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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 99 insertions, 16 deletions

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 1a662f2bb7bb..26a94e5cd5df 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -54,10 +54,23 @@
 #include <net/tcp_states.h>
 #include <net/tcp.h>
 
+struct fq_skb_cb {
+	u64	        time_to_send;
+};
+
+static inline struct fq_skb_cb *fq_skb_cb(struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct fq_skb_cb));
+	return (struct fq_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
 /*
- * Per flow structure, dynamically allocated
+ * Per flow structure, dynamically allocated.
+ * If packets have monotically increasing time_to_send, they are placed in O(1)
+ * in linear list (head,tail), otherwise are placed in a rbtree (t_root).
  */
 struct fq_flow {
+	struct rb_root	t_root;
 	struct sk_buff	*head;		/* list of skbs for this flow : first skb */
 	union {
 		struct sk_buff *tail;	/* last skb in the list */
@@ -257,6 +270,17 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 		 */
 		sk = (struct sock *)((hash << 1) | 1UL);
 		skb_orphan(skb);
+	} else if (sk->sk_state == TCP_CLOSE) {
+		unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
+		/*
+		 * Sockets in TCP_CLOSE are non connected.
+		 * Typical use case is UDP sockets, they can send packets
+		 * with sendto() to many different destinations.
+		 * We probably could use a generic bit advertising
+		 * non connected sockets, instead of sk_state == TCP_CLOSE,
+		 * if we care enough.
+		 */
+		sk = (struct sock *)((hash << 1) | 1UL);
 	}
 
 	root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)];
@@ -277,7 +301,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 			 * It not, we need to refill credit with
 			 * initial quantum
 			 */
-			if (unlikely(skb->sk &&
+			if (unlikely(skb->sk == sk &&
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
@@ -298,9 +322,11 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 		q->stat_allocation_errors++;
 		return &q->internal;
 	}
+	/* f->t_root is already zeroed after kmem_cache_zalloc() */
+
 	fq_flow_set_detached(f);
 	f->sk = sk;
-	if (skb->sk)
+	if (skb->sk == sk)
 		f->socket_hash = sk->sk_hash;
 	f->credit = q->initial_quantum;
 
@@ -312,14 +338,40 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 	return f;
 }
 
+static struct sk_buff *fq_peek(struct fq_flow *flow)
+{
+	struct sk_buff *skb = skb_rb_first(&flow->t_root);
+	struct sk_buff *head = flow->head;
+
+	if (!skb)
+		return head;
+
+	if (!head)
+		return skb;
+
+	if (fq_skb_cb(skb)->time_to_send < fq_skb_cb(head)->time_to_send)
+		return skb;
+	return head;
+}
+
+static void fq_erase_head(struct Qdisc *sch, struct fq_flow *flow,
+			  struct sk_buff *skb)
+{
+	if (skb == flow->head) {
+		flow->head = skb->next;
+	} else {
+		rb_erase(&skb->rbnode, &flow->t_root);
+		skb->dev = qdisc_dev(sch);
+	}
+}
 
 /* remove one skb from head of flow queue */
 static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow)
 {
-	struct sk_buff *skb = flow->head;
+	struct sk_buff *skb = fq_peek(flow);
 
 	if (skb) {
-		flow->head = skb->next;
+		fq_erase_head(sch, flow, skb);
 		skb_mark_not_on_list(skb);
 		flow->qlen--;
 		qdisc_qstats_backlog_dec(sch, skb);
@@ -330,15 +382,36 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow)
 
 static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb)
 {
-	struct sk_buff *head = flow->head;
+	struct rb_node **p, *parent;
+	struct sk_buff *head, *aux;
 
-	skb->next = NULL;
-	if (!head)
-		flow->head = skb;
-	else
-		flow->tail->next = skb;
+	fq_skb_cb(skb)->time_to_send = skb->tstamp ?: ktime_get_ns();
+
+	head = flow->head;
+	if (!head ||
+	    fq_skb_cb(skb)->time_to_send >= fq_skb_cb(flow->tail)->time_to_send) {
+		if (!head)
+			flow->head = skb;
+		else
+			flow->tail->next = skb;
+		flow->tail = skb;
+		skb->next = NULL;
+		return;
+	}
+
+	p = &flow->t_root.rb_node;
+	parent = NULL;
 
-	flow->tail = skb;
+	while (*p) {
+		parent = *p;
+		aux = rb_to_skb(parent);
+		if (fq_skb_cb(skb)->time_to_send >= fq_skb_cb(aux)->time_to_send)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+	rb_link_node(&skb->rbnode, parent, p);
+	rb_insert_color(&skb->rbnode, &flow->t_root);
 }
 
 static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
@@ -450,9 +523,9 @@ begin:
 		goto begin;
 	}
 
-	skb = f->head;
+	skb = fq_peek(f);
 	if (skb) {
-		u64 time_next_packet = max_t(u64, ktime_to_ns(skb->tstamp),
+		u64 time_next_packet = max_t(u64, fq_skb_cb(skb)->time_to_send,
 					     f->time_next_packet);
 
 		if (now < time_next_packet) {
@@ -533,6 +606,15 @@ out:
 
 static void fq_flow_purge(struct fq_flow *flow)
 {
+	struct rb_node *p = rb_first(&flow->t_root);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, &flow->t_root);
+		rtnl_kfree_skbs(skb, skb);
+	}
 	rtnl_kfree_skbs(flow->head, flow->tail);
 	flow->head = NULL;
 	flow->qlen = 0;
@@ -684,7 +766,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
@@ -823,7 +906,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	u64 ce_threshold = q->ce_threshold;
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;