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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 51 insertions, 25 deletions

diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index b85885a9d8a1..0e9d761cdd80 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,8 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 	return 0;
 }
 
-static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
+static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
+		       struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct mqprio_sched *priv = qdisc_priv(sch);
@@ -229,7 +230,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 		qdisc = qdisc_create_dflt(dev_queue,
 					  get_default_qdisc_ops(dev, i),
 					  TC_H_MAKE(TC_H_MAJ(sch->handle),
-						    TC_H_MIN(i + 1)));
+						    TC_H_MIN(i + 1)), extack);
 		if (!qdisc)
 			return -ENOMEM;
 
@@ -319,7 +320,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
 }
 
 static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
-		    struct Qdisc **old)
+			struct Qdisc **old, struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
@@ -388,22 +389,40 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb);
 	struct tc_mqprio_qopt opt = { 0 };
 	struct Qdisc *qdisc;
-	unsigned int i;
+	unsigned int ntx, tc;
 
 	sch->q.qlen = 0;
 	memset(&sch->bstats, 0, sizeof(sch->bstats));
 	memset(&sch->qstats, 0, sizeof(sch->qstats));
 
-	for (i = 0; i < dev->num_tx_queues; i++) {
-		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
+	/* MQ supports lockless qdiscs. However, statistics accounting needs
+	 * to account for all, none, or a mix of locked and unlocked child
+	 * qdiscs. Percpu stats are added to counters in-band and locking
+	 * qdisc totals are added at end.
+	 */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
 		spin_lock_bh(qdisc_lock(qdisc));
-		sch->q.qlen		+= qdisc->q.qlen;
-		sch->bstats.bytes	+= qdisc->bstats.bytes;
-		sch->bstats.packets	+= qdisc->bstats.packets;
-		sch->qstats.backlog	+= qdisc->qstats.backlog;
-		sch->qstats.drops	+= qdisc->qstats.drops;
-		sch->qstats.requeues	+= qdisc->qstats.requeues;
-		sch->qstats.overlimits	+= qdisc->qstats.overlimits;
+
+		if (qdisc_is_percpu_stats(qdisc)) {
+			__u32 qlen = qdisc_qlen_sum(qdisc);
+
+			__gnet_stats_copy_basic(NULL, &sch->bstats,
+						qdisc->cpu_bstats,
+						&qdisc->bstats);
+			__gnet_stats_copy_queue(&sch->qstats,
+						qdisc->cpu_qstats,
+						&qdisc->qstats, qlen);
+		} else {
+			sch->q.qlen		+= qdisc->q.qlen;
+			sch->bstats.bytes	+= qdisc->bstats.bytes;
+			sch->bstats.packets	+= qdisc->bstats.packets;
+			sch->qstats.backlog	+= qdisc->qstats.backlog;
+			sch->qstats.drops	+= qdisc->qstats.drops;
+			sch->qstats.requeues	+= qdisc->qstats.requeues;
+			sch->qstats.overlimits	+= qdisc->qstats.overlimits;
+		}
+
 		spin_unlock_bh(qdisc_lock(qdisc));
 	}
 
@@ -411,9 +430,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
 	opt.hw = priv->hw_offload;
 
-	for (i = 0; i < netdev_get_num_tc(dev); i++) {
-		opt.count[i] = dev->tc_to_txq[i].count;
-		opt.offset[i] = dev->tc_to_txq[i].offset;
+	for (tc = 0; tc < netdev_get_num_tc(dev); tc++) {
+		opt.count[tc] = dev->tc_to_txq[tc].count;
+		opt.offset[tc] = dev->tc_to_txq[tc].offset;
 	}
 
 	if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt))
@@ -495,7 +514,6 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	if (cl >= TC_H_MIN_PRIORITY) {
 		int i;
 		__u32 qlen = 0;
-		struct Qdisc *qdisc;
 		struct gnet_stats_queue qstats = {0};
 		struct gnet_stats_basic_packed bstats = {0};
 		struct net_device *dev = qdisc_dev(sch);
@@ -511,18 +529,26 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
 			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
+			struct Qdisc *qdisc = rtnl_dereference(q->qdisc);
+			struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
+			struct gnet_stats_queue __percpu *cpu_qstats = NULL;
 
-			qdisc = rtnl_dereference(q->qdisc);
 			spin_lock_bh(qdisc_lock(qdisc));
-			qlen		  += qdisc->q.qlen;
-			bstats.bytes      += qdisc->bstats.bytes;
-			bstats.packets    += qdisc->bstats.packets;
-			qstats.backlog    += qdisc->qstats.backlog;
-			qstats.drops      += qdisc->qstats.drops;
-			qstats.requeues   += qdisc->qstats.requeues;
-			qstats.overlimits += qdisc->qstats.overlimits;
+			if (qdisc_is_percpu_stats(qdisc)) {
+				cpu_bstats = qdisc->cpu_bstats;
+				cpu_qstats = qdisc->cpu_qstats;
+			}
+
+			qlen = qdisc_qlen_sum(qdisc);
+			__gnet_stats_copy_basic(NULL, &sch->bstats,
+						cpu_bstats, &qdisc->bstats);
+			__gnet_stats_copy_queue(&sch->qstats,
+						cpu_qstats,
+						&qdisc->qstats,
+						qlen);
 			spin_unlock_bh(qdisc_lock(qdisc));
 		}
+
 		/* Reclaim root sleeping lock before completing stats */
 		if (d->lock)
 			spin_lock_bh(d->lock);