1 files changed, 291 insertions, 214 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d1f837579398..97d57c52b9ad 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -117,34 +117,58 @@ bool inet_rcv_saddr_any(const struct sock *sk)
 	return !sk->sk_rcv_saddr;
 }
 
-void inet_get_local_port_range(struct net *net, int *low, int *high)
+/**
+ *	inet_sk_get_local_port_range - fetch ephemeral ports range
+ *	@sk: socket
+ *	@low: pointer to low port
+ *	@high: pointer to high port
+ *
+ *	Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range)
+ *	Range can be overridden if socket got IP_LOCAL_PORT_RANGE option.
+ *	Returns true if IP_LOCAL_PORT_RANGE was set on this socket.
+ */
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 {
-	unsigned int seq;
-
-	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+	int lo, hi, sk_lo, sk_hi;
+	bool local_range = false;
+	u32 sk_range;
+
+	inet_get_local_port_range(sock_net(sk), &lo, &hi);
+
+	sk_range = READ_ONCE(inet_sk(sk)->local_port_range);
+	if (unlikely(sk_range)) {
+		sk_lo = sk_range & 0xffff;
+		sk_hi = sk_range >> 16;
+
+		if (lo <= sk_lo && sk_lo <= hi)
+			lo = sk_lo;
+		if (lo <= sk_hi && sk_hi <= hi)
+			hi = sk_hi;
+		local_range = true;
+	}
 
-		*low = net->ipv4.ip_local_ports.range[0];
-		*high = net->ipv4.ip_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+	*low = lo;
+	*high = hi;
+	return local_range;
 }
-EXPORT_SYMBOL(inet_get_local_port_range);
+EXPORT_SYMBOL(inet_sk_get_local_port_range);
 
 static bool inet_use_bhash2_on_bind(const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6) {
-		int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			return false;
 
-		return addr_type != IPV6_ADDR_ANY &&
-			addr_type != IPV6_ADDR_MAPPED;
+		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return true;
 	}
 #endif
 	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
 }
 
 static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
-			       kuid_t sk_uid, bool relax,
+			       kuid_t uid, bool relax,
 			       bool reuseport_cb_ok, bool reuseport_ok)
 {
 	int bound_dev_if2;
@@ -161,12 +185,12 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 			if (!relax || (!reuseport_ok && sk->sk_reuseport &&
 				       sk2->sk_reuseport && reuseport_cb_ok &&
 				       (sk2->sk_state == TCP_TIME_WAIT ||
-					uid_eq(sk_uid, sock_i_uid(sk2)))))
+					uid_eq(uid, sk_uid(sk2)))))
 				return true;
 		} else if (!reuseport_ok || !sk->sk_reuseport ||
 			   !sk2->sk_reuseport || !reuseport_cb_ok ||
 			   (sk2->sk_state != TCP_TIME_WAIT &&
-			    !uid_eq(sk_uid, sock_i_uid(sk2)))) {
+			    !uid_eq(uid, sk_uid(sk2)))) {
 			return true;
 		}
 	}
@@ -174,35 +198,33 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 }
 
 static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
-				   kuid_t sk_uid, bool relax,
+				   kuid_t uid, bool relax,
 				   bool reuseport_cb_ok, bool reuseport_ok)
 {
-	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
-		return false;
+	if (ipv6_only_sock(sk2)) {
+		if (sk->sk_family == AF_INET)
+			return false;
 
-	return inet_bind_conflict(sk, sk2, sk_uid, relax,
+#if IS_ENABLED(CONFIG_IPV6)
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return false;
+#endif
+	}
+
+	return inet_bind_conflict(sk, sk2, uid, relax,
 				  reuseport_cb_ok, reuseport_ok);
 }
 
 static bool inet_bhash2_conflict(const struct sock *sk,
 				 const struct inet_bind2_bucket *tb2,
-				 kuid_t sk_uid,
+				 kuid_t uid,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
-	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
-	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
-		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
-					   reuseport_cb_ok, reuseport_ok))
-			return true;
-	}
-
-	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
-		sk2 = (struct sock *)tw2;
-
-		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+	sk_for_each_bound(sk2, &tb2->owners) {
+		if (__inet_bhash2_conflict(sk, sk2, uid, relax,
 					   reuseport_cb_ok, reuseport_ok))
 			return true;
 	}
@@ -210,15 +232,20 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 	return false;
 }
 
+#define sk_for_each_bound_bhash(__sk, __tb2, __tb)			\
+	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
+		sk_for_each_bound((__sk), &(__tb2)->owners)
+
 /* This should be called only when the tb and tb2 hashbuckets' locks are held */
 static int inet_csk_bind_conflict(const struct sock *sk,
 				  const struct inet_bind_bucket *tb,
 				  const struct inet_bind2_bucket *tb2, /* may be null */
 				  bool relax, bool reuseport_ok)
 {
-	bool reuseport_cb_ok;
 	struct sock_reuseport *reuseport_cb;
-	kuid_t uid = sock_i_uid((struct sock *)sk);
+	kuid_t uid = sk_uid(sk);
+	bool reuseport_cb_ok;
+	struct sock *sk2;
 
 	rcu_read_lock();
 	reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
@@ -226,32 +253,29 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 	reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks);
 	rcu_read_unlock();
 
-	/*
-	 * Unlike other sk lookup places we do not check
+	/* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if
+	 * ipv4) should have been checked already. We need to do these two
+	 * checks separately because their spinlocks have to be acquired/released
+	 * independently of each other, to prevent possible deadlocks
+	 */
+	if (inet_use_bhash2_on_bind(sk))
+		return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax,
+						   reuseport_cb_ok, reuseport_ok);
+
+	/* Unlike other sk lookup places we do not check
 	 * for sk_net here, since _all_ the socks listed
 	 * in tb->owners and tb2->owners list belong
 	 * to the same net - the one this bucket belongs to.
 	 */
+	sk_for_each_bound_bhash(sk2, tb2, tb) {
+		if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok))
+			continue;
 
-	if (!inet_use_bhash2_on_bind(sk)) {
-		struct sock *sk2;
-
-		sk_for_each_bound(sk2, &tb->owners)
-			if (inet_bind_conflict(sk, sk2, uid, relax,
-					       reuseport_cb_ok, reuseport_ok) &&
-			    inet_rcv_saddr_equal(sk, sk2, true))
-				return true;
-
-		return false;
+		if (inet_rcv_saddr_equal(sk, sk2, true))
+			return true;
 	}
 
-	/* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if
-	 * ipv4) should have been checked already. We need to do these two
-	 * checks separately because their spinlocks have to be acquired/released
-	 * independently of each other, to prevent possible deadlocks
-	 */
-	return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
-					   reuseport_ok);
+	return false;
 }
 
 /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or
@@ -263,11 +287,12 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l3mdev,
 					  bool relax, bool reuseport_ok)
 {
-	kuid_t uid = sock_i_uid((struct sock *)sk);
 	const struct net *net = sock_net(sk);
 	struct sock_reuseport *reuseport_cb;
 	struct inet_bind_hashbucket *head2;
 	struct inet_bind2_bucket *tb2;
+	kuid_t uid = sk_uid(sk);
+	bool conflict = false;
 	bool reuseport_cb_ok;
 
 	rcu_read_lock();
@@ -280,18 +305,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
 
 	spin_lock(&head2->lock);
 
-	inet_bind_bucket_for_each(tb2, &head2->chain)
-		if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
-			break;
+	inet_bind_bucket_for_each(tb2, &head2->chain) {
+		if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
+			continue;
 
-	if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
-					reuseport_ok)) {
-		spin_unlock(&head2->lock);
-		return true;
+		if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,	reuseport_ok))
+			continue;
+
+		conflict = true;
+		break;
 	}
 
 	spin_unlock(&head2->lock);
-	return false;
+
+	return conflict;
 }
 
 /*
@@ -303,7 +330,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret,
 			struct inet_bind2_bucket **tb2_ret,
 			struct inet_bind_hashbucket **head2_ret, int *port_ret)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	int i, low, high, attempt_half, port, l3mdev;
 	struct inet_bind_hashbucket *head, *head2;
 	struct net *net = sock_net(sk);
@@ -316,7 +343,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret,
 ports_exhausted:
 	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
 other_half_scan:
-	inet_get_local_port_range(net, &low, &high);
+	inet_sk_get_local_port_range(sk, &low, &high);
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	if (high - low < 4)
 		attempt_half = 0;
@@ -396,17 +423,15 @@ success:
 }
 
 static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
-				     struct sock *sk)
+				     const struct sock *sk)
 {
-	kuid_t uid = sock_i_uid(sk);
-
 	if (tb->fastreuseport <= 0)
 		return 0;
 	if (!sk->sk_reuseport)
 		return 0;
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
 		return 0;
-	if (!uid_eq(tb->fastuid, uid))
+	if (!uid_eq(tb->fastuid, sk_uid(sk)))
 		return 0;
 	/* We only need to check the rcv_saddr if this tb was once marked
 	 * without fastreuseport and then was reset, as we can only know that
@@ -428,17 +453,17 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 				    ipv6_only_sock(sk), true, false);
 }
 
-void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
-			       struct sock *sk)
+void inet_csk_update_fastreuse(const struct sock *sk,
+			       struct inet_bind_bucket *tb,
+			       struct inet_bind2_bucket *tb2)
 {
-	kuid_t uid = sock_i_uid(sk);
 	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->bhash2)) {
 		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
 			tb->fastreuseport = FASTREUSEPORT_ANY;
-			tb->fastuid = uid;
+			tb->fastuid = sk_uid(sk);
 			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 			tb->fast_ipv6_only = ipv6_only_sock(sk);
 			tb->fast_sk_family = sk->sk_family;
@@ -465,7 +490,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 			 */
 			if (!sk_reuseport_match(tb, sk)) {
 				tb->fastreuseport = FASTREUSEPORT_STRICT;
-				tb->fastuid = uid;
+				tb->fastuid = sk_uid(sk);
 				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
 				tb->fast_ipv6_only = ipv6_only_sock(sk);
 				tb->fast_sk_family = sk->sk_family;
@@ -477,6 +502,9 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 			tb->fastreuseport = 0;
 		}
 	}
+
+	tb2->fastreuse = tb->fastreuse;
+	tb2->fastreuseport = tb->fastreuseport;
 }
 
 /* Obtain a reference to a local port for the given sock,
@@ -485,10 +513,10 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
  */
 int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 	bool found_port = false, check_bind_conflict = true;
 	bool bhash_created = false, bhash2_created = false;
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	int ret = -EADDRINUSE, port = snum, l3mdev;
 	struct inet_bind_hashbucket *head, *head2;
 	struct inet_bind2_bucket *tb2 = NULL;
@@ -526,7 +554,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	}
 
 	if (!found_port) {
-		if (!hlist_empty(&tb->owners)) {
+		if (!hlist_empty(&tb->bhash2)) {
 			if (sk->sk_reuse == SK_FORCE_REUSE ||
 			    (tb->fastreuse > 0 && reuse) ||
 			    sk_reuseport_match(tb, sk))
@@ -546,7 +574,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 
 	if (!tb2) {
 		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep,
-					       net, head2, port, l3mdev, sk);
+					       net, head2, tb, sk);
 		if (!tb2)
 			goto fail_unlock;
 		bhash2_created = true;
@@ -558,7 +586,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	}
 
 success:
-	inet_csk_update_fastreuse(tb, sk);
+	inet_csk_update_fastreuse(sk, tb, tb2);
 
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, tb2, port);
@@ -568,11 +596,10 @@ success:
 
 fail_unlock:
 	if (ret) {
-		if (bhash_created)
-			inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
 		if (bhash2_created)
-			inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
-						  tb2);
+			inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2);
+		if (bhash_created)
+			inet_bind_bucket_destroy(tb);
 	}
 	if (head2_lock_acquired)
 		spin_unlock(&head2->lock);
@@ -633,7 +660,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 /*
  * This will accept the next outstanding connection.
  */
-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)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
@@ -652,7 +679,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 
 	/* Find already established connection */
 	if (reqsk_queue_empty(queue)) {
-		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+		long timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK);
 
 		/* If this is a non blocking socket don't sleep */
 		error = -EAGAIN;
@@ -664,6 +691,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 			goto out_err;
 	}
 	req = reqsk_queue_remove(queue, sk);
+	arg->is_empty = reqsk_queue_empty(queue);
 	newsk = req->sk;
 
 	if (sk->sk_protocol == IPPROTO_TCP &&
@@ -682,36 +710,18 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
 
-out:
 	release_sock(sk);
-	if (newsk && mem_cgroup_sockets_enabled) {
-		int amt;
 
-		/* atomically get the memory usage, set and charge the
-		 * newsk->sk_memcg.
-		 */
-		lock_sock(newsk);
-
-		/* The socket has not been accepted yet, no need to look at
-		 * newsk->sk_wmem_queued.
-		 */
-		amt = sk_mem_pages(newsk->sk_forward_alloc +
-				   atomic_read(&newsk->sk_rmem_alloc));
-		mem_cgroup_sk_alloc(newsk);
-		if (newsk->sk_memcg && amt)
-			mem_cgroup_charge_skmem(newsk->sk_memcg, amt,
-						GFP_KERNEL | __GFP_NOFAIL);
-
-		release_sock(newsk);
-	}
 	if (req)
 		reqsk_put(req);
+
+	inet_init_csk_locks(newsk);
 	return newsk;
+
 out_err:
-	newsk = NULL;
-	req = NULL;
-	*err = error;
-	goto out;
+	release_sock(sk);
+	arg->err = error;
+	return NULL;
 }
 EXPORT_SYMBOL(inet_csk_accept);
 
@@ -727,36 +737,38 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0);
+	timer_setup(&sk->tcp_retransmit_timer, retransmit_handler, 0);
 	timer_setup(&icsk->icsk_delack_timer, delack_handler, 0);
-	timer_setup(&sk->sk_timer, keepalive_handler, 0);
+	timer_setup(&icsk->icsk_keepalive_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
-EXPORT_SYMBOL(inet_csk_init_xmit_timers);
 
 void inet_csk_clear_xmit_timers(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+	smp_store_release(&icsk->icsk_pending, 0);
+	smp_store_release(&icsk->icsk_ack.pending, 0);
 
-	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer(sk, &sk->tcp_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
-	sk_stop_timer(sk, &sk->sk_timer);
+	sk_stop_timer(sk, &icsk->icsk_keepalive_timer);
 }
-EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
 
-void inet_csk_delete_keepalive_timer(struct sock *sk)
+void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 {
-	sk_stop_timer(sk, &sk->sk_timer);
-}
-EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
-void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
-{
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+	/* ongoing timer handlers need to acquire socket lock. */
+	sock_not_owned_by_me(sk);
+
+	smp_store_release(&icsk->icsk_pending, 0);
+	smp_store_release(&icsk->icsk_ack.pending, 0);
+
+	sk_stop_timer_sync(sk, &sk->tcp_retransmit_timer);
+	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
+	sk_stop_timer_sync(sk, &icsk->icsk_keepalive_timer);
 }
-EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
 
 struct dst_entry *inet_csk_route_req(const struct sock *sk,
 				     struct flowi4 *fl4,
@@ -771,11 +783,11 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	opt = rcu_dereference(ireq->ireq_opt);
 
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
-			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+			   ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num), sk->sk_uid);
+			   htons(ireq->ir_num), sk_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -792,7 +804,6 @@ no_route:
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(inet_csk_route_req);
 
 struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
@@ -809,11 +820,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	fl4 = &newinet->cork.fl.u.ip4;
 
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
-			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+			   ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num), sk->sk_uid);
+			   htons(ireq->ir_num), sk_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -851,15 +862,61 @@ static void syn_ack_recalc(struct request_sock *req,
 		  req->num_timeout >= rskq_defer_accept - 1;
 }
 
-int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
+static struct request_sock *
+reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
+		   bool attach_listener)
 {
-	int err = req->rsk_ops->rtx_syn_ack(parent, req);
+	struct request_sock *req;
 
-	if (!err)
-		req->num_retrans++;
-	return err;
+	req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	if (!req)
+		return NULL;
+	req->rsk_listener = NULL;
+	if (attach_listener) {
+		if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) {
+			kmem_cache_free(ops->slab, req);
+			return NULL;
+		}
+		req->rsk_listener = sk_listener;
+	}
+	req->rsk_ops = ops;
+	req_to_sk(req)->sk_prot = sk_listener->sk_prot;
+	sk_node_init(&req_to_sk(req)->sk_node);
+	sk_tx_queue_clear(req_to_sk(req));
+	req->saved_syn = NULL;
+	req->syncookie = 0;
+	req->num_timeout = 0;
+	req->num_retrans = 0;
+	req->sk = NULL;
+	refcount_set(&req->rsk_refcnt, 0);
+
+	return req;
+}
+#define reqsk_alloc(...)	alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__))
+
+struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
+				      struct sock *sk_listener,
+				      bool attach_listener)
+{
+	struct request_sock *req = reqsk_alloc(ops, sk_listener,
+					       attach_listener);
+
+	if (req) {
+		struct inet_request_sock *ireq = inet_rsk(req);
+
+		ireq->ireq_opt = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+		ireq->pktopts = NULL;
+#endif
+		atomic64_set(&ireq->ir_cookie, 0);
+		ireq->ireq_state = TCP_NEW_SYN_RECV;
+		write_pnet(&ireq->ireq_net, sock_net(sk_listener));
+		ireq->ireq_family = sk_listener->sk_family;
+	}
+
+	return req;
 }
-EXPORT_SYMBOL(inet_rtx_syn_ack);
+EXPORT_SYMBOL(inet_reqsk_alloc);
 
 static struct request_sock *inet_reqsk_clone(struct request_sock *req,
 					     struct sock *sk)
@@ -881,8 +938,9 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req,
 
 	memcpy(nreq_sk, req_sk,
 	       offsetof(struct sock, sk_dontcopy_begin));
-	memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end,
-	       req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end));
+	unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end,
+		      req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end),
+		      /* alloc is larger than struct, see above */);
 
 	sk_node_init(&nreq_sk->sk_node);
 	nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
@@ -928,40 +986,50 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 	bool found = false;
 
 	if (sk_hashed(sk)) {
-		struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
-		spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
+		struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
+		spinlock_t *lock;
 
+		lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
 		spin_lock(lock);
 		found = __sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
 	}
-	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
-		reqsk_put(req);
+
 	return found;
 }
 
-bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+static bool __inet_csk_reqsk_queue_drop(struct sock *sk,
+					struct request_sock *req,
+					bool from_timer)
 {
 	bool unlinked = reqsk_queue_unlink(req);
 
+	if (!from_timer && timer_delete_sync(&req->rsk_timer))
+		reqsk_put(req);
+
 	if (unlinked) {
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
 		reqsk_put(req);
 	}
+
 	return unlinked;
 }
-EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
+
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+{
+	return __inet_csk_reqsk_queue_drop(sk, req, false);
+}
 
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
 {
 	inet_csk_reqsk_queue_drop(sk, req);
 	reqsk_put(req);
 }
-EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
+EXPORT_IPV6_MOD(inet_csk_reqsk_queue_drop_and_put);
 
 static void reqsk_timer_handler(struct timer_list *t)
 {
-	struct request_sock *req = from_timer(req, t, rsk_timer);
+	struct request_sock *req = timer_container_of(req, t, rsk_timer);
 	struct request_sock *nreq = NULL, *oreq = req;
 	struct sock *sk_listener = req->rsk_listener;
 	struct inet_connection_sock *icsk;
@@ -995,7 +1063,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 
 	icsk = inet_csk(sk_listener);
 	net = sock_net(sk_listener);
-	max_syn_ack_retries = icsk->icsk_syn_retries ? :
+	max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
 		READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
@@ -1026,23 +1094,25 @@ static void reqsk_timer_handler(struct timer_list *t)
 			young <<= 1;
 		}
 	}
+
 	syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept),
 		       &expire, &resend);
-	req->rsk_ops->syn_ack_timeout(req);
+	tcp_syn_ack_timeout(req);
+
 	if (!expire &&
 	    (!resend ||
-	     !inet_rtx_syn_ack(sk_listener, req) ||
+	     !tcp_rtx_synack(sk_listener, req) ||
 	     inet_rsk(req)->acked)) {
 		if (req->num_timeout++ == 0)
 			atomic_dec(&queue->young);
-		mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX));
+		mod_timer(&req->rsk_timer, jiffies + tcp_reqsk_timeout(req));
 
 		if (!nreq)
 			return;
 
 		if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
 			/* delete timer */
-			inet_csk_reqsk_queue_drop(sk_listener, nreq);
+			__inet_csk_reqsk_queue_drop(sk_listener, nreq, true);
 			goto no_ownership;
 		}
 
@@ -1068,30 +1138,38 @@ no_ownership:
 	}
 
 drop:
-	inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
+	__inet_csk_reqsk_queue_drop(sk_listener, oreq, true);
+	reqsk_put(oreq);
 }
 
-static void reqsk_queue_hash_req(struct request_sock *req,
-				 unsigned long timeout)
+static bool reqsk_queue_hash_req(struct request_sock *req)
 {
+	bool found_dup_sk = false;
+
+	if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk))
+		return false;
+
+	/* The timer needs to be setup after a successful insertion. */
+	req->timeout = tcp_timeout_init((struct sock *)req);
 	timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
-	mod_timer(&req->rsk_timer, jiffies + timeout);
+	mod_timer(&req->rsk_timer, jiffies + req->timeout);
 
-	inet_ehash_insert(req_to_sk(req), NULL, NULL);
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
 	refcount_set(&req->rsk_refcnt, 2 + 1);
+	return true;
 }
 
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
-				   unsigned long timeout)
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req)
 {
-	reqsk_queue_hash_req(req, timeout);
+	if (!reqsk_queue_hash_req(req))
+		return false;
+
 	inet_csk_reqsk_queue_added(sk);
+	return true;
 }
-EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
 static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
 			   const gfp_t priority)
@@ -1101,8 +1179,7 @@ static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
 	if (!icsk->icsk_ulp_ops)
 		return;
 
-	if (icsk->icsk_ulp_ops->clone)
-		icsk->icsk_ulp_ops->clone(req, newsk, priority);
+	icsk->icsk_ulp_ops->clone(req, newsk, priority);
 }
 
 /**
@@ -1118,42 +1195,61 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 				 const gfp_t priority)
 {
 	struct sock *newsk = sk_clone_lock(sk, priority);
+	struct inet_connection_sock *newicsk;
+	struct inet_request_sock *ireq;
+	struct inet_sock *newinet;
 
-	if (newsk) {
-		struct inet_connection_sock *newicsk = inet_csk(newsk);
+	if (!newsk)
+		return NULL;
 
-		inet_sk_set_state(newsk, TCP_SYN_RECV);
-		newicsk->icsk_bind_hash = NULL;
-		newicsk->icsk_bind2_hash = NULL;
+	newicsk = inet_csk(newsk);
+	newinet = inet_sk(newsk);
+	ireq = inet_rsk(req);
 
-		inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
-		inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
-		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
+	newicsk->icsk_bind_hash = NULL;
+	newicsk->icsk_bind2_hash = NULL;
 
-		/* listeners have SOCK_RCU_FREE, not the children */
-		sock_reset_flag(newsk, SOCK_RCU_FREE);
+	newinet->inet_dport = ireq->ir_rmt_port;
+	newinet->inet_num = ireq->ir_num;
+	newinet->inet_sport = htons(ireq->ir_num);
 
-		inet_sk(newsk)->mc_list = NULL;
+	newsk->sk_bound_dev_if = ireq->ir_iif;
 
-		newsk->sk_mark = inet_rsk(req)->ir_mark;
-		atomic64_set(&newsk->sk_cookie,
-			     atomic64_read(&inet_rsk(req)->ir_cookie));
+	newsk->sk_daddr = ireq->ir_rmt_addr;
+	newsk->sk_rcv_saddr = ireq->ir_loc_addr;
+	newinet->inet_saddr = ireq->ir_loc_addr;
 
-		newicsk->icsk_retransmits = 0;
-		newicsk->icsk_backoff	  = 0;
-		newicsk->icsk_probes_out  = 0;
-		newicsk->icsk_probes_tstamp = 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+#endif
 
-		/* Deinitialize accept_queue to trap illegal accesses. */
-		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
+	/* listeners have SOCK_RCU_FREE, not the children */
+	sock_reset_flag(newsk, SOCK_RCU_FREE);
 
-		inet_clone_ulp(req, newsk, priority);
+	inet_sk(newsk)->mc_list = NULL;
+
+	newsk->sk_mark = inet_rsk(req)->ir_mark;
+	atomic64_set(&newsk->sk_cookie,
+		     atomic64_read(&inet_rsk(req)->ir_cookie));
+
+	newicsk->icsk_retransmits = 0;
+	newicsk->icsk_backoff	  = 0;
+	newicsk->icsk_probes_out  = 0;
+	newicsk->icsk_probes_tstamp = 0;
+
+	/* Deinitialize accept_queue to trap illegal accesses. */
+	memset(&newicsk->icsk_accept_queue, 0,
+	       sizeof(newicsk->icsk_accept_queue));
+
+	inet_sk_set_state(newsk, TCP_SYN_RECV);
+
+	inet_clone_ulp(req, newsk, priority);
+
+	security_inet_csk_clone(newsk, req);
 
-		security_inet_csk_clone(newsk, req);
-	}
 	return newsk;
 }
-EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
 
 /*
  * At this point, there should be no process reference to this
@@ -1178,16 +1274,21 @@ void inet_csk_destroy_sock(struct sock *sk)
 
 	xfrm_sk_free_policy(sk);
 
-	sk_refcnt_debug_release(sk);
-
-	this_cpu_dec(*sk->sk_prot->orphan_count);
+	tcp_orphan_count_dec();
 
 	sock_put(sk);
 }
 EXPORT_SYMBOL(inet_csk_destroy_sock);
 
+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);
+	tcp_orphan_count_inc();
+}
+
 /* This function allows to force a closure of a socket after the call to
- * tcp/dccp_create_openreq_child().
+ * tcp_create_openreq_child().
  */
 void inet_csk_prepare_forced_close(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
@@ -1225,9 +1326,6 @@ int inet_csk_listen_start(struct sock *sk)
 	sk->sk_ack_backlog = 0;
 	inet_csk_delack_init(sk);
 
-	if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT)
-		sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-
 	/* There is race window here: we announce ourselves listening,
 	 * but this transition is still not validated by get_port().
 	 * It is OK, because this socket enters to hash table only
@@ -1248,7 +1346,6 @@ int inet_csk_listen_start(struct sock *sk)
 	inet_sk_set_state(sk, TCP_CLOSE);
 	return err;
 }
-EXPORT_SYMBOL_GPL(inet_csk_listen_start);
 
 static void inet_child_forget(struct sock *sk, struct request_sock *req,
 			      struct sock *child)
@@ -1257,7 +1354,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 
 	sock_orphan(child);
 
-	this_cpu_inc(*sk->sk_prot->orphan_count);
+	tcp_orphan_count_inc();
 
 	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
 		BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
@@ -1343,7 +1440,6 @@ child_put:
 	sock_put(child);
 	return NULL;
 }
-EXPORT_SYMBOL(inet_csk_complete_hashdance);
 
 /*
  *	This routine closes sockets which have been at least partially
@@ -1421,34 +1517,16 @@ skip_child_forget:
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
 
-void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
-{
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
-	const struct inet_sock *inet = inet_sk(sk);
-
-	sin->sin_family		= AF_INET;
-	sin->sin_addr.s_addr	= inet->inet_daddr;
-	sin->sin_port		= inet->inet_dport;
-}
-EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
-
 static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct ip_options_rcu *inet_opt;
-	__be32 daddr = inet->inet_daddr;
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
 	rcu_read_lock();
-	inet_opt = rcu_dereference(inet->inet_opt);
-	if (inet_opt && inet_opt->opt.srr)
-		daddr = inet_opt->opt.faddr;
 	fl4 = &fl->u.ip4;
-	rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr,
-				   inet->inet_saddr, inet->inet_dport,
-				   inet->inet_sport, sk->sk_protocol,
-				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+	inet_sk_init_flowi4(inet, fl4);
+	rt = ip_route_output_flow(sock_net(sk), fl4, sk);
 	if (IS_ERR(rt))
 		rt = NULL;
 	if (rt)
@@ -1476,4 +1554,3 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 out:
 	return dst;
 }
-EXPORT_SYMBOL_GPL(inet_csk_update_pmtu);