1 files changed, 69 insertions, 56 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d0670f00d52..14d02ea905b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,27 +29,16 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
-/*
- * This struct holds the first and last local port number.
- */
-struct local_ports sysctl_local_ports __read_mostly = {
-	.lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
-	.range = { 32768, 61000 },
-};
-
-unsigned long *sysctl_local_reserved_ports;
-EXPORT_SYMBOL(sysctl_local_reserved_ports);
-
-void inet_get_local_port_range(int *low, int *high)
+void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
-		*low = sysctl_local_ports.range[0];
-		*high = sysctl_local_ports.range[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+		*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));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
@@ -57,8 +46,9 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			   const struct inet_bind_bucket *tb, bool relax)
 {
 	struct sock *sk2;
-	struct hlist_node *node;
 	int reuse = sk->sk_reuse;
+	int reuseport = sk->sk_reuseport;
+	kuid_t uid = sock_i_uid((struct sock *)sk);
 
 	/*
 	 * Unlike other sk lookup places we do not check
@@ -67,30 +57,32 @@ int inet_csk_bind_conflict(const struct sock *sk,
 	 * one this bucket belongs to.
 	 */
 
-	sk_for_each_bound(sk2, node, &tb->owners) {
+	sk_for_each_bound(sk2, &tb->owners) {
 		if (sk != sk2 &&
 		    !inet_v6_ipv6only(sk2) &&
 		    (!sk->sk_bound_dev_if ||
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
-			if (!reuse || !sk2->sk_reuse ||
-			    sk2->sk_state == TCP_LISTEN) {
-				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
-				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
-				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+			if ((!reuse || !sk2->sk_reuse ||
+			    sk2->sk_state == TCP_LISTEN) &&
+			    (!reuseport || !sk2->sk_reuseport ||
+			    (sk2->sk_state != TCP_TIME_WAIT &&
+			     !uid_eq(uid, sock_i_uid(sk2))))) {
+
+				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
 					break;
 			}
 			if (!relax && reuse && sk2->sk_reuse &&
 			    sk2->sk_state != TCP_LISTEN) {
-				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 
-				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
-				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
 					break;
 			}
 		}
 	}
-	return node != NULL;
+	return sk2 != NULL;
 }
 EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
 
@@ -101,33 +93,36 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct inet_bind_hashbucket *head;
-	struct hlist_node *node;
 	struct inet_bind_bucket *tb;
 	int ret, attempts = 5;
 	struct net *net = sock_net(sk);
 	int smallest_size = -1, smallest_rover;
+	kuid_t uid = sock_i_uid(sk);
 
 	local_bh_disable();
 	if (!snum) {
 		int remaining, rover, low, high;
 
 again:
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
-		smallest_rover = rover = net_random() % remaining + low;
+		smallest_rover = rover = prandom_u32() % remaining + low;
 
 		smallest_size = -1;
 		do {
-			if (inet_is_reserved_local_port(rover))
+			if (inet_is_local_reserved_port(net, rover))
 				goto next_nolock;
 			head = &hashinfo->bhash[inet_bhashfn(net, rover,
 					hashinfo->bhash_size)];
 			spin_lock(&head->lock);
-			inet_bind_bucket_for_each(tb, node, &head->chain)
+			inet_bind_bucket_for_each(tb, &head->chain)
 				if (net_eq(ib_net(tb), net) && tb->port == rover) {
-					if (tb->fastreuse > 0 &&
-					    sk->sk_reuse &&
-					    sk->sk_state != TCP_LISTEN &&
+					if (((tb->fastreuse > 0 &&
+					      sk->sk_reuse &&
+					      sk->sk_state != TCP_LISTEN) ||
+					     (tb->fastreuseport > 0 &&
+					      sk->sk_reuseport &&
+					      uid_eq(tb->fastuid, uid))) &&
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
@@ -174,7 +169,7 @@ have_snum:
 		head = &hashinfo->bhash[inet_bhashfn(net, snum,
 				hashinfo->bhash_size)];
 		spin_lock(&head->lock);
-		inet_bind_bucket_for_each(tb, node, &head->chain)
+		inet_bind_bucket_for_each(tb, &head->chain)
 			if (net_eq(ib_net(tb), net) && tb->port == snum)
 				goto tb_found;
 	}
@@ -185,14 +180,18 @@ tb_found:
 		if (sk->sk_reuse == SK_FORCE_REUSE)
 			goto success;
 
-		if (tb->fastreuse > 0 &&
-		    sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+		if (((tb->fastreuse > 0 &&
+		      sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
+		     (tb->fastreuseport > 0 &&
+		      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
 		    smallest_size == -1) {
 			goto success;
 		} else {
 			ret = 1;
 			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
-				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+				if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
+				     (tb->fastreuseport > 0 &&
+				      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
 				    smallest_size != -1 && --attempts >= 0) {
 					spin_unlock(&head->lock);
 					goto again;
@@ -212,9 +211,19 @@ tb_not_found:
 			tb->fastreuse = 1;
 		else
 			tb->fastreuse = 0;
-	} else if (tb->fastreuse &&
-		   (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
-		tb->fastreuse = 0;
+		if (sk->sk_reuseport) {
+			tb->fastreuseport = 1;
+			tb->fastuid = uid;
+		} else
+			tb->fastreuseport = 0;
+	} else {
+		if (tb->fastreuse &&
+		    (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
+			tb->fastreuse = 0;
+		if (tb->fastreuseport &&
+		    (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)))
+			tb->fastreuseport = 0;
+	}
 success:
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, snum);
@@ -396,12 +405,12 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 	int flags = inet_sk_flowi_flags(sk);
 
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol,
 			   flags,
-			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -433,11 +442,11 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 
 	rcu_read_lock();
 	opt = rcu_dereference(newinet->inet_opt);
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
-			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -483,9 +492,9 @@ struct request_sock *inet_csk_search_req(const struct sock *sk,
 	     prev = &req->dl_next) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 
-		if (ireq->rmt_port == rport &&
-		    ireq->rmt_addr == raddr &&
-		    ireq->loc_addr == laddr &&
+		if (ireq->ir_rmt_port == rport &&
+		    ireq->ir_rmt_addr == raddr &&
+		    ireq->ir_loc_addr == laddr &&
 		    AF_INET_FAMILY(req->rsk_ops->family)) {
 			WARN_ON(req->sk);
 			*prevp = prev;
@@ -502,7 +511,8 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	const u32 h = inet_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port,
+	const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr,
+				     inet_rsk(req)->ir_rmt_port,
 				     lopt->hash_rnd, lopt->nr_table_entries);
 
 	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
@@ -538,7 +548,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 
 int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
 {
-	int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL);
+	int err = req->rsk_ops->rtx_syn_ack(parent, req);
 
 	if (!err)
 		req->num_retrans++;
@@ -662,11 +672,13 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newsk->sk_state = TCP_SYN_RECV;
 		newicsk->icsk_bind_hash = NULL;
 
-		inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port;
-		inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port);
-		inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
+		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);
 		newsk->sk_write_space = sk_stream_write_space;
 
+		newsk->sk_mark = inet_rsk(req)->ir_mark;
+
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
@@ -714,6 +726,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock);
  * tcp/dccp_create_openreq_child().
  */
 void inet_csk_prepare_forced_close(struct sock *sk)
+	__releases(&sk->sk_lock.slock)
 {
 	/* sk_clone_lock locked the socket and set refcnt to 2 */
 	bh_unlock_sock(sk);