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

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 77 insertions, 25 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 9481f2c142e2..31284c078d06 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -12,6 +12,7 @@
 #include <linux/list.h>
 #include <linux/refcount.h>
 #include <linux/workqueue.h>
+#include <linux/mutex.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -51,7 +52,10 @@ struct qdisc_size_table {
 struct qdisc_skb_head {
 	struct sk_buff	*head;
 	struct sk_buff	*tail;
-	__u32		qlen;
+	union {
+		u32		qlen;
+		atomic_t	atomic_qlen;
+	};
 	spinlock_t	lock;
 };
 
@@ -178,6 +182,7 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
 }
 
 struct Qdisc_class_ops {
+	unsigned int		flags;
 	/* Child qdisc manipulation */
 	struct netdev_queue *	(*select_queue)(struct Qdisc *, struct tcmsg *);
 	int			(*graft)(struct Qdisc *, unsigned long cl,
@@ -209,6 +214,13 @@ struct Qdisc_class_ops {
 					struct gnet_dump *);
 };
 
+/* Qdisc_class_ops flag values */
+
+/* Implements API that doesn't require rtnl lock */
+enum qdisc_class_ops_flags {
+	QDISC_CLASS_OPS_DOIT_UNLOCKED = 1,
+};
+
 struct Qdisc_ops {
 	struct Qdisc_ops	*next;
 	const struct Qdisc_class_ops	*cl_ops;
@@ -272,19 +284,21 @@ struct tcf_proto_ops {
 					    const struct tcf_proto *,
 					    struct tcf_result *);
 	int			(*init)(struct tcf_proto*);
-	void			(*destroy)(struct tcf_proto *tp,
+	void			(*destroy)(struct tcf_proto *tp, bool rtnl_held,
 					   struct netlink_ext_ack *extack);
 
 	void*			(*get)(struct tcf_proto*, u32 handle);
+	void			(*put)(struct tcf_proto *tp, void *f);
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
-					void **, bool,
+					void **, bool, bool,
 					struct netlink_ext_ack *);
 	int			(*delete)(struct tcf_proto *tp, void *arg,
-					  bool *last,
+					  bool *last, bool rtnl_held,
 					  struct netlink_ext_ack *);
-	void			(*walk)(struct tcf_proto*, struct tcf_walker *arg);
+	void			(*walk)(struct tcf_proto *tp,
+					struct tcf_walker *arg, bool rtnl_held);
 	int			(*reoffload)(struct tcf_proto *tp, bool add,
 					     tc_setup_cb_t *cb, void *cb_priv,
 					     struct netlink_ext_ack *extack);
@@ -297,12 +311,18 @@ struct tcf_proto_ops {
 
 	/* rtnetlink specific */
 	int			(*dump)(struct net*, struct tcf_proto*, void *,
-					struct sk_buff *skb, struct tcmsg*);
+					struct sk_buff *skb, struct tcmsg*,
+					bool);
 	int			(*tmplt_dump)(struct sk_buff *skb,
 					      struct net *net,
 					      void *tmplt_priv);
 
 	struct module		*owner;
+	int			flags;
+};
+
+enum tcf_proto_ops_flags {
+	TCF_PROTO_OPS_DOIT_UNLOCKED = 1,
 };
 
 struct tcf_proto {
@@ -321,6 +341,12 @@ struct tcf_proto {
 	void			*data;
 	const struct tcf_proto_ops	*ops;
 	struct tcf_chain	*chain;
+	/* Lock protects tcf_proto shared state and can be used by unlocked
+	 * classifiers to protect their private data.
+	 */
+	spinlock_t		lock;
+	bool			deleting;
+	refcount_t		refcnt;
 	struct rcu_head		rcu;
 };
 
@@ -340,6 +366,8 @@ struct qdisc_skb_cb {
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
 
 struct tcf_chain {
+	/* Protects filter_chain. */
+	struct mutex filter_chain_lock;
 	struct tcf_proto __rcu *filter_chain;
 	struct list_head list;
 	struct tcf_block *block;
@@ -347,11 +375,16 @@ struct tcf_chain {
 	unsigned int refcnt;
 	unsigned int action_refcnt;
 	bool explicitly_created;
+	bool flushing;
 	const struct tcf_proto_ops *tmplt_ops;
 	void *tmplt_priv;
 };
 
 struct tcf_block {
+	/* Lock protects tcf_block and lifetime-management data of chains
+	 * attached to the block (refcnt, action_refcnt, explicitly_created).
+	 */
+	struct mutex lock;
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
 	refcount_t refcnt;
@@ -369,6 +402,34 @@ struct tcf_block {
 	struct rcu_head rcu;
 };
 
+#ifdef CONFIG_PROVE_LOCKING
+static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
+{
+	return lockdep_is_held(&chain->filter_chain_lock);
+}
+
+static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
+{
+	return lockdep_is_held(&tp->lock);
+}
+#else
+static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain)
+{
+	return true;
+}
+
+static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
+{
+	return true;
+}
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+
+#define tcf_chain_dereference(p, chain)					\
+	rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain))
+
+#define tcf_proto_dereference(p, tp)					\
+	rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp))
+
 static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
 {
 	if (*flags & TCA_CLS_FLAGS_IN_HW)
@@ -408,27 +469,19 @@ 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)
+static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
-	__u32 qlen = q->qstats.qlen;
-	int i;
+	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK) {
-		for_each_possible_cpu(i)
-			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
-	} else {
+	if (q->flags & TCQ_F_NOLOCK)
+		qlen += atomic_read(&q->q.atomic_qlen);
+	else
 		qlen += q->q.qlen;
-	}
 
 	return qlen;
 }
@@ -580,8 +633,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_put(struct Qdisc *qdisc);
 void qdisc_put_unlocked(struct Qdisc *qdisc);
-void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
-			       unsigned int len);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len);
 #ifdef CONFIG_NET_SCHED
 int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
 			      void *type_data);
@@ -825,14 +877,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
 	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
 }
 
-static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
 {
-	this_cpu_inc(sch->cpu_qstats->qlen);
+	atomic_inc(&sch->q.atomic_qlen);
 }
 
-static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
 {
-	this_cpu_dec(sch->cpu_qstats->qlen);
+	atomic_dec(&sch->q.atomic_qlen);
 }
 
 static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)