1 files changed, 103 insertions, 74 deletions

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f0761f060a83..43d7852ce07e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -22,6 +22,7 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/busy_poll.h>
+#include <net/rstreason.h>
 
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
@@ -43,7 +44,7 @@ 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. */
@@ -51,16 +52,17 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
 	return TCP_TW_SUCCESS;
 }
 
-static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq)
+static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq,
+				u32 rcv_nxt)
 {
 #ifdef CONFIG_TCP_AO
 	struct tcp_ao_info *ao;
 
 	ao = rcu_dereference(tcptw->ao_info);
-	if (unlikely(ao && seq < tcptw->tw_rcv_nxt))
+	if (unlikely(ao && seq < rcv_nxt))
 		WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1);
 #endif
-	tcptw->tw_rcv_nxt = seq;
+	WRITE_ONCE(tcptw->tw_rcv_nxt, seq);
 }
 
 /*
@@ -95,45 +97,49 @@ 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)
+			   const struct tcphdr *th, u32 *tw_isn,
+			   enum skb_drop_reason *drop_reason)
 {
-	struct tcp_options_received tmp_opt;
 	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;
 	bool paws_reject = false;
+	int ts_recent_stamp;
 
 	tmp_opt.saw_tstamp = 0;
-	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
+	ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
+	if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) {
 		tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			if (tmp_opt.rcv_tsecr)
 				tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
-			tmp_opt.ts_recent	= tcptw->tw_ts_recent;
-			tmp_opt.ts_recent_stamp	= tcptw->tw_ts_recent_stamp;
+			tmp_opt.ts_recent	= READ_ONCE(tcptw->tw_ts_recent);
+			tmp_opt.ts_recent_stamp	= ts_recent_stamp;
 			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
 
-	if (tw->tw_substate == TCP_FIN_WAIT2) {
+	if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) {
 		/* Just repeat all the checks of tcp_rcv_state_process() */
 
 		/* Out of window, send ACK */
 		if (paws_reject ||
 		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-				   tcptw->tw_rcv_nxt,
-				   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
+				   rcv_nxt,
+				   rcv_nxt + tcptw->tw_rcv_wnd))
 			return tcp_timewait_check_oow_rate_limit(
 				tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);
 
 		if (th->rst)
 			goto kill;
 
-		if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
+		if (th->syn && !before(TCP_SKB_CB(skb)->seq, rcv_nxt))
 			return TCP_TW_RST;
 
 		/* Dup ACK? */
 		if (!th->ack ||
-		    !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
+		    !after(TCP_SKB_CB(skb)->end_seq, rcv_nxt) ||
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
 			inet_twsk_put(tw);
 			return TCP_TW_SUCCESS;
@@ -143,16 +149,22 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		 * reset.
 		 */
 		if (!th->fin ||
-		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1)
+		    TCP_SKB_CB(skb)->end_seq != rcv_nxt + 1)
 			return TCP_TW_RST;
 
 		/* FIN arrived, enter true time-wait state. */
-		tw->tw_substate	  = TCP_TIME_WAIT;
-		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
+		WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT);
+		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq,
+				    rcv_nxt);
 
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
-			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
+			u64 ts = tcp_clock_ms();
+
+			WRITE_ONCE(tw->tw_entry_stamp, ts);
+			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
+				   div_u64(ts, MSEC_PER_SEC));
+			WRITE_ONCE(tcptw->tw_ts_recent,
+				   tmp_opt.rcv_tsval);
 		}
 
 		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
@@ -177,7 +189,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	 */
 
 	if (!paws_reject &&
-	    (TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt &&
+	    (TCP_SKB_CB(skb)->seq == rcv_nxt &&
 	     (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) {
 		/* In window segment, it may be only reset or bare ack. */
 
@@ -196,8 +208,10 @@ kill:
 		}
 
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
+			WRITE_ONCE(tcptw->tw_ts_recent,
+				   tmp_opt.rcv_tsval);
+			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
+				   ktime_get_seconds());
 		}
 
 		inet_twsk_put(tw);
@@ -222,18 +236,20 @@ kill:
 	 */
 
 	if (th->syn && !th->rst && !th->ack && !paws_reject &&
-	    (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
+	    (after(TCP_SKB_CB(skb)->seq, rcv_nxt) ||
 	     (tmp_opt.saw_tstamp &&
-	      (s32)(tcptw->tw_ts_recent - tmp_opt.rcv_tsval) < 0))) {
+	      (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) {
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
 		if (isn == 0)
 			isn++;
-		TCP_SKB_CB(skb)->tcp_tw_isn = isn;
+		*tw_isn = isn;
 		return TCP_TW_SYN;
 	}
 
-	if (paws_reject)
-		__NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED);
+	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.
@@ -251,7 +267,7 @@ kill:
 	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)
 {
@@ -306,6 +322,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		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);
@@ -316,6 +334,10 @@ 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);
@@ -338,17 +360,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == TCP_TIME_WAIT)
 			timeo = TCP_TIMEWAIT_LEN;
 
-		/* tw_timer is pinned, so we need to make sure BH are disabled
-		 * in following section, otherwise timer handler could run before
-		 * we complete the initialization.
-		 */
-		local_bh_disable();
-		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates.
 		 * Note that access to tw after this point is illegal.
 		 */
-		inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo);
-		local_bh_enable();
+		inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
@@ -386,9 +401,9 @@ void tcp_twsk_destructor(struct sock *sk)
 #endif
 	tcp_ao_destroy_sock(sk, true);
 }
-EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+EXPORT_IPV6_MOD_GPL(tcp_twsk_destructor);
 
-void tcp_twsk_purge(struct list_head *net_exit_list, int family)
+void tcp_twsk_purge(struct list_head *net_exit_list)
 {
 	bool purged_once = false;
 	struct net *net;
@@ -396,14 +411,13 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
 	list_for_each_entry(net, net_exit_list, exit_list) {
 		if (net->ipv4.tcp_death_row.hashinfo->pernet) {
 			/* Even if tw_refcount == 1, we must clean up kernel reqsk */
-			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
+			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo);
 		} else if (!purged_once) {
-			inet_twsk_purge(&tcp_hashinfo, family);
+			inet_twsk_purge(&tcp_hashinfo);
 			purged_once = true;
 		}
 	}
 }
-EXPORT_SYMBOL_GPL(tcp_twsk_purge);
 
 /* Warning : This function is called without sk_listener being locked.
  * Be sure to read socket fields once, as their value could change under us.
@@ -446,12 +460,13 @@ 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)
 {
-	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+	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)
@@ -481,7 +496,7 @@ 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,
@@ -515,9 +530,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	const struct tcp_sock *oldtp;
 	struct tcp_sock *newtp;
 	u32 seq;
-#ifdef CONFIG_TCP_AO
-	struct tcp_ao_key *ao_key;
-#endif
 
 	if (!newsk)
 		return NULL;
@@ -558,8 +570,7 @@ 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;
@@ -579,7 +590,7 @@ 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 {
@@ -608,10 +619,14 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 #endif
 #ifdef CONFIG_TCP_AO
 	newtp->ao_info = NULL;
-	ao_key = treq->af_specific->ao_lookup(sk, req,
-				tcp_rsk(req)->ao_keyid, -1);
-	if (ao_key)
-		newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
+
+	if (tcp_rsk_used_ao(req)) {
+		struct tcp_ao_key *ao_key;
+
+		ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1);
+		if (ao_key)
+			newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
+	}
  #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
@@ -625,6 +640,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
+	xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1);
+
 	return newsk;
 }
 EXPORT_SYMBOL(tcp_create_openreq_child);
@@ -645,12 +662,14 @@ 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;
 
@@ -659,9 +678,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		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.
@@ -776,34 +800,34 @@ 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 + req->rsk_rcv_wnd)) {
+	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. */
@@ -852,6 +876,10 @@ 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);
@@ -864,6 +892,7 @@ 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);
 
@@ -879,7 +908,7 @@ embryonic_reset:
 		 * avoid becoming vulnerable to outside attack aiming at
 		 * resetting legit local connections.
 		 */
-		req->rsk_ops->send_reset(sk, skb);
+		req->rsk_ops->send_reset(sk, skb, SK_RST_REASON_INVALID_SYN);
 	} else if (fastopen) { /* received a valid RST pkt */
 		reqsk_fastopen_remove(sk, req, true);
 		tcp_reset(sk, skb);
@@ -893,7 +922,7 @@ 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,
@@ -935,4 +964,4 @@ 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);