taprio: Adjust timestamps for TCP packets

When the taprio qdisc is running in "txtime offload" mode, it will
set the launchtime value (in skb->tstamp) for all the packets which do
not have the SO_TXTIME socket option. But, the TCP packets already have
this value set and it indicates the earliest departure time represented
in CLOCK_MONOTONIC clock.

We need to respect the timestamp set by the TCP subsystem. So, convert
this time to the clock which taprio is using and ensure that the packet
is not transmitted before the deadline set by TCP.

Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 40 insertions, 1 deletions

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 5c5e7db520dc..388750ddc57a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -22,6 +22,7 @@
 #include <net/pkt_cls.h>
 #include <net/sch_generic.h>
 #include <net/sock.h>
+#include <net/tcp.h>
 
 static LIST_HEAD(taprio_list);
 static DEFINE_SPINLOCK(taprio_list_lock);
@@ -267,6 +268,41 @@ static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch)
 	return entry;
 }
 
+/* This returns the tstamp value set by TCP in terms of the set clock. */
+static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb)
+{
+	unsigned int offset = skb_network_offset(skb);
+	const struct ipv6hdr *ipv6h;
+	const struct iphdr *iph;
+	struct ipv6hdr _ipv6h;
+
+	ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
+	if (!ipv6h)
+		return 0;
+
+	if (ipv6h->version == 4) {
+		iph = (struct iphdr *)ipv6h;
+		offset += iph->ihl * 4;
+
+		/* special-case 6in4 tunnelling, as that is a common way to get
+		 * v6 connectivity in the home
+		 */
+		if (iph->protocol == IPPROTO_IPV6) {
+			ipv6h = skb_header_pointer(skb, offset,
+						   sizeof(_ipv6h), &_ipv6h);
+
+			if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP)
+				return 0;
+		} else if (iph->protocol != IPPROTO_TCP) {
+			return 0;
+		}
+	} else if (ipv6h->version == 6 && ipv6h->nexthdr != IPPROTO_TCP) {
+		return 0;
+	}
+
+	return ktime_mono_to_any(skb->skb_mstamp_ns, q->tk_offset);
+}
+
 /* There are a few scenarios where we will have to modify the txtime from
  * what is read from next_txtime in sched_entry. They are:
  * 1. If txtime is in the past,
@@ -284,7 +320,7 @@ static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch)
  */
 static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch)
 {
-	ktime_t transmit_end_time, interval_end, interval_start;
+	ktime_t transmit_end_time, interval_end, interval_start, tcp_tstamp;
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct sched_gate_list *sched, *admin;
 	ktime_t minimum_time, now, txtime;
@@ -295,6 +331,9 @@ static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch)
 	now = taprio_get_time(q);
 	minimum_time = ktime_add_ns(now, q->txtime_delay);
 
+	tcp_tstamp = get_tcp_tstamp(q, skb);
+	minimum_time = max_t(ktime_t, minimum_time, tcp_tstamp);
+
 	rcu_read_lock();
 	admin = rcu_dereference(q->admin_sched);
 	sched = rcu_dereference(q->oper_sched);