1 files changed, 166 insertions, 154 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index de2c78529afa..ecb362025c4e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * NET		Generic infrastructure for INET connection oriented protocols.
  *
@@ -6,11 +7,6 @@
  * Authors:	Many people, see the TCP sources
  *
  * 		From code originally in TCP
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
  */
 #ifndef _INET_CONNECTION_SOCK_H
 #define _INET_CONNECTION_SOCK_H
@@ -19,16 +15,17 @@
 #include <linux/string.h>
 #include <linux/timer.h>
 #include <linux/poll.h>
+#include <linux/kernel.h>
+#include <linux/sockptr.h>
 
 #include <net/inet_sock.h>
 #include <net/request_sock.h>
 
-#define INET_CSK_DEBUG 1
-
 /* Cancel timers, when they are not required. */
 #undef INET_CSK_CLEAR_TIMERS
 
 struct inet_bind_bucket;
+struct inet_bind2_bucket;
 struct tcp_congestion_ops;
 
 /*
@@ -36,44 +33,38 @@ struct tcp_congestion_ops;
  * (i.e. things that depend on the address family)
  */
 struct inet_connection_sock_af_ops {
-	int	    (*queue_xmit)(struct sk_buff *skb, struct flowi *fl);
+	int	    (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 	void	    (*send_check)(struct sock *sk, struct sk_buff *skb);
 	int	    (*rebuild_header)(struct sock *sk);
 	void	    (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
 	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
-	struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb,
+	struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req,
-				      struct dst_entry *dst);
+				      struct dst_entry *dst,
+				      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, 
-				  char __user *optval, unsigned int optlen);
-	int	    (*getsockopt)(struct sock *sk, int level, int optname, 
+	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);
-#ifdef CONFIG_COMPAT
-	int	    (*compat_setsockopt)(struct sock *sk,
-				int level, int optname,
-				char __user *optval, unsigned int optlen);
-	int	    (*compat_getsockopt)(struct sock *sk,
-				int level, int optname,
-				char __user *optval, int __user *optlen);
-#endif
-	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
-	int	    (*bind_conflict)(const struct sock *sk,
-				     const struct inet_bind_bucket *tb, bool relax);
+	void	    (*mtu_reduced)(struct sock *sk);
 };
 
 /** inet_connection_sock - INET connection oriented sock
  *
- * @icsk_accept_queue:	   FIFO of established children 
+ * @icsk_accept_queue:	   FIFO of established children
  * @icsk_bind_hash:	   Bind node
- * @icsk_timeout:	   Timeout
- * @icsk_retransmit_timer: Resend (no ack)
+ * @icsk_bind2_hash:	   Bind node in the bhash2 table
+ * @icsk_delack_timer:     Delayed ACK timer
+ * @icsk_keepalive_timer:  Keepalive timer
+ * @mptcp_tout_timer: mptcp timer
  * @icsk_rto:		   Retransmit timeout
  * @icsk_pmtu_cookie	   Last pmtu seen by socket
  * @icsk_ca_ops		   Pluggable congestion control hook
  * @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_ca_state:	   Congestion control state
  * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts
  * @icsk_pending:	   Scheduled timer event
@@ -83,21 +74,34 @@ 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 timer_list	  icsk_retransmit_timer;
- 	struct timer_list	  icsk_delack_timer;
+	struct inet_bind2_bucket  *icsk_bind2_hash;
+	struct timer_list	  icsk_delack_timer;
+	union {
+		struct timer_list icsk_keepalive_timer;
+		struct timer_list mptcp_tout_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;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state;
+	__u8			  icsk_ca_state:5,
+				  icsk_ca_initialized:1,
+				  icsk_ca_setsockopt:1,
+				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
 	__u8			  icsk_backoff;
@@ -108,60 +112,67 @@ struct inet_connection_sock {
 		__u8		  pending;	 /* ACK is pending			   */
 		__u8		  quick;	 /* Scheduled number of quick acks	   */
 		__u8		  pingpong;	 /* The session is interactive		   */
-		__u8		  blocked;	 /* Delayed ACK was blocked by socket lock */
-		__u32		  ato;		 /* Predicted tick of soft clock	   */
-		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
+		__u8		  retry;	 /* Number of attempts			   */
+		#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	   */ 
+		__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_ca_priv[16];
+	u32			  icsk_probes_tstamp;
 	u32			  icsk_user_timeout;
-#define ICSK_CA_PRIV_SIZE	(16 * sizeof(u32))
+
+	u64			  icsk_ca_priv[104 / 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)
 {
 	return (void *)inet_csk(sk)->icsk_ca_priv;
 }
 
-extern struct sock *inet_csk_clone_lock(const struct sock *sk,
-					const struct request_sock *req,
-					const gfp_t priority);
+struct sock *inet_csk_clone_lock(const struct sock *sk,
+				 const struct request_sock *req,
+				 const gfp_t priority);
 
 enum inet_csk_ack_state_t {
 	ICSK_ACK_SCHED	= 1,
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
-	ICSK_ACK_PUSHED2 = 8
+	ICSK_ACK_PUSHED2 = 8,
+	ICSK_ACK_NOW = 16,	/* Send the next ACK immediately (once) */
+	ICSK_ACK_NOMEM = 32,
 };
 
-extern void inet_csk_init_xmit_timers(struct sock *sk,
-				      void (*retransmit_handler)(unsigned long),
-				      void (*delack_handler)(unsigned long),
-				      void (*keepalive_handler)(unsigned long));
-extern void inet_csk_clear_xmit_timers(struct sock *sk);
+void inet_csk_init_xmit_timers(struct sock *sk,
+			       void (*retransmit_handler)(struct timer_list *),
+			       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)
 {
@@ -178,33 +189,35 @@ static inline void inet_csk_delack_init(struct sock *sk)
 	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
 }
 
-extern void inet_csk_delete_keepalive_timer(struct sock *sk);
-extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
+static inline unsigned long tcp_timeout_expires(const struct sock *sk)
+{
+	return READ_ONCE(sk->tcp_retransmit_timer.expires);
+}
 
-#ifdef INET_CSK_DEBUG
-extern const char inet_csk_timer_bug_msg[];
-#endif
+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);
+		sk_stop_timer(sk, &sk->tcp_retransmit_timer);
 #endif
 	} else if (what == ICSK_TIME_DACK) {
-		icsk->icsk_ack.blocked = 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);
 #endif
+	} else {
+		pr_debug("inet_csk BUG: unknown timer value\n");
 	}
-#ifdef INET_CSK_DEBUG
-	else {
-		pr_debug("%s", inet_csk_timer_bug_msg);
-	}
-#endif
 }
 
 /*
@@ -217,71 +230,55 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (when > max_when) {
-#ifdef INET_CSK_DEBUG
 		pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
-			 sk, what, when, current_text_addr());
-#endif
+			 sk, what, when, (void *)_THIS_IP_);
 		when = max_when;
 	}
 
+	when += jiffies;
 	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
-	    what == ICSK_TIME_EARLY_RETRANS || what ==  ICSK_TIME_LOSS_PROBE) {
-		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, &sk->tcp_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);
-	}
-#ifdef INET_CSK_DEBUG
-	else {
-		pr_debug("%s", inet_csk_timer_bug_msg);
+		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");
 	}
-#endif
 }
 
-extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+static inline unsigned long
+inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
+		     unsigned long max_when)
+{
+        u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;
 
-extern struct request_sock *inet_csk_search_req(const struct sock *sk,
-						struct request_sock ***prevp,
-						const __be16 rport,
-						const __be32 raddr,
-						const __be32 laddr);
-extern int inet_csk_bind_conflict(const struct sock *sk,
-				  const struct inet_bind_bucket *tb, bool relax);
-extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
+        return (unsigned long)min_t(u64, when, max_when);
+}
 
-extern struct dst_entry* inet_csk_route_req(struct sock *sk,
-					    struct flowi4 *fl4,
-					    const struct request_sock *req);
-extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk,
-						   struct sock *newsk,
-						   const struct request_sock *req);
+struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg);
 
-static inline void inet_csk_reqsk_queue_add(struct sock *sk,
-					    struct request_sock *req,
-					    struct sock *child)
-{
-	reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
-}
+int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
-extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
-					  struct request_sock *req,
-					  unsigned long timeout);
+struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
+				     const struct request_sock *req);
+struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
+					    struct sock *newsk,
+					    const struct request_sock *req);
 
-static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
-						struct request_sock *req)
-{
-	if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
-		inet_csk_delete_keepalive_timer(sk);
-}
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child);
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req);
+struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
+					 struct request_sock *req,
+					 bool own_req);
 
-static inline void inet_csk_reqsk_queue_added(struct sock *sk,
-					      const unsigned long timeout)
+static inline void inet_csk_reqsk_queue_added(struct sock *sk)
 {
-	if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
-		inet_csk_reset_keepalive_timer(sk, timeout);
+	reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
 }
 
 static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
@@ -289,58 +286,73 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
 	return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
 }
 
-static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
+static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
 {
-	return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
+	return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog);
 }
 
-static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
+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);
+
+void inet_csk_destroy_sock(struct sock *sk);
+void inet_csk_prepare_for_destroy_sock(struct sock *sk);
+void inet_csk_prepare_forced_close(struct sock *sk);
+
+/*
+ * LISTEN is a special case for poll..
+ */
+static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
 {
-	return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
+	return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
+			(EPOLLIN | EPOLLRDNORM) : 0;
 }
 
-static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
-					       struct request_sock *req,
-					       struct request_sock **prev)
+int inet_csk_listen_start(struct sock *sk);
+void inet_csk_listen_stop(struct sock *sk);
+
+/* update the fast reuse flag when adding a socket */
+void inet_csk_update_fastreuse(const struct sock *sk,
+			       struct inet_bind_bucket *tb,
+			       struct inet_bind2_bucket *tb2);
+
+struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
+
+static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
 {
-	reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
+	inet_csk(sk)->icsk_ack.pingpong =
+		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);
 }
 
-static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
-					     struct request_sock *req,
-					     struct request_sock **prev)
+static inline void inet_csk_exit_pingpong_mode(struct sock *sk)
 {
-	inet_csk_reqsk_queue_unlink(sk, req, prev);
-	inet_csk_reqsk_queue_removed(sk, req);
-	reqsk_free(req);
+	inet_csk(sk)->icsk_ack.pingpong = 0;
 }
 
-extern void inet_csk_reqsk_queue_prune(struct sock *parent,
-				       const unsigned long interval,
-				       const unsigned long timeout,
-				       const unsigned long max_rto);
-
-extern void inet_csk_destroy_sock(struct sock *sk);
-extern void inet_csk_prepare_forced_close(struct sock *sk);
+static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
+{
+	return inet_csk(sk)->icsk_ack.pingpong >=
+	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh);
+}
 
-/*
- * LISTEN is a special case for poll..
- */
-static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
+static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
 {
-	return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
-			(POLLIN | POLLRDNORM) : 0;
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ack.pingpong < U8_MAX)
+		icsk->icsk_ack.pingpong++;
 }
 
-extern int  inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
-extern void inet_csk_listen_stop(struct sock *sk);
+static inline bool inet_csk_has_ulp(const struct sock *sk)
+{
+	return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
+}
 
-extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
+static inline void inet_init_csk_locks(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
-extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
-				      char __user *optval, int __user *optlen);
-extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
-				      char __user *optval, unsigned int optlen);
+	spin_lock_init(&icsk->icsk_accept_queue.rskq_lock);
+	spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock);
+}
 
-extern struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET_CONNECTION_SOCK_H */