1 files changed, 67 insertions, 57 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5a7c41fbc6d3..8d4eac793700 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -318,36 +318,47 @@ static u16 tcp_select_window(struct sock *sk)
 }
 
 /* Packet ECN state for a SYN-ACK */
-static inline void TCP_ECN_send_synack(const struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 {
+	const struct tcp_sock *tp = tcp_sk(sk);
+
 	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
 	if (!(tp->ecn_flags & TCP_ECN_OK))
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
+	else if (tcp_ca_needs_ecn(sk))
+		INET_ECN_xmit(sk);
 }
 
 /* Packet ECN state for a SYN.  */
-static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
+static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->ecn_flags = 0;
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+	    tcp_ca_needs_ecn(sk)) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
+		if (tcp_ca_needs_ecn(sk))
+			INET_ECN_xmit(sk);
 	}
 }
 
-static __inline__ void
-TCP_ECN_make_synack(const struct request_sock *req, struct tcphdr *th)
+static void
+tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
+		    struct sock *sk)
 {
-	if (inet_rsk(req)->ecn_ok)
+	if (inet_rsk(req)->ecn_ok) {
 		th->ece = 1;
+		if (tcp_ca_needs_ecn(sk))
+			INET_ECN_xmit(sk);
+	}
 }
 
 /* Set up ECN state for a packet on a ESTABLISHED socket that is about to
  * be sent.
  */
-static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
+static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 				int tcp_header_len)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -362,7 +373,7 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
 				tcp_hdr(skb)->cwr = 1;
 				skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
 			}
-		} else {
+		} else if (!tcp_ca_needs_ecn(sk)) {
 			/* ACK or retransmitted segment: clear ECT|CE */
 			INET_ECN_dontxmit(sk);
 		}
@@ -384,7 +395,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 	TCP_SKB_CB(skb)->tcp_flags = flags;
 	TCP_SKB_CB(skb)->sacked = 0;
 
-	shinfo->gso_segs = 1;
+	tcp_skb_pcount_set(skb, 1);
 	shinfo->gso_size = 0;
 	shinfo->gso_type = 0;
 
@@ -550,7 +561,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
+		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -618,7 +629,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
 	}
 	if (likely(ireq->tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = TCP_SKB_CB(skb)->when;
+		opts->tsval = tcp_skb_timestamp(skb);
 		opts->tsecr = req->ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -647,7 +658,6 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 					struct tcp_out_options *opts,
 					struct tcp_md5sig_key **md5)
 {
-	struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int size = 0;
 	unsigned int eff_sacks;
@@ -666,7 +676,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
+		opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		size += TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -886,8 +896,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 			skb = skb_clone(skb, gfp_mask);
 		if (unlikely(!skb))
 			return -ENOBUFS;
-		/* Our usage of tstamp should remain private */
-		skb->tstamp.tv64 = 0;
 	}
 
 	inet = inet_sk(sk);
@@ -952,7 +960,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
-		TCP_ECN_send(sk, skb, tcp_header_size);
+		tcp_ecn_send(sk, skb, tcp_header_size);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Calculate the MD5 hash, as we have all we need now */
@@ -975,7 +983,18 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
+	/* OK, its time to fill skb_shinfo(skb)->gso_segs */
+	skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
+
+	/* Our usage of tstamp should remain private */
+	skb->tstamp.tv64 = 0;
+
+	/* Cleanup our debris for IP stacks */
+	memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
+			       sizeof(struct inet6_skb_parm)));
+
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+
 	if (likely(err <= 0))
 		return err;
 
@@ -995,7 +1014,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Advance write_seq and place onto the write_queue. */
 	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
@@ -1014,11 +1033,11 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
-		shinfo->gso_segs = 1;
+		tcp_skb_pcount_set(skb, 1);
 		shinfo->gso_size = 0;
 		shinfo->gso_type = 0;
 	} else {
-		shinfo->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
+		tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
 		shinfo->gso_size = mss_now;
 		shinfo->gso_type = sk->sk_gso_type;
 	}
@@ -1146,10 +1165,6 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 
 	buff->ip_summed = skb->ip_summed;
 
-	/* Looks stupid, but our code really uses when of
-	 * skbs, which it never sent before. --ANK
-	 */
-	TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
 	buff->tstamp = skb->tstamp;
 	tcp_fragment_tstamp(skb, buff);
 
@@ -1171,7 +1186,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	}
 
 	/* Link BUFF into the send queue. */
-	skb_header_release(buff);
+	__skb_header_release(buff);
 	tcp_insert_write_queue_after(skb, buff, sk);
 
 	return 0;
@@ -1675,7 +1690,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	tcp_set_skb_tso_segs(sk, buff, mss_now);
 
 	/* Link BUFF into the send queue. */
-	skb_header_release(buff);
+	__skb_header_release(buff);
 	tcp_insert_write_queue_after(skb, buff, sk);
 
 	return 0;
@@ -1874,8 +1889,8 @@ static int tcp_mtu_probe(struct sock *sk)
 	tcp_init_tso_segs(sk, nskb, nskb->len);
 
 	/* We're ready to send.  If this fails, the probe will
-	 * be resegmented into mss-sized pieces by tcp_write_xmit(). */
-	TCP_SKB_CB(nskb)->when = tcp_time_stamp;
+	 * be resegmented into mss-sized pieces by tcp_write_xmit().
+	 */
 	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
 		/* Decrement cwnd here because we are sending
 		 * effectively two packets. */
@@ -1935,8 +1950,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		BUG_ON(!tso_segs);
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
-			/* "when" is used as a start point for the retransmit timer */
-			TCP_SKB_CB(skb)->when = tcp_time_stamp;
+			/* "skb_mstamp" is used as a start point for the retransmit timer */
+			skb_mstamp_get(&skb->skb_mstamp);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2000,8 +2015,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
 			break;
 
-		TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
@@ -2097,10 +2110,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 static bool skb_still_in_host_queue(const struct sock *sk,
 				    const struct sk_buff *skb)
 {
-	const struct sk_buff *fclone = skb + 1;
-
-	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-		     fclone->fclone == SKB_FCLONE_CLONE)) {
+	if (unlikely(skb_fclone_busy(skb))) {
 		NET_INC_STATS_BH(sock_net(sk),
 				 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
 		return true;
@@ -2499,7 +2509,6 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	/* Make a copy, if the first transmission SKB clone we made
 	 * is still in somebody's hands, else make a clone.
 	 */
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
 	/* make sure skb->data is aligned on arches that require it
 	 * and check if ack-trimming & collapsing extended the headroom
@@ -2544,7 +2553,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* Save stamp of the first retransmit. */
 		if (!tp->retrans_stamp)
-			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
+			tp->retrans_stamp = tcp_skb_timestamp(skb);
 
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
@@ -2752,7 +2761,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
 	/* Send it off. */
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
 
@@ -2780,7 +2788,7 @@ int tcp_send_synack(struct sock *sk)
 			if (nskb == NULL)
 				return -ENOMEM;
 			tcp_unlink_write_queue(skb, sk);
-			skb_header_release(nskb);
+			__skb_header_release(nskb);
 			__tcp_add_write_queue_head(sk, nskb);
 			sk_wmem_free_skb(sk, skb);
 			sk->sk_wmem_queued += nskb->truesize;
@@ -2789,9 +2797,8 @@ int tcp_send_synack(struct sock *sk)
 		}
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
-		TCP_ECN_send_synack(tcp_sk(sk), skb);
+		tcp_ecn_send_synack(sk, skb);
 	}
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 }
 
@@ -2835,10 +2842,10 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(req->cookie_ts))
-		TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
+		skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req);
 	else
 #endif
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
+	skb_mstamp_get(&skb->skb_mstamp);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
 					     foc) + sizeof(*th);
 
@@ -2849,7 +2856,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
-	TCP_ECN_make_synack(req, th);
+	tcp_ecn_make_synack(req, th, sk);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
@@ -2956,7 +2963,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
 	tcb->end_seq += skb->len;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	__tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
@@ -3086,9 +3093,9 @@ int tcp_connect(struct sock *sk)
 	skb_reserve(buff, MAX_TCP_HEADER);
 
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
-	tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
+	tp->retrans_stamp = tcp_time_stamp;
 	tcp_connect_queue_skb(sk, buff);
-	TCP_ECN_send_syn(sk, buff);
+	tcp_ecn_send_syn(sk, buff);
 
 	/* Send off SYN; include data in Fast Open. */
 	err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
@@ -3120,6 +3127,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
+	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
+
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3176,6 +3185,8 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
+	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
+
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
@@ -3194,9 +3205,10 @@ void tcp_send_ack(struct sock *sk)
 	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
 
 	/* Send it off, this clears delayed acks for us. */
-	TCP_SKB_CB(buff)->when = tcp_time_stamp;
+	skb_mstamp_get(&buff->skb_mstamp);
 	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
 }
+EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
@@ -3226,7 +3238,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	 * send it.
 	 */
 	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
+	skb_mstamp_get(&skb->skb_mstamp);
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
@@ -3270,7 +3282,6 @@ int tcp_write_wakeup(struct sock *sk)
 			tcp_set_skb_tso_segs(sk, skb, mss);
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-		TCP_SKB_CB(skb)->when = tcp_time_stamp;
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 		if (!err)
 			tcp_event_new_data_sent(sk, skb);
@@ -3289,6 +3300,7 @@ void tcp_send_probe0(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned long probe_max;
 	int err;
 
 	err = tcp_write_wakeup(sk);
@@ -3304,9 +3316,7 @@ void tcp_send_probe0(struct sock *sk)
 		if (icsk->icsk_backoff < sysctl_tcp_retries2)
 			icsk->icsk_backoff++;
 		icsk->icsk_probes_out++;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
-					  TCP_RTO_MAX);
+		probe_max = TCP_RTO_MAX;
 	} else {
 		/* If packet was not sent due to local congestion,
 		 * do not backoff and do not remember icsk_probes_out.
@@ -3316,11 +3326,11 @@ void tcp_send_probe0(struct sock *sk)
 		 */
 		if (!icsk->icsk_probes_out)
 			icsk->icsk_probes_out = 1;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff,
-					      TCP_RESOURCE_PROBE_INTERVAL),
-					  TCP_RTO_MAX);
+		probe_max = TCP_RESOURCE_PROBE_INTERVAL;
 	}
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+				  inet_csk_rto_backoff(icsk, probe_max),
+				  TCP_RTO_MAX);
 }
 
 int tcp_rtx_synack(struct sock *sk, struct request_sock *req)