Merge branch 'net-prepare-pacing-offload-support'

Eric Dumazet says:

====================
net: prepare pacing offload support

Some network devices have the ability to offload EDT (Earliest
Departure Time) which is the model used for TCP pacing and FQ
packet scheduler.

Some of them implement the timing wheel mechanism described in
https://saeed.github.io/files/carousel-sigcomm17.pdf
with an associated 'timing wheel horizon'.

In order to upstream the NIC support, this series adds :

1) timing wheel horizon as a per-device attribute.

2) FQ packet scheduler support, to let paced packets
   below the timing wheel horizon be handled by the driver.

v1: https://lore.kernel.org/20240930152304.472767-2-edumazet@google.com
====================

Link: https://patch.msgid.link/20241003121219.2396589-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 44 insertions, 6 deletions

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 0c4d5d40cae9..d7131a1afadf 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -1137,6 +1137,10 @@ attribute-sets:
         name: dpll-pin
         type: nest
         nested-attributes: link-dpll-pin-attrs
+      -
+        name: max-pacing-offload-horizon
+        type: uint
+        doc: EDT offload horizon supported by the device (in nsec).
   -
     name: af-spec-attrs
     attributes:
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 22b07c814f4a..49f03cb78c6e 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -183,3 +183,4 @@ struct_devlink_port*                devlink_port
 struct_dpll_pin*                    dpll_pin                                                        
 struct hlist_head                   page_pools
 struct dim_irq_moder*               irq_moder
+u64                                 max_pacing_offload_horizon
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4d20c776a4ff..49a7e7db0883 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2009,6 +2009,8 @@ enum netdev_reg_state {
  *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
  *		   where the clock is recovered.
  *
+ *	@max_pacing_offload_horizon: max EDT offload horizon in nsec.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2399,6 +2401,8 @@ struct net_device {
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
 
+	u64			max_pacing_offload_horizon;
+
 	u8			priv[] ____cacheline_aligned
 				       __counted_by(priv_len);
 } ____cacheline_aligned;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6dc258993b17..506ba9c80e83 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -377,6 +377,7 @@ enum {
 	IFLA_GSO_IPV4_MAX_SIZE,
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
+	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };
 
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index a3cd0c2dc995..25a9a47001cd 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -836,6 +836,8 @@ enum {
 
 	TCA_FQ_WEIGHTS,		/* Weights for each band */
 
+	TCA_FQ_OFFLOAD_HORIZON, /* dequeue paced packets within this horizon immediately (us units) */
+
 	__TCA_FQ_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f0a520987085..682d8d3127db 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1118,6 +1118,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */
 	       + rtnl_devlink_port_size(dev)
 	       + rtnl_dpll_pin_size(dev)
+	       + nla_total_size(8)  /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
 	       + 0;
 }
 
@@ -1867,6 +1868,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			READ_ONCE(dev->tso_max_size)) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS,
 			READ_ONCE(dev->tso_max_segs)) ||
+	    nla_put_uint(skb, IFLA_MAX_PACING_OFFLOAD_HORIZON,
+			 READ_ONCE(dev->max_pacing_offload_horizon)) ||
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES,
 			READ_ONCE(dev->num_rx_queues)) ||
@@ -1975,6 +1978,7 @@ nla_put_failure:
 }
 
 static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+	[IFLA_UNSPEC]		= { .strict_start_type = IFLA_DPLL_PIN },
 	[IFLA_IFNAME]		= { .type = NLA_STRING, .len = IFNAMSIZ-1 },
 	[IFLA_ADDRESS]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
 	[IFLA_BROADCAST]	= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 19a49af5a9e5..aeabf45c9200 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -111,6 +111,7 @@ struct fq_perband_flows {
 struct fq_sched_data {
 /* Read mostly cache line */
 
+	u64		offload_horizon;
 	u32		quantum;
 	u32		initial_quantum;
 	u32		flow_refill_delay;
@@ -299,7 +300,7 @@ static void fq_gc(struct fq_sched_data *q,
 }
 
 /* Fast path can be used if :
- * 1) Packet tstamp is in the past.
+ * 1) Packet tstamp is in the past, or within the pacing offload horizon.
  * 2) FQ qlen == 0   OR
  *   (no flow is currently eligible for transmit,
  *    AND fast path queue has less than 8 packets)
@@ -314,7 +315,7 @@ static bool fq_fastpath_check(const struct Qdisc *sch, struct sk_buff *skb,
 	const struct fq_sched_data *q = qdisc_priv(sch);
 	const struct sock *sk;
 
-	if (fq_skb_cb(skb)->time_to_send > now)
+	if (fq_skb_cb(skb)->time_to_send > now + q->offload_horizon)
 		return false;
 
 	if (sch->q.qlen != 0) {
@@ -595,15 +596,18 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 	unsigned long sample;
 	struct rb_node *p;
 
-	if (q->time_next_delayed_flow > now)
+	if (q->time_next_delayed_flow > now + q->offload_horizon)
 		return;
 
 	/* Update unthrottle latency EWMA.
 	 * This is cheap and can help diagnosing timer/latency problems.
 	 */
 	sample = (unsigned long)(now - q->time_next_delayed_flow);
-	q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3;
-	q->unthrottle_latency_ns += sample >> 3;
+	if ((long)sample > 0) {
+		q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3;
+		q->unthrottle_latency_ns += sample >> 3;
+	}
+	now += q->offload_horizon;
 
 	q->time_next_delayed_flow = ~0ULL;
 	while ((p = rb_first(&q->delayed)) != NULL) {
@@ -687,7 +691,7 @@ begin:
 		u64 time_next_packet = max_t(u64, fq_skb_cb(skb)->time_to_send,
 					     f->time_next_packet);
 
-		if (now < time_next_packet) {
+		if (now + q->offload_horizon < time_next_packet) {
 			head->first = f->next;
 			f->time_next_packet = time_next_packet;
 			fq_flow_set_throttled(q, f);
@@ -925,6 +929,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_HORIZON_DROP]		= { .type = NLA_U8 },
 	[TCA_FQ_PRIOMAP]		= NLA_POLICY_EXACT_LEN(sizeof(struct tc_prio_qopt)),
 	[TCA_FQ_WEIGHTS]		= NLA_POLICY_EXACT_LEN(FQ_BANDS * sizeof(s32)),
+	[TCA_FQ_OFFLOAD_HORIZON]	= { .type = NLA_U32 },
 };
 
 /* compress a u8 array with all elems <= 3 to an array of 2-bit fields */
@@ -1100,6 +1105,17 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 		WRITE_ONCE(q->horizon_drop,
 			   nla_get_u8(tb[TCA_FQ_HORIZON_DROP]));
 
+	if (tb[TCA_FQ_OFFLOAD_HORIZON]) {
+		u64 offload_horizon = (u64)NSEC_PER_USEC *
+				      nla_get_u32(tb[TCA_FQ_OFFLOAD_HORIZON]);
+
+		if (offload_horizon <= qdisc_dev(sch)->max_pacing_offload_horizon) {
+			WRITE_ONCE(q->offload_horizon, offload_horizon);
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "invalid offload_horizon");
+			err = -EINVAL;
+		}
+	}
 	if (!err) {
 
 		sch_tree_unlock(sch);
@@ -1183,6 +1199,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.bands = FQ_BANDS,
 	};
 	struct nlattr *opts;
+	u64 offload_horizon;
 	u64 ce_threshold;
 	s32 weights[3];
 	u64 horizon;
@@ -1199,6 +1216,9 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	horizon = READ_ONCE(q->horizon);
 	do_div(horizon, NSEC_PER_USEC);
 
+	offload_horizon = READ_ONCE(q->offload_horizon);
+	do_div(offload_horizon, NSEC_PER_USEC);
+
 	if (nla_put_u32(skb, TCA_FQ_PLIMIT,
 			READ_ONCE(sch->limit)) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT,
@@ -1224,6 +1244,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_TIMER_SLACK,
 			READ_ONCE(q->timer_slack)) ||
 	    nla_put_u32(skb, TCA_FQ_HORIZON, (u32)horizon) ||
+	    nla_put_u32(skb, TCA_FQ_OFFLOAD_HORIZON, (u32)offload_horizon) ||
 	    nla_put_u8(skb, TCA_FQ_HORIZON_DROP,
 		       READ_ONCE(q->horizon_drop)))
 		goto nla_put_failure;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index f0d71b2a3f1e..96ec2b01e725 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -377,6 +377,7 @@ enum {
 	IFLA_GSO_IPV4_MAX_SIZE,
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
+	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };