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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 89 insertions, 4 deletions

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 93b9d70a9b28..7f8ea9e297c3 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <net/inet_ecn.h>
 #include <net/red.h>
 
@@ -40,6 +41,7 @@ struct red_sched_data {
 	u32			limit;		/* HARD maximal queue length */
 	unsigned char		flags;
 	struct timer_list	adapt_timer;
+	struct Qdisc		*sch;
 	struct red_parms	parms;
 	struct red_vars		vars;
 	struct red_stats	stats;
@@ -147,11 +149,37 @@ static void red_reset(struct Qdisc *sch)
 	red_restart(&q->vars);
 }
 
+static int red_offload(struct Qdisc *sch, bool enable)
+{
+	struct red_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_red_qopt_offload opt = {
+		.handle = sch->handle,
+		.parent = sch->parent,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	if (enable) {
+		opt.command = TC_RED_REPLACE;
+		opt.set.min = q->parms.qth_min >> q->parms.Wlog;
+		opt.set.max = q->parms.qth_max >> q->parms.Wlog;
+		opt.set.probability = q->parms.max_P;
+		opt.set.is_ecn = red_use_ecn(q);
+	} else {
+		opt.command = TC_RED_DESTROY;
+	}
+
+	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt);
+}
+
 static void red_destroy(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	del_timer_sync(&q->adapt_timer);
+	red_offload(sch, false);
 	qdisc_destroy(q->qdisc);
 }
 
@@ -218,13 +246,14 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 		red_start_of_idle_period(&q->vars);
 
 	sch_tree_unlock(sch);
+	red_offload(sch, true);
 	return 0;
 }
 
-static inline void red_adaptative_timer(unsigned long arg)
+static inline void red_adaptative_timer(struct timer_list *t)
 {
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	struct red_sched_data *q = qdisc_priv(sch);
+	struct red_sched_data *q = from_timer(q, t, adapt_timer);
+	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
 	spin_lock(root_lock);
@@ -238,10 +267,40 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt)
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	q->qdisc = &noop_qdisc;
-	setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch);
+	q->sch = sch;
+	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
 	return red_change(sch, opt);
 }
 
+static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_red_qopt_offload hw_stats = {
+		.command = TC_RED_STATS,
+		.handle = sch->handle,
+		.parent = sch->parent,
+		{
+			.stats.bstats = &sch->bstats,
+			.stats.qstats = &sch->qstats,
+		},
+	};
+	int err;
+
+	opt->flags &= ~TC_RED_OFFLOADED;
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return 0;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED,
+					    &hw_stats);
+	if (err == -EOPNOTSUPP)
+		return 0;
+
+	if (!err)
+		opt->flags |= TC_RED_OFFLOADED;
+
+	return err;
+}
+
 static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
@@ -255,8 +314,13 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.Plog		= q->parms.Plog,
 		.Scell_log	= q->parms.Scell_log,
 	};
+	int err;
 
 	sch->qstats.backlog = q->qdisc->qstats.backlog;
+	err = red_dump_offload(sch, &opt);
+	if (err)
+		goto nla_put_failure;
+
 	opts = nla_nest_start(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
@@ -273,6 +337,7 @@ nla_put_failure:
 static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 	struct tc_red_xstats st = {
 		.early	= q->stats.prob_drop + q->stats.forced_drop,
 		.pdrop	= q->stats.pdrop,
@@ -280,6 +345,26 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 		.marked	= q->stats.prob_mark + q->stats.forced_mark,
 	};
 
+	if (tc_can_offload(dev) &&  dev->netdev_ops->ndo_setup_tc) {
+		struct red_stats hw_stats = {0};
+		struct tc_red_qopt_offload hw_stats_request = {
+			.command = TC_RED_XSTATS,
+			.handle = sch->handle,
+			.parent = sch->parent,
+			{
+				.xstats = &hw_stats,
+			},
+		};
+		if (!dev->netdev_ops->ndo_setup_tc(dev,
+						   TC_SETUP_QDISC_RED,
+						   &hw_stats_request)) {
+			st.early += hw_stats.prob_drop + hw_stats.forced_drop;
+			st.pdrop += hw_stats.pdrop;
+			st.other += hw_stats.other;
+			st.marked += hw_stats.prob_mark + hw_stats.forced_mark;
+		}
+	}
+
 	return gnet_stats_copy_app(d, &st, sizeof(st));
 }