1 files changed, 166 insertions, 73 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1db253e36045..a369e8a70b2c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -518,17 +518,26 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
 		struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
+		u8 *p = (u8 *)ptr;
+		u32 len; /* Fast Open option length */
+
+		if (foc->exp) {
+			len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+			*ptr = htonl((TCPOPT_EXP << 24) | (len << 16) |
+				     TCPOPT_FASTOPEN_MAGIC);
+			p += TCPOLEN_EXP_FASTOPEN_BASE;
+		} else {
+			len = TCPOLEN_FASTOPEN_BASE + foc->len;
+			*p++ = TCPOPT_FASTOPEN;
+			*p++ = len;
+		}
 
-		*ptr++ = htonl((TCPOPT_EXP << 24) |
-			       ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
-			       TCPOPT_FASTOPEN_MAGIC);
-
-		memcpy(ptr, foc->val, foc->len);
-		if ((foc->len & 3) == 2) {
-			u8 *align = ((u8 *)ptr) + foc->len;
-			align[0] = align[1] = TCPOPT_NOP;
+		memcpy(p, foc->val, foc->len);
+		if ((len & 3) == 2) {
+			p[foc->len] = TCPOPT_NOP;
+			p[foc->len + 1] = TCPOPT_NOP;
 		}
-		ptr += (foc->len + 3) >> 2;
+		ptr += (len + 3) >> 2;
 	}
 }
 
@@ -565,7 +574,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	opts->mss = tcp_advertise_mss(sk);
 	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
+	if (likely(sysctl_tcp_timestamps && !*md5)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
@@ -583,13 +592,17 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	}
 
 	if (fastopen && fastopen->cookie.len >= 0) {
-		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
+		u32 need = fastopen->cookie.len;
+
+		need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE :
+					       TCPOLEN_FASTOPEN_BASE;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
 			opts->options |= OPTION_FAST_OPEN_COOKIE;
 			opts->fastopen_cookie = &fastopen->cookie;
 			remaining -= need;
 			tp->syn_fastopen = 1;
+			tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0;
 		}
 	}
 
@@ -601,15 +614,14 @@ static unsigned int tcp_synack_options(struct sock *sk,
 				   struct request_sock *req,
 				   unsigned int mss, struct sk_buff *skb,
 				   struct tcp_out_options *opts,
-				   struct tcp_md5sig_key **md5,
+				   const struct tcp_md5sig_key *md5,
 				   struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 
 #ifdef CONFIG_TCP_MD5SIG
-	*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
-	if (*md5) {
+	if (md5) {
 		opts->options |= OPTION_MD5;
 		remaining -= TCPOLEN_MD5SIG_ALIGNED;
 
@@ -620,8 +632,6 @@ static unsigned int tcp_synack_options(struct sock *sk,
 		 */
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
-#else
-	*md5 = NULL;
 #endif
 
 	/* We always send an MSS option. */
@@ -645,7 +655,10 @@ static unsigned int tcp_synack_options(struct sock *sk,
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 	if (foc != NULL && foc->len >= 0) {
-		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+		u32 need = foc->len;
+
+		need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE :
+				   TCPOLEN_FASTOPEN_BASE;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
 			opts->options |= OPTION_FAST_OPEN_COOKIE;
@@ -989,7 +1002,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (md5) {
 		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
 		tp->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, sk, NULL, skb);
+					       md5, sk, skb);
 	}
 #endif
 
@@ -1151,7 +1164,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 
 	/* Get a new skb... force flag on. */
 	buff = sk_stream_alloc_skb(sk, nsize, gfp);
-	if (buff == NULL)
+	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
 
 	sk->sk_wmem_queued += buff->truesize;
@@ -1354,6 +1367,8 @@ void tcp_mtup_init(struct sock *sk)
 			       icsk->icsk_af_ops->net_header_len;
 	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
 	icsk->icsk_mtup.probe_size = 0;
+	if (icsk->icsk_mtup.enabled)
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
 }
 EXPORT_SYMBOL(tcp_mtup_init);
 
@@ -1708,7 +1723,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 		return tcp_fragment(sk, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp);
-	if (unlikely(buff == NULL))
+	if (unlikely(!buff))
 		return -ENOMEM;
 
 	sk->sk_wmem_queued += buff->truesize;
@@ -1752,20 +1767,23 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 bool *is_cwnd_limited, u32 max_segs)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 age, send_win, cong_win, limit, in_flight;
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct skb_mstamp now;
+	struct sk_buff *head;
 	int win_divisor;
 
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 		goto send_now;
 
-	if (icsk->icsk_ca_state != TCP_CA_Open)
+	if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR)))
 		goto send_now;
 
-	/* Defer for less than two clock ticks. */
-	if (tp->tso_deferred &&
-	    (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
+	/* Avoid bursty behavior by allowing defer
+	 * only if the last write was recent.
+	 */
+	if ((s32)(tcp_time_stamp - tp->lsndtime) > 0)
 		goto send_now;
 
 	in_flight = tcp_packets_in_flight(tp);
@@ -1807,11 +1825,14 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 			goto send_now;
 	}
 
-	/* Ok, it looks like it is advisable to defer.
-	 * Do not rearm the timer if already set to not break TCP ACK clocking.
-	 */
-	if (!tp->tso_deferred)
-		tp->tso_deferred = 1 | (jiffies << 1);
+	head = tcp_write_queue_head(sk);
+	skb_mstamp_get(&now);
+	age = skb_mstamp_us_delta(&now, &head->skb_mstamp);
+	/* If next ACK is likely to come too late (half srtt), do not defer */
+	if (age < (tp->srtt_us >> 4))
+		goto send_now;
+
+	/* Ok, it looks like it is advisable to defer. */
 
 	if (cong_win < send_win && cong_win < skb->len)
 		*is_cwnd_limited = true;
@@ -1819,10 +1840,34 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	return true;
 
 send_now:
-	tp->tso_deferred = 0;
 	return false;
 }
 
+static inline void tcp_mtu_check_reprobe(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
+	u32 interval;
+	s32 delta;
+
+	interval = net->ipv4.sysctl_tcp_probe_interval;
+	delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp;
+	if (unlikely(delta >= interval * HZ)) {
+		int mss = tcp_current_mss(sk);
+
+		/* Update current search range */
+		icsk->icsk_mtup.probe_size = 0;
+		icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp +
+			sizeof(struct tcphdr) +
+			icsk->icsk_af_ops->net_header_len;
+		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
+
+		/* Update probe time stamp */
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
+	}
+}
+
 /* Create a new MTU probe if we are ready.
  * MTU probe is regularly attempting to increase the path MTU by
  * deliberately sending larger packets.  This discovers routing
@@ -1837,11 +1882,13 @@ static int tcp_mtu_probe(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sk_buff *skb, *nskb, *next;
+	struct net *net = sock_net(sk);
 	int len;
 	int probe_size;
 	int size_needed;
 	int copy;
 	int mss_now;
+	int interval;
 
 	/* Not currently probing/verifying,
 	 * not in recovery,
@@ -1854,12 +1901,25 @@ static int tcp_mtu_probe(struct sock *sk)
 	    tp->rx_opt.num_sacks || tp->rx_opt.dsack)
 		return -1;
 
-	/* Very simple search strategy: just double the MSS. */
+	/* Use binary search for probe_size between tcp_mss_base,
+	 * and current mss_clamp. if (search_high - search_low)
+	 * smaller than a threshold, backoff from probing.
+	 */
 	mss_now = tcp_current_mss(sk);
-	probe_size = 2 * tp->mss_cache;
+	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
+				    icsk->icsk_mtup.search_low) >> 1);
 	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
-	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
-		/* TODO: set timer for probe_converge_event */
+	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
+	/* When misfortune happens, we are reprobing actively,
+	 * and then reprobe timer has expired. We stick with current
+	 * probing process by not resetting search range to its orignal.
+	 */
+	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
+		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+		/* Check whether enough time has elaplased for
+		 * another round of probing.
+		 */
+		tcp_mtu_check_reprobe(sk);
 		return -1;
 	}
 
@@ -1881,7 +1941,8 @@ static int tcp_mtu_probe(struct sock *sk)
 	}
 
 	/* We're allowed to probe.  Build it now. */
-	if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
+	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC);
+	if (!nskb)
 		return -1;
 	sk->sk_wmem_queued += nskb->truesize;
 	sk_mem_charge(sk, nskb->truesize);
@@ -2179,7 +2240,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	int mss = tcp_current_mss(sk);
 	int err = -1;
 
-	if (tcp_send_head(sk) != NULL) {
+	if (tcp_send_head(sk)) {
 		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
 		goto rearm_timer;
 	}
@@ -2689,7 +2750,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		if (skb == tcp_send_head(sk))
 			break;
 		/* we could do better than to assign each time */
-		if (hole == NULL)
+		if (!hole)
 			tp->retransmit_skb_hint = skb;
 
 		/* Assume this retransmit will generate
@@ -2713,7 +2774,7 @@ begin_fwd:
 			if (!tcp_can_forward_retransmit(sk))
 				break;
 			/* Backtrack if necessary to non-L'ed skb */
-			if (hole != NULL) {
+			if (hole) {
 				skb = hole;
 				hole = NULL;
 			}
@@ -2721,7 +2782,7 @@ begin_fwd:
 			goto begin_fwd;
 
 		} else if (!(sacked & TCPCB_LOST)) {
-			if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
+			if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
 				hole = skb;
 			continue;
 
@@ -2751,39 +2812,65 @@ begin_fwd:
 	}
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
@@ -2824,14 +2911,14 @@ int tcp_send_synack(struct sock *sk)
 	struct sk_buff *skb;
 
 	skb = tcp_write_queue_head(sk);
-	if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+	if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
 		pr_debug("%s: wrong queue state\n", __func__);
 		return -EFAULT;
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
 		if (skb_cloned(skb)) {
 			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
-			if (nskb == NULL)
+			if (!nskb)
 				return -ENOMEM;
 			tcp_unlink_write_queue(skb, sk);
 			__skb_header_release(nskb);
@@ -2866,7 +2953,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcphdr *th;
 	struct sk_buff *skb;
-	struct tcp_md5sig_key *md5;
+	struct tcp_md5sig_key *md5 = NULL;
 	int tcp_header_size;
 	int mss;
 
@@ -2879,7 +2966,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	skb_reserve(skb, MAX_TCP_HEADER);
 
 	skb_dst_set(skb, dst);
-	security_skb_owned_by(skb, sk);
 
 	mss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
@@ -2892,7 +2978,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	else
 #endif
 	skb_mstamp_get(&skb->skb_mstamp);
-	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
+
+#ifdef CONFIG_TCP_MD5SIG
+	rcu_read_lock();
+	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
+#endif
+	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
 					     foc) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
@@ -2923,12 +3014,14 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
-	if (md5) {
+	if (md5)
 		tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, NULL, req, skb);
-	}
+					       md5, req_to_sk(req), skb);
+	rcu_read_unlock();
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
@@ -2966,7 +3059,7 @@ static void tcp_connect_init(struct sock *sk)
 		(sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
 
 #ifdef CONFIG_TCP_MD5SIG
-	if (tp->af_specific->md5_lookup(sk, sk) != NULL)
+	if (tp->af_specific->md5_lookup(sk, sk))
 		tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
 
@@ -3252,7 +3345,7 @@ void tcp_send_ack(struct sock *sk)
 	 * sock.
 	 */
 	buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
-	if (buff == NULL) {
+	if (!buff) {
 		inet_csk_schedule_ack(sk);
 		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
@@ -3296,7 +3389,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 
 	/* We don't queue it, tcp_transmit_skb() sets ownership. */
 	skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
-	if (skb == NULL)
+	if (!skb)
 		return -1;
 
 	/* Reserve space for headers and set control bits. */
@@ -3327,8 +3420,8 @@ int tcp_write_wakeup(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return -1;
 
-	if ((skb = tcp_send_head(sk)) != NULL &&
-	    before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
+	skb = tcp_send_head(sk);
+	if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
 		int err;
 		unsigned int mss = tcp_current_mss(sk);
 		unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;