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, 125 insertions, 25 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index becf86a..e2ab136 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -71,6 +71,7 @@ struct Qdisc {
 				      * qdisc_tree_decrease_qlen() should stop.
 				      */
 #define TCQ_F_INVISIBLE		0x80 /* invisible by default in dump */
+#define TCQ_F_NOLOCK		0x100 /* qdisc does not require locking */
 #define TCQ_F_OFFLOADED		0x200 /* qdisc is offloaded to HW */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
@@ -88,14 +89,14 @@ struct Qdisc {
 	/*
 	 * For performance sake on SMP, we put highly modified fields at the end
 	 */
-	struct sk_buff		*gso_skb ____cacheline_aligned_in_smp;
+	struct sk_buff_head	gso_skb ____cacheline_aligned_in_smp;
 	struct qdisc_skb_head	q;
 	struct gnet_stats_basic_packed bstats;
 	seqcount_t		running;
 	struct gnet_stats_queue	qstats;
 	unsigned long		state;
 	struct Qdisc            *next_sched;
-	struct sk_buff		*skb_bad_txq;
+	struct sk_buff_head	skb_bad_txq;
 	int			padded;
 	refcount_t		refcnt;
 
@@ -150,19 +151,23 @@ struct Qdisc_class_ops {
 	/* Child qdisc manipulation */
 	struct netdev_queue *	(*select_queue)(struct Qdisc *, struct tcmsg *);
 	int			(*graft)(struct Qdisc *, unsigned long cl,
-					struct Qdisc *, struct Qdisc **);
+					struct Qdisc *, struct Qdisc **,
+					struct netlink_ext_ack *extack);
 	struct Qdisc *		(*leaf)(struct Qdisc *, unsigned long cl);
 	void			(*qlen_notify)(struct Qdisc *, unsigned long);
 
 	/* Class manipulation routines */
 	unsigned long		(*find)(struct Qdisc *, u32 classid);
 	int			(*change)(struct Qdisc *, u32, u32,
-					struct nlattr **, unsigned long *);
+					struct nlattr **, unsigned long *,
+					struct netlink_ext_ack *);
 	int			(*delete)(struct Qdisc *, unsigned long);
 	void			(*walk)(struct Qdisc *, struct qdisc_walker * arg);
 
 	/* Filter manipulation */
-	struct tcf_block *	(*tcf_block)(struct Qdisc *, unsigned long);
+	struct tcf_block *	(*tcf_block)(struct Qdisc *sch,
+					     unsigned long arg,
+					     struct netlink_ext_ack *extack);
 	unsigned long		(*bind_tcf)(struct Qdisc *, unsigned long,
 					u32 classid);
 	void			(*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -187,15 +192,26 @@ struct Qdisc_ops {
 	struct sk_buff *	(*dequeue)(struct Qdisc *);
 	struct sk_buff *	(*peek)(struct Qdisc *);
 
-	int			(*init)(struct Qdisc *, struct nlattr *arg);
+	int			(*init)(struct Qdisc *sch, struct nlattr *arg,
+					struct netlink_ext_ack *extack);
 	void			(*reset)(struct Qdisc *);
 	void			(*destroy)(struct Qdisc *);
-	int			(*change)(struct Qdisc *, struct nlattr *arg);
-	void			(*attach)(struct Qdisc *);
+	int			(*change)(struct Qdisc *sch,
+					  struct nlattr *arg,
+					  struct netlink_ext_ack *extack);
+	void			(*attach)(struct Qdisc *sch);
+	int			(*change_tx_queue_len)(struct Qdisc *, unsigned int);
 
 	int			(*dump)(struct Qdisc *, struct sk_buff *);
 	int			(*dump_stats)(struct Qdisc *, struct gnet_dump *);
 
+	void			(*ingress_block_set)(struct Qdisc *sch,
+						     u32 block_index);
+	void			(*egress_block_set)(struct Qdisc *sch,
+						    u32 block_index);
+	u32			(*ingress_block_get)(struct Qdisc *sch);
+	u32			(*egress_block_get)(struct Qdisc *sch);
+
 	struct module		*owner;
 };
 
@@ -218,14 +234,18 @@ struct tcf_proto_ops {
 					    const struct tcf_proto *,
 					    struct tcf_result *);
 	int			(*init)(struct tcf_proto*);
-	void			(*destroy)(struct tcf_proto*);
+	void			(*destroy)(struct tcf_proto *tp,
+					   struct netlink_ext_ack *extack);
 
 	void*			(*get)(struct tcf_proto*, u32 handle);
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
-					void **, bool);
-	int			(*delete)(struct tcf_proto*, void *, bool*);
+					void **, bool,
+					struct netlink_ext_ack *);
+	int			(*delete)(struct tcf_proto *tp, void *arg,
+					  bool *last,
+					  struct netlink_ext_ack *);
 	void			(*walk)(struct tcf_proto*, struct tcf_walker *arg);
 	void			(*bind_class)(void *, u32, unsigned long);
 
@@ -247,8 +267,6 @@ struct tcf_proto {
 
 	/* All the rest */
 	u32			prio;
-	u32			classid;
-	struct Qdisc		*q;
 	void			*data;
 	const struct tcf_proto_ops	*ops;
 	struct tcf_chain	*chain;
@@ -267,8 +285,7 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
 
 struct tcf_chain {
 	struct tcf_proto __rcu *filter_chain;
-	tcf_chain_head_change_t *chain_head_change;
-	void *chain_head_change_priv;
+	struct list_head filter_chain_list;
 	struct list_head list;
 	struct tcf_block *block;
 	u32 index; /* chain index */
@@ -277,12 +294,33 @@ struct tcf_chain {
 
 struct tcf_block {
 	struct list_head chain_list;
+	u32 index; /* block index for shared blocks */
+	unsigned int refcnt;
 	struct net *net;
 	struct Qdisc *q;
 	struct list_head cb_list;
-	struct work_struct work;
+	struct list_head owner_list;
+	bool keep_dst;
+	unsigned int offloadcnt; /* Number of oddloaded filters */
+	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
 };
 
+static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
+{
+	if (*flags & TCA_CLS_FLAGS_IN_HW)
+		return;
+	*flags |= TCA_CLS_FLAGS_IN_HW;
+	block->offloadcnt++;
+}
+
+static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags)
+{
+	if (!(*flags & TCA_CLS_FLAGS_IN_HW))
+		return;
+	*flags &= ~TCA_CLS_FLAGS_IN_HW;
+	block->offloadcnt--;
+}
+
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;
@@ -291,11 +329,31 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
+static inline int qdisc_qlen_cpu(const struct Qdisc *q)
+{
+	return this_cpu_ptr(q->cpu_qstats)->qlen;
+}
+
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
 }
 
+static inline int qdisc_qlen_sum(const struct Qdisc *q)
+{
+	__u32 qlen = 0;
+	int i;
+
+	if (q->flags & TCQ_F_NOLOCK) {
+		for_each_possible_cpu(i)
+			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
+	} else {
+		qlen = q->q.qlen;
+	}
+
+	return qlen;
+}
+
 static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
 {
 	return (struct qdisc_skb_cb *)skb->cb;
@@ -432,6 +490,7 @@ void qdisc_class_hash_remove(struct Qdisc_class_hash *,
 void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
 void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
 
+int dev_qdisc_change_tx_queue_len(struct net_device *dev);
 void dev_init_scheduler(struct net_device *dev);
 void dev_shutdown(struct net_device *dev);
 void dev_activate(struct net_device *dev);
@@ -444,10 +503,12 @@ void qdisc_destroy(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
 			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
-			  const struct Qdisc_ops *ops);
+			  const struct Qdisc_ops *ops,
+			  struct netlink_ext_ack *extack);
 void qdisc_free(struct Qdisc *qdisc);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
-				const struct Qdisc_ops *ops, u32 parentid);
+				const struct Qdisc_ops *ops, u32 parentid,
+				struct netlink_ext_ack *extack);
 void __qdisc_calculate_pkt_len(struct sk_buff *skb,
 			       const struct qdisc_size_table *stab);
 int skb_do_redirect(struct sk_buff *);
@@ -633,12 +694,39 @@ static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch,
 	sch->qstats.backlog -= qdisc_pkt_len(skb);
 }
 
+static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch,
+						const struct sk_buff *skb)
+{
+	this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
+}
+
 static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch,
 					    const struct sk_buff *skb)
 {
 	sch->qstats.backlog += qdisc_pkt_len(skb);
 }
 
+static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
+						const struct sk_buff *skb)
+{
+	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
+}
+
+static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
+{
+	this_cpu_inc(sch->cpu_qstats->qlen);
+}
+
+static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
+{
+	this_cpu_dec(sch->cpu_qstats->qlen);
+}
+
+static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
+{
+	this_cpu_inc(sch->cpu_qstats->requeues);
+}
+
 static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count)
 {
 	sch->qstats.drops += count;
@@ -769,26 +857,30 @@ static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
 /* generic pseudo peek method for non-work-conserving qdisc */
 static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch)
 {
+	struct sk_buff *skb = skb_peek(&sch->gso_skb);
+
 	/* we can reuse ->gso_skb because peek isn't called for root qdiscs */
-	if (!sch->gso_skb) {
-		sch->gso_skb = sch->dequeue(sch);
-		if (sch->gso_skb) {
+	if (!skb) {
+		skb = sch->dequeue(sch);
+
+		if (skb) {
+			__skb_queue_head(&sch->gso_skb, skb);
 			/* it's still part of the queue */
-			qdisc_qstats_backlog_inc(sch, sch->gso_skb);
+			qdisc_qstats_backlog_inc(sch, skb);
 			sch->q.qlen++;
 		}
 	}
 
-	return sch->gso_skb;
+	return skb;
 }
 
 /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */
 static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 {
-	struct sk_buff *skb = sch->gso_skb;
+	struct sk_buff *skb = skb_peek(&sch->gso_skb);
 
 	if (skb) {
-		sch->gso_skb = NULL;
+		skb = __skb_dequeue(&sch->gso_skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
@@ -846,6 +938,14 @@ static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
 	qdisc_qstats_drop(sch);
 }
 
+static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch,
+				 struct sk_buff **to_free)
+{
+	__qdisc_drop(skb, to_free);
+	qdisc_qstats_cpu_drop(sch);
+
+	return NET_XMIT_DROP;
+}
 
 static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)