tcp: new list for sent but unacked skbs for RACK recovery

This patch adds a new queue (list) that tracks the sent but not yet
acked or SACKed skbs for a TCP connection. The list is chronologically
ordered by skb->skb_mstamp (the head is the oldest sent skb).

This list will be used to optimize TCP Rack recovery, which checks
an skb's timestamp to judge if it has been lost and needs to be
retransmitted. Since TCP write queue is ordered by sequence instead
of sent time, RACK has to scan over the write queue to catch all
eligible packets to detect lost retransmission, and iterates through
SACKed skbs repeatedly.

Special cares for rare events:
1. TCP repair fakes skb transmission so the send queue needs adjusted
2. SACK reneging would require re-inserting SACKed skbs into the
   send queue. For now I believe it's not worth the complexity to
   make RACK work perfectly on SACK reneging, so we do nothing here.
3. Fast Open: currently for non-TFO, send-queue correctly queues
   the pure SYN packet. For TFO which queues a pure SYN and
   then a data packet, send-queue only queues the data packet but
   not the pure SYN due to the structure of TFO code. This is okay
   because the SYN receiver would never respond with a SACK on a
   missing SYN (i.e. SYN is never fast-retransmitted by SACK/RACK).

In order to not grow sk_buff, we use an union for the new list and
_skb_refdst/destructor fields. This is a bit complicated because
we need to make sure _skb_refdst and destructor are properly zeroed
before skb is cloned/copied at transmit, and before being freed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 41 insertions, 13 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c115e37ca608..8cf742fd4f99 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -415,6 +415,7 @@ void tcp_init_sock(struct sock *sk)
 	tp->out_of_order_queue = RB_ROOT;
 	tcp_init_xmit_timers(sk);
 	INIT_LIST_HEAD(&tp->tsq_node);
+	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -881,6 +882,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 			 * available to the caller, no more, no less.
 			 */
 			skb->reserved_tailroom = skb->end - skb->tail - size;
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
 		__kfree_skb(skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5b8d61846c2..fb0d7ed84b94 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1593,6 +1593,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						tcp_skb_pcount(skb),
 						skb->skb_mstamp);
 			tcp_rate_skb_delivered(sk, skb, state->rate);
+			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+				list_del_init(&skb->tcp_tsorted_anchor);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -3054,8 +3056,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 
 	shinfo = skb_shinfo(skb);
 	if (!before(shinfo->tskey, prior_snd_una) &&
-	    before(shinfo->tskey, tcp_sk(sk)->snd_una))
-		__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
+		tcp_skb_tsorted_save(skb) {
+			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+		} tcp_skb_tsorted_restore(skb);
+	}
 }
 
 /* Remove acknowledged frames from the retransmission queue. If our packet
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 188a6f31356d..2341b9f857b6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -446,6 +446,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
 
 		INIT_LIST_HEAD(&newtp->tsq_node);
+		INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0bc9e46a5369..8162e2880178 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -971,6 +971,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 		      HRTIMER_MODE_ABS_PINNED);
 }
 
+static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	skb->skb_mstamp = tp->tcp_mstamp;
+	list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+}
+
 /* This routine actually transmits TCP packets queued in by
  * tcp_do_sendmsg().  This is used by both the initial
  * transmission and possible later retransmissions.
@@ -1003,10 +1009,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
 		oskb = skb;
-		if (unlikely(skb_cloned(skb)))
-			skb = pskb_copy(skb, gfp_mask);
-		else
-			skb = skb_clone(skb, gfp_mask);
+
+		tcp_skb_tsorted_save(oskb) {
+			if (unlikely(skb_cloned(oskb)))
+				skb = pskb_copy(oskb, gfp_mask);
+			else
+				skb = skb_clone(oskb, gfp_mask);
+		} tcp_skb_tsorted_restore(oskb);
+
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
@@ -1127,7 +1137,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		err = net_xmit_eval(err);
 	}
 	if (!err && oskb) {
-		oskb->skb_mstamp = tp->tcp_mstamp;
+		tcp_update_skb_after_send(tp, oskb);
 		tcp_rate_skb_sent(sk, oskb);
 	}
 	return err;
@@ -1328,6 +1338,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	/* Link BUFF into the send queue. */
 	__skb_header_release(buff);
 	tcp_insert_write_queue_after(skb, buff, sk);
+	list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor);
 
 	return 0;
 }
@@ -2260,7 +2271,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp" is used as a start point for the retransmit timer */
-			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_update_skb_after_send(tp, skb);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2838,11 +2849,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
-		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			     -ENOBUFS;
+		tcp_skb_tsorted_save(skb) {
+			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
+			err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+				     -ENOBUFS;
+		} tcp_skb_tsorted_restore(skb);
+
 		if (!err)
-			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_update_skb_after_send(tp, skb);
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
@@ -3023,6 +3037,7 @@ coalesce:
 				goto coalesce;
 			return;
 		}
+		INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_mem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
@@ -3078,9 +3093,14 @@ int tcp_send_synack(struct sock *sk)
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
 		if (skb_cloned(skb)) {
-			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
+			struct sk_buff *nskb;
+
+			tcp_skb_tsorted_save(skb) {
+				nskb = skb_copy(skb, GFP_ATOMIC);
+			} tcp_skb_tsorted_restore(skb);
 			if (!nskb)
 				return -ENOMEM;
+			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
 			tcp_unlink_write_queue(skb, sk);
 			__skb_header_release(nskb);
 			__tcp_add_write_queue_head(sk, nskb);