Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 125 insertions, 9 deletions

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index cdd96b9a27bc..e26a24017faa 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -78,18 +78,42 @@ struct cbs_sched_data {
 	s64 sendslope; /* in bytes/s */
 	s64 idleslope; /* in bytes/s */
 	struct qdisc_watchdog watchdog;
-	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch);
+	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free);
 	struct sk_buff *(*dequeue)(struct Qdisc *sch);
+	struct Qdisc *qdisc;
 };
 
-static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			     struct Qdisc *child,
+			     struct sk_buff **to_free)
 {
-	return qdisc_enqueue_tail(skb, sch);
+	int err;
+
+	err = child->ops->enqueue(skb, child, to_free);
+	if (err != NET_XMIT_SUCCESS)
+		return err;
+
+	qdisc_qstats_backlog_inc(sch, skb);
+	sch->q.qlen++;
+
+	return NET_XMIT_SUCCESS;
 }
 
-static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch,
+			       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
+
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
+}
+
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch,
+			    struct sk_buff **to_free)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
 
 	if (sch->q.qlen == 0 && q->credits > 0) {
 		/* We need to stop accumulating credits when there's
@@ -99,7 +123,7 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
 		q->last = ktime_get_ns();
 	}
 
-	return qdisc_enqueue_tail(skb, sch);
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
 }
 
 static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
@@ -107,7 +131,7 @@ static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 
-	return q->enqueue(skb, sch);
+	return q->enqueue(skb, sch, to_free);
 }
 
 /* timediff is in ns, slope is in bytes/s */
@@ -132,9 +156,25 @@ static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate)
 	return div64_s64(len * slope, port_rate);
 }
 
+static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child)
+{
+	struct sk_buff *skb;
+
+	skb = child->ops->dequeue(child);
+	if (!skb)
+		return NULL;
+
+	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+
+	return skb;
+}
+
 static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
 	s64 now = ktime_get_ns();
 	struct sk_buff *skb;
 	s64 credits;
@@ -157,8 +197,7 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 			return NULL;
 		}
 	}
-
-	skb = qdisc_dequeue_head(sch);
+	skb = cbs_child_dequeue(sch, qdisc);
 	if (!skb)
 		return NULL;
 
@@ -178,7 +217,10 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 
 static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
 {
-	return qdisc_dequeue_head(sch);
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
+
+	return cbs_child_dequeue(sch, qdisc);
 }
 
 static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
@@ -310,6 +352,13 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 		return -EINVAL;
 	}
 
+	q->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+				     sch->handle, extack);
+	if (!q->qdisc)
+		return -ENOMEM;
+
+	qdisc_hash_add(q->qdisc, false);
+
 	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
 
 	q->enqueue = cbs_enqueue_soft;
@@ -328,6 +377,9 @@ static void cbs_destroy(struct Qdisc *sch)
 	qdisc_watchdog_cancel(&q->watchdog);
 
 	cbs_disable_offload(dev, q);
+
+	if (q->qdisc)
+		qdisc_destroy(q->qdisc);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -356,8 +408,72 @@ nla_put_failure:
 	return -1;
 }
 
+static int cbs_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	if (cl != 1 || !q->qdisc)	/* only one class */
+		return -ENOENT;
+
+	tcm->tcm_handle |= TC_H_MIN(1);
+	tcm->tcm_info = q->qdisc->handle;
+
+	return 0;
+}
+
+static int cbs_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		     struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					sch->handle, NULL);
+		if (!new)
+			new = &noop_qdisc;
+	}
+
+	*old = qdisc_replace(sch, new, &q->qdisc);
+	return 0;
+}
+
+static struct Qdisc *cbs_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	return q->qdisc;
+}
+
+static unsigned long cbs_find(struct Qdisc *sch, u32 classid)
+{
+	return 1;
+}
+
+static void cbs_walk(struct Qdisc *sch, struct qdisc_walker *walker)
+{
+	if (!walker->stop) {
+		if (walker->count >= walker->skip) {
+			if (walker->fn(sch, 1, walker) < 0) {
+				walker->stop = 1;
+				return;
+			}
+		}
+		walker->count++;
+	}
+}
+
+static const struct Qdisc_class_ops cbs_class_ops = {
+	.graft		=	cbs_graft,
+	.leaf		=	cbs_leaf,
+	.find		=	cbs_find,
+	.walk		=	cbs_walk,
+	.dump		=	cbs_dump_class,
+};
+
 static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
 	.id		=	"cbs",
+	.cl_ops		=	&cbs_class_ops,
 	.priv_size	=	sizeof(struct cbs_sched_data),
 	.enqueue	=	cbs_enqueue,
 	.dequeue	=	cbs_dequeue,