Merge branch 'listener-refactoring-preparations'

Eric Dumazet says:

====================
tcp: listener refactoring preparations

This patch series makes changes to TCP/DCCP stacks so that
we can switch listener code to lockless mode.

This is done by marking const the listener socket in all
appropriate paths.

FastOpen code had to be changed to not dynamically allocate
a very small structure to make code simpler for following changes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 41 insertions, 57 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8a556643b874..3af85eecbe11 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -219,17 +219,13 @@ int inet_listen(struct socket *sock, int backlog)
 		 * shutdown() (rather than close()).
 		 */
 		if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 &&
-		    !inet_csk(sk)->icsk_accept_queue.fastopenq) {
+		    !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
 			if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0)
-				err = fastopen_init_queue(sk, backlog);
+				fastopen_queue_tune(sk, backlog);
 			else if ((sysctl_tcp_fastopen &
 				  TFO_SERVER_WO_SOCKOPT2) != 0)
-				err = fastopen_init_queue(sk,
+				fastopen_queue_tune(sk,
 				    ((uint)sysctl_tcp_fastopen) >> 16);
-			else
-				err = 0;
-			if (err)
-				goto out;
 
 			tcp_fastopen_init_key_once(true);
 		}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ba2f90d90cb5..e1527882a578 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -335,9 +335,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 
 	sk_acceptq_removed(sk);
 	if (sk->sk_protocol == IPPROTO_TCP &&
-	    tcp_rsk(req)->tfo_listener &&
-	    queue->fastopenq) {
-		spin_lock_bh(&queue->fastopenq->lock);
+	    tcp_rsk(req)->tfo_listener) {
+		spin_lock_bh(&queue->fastopenq.lock);
 		if (tcp_rsk(req)->tfo_listener) {
 			/* We are still waiting for the final ACK from 3WHS
 			 * so can't free req now. Instead, we set req->sk to
@@ -348,7 +347,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 			req->sk = NULL;
 			req = NULL;
 		}
-		spin_unlock_bh(&queue->fastopenq->lock);
+		spin_unlock_bh(&queue->fastopenq.lock);
 	}
 out:
 	release_sock(sk);
@@ -439,7 +438,7 @@ no_route:
 }
 EXPORT_SYMBOL_GPL(inet_csk_route_req);
 
-struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
+struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
 					    const struct request_sock *req)
 {
@@ -886,12 +885,12 @@ void inet_csk_listen_stop(struct sock *sk)
 		sk_acceptq_removed(sk);
 		reqsk_put(req);
 	}
-	if (queue->fastopenq) {
+	if (queue->fastopenq.rskq_rst_head) {
 		/* Free all the reqs queued in rskq_rst_head. */
-		spin_lock_bh(&queue->fastopenq->lock);
-		acc_req = queue->fastopenq->rskq_rst_head;
-		queue->fastopenq->rskq_rst_head = NULL;
-		spin_unlock_bh(&queue->fastopenq->lock);
+		spin_lock_bh(&queue->fastopenq.lock);
+		acc_req = queue->fastopenq.rskq_rst_head;
+		queue->fastopenq.rskq_rst_head = NULL;
+		spin_unlock_bh(&queue->fastopenq.lock);
 		while ((req = acc_req) != NULL) {
 			acc_req = req->dl_next;
 			reqsk_put(req);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 89120196a949..56742e995dd3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -126,7 +126,7 @@ void inet_put_port(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_put_port);
 
-int __inet_inherit_port(struct sock *sk, struct sock *child)
+int __inet_inherit_port(const struct sock *sk, struct sock *child)
 {
 	struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
 	unsigned short port = inet_sk(child)->inet_num;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6595affded20..6b97b5f6457c 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -192,15 +192,11 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 }
 EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
 
-__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
-			      __u16 *mssp)
+__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	const struct tcphdr *th = tcp_hdr(skb);
 
-	tcp_synq_overflow(sk);
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
-
 	return __cookie_v4_init_sequence(iph, th, mssp);
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b8b8fa184f75..3c96fa87ff9e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2253,13 +2253,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 }
 EXPORT_SYMBOL(tcp_disconnect);
 
-void tcp_sock_destruct(struct sock *sk)
-{
-	inet_sock_destruct(sk);
-
-	kfree(inet_csk(sk)->icsk_accept_queue.fastopenq);
-}
-
 static inline bool tcp_can_repair_sock(const struct sock *sk)
 {
 	return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
@@ -2581,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		    TCPF_LISTEN))) {
 			tcp_fastopen_init_key_once(true);
 
-			err = fastopen_init_queue(sk, val);
+			fastopen_queue_tune(sk, val);
 		} else {
 			err = -EINVAL;
 		}
@@ -2849,10 +2842,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_FASTOPEN:
-		if (icsk->icsk_accept_queue.fastopenq)
-			val = icsk->icsk_accept_queue.fastopenq->max_qlen;
-		else
-			val = 0;
+		val = icsk->icsk_accept_queue.fastopenq.max_qlen;
 		break;
 
 	case TCP_TIMESTAMP:
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index db43c6286cf7..f69f436fcbcc 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -142,9 +142,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	if (!child)
 		return NULL;
 
-	spin_lock(&queue->fastopenq->lock);
-	queue->fastopenq->qlen++;
-	spin_unlock(&queue->fastopenq->lock);
+	spin_lock(&queue->fastopenq.lock);
+	queue->fastopenq.qlen++;
+	spin_unlock(&queue->fastopenq.lock);
 
 	/* Initialize the child socket. Have to fix some values to take
 	 * into account the child is a Fast Open socket and is created
@@ -237,8 +237,8 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	 * between qlen overflow causing Fast Open to be disabled
 	 * temporarily vs a server not supporting Fast Open at all.
 	 */
-	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
-	if (!fastopenq || fastopenq->max_qlen == 0)
+	fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+	if (fastopenq->max_qlen == 0)
 		return false;
 
 	if (fastopenq->qlen >= fastopenq->max_qlen) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4964d53907e9..e58cbcd2f07e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5472,7 +5472,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 }
 
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
-					 const struct tcphdr *th, unsigned int len)
+					 const struct tcphdr *th)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5698,11 +5698,11 @@ reset_and_undo:
  *	address independent.
  */
 
-int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
-			  const struct tcphdr *th, unsigned int len)
+int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcphdr *th = tcp_hdr(skb);
 	struct request_sock *req;
 	int queued = 0;
 	bool acceptable;
@@ -5749,7 +5749,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		goto discard;
 
 	case TCP_SYN_SENT:
-		queued = tcp_rcv_synsent_state_process(sk, skb, th, len);
+		queued = tcp_rcv_synsent_state_process(sk, skb, th);
 		if (queued >= 0)
 			return queued;
 
@@ -6064,7 +6064,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc);
 /*
  * Return true if a syncookie should be sent
  */
-static bool tcp_syn_flood_action(struct sock *sk,
+static bool tcp_syn_flood_action(const struct sock *sk,
 				 const struct sk_buff *skb,
 				 const char *proto)
 {
@@ -6082,11 +6082,12 @@ static bool tcp_syn_flood_action(struct sock *sk,
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
 
 	lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
-	if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
-		lopt->synflood_warned = 1;
+	if (!lopt->synflood_warned &&
+	    sysctl_tcp_syncookies != 2 &&
+	    xchg(&lopt->synflood_warned, 1) == 0)
 		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
 			proto, ntohs(tcp_hdr(skb)->dest), msg);
-	}
+
 	return want_cookie;
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a23ba7daecbf..64ece718d66c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -576,7 +576,7 @@ EXPORT_SYMBOL(tcp_v4_send_check);
  *	Exception: precedence violation. We do not implement it in any case.
  */
 
-static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
+static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct {
@@ -795,7 +795,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	inet_twsk_put(tw);
 }
 
-static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
+static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
@@ -1180,7 +1180,8 @@ static void tcp_v4_init_req(struct request_sock *req,
 	ireq->opt = tcp_v4_save_options(skb);
 }
 
-static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl,
+static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
+					  struct flowi *fl,
 					  const struct request_sock *req,
 					  bool *strict)
 {
@@ -1242,7 +1243,7 @@ EXPORT_SYMBOL(tcp_v4_conn_request);
  * The three way handshake has completed - we got a valid synack -
  * now create the new socket.
  */
-struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
+struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst)
 {
@@ -1420,7 +1421,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 	} else
 		sock_rps_save_rxhash(sk, skb);
 
-	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
+	if (tcp_rcv_state_process(sk, skb)) {
 		rsk = sk;
 		goto reset;
 	}
@@ -2185,7 +2186,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct inet_sock *inet = inet_sk(sk);
-	struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
+	const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
 	__be32 dest = inet->inet_daddr;
 	__be32 src = inet->inet_rcv_saddr;
 	__u16 destp = ntohs(inet->inet_dport);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e4fe62b6b106..897e34273ba3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -441,7 +441,9 @@ EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
  * Actually, we could lots of memory writes here. tp of listening
  * socket contains all necessary default parameters.
  */
-struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
+struct sock *tcp_create_openreq_child(const struct sock *sk,
+				      struct request_sock *req,
+				      struct sk_buff *skb)
 {
 	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
 
@@ -821,8 +823,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int state = child->sk_state;
 
 	if (!sock_owned_by_user(child)) {
-		ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb),
-					    skb->len);
+		ret = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
 			parent->sk_data_ready(parent);