Merge branch 'tcp'

Eric Dumazet says:

====================
tcp: deduplicate TCP_SKB_CB(skb)->when

TCP_SKB_CB(skb)->when has different meaning in output and input paths.

In output path, it contains a timestamp.
In input path, it contains an ISN, chosen by tcp_timewait_state_process()

Its usage in output path is obsolete after usec timestamping.
Lets simplify and clean this.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/tcp.h

@@ -672,6 +672,12 @@ void tcp_send_window_probe(struct sock *sk);
  */
 #define tcp_time_stamp		((__u32)(jiffies))
 
+static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
+{
+	return skb->skb_mstamp.stamp_jiffies;
+}
+
+
 #define tcp_flag_byte(th) (((u_int8_t *)th)[13])
 
 #define TCPHDR_FIN 0x01
@@ -698,7 +704,7 @@ struct tcp_skb_cb {
 	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	__u32		when;		/* used to compute rtt's	*/
+	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/

net/ipv4/tcp_input.c

@@ -2967,7 +2967,8 @@ void tcp_rearm_rto(struct sock *sk)
 		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 			struct sk_buff *skb = tcp_write_queue_head(sk);
-			const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
+			const u32 rto_time_stamp =
+				tcp_skb_timestamp(skb) + rto;
 			s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
@@ -5906,7 +5907,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct request_sock *req;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct dst_entry *dst = NULL;
-	__u32 isn = TCP_SKB_CB(skb)->when;
+	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	bool want_cookie = false, fastopen;
 	struct flowi fl;
 	struct tcp_fastopen_cookie foc = { .len = -1 };

net/ipv4/tcp_ipv4.c

@@ -437,8 +437,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
 
-		remaining = icsk->icsk_rto - min(icsk->icsk_rto,
-				tcp_time_stamp - TCP_SKB_CB(skb)->when);
+		remaining = icsk->icsk_rto -
+			    min(icsk->icsk_rto,
+				tcp_time_stamp - tcp_skb_timestamp(skb));
 
 		if (remaining) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
@@ -1627,7 +1628,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when	 = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 

net/ipv4/tcp_minisocks.c

@@ -232,7 +232,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
 		if (isn == 0)
 			isn++;
-		TCP_SKB_CB(skb)->when = isn;
+		TCP_SKB_CB(skb)->tcp_tw_isn = isn;
 		return TCP_TW_SYN;
 	}
 

net/ipv4/tcp_output.c

@@ -550,7 +550,7 @@ 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 +618,7 @@ 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 +647,6 @@ 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 +665,7 @@ 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 +885,6 @@ 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);
@@ -975,7 +972,10 @@ 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));
 
+	/* Our usage of tstamp should remain private */
+	skb->tstamp.tv64 = 0;
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+
 	if (likely(err <= 0))
 		return err;
 
@@ -1149,7 +1149,6 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	/* 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);
 
@@ -1874,8 +1873,8 @@ 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 +1934,8 @@ 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 +1999,6 @@ 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;
 
@@ -2499,7 +2496,6 @@ 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 +2540,7 @@ 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 +2748,6 @@ 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);
 
@@ -2791,7 +2786,6 @@ int tcp_send_synack(struct sock *sk)
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
 		TCP_ECN_send_synack(tcp_sk(sk), skb);
 	}
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 }
 
@@ -2835,10 +2829,10 @@ 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);
 
@@ -3086,7 +3080,7 @@ 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);
 
@@ -3194,7 +3188,7 @@ 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));
 }
 
@@ -3226,7 +3220,7 @@ 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 +3264,6 @@ 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);

net/ipv4/tcp_timer.c

@@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk,
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
-	if (unlikely(!tcp_sk(sk)->retrans_stamp))
-		start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
-	else
 	start_ts = tcp_sk(sk)->retrans_stamp;
+	if (unlikely(!start_ts))
+		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);

net/ipv6/tcp_ipv6.c

@@ -738,7 +738,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = inet6_iif(skb);
 
-	if (!TCP_SKB_CB(skb)->when &&
+	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
 	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
@@ -1412,7 +1412,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;