Merge branch 'so_txtime-improvements'

Willem de Bruijn says:

====================
SO_TXTIME improvements

FQ targets monotonic timestamps as generated by the TCP stack.

But SO_TXTIME was later added, which can send skbs with timestamps
against other clocks. It is now possible to detect these through skb
tstamp_type.

Make FQ robust by converting these timestamps for use in FQ (patch 2).

This also requires testing against out-of-bounds values. Prefer to do
this at the source, when parsing SCM_TXTIME (patch 1). But, tests in
the hot path are still needed, to handle BPF sources.

Extend the so_txtime selftest to handle this new case (patch 3).

v1: https://lore.kernel.org/20260603190243.2789335-1-willemdebruijn.kernel@gmail.com
====================

Link: https://patch.msgid.link/20260604194221.3319080-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/core/sock.c

@@ -3045,12 +3045,42 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 		sockc->tsflags |= tsflags;
 		break;
 	case SCM_TXTIME:
+	{
+		ktime_t tmin;
+		u64 txtime;
+
 		if (!sock_flag(sk, SOCK_TXTIME))
 			return -EINVAL;
 		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
 			return -EINVAL;
-		sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
+
+		txtime = get_unaligned((u64 *)CMSG_DATA(cmsg));
+
+		/* Allow sending without a delivery time: zero special case */
+		if (!txtime) {
+			sockc->transmit_time = 0;
+			break;
+		}
+
+		switch (sk->sk_clockid) {
+		case CLOCK_MONOTONIC:
+			tmin = 1;
+			break;
+		case CLOCK_REALTIME:
+			tmin = max(ktime_mono_to_real(0), 1);
+			break;
+		case CLOCK_TAI:
+			tmin = max(ktime_mono_to_any(0, TK_OFFS_TAI), 1);
+			break;
+		default:
+			tmin = 1;
+			WARN_ON_ONCE(1);
+			break;
+		}
+
+		sockc->transmit_time = max_t(ktime_t, txtime, tmin);
 		break;
+	}
 	case SCM_TS_OPT_ID:
 		if (sk_is_tcp(sk))
 			return -EINVAL;

net/sched/sch_fq.c

@@ -537,10 +537,10 @@ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb)
 	rb_insert_color(&skb->rbnode, &flow->t_root);
 }
 
-static bool fq_packet_beyond_horizon(const struct sk_buff *skb,
+static bool fq_packet_beyond_horizon(ktime_t time_to_send,
 				     const struct fq_sched_data *q, u64 now)
 {
-	return unlikely((s64)skb->tstamp > (s64)(now + q->horizon));
+	return unlikely((s64)time_to_send > (s64)(now + q->horizon));
 }
 
 static void fq_flow_adjust_timer(struct fq_sched_data *q, struct fq_flow *flow,
@@ -561,6 +561,36 @@ static void fq_flow_adjust_timer(struct fq_sched_data *q, struct fq_flow *flow,
 	}
 }
 
+static ktime_t fq_skb_tstamp_to_mono(struct sk_buff *skb)
+{
+	const ktime_t mono_max = NSEC_PER_SEC * TIME_UPTIME_SEC_MAX;
+
+	if (likely(skb->tstamp_type == SKB_CLOCK_MONOTONIC))
+		return max(skb->tstamp, 1);
+
+	if (skb->tstamp_type == SKB_CLOCK_TAI)
+		return max(ktime_sub(skb->tstamp, ktime_mono_to_any(0, TK_OFFS_TAI)), 1);
+
+	if (likely(skb->tstamp > mono_max))
+		return max(ktime_sub(skb->tstamp, ktime_mono_to_real(0)), 1);
+
+	/* Handle BPF programs setting skb->stamp but not tstamp_type */
+	net_warn_ratelimited("fq: likely mono tstamp with tstamp_type 0\n");
+
+	skb->tstamp_type = SKB_CLOCK_MONOTONIC;
+	return max(skb->tstamp, 1);
+}
+
+static void fq_mono_to_skb_tstamp(struct sk_buff *skb, ktime_t time_to_send)
+{
+	if (skb->tstamp_type == SKB_CLOCK_MONOTONIC)
+		skb->tstamp = time_to_send;
+	else if (skb->tstamp_type == SKB_CLOCK_REALTIME)
+		skb->tstamp = ktime_mono_to_real(time_to_send);
+	else
+		skb->tstamp = ktime_mono_to_any(time_to_send, TK_OFFS_TAI);
+}
+
 static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		      struct sk_buff **to_free)
 {
@@ -579,17 +609,20 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (!skb->tstamp) {
 		fq_skb_cb(skb)->time_to_send = now;
 	} else {
+		ktime_t time_to_send = fq_skb_tstamp_to_mono(skb);
+
 		/* Check if packet timestamp is too far in the future. */
-		if (fq_packet_beyond_horizon(skb, q, now)) {
+		if (fq_packet_beyond_horizon(time_to_send, q, now)) {
 			if (q->horizon_drop) {
 				q->stat_horizon_drops++;
 				return qdisc_drop_reason(skb, sch, to_free,
 							 QDISC_DROP_HORIZON_LIMIT);
 			}
 			q->stat_horizon_caps++;
-			skb->tstamp = now + q->horizon;
+			time_to_send = now + q->horizon;
+			fq_mono_to_skb_tstamp(skb, time_to_send);
 		}
-		fq_skb_cb(skb)->time_to_send = skb->tstamp;
+		fq_skb_cb(skb)->time_to_send = (u64)time_to_send;
 	}
 
 	f = fq_classify(sch, skb, now);

tools/testing/selftests/drivers/net/so_txtime.py

@@ -46,7 +46,7 @@ def _qdisc_setup(ifname, qdisc, optargs=""):
     tc(f"qdisc replace dev {ifname} root {qdisc} {optargs}")
 
 
-def _test_variants_mono():
+def _test_variants_fq():
     for ipver in ["4", "6"]:
         for testcase in [
             ["no_delay", "a,-1", "a,-1"],
@@ -59,13 +59,20 @@ def _test_variants_mono():
             yield KsftNamedVariant(name, ipver, testcase[1], testcase[2])
 
 
-@ksft_variants(_test_variants_mono())
-def test_so_txtime_mono(cfg, ipver, args_tx, args_rx):
+@ksft_variants(_test_variants_fq())
+def test_so_txtime_fq_mono(cfg, ipver, args_tx, args_rx):
     """Run all variants of monotonic (fq) tests."""
     _qdisc_setup(cfg.ifname, "fq")
     test_so_txtime(cfg, "mono", ipver, args_tx, args_rx, True)
 
 
+@ksft_variants(_test_variants_fq())
+def test_so_txtime_fq_tai(cfg, ipver, args_tx, args_rx):
+    """Run all variants of fq tests, but pass CLOCK_TAI to test conversion."""
+    _qdisc_setup(cfg.ifname, "fq")
+    test_so_txtime(cfg, "tai", ipver, args_tx, args_rx, True)
+
+
 def _test_variants_etf():
     for ipver in ["4", "6"]:
         for testcase in [
@@ -95,7 +102,10 @@ def test_so_txtime_etf(cfg, ipver, args_tx, args_rx, expect_fail):
 def main() -> None:
     """Boilerplate ksft main."""
     with NetDrvEpEnv(__file__) as cfg:
-        ksft_run([test_so_txtime_mono, test_so_txtime_etf], args=(cfg,))
+        ksft_run(
+            [test_so_txtime_fq_mono, test_so_txtime_fq_tai, test_so_txtime_etf],
+            args=(cfg,),
+        )
     ksft_exit()