack.pending = 0;
+ smp_store_release(&icsk->icsk_ack.pending, 0);
icsk->icsk_ack.retry = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -223,16 +231,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
when = max_when;
}
+ when += jiffies;
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
- what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE ||
- what == ICSK_TIME_REO_TIMEOUT) {
- icsk->icsk_pending = what;
- icsk->icsk_timeout = jiffies + when;
- sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
+ what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) {
+ smp_store_release(&icsk->icsk_pending, what);
+ sk_reset_timer(sk, &icsk->icsk_retransmit_timer, when);
} else if (what == ICSK_TIME_DACK) {
- icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
- icsk->icsk_ack.timeout = jiffies + when;
- sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
+ smp_store_release(&icsk->icsk_ack.pending,
+ icsk->icsk_ack.pending | ICSK_ACK_TIMER);
+ sk_reset_timer(sk, &icsk->icsk_delack_timer, when);
} else {
pr_debug("inet_csk BUG: unknown timer value\n");
}
@@ -247,7 +254,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
return (unsigned long)min_t(u64, when, max_when);
}
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
+struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg);
int inet_csk_get_port(struct sock *sk, unsigned short snum);
@@ -260,7 +267,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child);
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req,
@@ -278,17 +285,25 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
- return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
+ return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog);
}
-void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
+static inline unsigned long
+reqsk_timeout(struct request_sock *req, unsigned long max_timeout)
+{
+ u64 timeout = (u64)req->timeout << req->num_timeout;
+
+ return (unsigned long)min_t(u64, timeout, max_timeout);
+}
+
static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
{
/* The below has to be done to allow calling inet_csk_destroy_sock */
sock_set_flag(sk, SOCK_DEAD);
- percpu_counter_inc(sk->sk_prot->orphan_count);
+ this_cpu_inc(*sk->sk_prot->orphan_count);
}
void inet_csk_destroy_sock(struct sock *sk);
@@ -303,22 +318,19 @@ static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
(EPOLLIN | EPOLLRDNORM) : 0;
}
-int inet_csk_listen_start(struct sock *sk, int backlog);
+int inet_csk_listen_start(struct sock *sk);
void inet_csk_listen_stop(struct sock *sk);
-void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
-
/* update the fast reuse flag when adding a socket */
void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
struct sock *sk);
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
-#define TCP_PINGPONG_THRESH 3
-
static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
{
- inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH;
+ inet_csk(sk)->icsk_ack.pingpong =
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);
}
static inline void inet_csk_exit_pingpong_mode(struct sock *sk)
@@ -328,7 +340,8 @@ static inline void inet_csk_exit_pingpong_mode(struct sock *sk)
static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
{
- return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
+ return inet_csk(sk)->icsk_ack.pingpong >=
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);
}
static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
@@ -339,9 +352,17 @@ static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
icsk->icsk_ack.pingpong++;
}
-static inline bool inet_csk_has_ulp(struct sock *sk)
+static inline bool inet_csk_has_ulp(const struct sock *sk)
{
- return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
+ return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
+}
+
+static inline void inet_init_csk_locks(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ spin_lock_init(&icsk->icsk_accept_queue.rskq_lock);
+ spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock);
}
#endif /* _INET_CONNECTION_SOCK_H */
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.