1 files changed, 114 insertions, 57 deletions

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bb1fe1ba867a..bd5462154f97 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -20,9 +20,11 @@
  */
 
 #include <net/tcp.h>
+#include <net/tcp_ecn.h>
 #include <net/xfrm.h>
 #include <net/busy_poll.h>
 #include <net/rstreason.h>
+#include <net/psp.h>
 
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
@@ -44,7 +46,7 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
 		/* Send ACK. Note, we do not put the bucket,
 		 * it will be released by caller.
 		 */
-		return TCP_TW_ACK;
+		return TCP_TW_ACK_OOW;
 	}
 
 	/* We are rate-limiting, so just release the tw sock and drop skb. */
@@ -97,14 +99,22 @@ static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq,
  */
 enum tcp_tw_status
 tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
-			   const struct tcphdr *th, u32 *tw_isn)
+			   const struct tcphdr *th, u32 *tw_isn,
+			   enum skb_drop_reason *drop_reason)
 {
 	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt);
 	struct tcp_options_received tmp_opt;
+	enum skb_drop_reason psp_drop;
 	bool paws_reject = false;
 	int ts_recent_stamp;
 
+	/* Instead of dropping immediately, wait to see what value is
+	 * returned. We will accept a non psp-encapsulated syn in the
+	 * case where TCP_TW_SYN is returned.
+	 */
+	psp_drop = psp_twsk_rx_policy_check(tw, skb);
+
 	tmp_opt.saw_tstamp = 0;
 	ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
 	if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) {
@@ -122,6 +132,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) {
 		/* Just repeat all the checks of tcp_rcv_state_process() */
 
+		if (psp_drop)
+			goto out_put;
+
 		/* Out of window, send ACK */
 		if (paws_reject ||
 		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
@@ -157,8 +170,11 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 				    rcv_nxt);
 
 		if (tmp_opt.saw_tstamp) {
+			u64 ts = tcp_clock_ms();
+
+			WRITE_ONCE(tw->tw_entry_stamp, ts);
 			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
-				  ktime_get_seconds());
+				   div_u64(ts, MSEC_PER_SEC));
 			WRITE_ONCE(tcptw->tw_ts_recent,
 				   tmp_opt.rcv_tsval);
 		}
@@ -189,6 +205,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	     (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) {
 		/* In window segment, it may be only reset or bare ack. */
 
+		if (psp_drop)
+			goto out_put;
+
 		if (th->rst) {
 			/* This is TIME_WAIT assassination, in two flavors.
 			 * Oh well... nobody has a sufficient solution to this
@@ -242,8 +261,13 @@ kill:
 		return TCP_TW_SYN;
 	}
 
-	if (paws_reject)
-		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED);
+	if (psp_drop)
+		goto out_put;
+
+	if (paws_reject) {
+		*drop_reason = SKB_DROP_REASON_TCP_RFC7323_TW_PAWS;
+		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWS_TW_REJECTED);
+	}
 
 	if (!th->rst) {
 		/* In this case we must reset the TIMEWAIT timer.
@@ -258,10 +282,12 @@ kill:
 		return tcp_timewait_check_oow_rate_limit(
 			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
 	}
+
+out_put:
 	inet_twsk_put(tw);
 	return TCP_TW_SUCCESS;
 }
-EXPORT_SYMBOL(tcp_timewait_state_process);
+EXPORT_IPV6_MOD(tcp_timewait_state_process);
 
 static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw)
 {
@@ -286,7 +312,6 @@ static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw)
 			return;
 		if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key))
 			goto out_free;
-		tcp_md5_add_sigpool();
 	}
 	return;
 out_free:
@@ -312,10 +337,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
 
-		tw->tw_transparent	= inet_test_bit(TRANSPARENT, sk);
 		tw->tw_mark		= sk->sk_mark;
 		tw->tw_priority		= READ_ONCE(sk->sk_priority);
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
+		/* refreshed when we enter true TIME-WAIT state */
+		tw->tw_entry_stamp	= tcp_time_stamp_ms(tp);
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
 		tcptw->tw_rcv_wnd	= tcp_receive_window(tp);
@@ -326,6 +352,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tcptw->tw_last_oow_ack_time = 0;
 		tcptw->tw_tx_delay	= tp->tcp_tx_delay;
 		tw->tw_txhash		= sk->sk_txhash;
+		tw->tw_tx_queue_mapping = sk->sk_tx_queue_mapping;
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
+		tw->tw_rx_queue_mapping = sk->sk_rx_queue_mapping;
+#endif
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
@@ -365,31 +395,21 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 }
 EXPORT_SYMBOL(tcp_time_wait);
 
-#ifdef CONFIG_TCP_MD5SIG
-static void tcp_md5_twsk_free_rcu(struct rcu_head *head)
-{
-	struct tcp_md5sig_key *key;
-
-	key = container_of(head, struct tcp_md5sig_key, rcu);
-	kfree(key);
-	static_branch_slow_dec_deferred(&tcp_md5_needed);
-	tcp_md5_release_sigpool();
-}
-#endif
-
 void tcp_twsk_destructor(struct sock *sk)
 {
 #ifdef CONFIG_TCP_MD5SIG
 	if (static_branch_unlikely(&tcp_md5_needed.key)) {
 		struct tcp_timewait_sock *twsk = tcp_twsk(sk);
 
-		if (twsk->tw_md5_key)
-			call_rcu(&twsk->tw_md5_key->rcu, tcp_md5_twsk_free_rcu);
+		if (twsk->tw_md5_key) {
+			kfree(twsk->tw_md5_key);
+			static_branch_slow_dec_deferred(&tcp_md5_needed);
+		}
 	}
 #endif
 	tcp_ao_destroy_sock(sk, true);
+	psp_twsk_assoc_free(inet_twsk(sk));
 }
-EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
 void tcp_twsk_purge(struct list_head *net_exit_list)
 {
@@ -448,12 +468,27 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 		rcv_wnd);
 	ireq->rcv_wscale = rcv_wscale;
 }
-EXPORT_SYMBOL(tcp_openreq_init_rwin);
 
-static void tcp_ecn_openreq_child(struct tcp_sock *tp,
-				  const struct request_sock *req)
+static void tcp_ecn_openreq_child(struct sock *sk,
+				  const struct request_sock *req,
+				  const struct sk_buff *skb)
 {
-	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+	const struct tcp_request_sock *treq = tcp_rsk(req);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (treq->accecn_ok) {
+		tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
+		tp->syn_ect_snt = treq->syn_ect_snt;
+		tcp_accecn_third_ack(sk, skb, treq->syn_ect_snt);
+		tp->saw_accecn_opt = treq->saw_accecn_opt;
+		tp->prev_ecnfield = treq->syn_ect_rcv;
+		tp->accecn_opt_demand = 1;
+		tcp_ecn_received_counters_payload(sk, skb);
+	} else {
+		tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
+				     TCP_ECN_MODE_RFC3168 :
+				     TCP_ECN_DISABLED);
+	}
 }
 
 void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
@@ -483,7 +518,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 
 	tcp_set_ca_state(sk, TCP_CA_Open);
 }
-EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
+EXPORT_IPV6_MOD_GPL(tcp_ca_openreq_child);
 
 static void smc_check_reset_syn_req(const struct tcp_sock *oldtp,
 				    struct request_sock *req,
@@ -557,8 +592,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
 
 	if (sock_flag(newsk, SOCK_KEEPOPEN))
-		inet_csk_reset_keepalive_timer(newsk,
-					       keepalive_time_when(newtp));
+		tcp_reset_keepalive_timer(newsk, keepalive_time_when(newtp));
 
 	newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
 	newtp->rx_opt.sack_ok = ireq->sack_ok;
@@ -578,7 +612,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	if (newtp->rx_opt.tstamp_ok) {
 		newtp->tcp_usec_ts = treq->req_usec_ts;
-		newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent);
+		newtp->rx_opt.ts_recent = req->ts_recent;
 		newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 		newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
 	} else {
@@ -619,7 +653,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 	newtp->rx_opt.mss_clamp = req->mss;
-	tcp_ecn_openreq_child(newtp, req);
+	tcp_ecn_openreq_child(newsk, req, skb);
 	newtp->fastopen_req = NULL;
 	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
@@ -650,28 +684,37 @@ EXPORT_SYMBOL(tcp_create_openreq_child);
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
-			   bool fastopen, bool *req_stolen)
+			   bool fastopen, bool *req_stolen,
+			   enum skb_drop_reason *drop_reason)
 {
 	struct tcp_options_received tmp_opt;
 	struct sock *child;
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
+	bool tsecr_reject = false;
 	bool paws_reject = false;
 	bool own_req;
 
 	tmp_opt.saw_tstamp = 0;
+	tmp_opt.accecn = 0;
 	if (th->doff > (sizeof(struct tcphdr)>>2)) {
 		tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
-			tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
-			if (tmp_opt.rcv_tsecr)
+			tmp_opt.ts_recent = req->ts_recent;
+			if (tmp_opt.rcv_tsecr) {
+				if (inet_rsk(req)->tstamp_ok && !fastopen)
+					tsecr_reject = !between(tmp_opt.rcv_tsecr,
+							tcp_rsk(req)->snt_tsval_first,
+							READ_ONCE(tcp_rsk(req)->snt_tsval_last));
 				tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off;
+			}
 			/* We do not store true stamp, but it is not required,
 			 * it can be estimated (approximately)
 			 * from another data.
 			 */
-			tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ;
+			tmp_opt.ts_recent_stamp = ktime_get_seconds() -
+				tcp_reqsk_timeout(req) / HZ;
 			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
@@ -707,10 +750,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
 					  &tcp_rsk(req)->last_oow_ack_time) &&
 
-		    !inet_rtx_syn_ack(sk, req)) {
+		    !tcp_rtx_synack(sk, req)) {
 			unsigned long expires = jiffies;
 
-			expires += reqsk_timeout(req, TCP_RTO_MAX);
+			expires += tcp_reqsk_timeout(req);
 			if (!fastopen)
 				mod_timer_pending(&req->rsk_timer, expires);
 			else
@@ -781,37 +824,34 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	     tcp_rsk(req)->snt_isn + 1))
 		return sk;
 
-	/* Also, it would be not so bad idea to check rcv_tsecr, which
-	 * is essentially ACK extension and too early or too late values
-	 * should cause reset in unsynchronized states.
-	 */
-
 	/* RFC793: "first check sequence number". */
 
-	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq,
-					  TCP_SKB_CB(skb)->end_seq,
-					  tcp_rsk(req)->rcv_nxt,
-					  tcp_rsk(req)->rcv_nxt +
-					  tcp_synack_window(req))) {
+	if (paws_reject || tsecr_reject ||
+	    !tcp_in_window(TCP_SKB_CB(skb)->seq,
+			   TCP_SKB_CB(skb)->end_seq,
+			   tcp_rsk(req)->rcv_nxt,
+			   tcp_rsk(req)->rcv_nxt +
+			   tcp_synack_window(req))) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST) &&
 		    !tcp_oow_rate_limited(sock_net(sk), skb,
 					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
 					  &tcp_rsk(req)->last_oow_ack_time))
 			req->rsk_ops->send_ack(sk, skb, req);
-		if (paws_reject)
+		if (paws_reject) {
+			SKB_DR_SET(*drop_reason, TCP_RFC7323_PAWS);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+		} else if (tsecr_reject) {
+			SKB_DR_SET(*drop_reason, TCP_RFC7323_TSECR);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TSECRREJECTED);
+		} else {
+			SKB_DR_SET(*drop_reason, TCP_OVERWINDOW);
+		}
 		return NULL;
 	}
 
 	/* In sequence, PAWS is OK. */
 
-	/* TODO: We probably should defer ts_recent change once
-	 * we take ownership of @req.
-	 */
-	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
-		WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
-
 	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
 		/* Truncate SYN, it is out of window starting
 		   at tcp_rsk(req)->rcv_isn + 1. */
@@ -835,6 +875,18 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!(flg & TCP_FLAG_ACK))
 		return NULL;
 
+	if (tcp_rsk(req)->accecn_ok && tmp_opt.accecn &&
+	    tcp_rsk(req)->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
+		u8 saw_opt = tcp_accecn_option_init(skb, tmp_opt.accecn);
+
+		tcp_rsk(req)->saw_accecn_opt = saw_opt;
+		if (tcp_rsk(req)->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN) {
+			u8 fail_mode = TCP_ACCECN_OPT_FAIL_RECV;
+
+			tcp_rsk(req)->accecn_fail_mode |= fail_mode;
+		}
+	}
+
 	/* For Fast Open no more processing is needed (sk is the
 	 * child socket).
 	 */
@@ -860,6 +912,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!child)
 		goto listen_overflow;
 
+	if (own_req && tmp_opt.saw_tstamp &&
+	    !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+		tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval;
+
 	if (own_req && rsk_drop_req(req)) {
 		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
 		inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
@@ -872,6 +928,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	return inet_csk_complete_hashdance(sk, child, req, own_req);
 
 listen_overflow:
+	SKB_DR_SET(*drop_reason, TCP_LISTEN_OVERFLOW);
 	if (sk != req->rsk_listener)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
 
@@ -901,7 +958,7 @@ embryonic_reset:
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(tcp_check_req);
+EXPORT_IPV6_MOD(tcp_check_req);
 
 /*
  * Queue segment on the new socket if the new socket is active,
@@ -943,4 +1000,4 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 	sock_put(child);
 	return reason;
 }
-EXPORT_SYMBOL(tcp_child_process);
+EXPORT_IPV6_MOD(tcp_child_process);