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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

44 files changed, 797 insertions, 289 deletions

diff --git a/include/net/act_api.h b/include/net/act_api.h
index b18c699681ca..71347a90a9d1 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -23,7 +23,6 @@ struct tc_action_ops;
 struct tc_action {
 	const struct tc_action_ops	*ops;
 	__u32				type; /* for backward compat(TCA_OLD_COMPAT) */
-	__u32				order;
 	struct tcf_idrinfo		*idrinfo;
 
 	u32				tcfa_index;
@@ -41,6 +40,7 @@ struct tc_action {
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	__rcu *goto_chain;
+	u32			tcfa_flags;
 };
 #define tcf_index	common.tcfa_index
 #define tcf_refcnt	common.tcfa_refcnt
@@ -94,7 +94,7 @@ struct tc_action_ops {
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
 			int bind, bool rtnl_held, struct tcf_proto *tp,
-			struct netlink_ext_ack *extack);
+			u32 flags, struct netlink_ext_ack *extack);
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int,
 			const struct tc_action_ops *,
@@ -154,7 +154,11 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
 int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   struct tc_action **a, const struct tc_action_ops *ops,
-		   int bind, bool cpustats);
+		   int bind, bool cpustats, u32 flags);
+int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
+			      struct nlattr *est, struct tc_action **a,
+			      const struct tc_action_ops *ops, int bind,
+			      u32 flags);
 void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
 
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
@@ -186,6 +190,43 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
 		    int ref);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
+
+static inline void tcf_action_update_bstats(struct tc_action *a,
+					    struct sk_buff *skb)
+{
+	if (likely(a->cpu_bstats)) {
+		bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+		return;
+	}
+	spin_lock(&a->tcfa_lock);
+	bstats_update(&a->tcfa_bstats, skb);
+	spin_unlock(&a->tcfa_lock);
+}
+
+static inline void tcf_action_inc_drop_qstats(struct tc_action *a)
+{
+	if (likely(a->cpu_qstats)) {
+		qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+		return;
+	}
+	spin_lock(&a->tcfa_lock);
+	qstats_drop_inc(&a->tcfa_qstats);
+	spin_unlock(&a->tcfa_lock);
+}
+
+static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a)
+{
+	if (likely(a->cpu_qstats)) {
+		qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats));
+		return;
+	}
+	spin_lock(&a->tcfa_lock);
+	qstats_overlimit_inc(&a->tcfa_qstats);
+	spin_unlock(&a->tcfa_lock);
+}
+
+void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets,
+			     bool drop, bool hw);
 int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
 
 int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 3f62b347b04a..1bab88184d3c 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -202,11 +202,11 @@ u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr,
 /*
  *	multicast prototypes (mcast.c)
  */
-static inline int ipv6_mc_may_pull(struct sk_buff *skb,
-				   unsigned int len)
+static inline bool ipv6_mc_may_pull(struct sk_buff *skb,
+				    unsigned int len)
 {
 	if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len)
-		return 0;
+		return false;
 
 	return pskb_may_pull(skb, len);
 }
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 80ea0f93d3f7..4206dc6d813f 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -10,7 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
-#include <linux/vm_sockets.h>
+#include <uapi/linux/vm_sockets.h>
 
 #include "vsock_addr.h"
 
@@ -27,6 +27,7 @@ extern spinlock_t vsock_table_lock;
 struct vsock_sock {
 	/* sk must be the first member. */
 	struct sock sk;
+	const struct vsock_transport *transport;
 	struct sockaddr_vm local_addr;
 	struct sockaddr_vm remote_addr;
 	/* Links for the global tables of bound and connected sockets. */
@@ -64,16 +65,18 @@ struct vsock_sock {
 	bool sent_request;
 	bool ignore_connecting_rst;
 
+	/* Protected by lock_sock(sk) */
+	u64 buffer_size;
+	u64 buffer_min_size;
+	u64 buffer_max_size;
+
 	/* Private to transport. */
 	void *trans;
 };
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-struct sock *__vsock_create(struct net *net,
-			    struct socket *sock,
-			    struct sock *parent,
-			    gfp_t priority, unsigned short type, int kern);
+struct sock *vsock_create_connected(struct sock *parent);
 
 /**** TRANSPORT ****/
 
@@ -88,7 +91,17 @@ struct vsock_transport_send_notify_data {
 	u64 data2; /* Transport-defined. */
 };
 
+/* Transport features flags */
+/* Transport provides host->guest communication */
+#define VSOCK_TRANSPORT_F_H2G		0x00000001
+/* Transport provides guest->host communication */
+#define VSOCK_TRANSPORT_F_G2H		0x00000002
+/* Transport provides DGRAM communication */
+#define VSOCK_TRANSPORT_F_DGRAM		0x00000004
+
 struct vsock_transport {
+	struct module *module;
+
 	/* Initialize/tear-down socket. */
 	int (*init)(struct vsock_sock *, struct vsock_sock *);
 	void (*destruct)(struct vsock_sock *);
@@ -139,33 +152,23 @@ struct vsock_transport {
 		struct vsock_transport_send_notify_data *);
 	int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t,
 		struct vsock_transport_send_notify_data *);
+	/* sk_lock held by the caller */
+	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
 
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);
 
-	/* Buffer sizes. */
-	void (*set_buffer_size)(struct vsock_sock *, u64);
-	void (*set_min_buffer_size)(struct vsock_sock *, u64);
-	void (*set_max_buffer_size)(struct vsock_sock *, u64);
-	u64 (*get_buffer_size)(struct vsock_sock *);
-	u64 (*get_min_buffer_size)(struct vsock_sock *);
-	u64 (*get_max_buffer_size)(struct vsock_sock *);
-
 	/* Addressing. */
 	u32 (*get_local_cid)(void);
 };
 
 /**** CORE ****/
 
-int __vsock_core_init(const struct vsock_transport *t, struct module *owner);
-static inline int vsock_core_init(const struct vsock_transport *t)
-{
-	return __vsock_core_init(t, THIS_MODULE);
-}
-void vsock_core_exit(void);
+int vsock_core_register(const struct vsock_transport *t, int features);
+void vsock_core_unregister(const struct vsock_transport *t);
 
 /* The transport may downcast this to access transport-specific functions */
-const struct vsock_transport *vsock_core_get_transport(void);
+const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk);
 
 /**** UTILS ****/
 
@@ -193,6 +196,8 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
 					 struct sockaddr_vm *dst);
 void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
+bool vsock_find_cid(unsigned int cid);
 
 /**** TAP ****/
 
diff --git a/include/net/arp.h b/include/net/arp.h
index c8f580a0e6b1..4950191f6b2b 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -57,8 +57,8 @@ static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key)
 		unsigned long now = jiffies;
 
 		/* avoid dirtying neighbour */
-		if (n->confirmed != now)
-			n->confirmed = now;
+		if (READ_ONCE(n->confirmed) != now)
+			WRITE_ONCE(n->confirmed, now);
 	}
 	rcu_read_unlock_bh();
 }
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 4ab2c49423dc..059524b87c4c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -565,6 +565,7 @@ struct vif_params {
  *	with the get_key() callback, must be in little endian,
  *	length given by @seq_len.
  * @seq_len: length of @seq.
+ * @vlan_id: vlan_id for VLAN group key (if nonzero)
  * @mode: key install mode (RX_TX, NO_TX or SET_TX)
  */
 struct key_params {
@@ -572,6 +573,7 @@ struct key_params {
 	const u8 *seq;
 	int key_len;
 	int seq_len;
+	u16 vlan_id;
 	u32 cipher;
 	enum nl80211_key_mode mode;
 };
@@ -1124,6 +1126,7 @@ struct sta_txpwr {
  *	(bitmask of BIT(%NL80211_STA_FLAG_...))
  * @listen_interval: listen interval or -1 for no change
  * @aid: AID or zero for no change
+ * @vlan_id: VLAN ID for station (if nonzero)
  * @peer_aid: mesh peer AID or zero for no change
  * @plink_action: plink action to take
  * @plink_state: set the peer link state for a station
@@ -1159,6 +1162,7 @@ struct station_parameters {
 	u32 sta_modify_mask;
 	int listen_interval;
 	u16 aid;
+	u16 vlan_id;
 	u16 peer_aid;
 	u8 supported_rates_len;
 	u8 plink_action;
@@ -2602,6 +2606,13 @@ enum wiphy_params_flags {
 
 #define IEEE80211_DEFAULT_AIRTIME_WEIGHT	256
 
+/* The per TXQ device queue limit in airtime */
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L	5000
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H	12000
+
+/* The per interface airtime threshold to switch to lower queue limit */
+#define IEEE80211_AQL_THRESHOLD			24000
+
 /**
  * struct cfg80211_pmksa - PMK Security Association
  *
@@ -6593,7 +6604,7 @@ struct cfg80211_roam_info {
  * time it is accessed in __cfg80211_roamed() due to delay in scheduling
  * rdev->event_work. In case of any failures, the reference is released
  * either in cfg80211_roamed() or in __cfg80211_romed(), Otherwise, it will be
- * released while diconneting from the current bss.
+ * released while disconnecting from the current bss.
  */
 void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
 		     gfp_t gfp);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 2116c88663a1..47f87b2fcf63 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -39,7 +39,8 @@ struct devlink {
 	possible_net_t _net;
 	struct mutex lock;
 	u8 reload_failed:1,
-	   reload_enabled:1;
+	   reload_enabled:1,
+	   registered:1;
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -401,6 +402,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
 	DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
 	DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
+	DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -435,6 +437,9 @@ enum devlink_param_generic_id {
 	"reset_dev_on_drv_probe"
 #define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE DEVLINK_PARAM_TYPE_U8
 
+#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce"
+#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
@@ -507,11 +512,13 @@ enum devlink_health_reporter_state {
 struct devlink_health_reporter_ops {
 	char *name;
 	int (*recover)(struct devlink_health_reporter *reporter,
-		       void *priv_ctx);
+		       void *priv_ctx, struct netlink_ext_ack *extack);
 	int (*dump)(struct devlink_health_reporter *reporter,
-		    struct devlink_fmsg *fmsg, void *priv_ctx);
+		    struct devlink_fmsg *fmsg, void *priv_ctx,
+		    struct netlink_ext_ack *extack);
 	int (*diagnose)(struct devlink_health_reporter *reporter,
-			struct devlink_fmsg *fmsg);
+			struct devlink_fmsg *fmsg,
+			struct netlink_ext_ack *extack);
 };
 
 /**
@@ -567,6 +574,21 @@ enum devlink_trap_generic_id {
 	DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE,
 	DEVLINK_TRAP_GENERIC_ID_TTL_ERROR,
 	DEVLINK_TRAP_GENERIC_ID_TAIL_DROP,
+	DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET,
+	DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC,
+	DEVLINK_TRAP_GENERIC_ID_DIP_LB,
+	DEVLINK_TRAP_GENERIC_ID_SIP_MC,
+	DEVLINK_TRAP_GENERIC_ID_SIP_LB,
+	DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR,
+	DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC,
+	DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE,
+	DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE,
+	DEVLINK_TRAP_GENERIC_ID_MTU_ERROR,
+	DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
+	DEVLINK_TRAP_GENERIC_ID_RPF,
+	DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE,
+	DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS,
+	DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS,
 
 	/* Add new generic trap IDs above */
 	__DEVLINK_TRAP_GENERIC_ID_MAX,
@@ -605,6 +627,36 @@ enum devlink_trap_group_generic_id {
 	"ttl_value_is_too_small"
 #define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \
 	"tail_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_NON_IP_PACKET \
+	"non_ip"
+#define DEVLINK_TRAP_GENERIC_NAME_UC_DIP_MC_DMAC \
+	"uc_dip_over_mc_dmac"
+#define DEVLINK_TRAP_GENERIC_NAME_DIP_LB \
+	"dip_is_loopback_address"
+#define DEVLINK_TRAP_GENERIC_NAME_SIP_MC \
+	"sip_is_mc"
+#define DEVLINK_TRAP_GENERIC_NAME_SIP_LB \
+	"sip_is_loopback_address"
+#define DEVLINK_TRAP_GENERIC_NAME_CORRUPTED_IP_HDR \
+	"ip_header_corrupted"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_SIP_BC \
+	"ipv4_sip_is_limited_bc"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_RESERVED_SCOPE \
+	"ipv6_mc_dip_reserved_scope"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE \
+	"ipv6_mc_dip_interface_local_scope"
+#define DEVLINK_TRAP_GENERIC_NAME_MTU_ERROR \
+	"mtu_value_is_too_small"
+#define DEVLINK_TRAP_GENERIC_NAME_UNRESOLVED_NEIGH \
+	"unresolved_neigh"
+#define DEVLINK_TRAP_GENERIC_NAME_RPF \
+	"mc_reverse_path_forwarding"
+#define DEVLINK_TRAP_GENERIC_NAME_REJECT_ROUTE \
+	"reject_route"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_LPM_UNICAST_MISS \
+	"ipv4_lpm_miss"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_LPM_UNICAST_MISS \
+	"ipv6_lpm_miss"
 
 #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
 	"l2_drops"
@@ -644,7 +696,7 @@ enum devlink_trap_group_generic_id {
 	}
 
 struct devlink_ops {
-	int (*reload_down)(struct devlink *devlink,
+	int (*reload_down)(struct devlink *devlink, bool netns_change,
 			   struct netlink_ext_ack *extack);
 	int (*reload_up)(struct devlink *devlink,
 			 struct netlink_ext_ack *extack);
@@ -772,6 +824,8 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev)
 
 struct ib_device;
 
+struct net *devlink_net(const struct devlink *devlink);
+void devlink_net_set(struct devlink *devlink, struct net *net);
 struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
 int devlink_register(struct devlink *devlink, struct device *dev);
 void devlink_unregister(struct devlink *devlink);
@@ -917,8 +971,6 @@ int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value);
 int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value);
 int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value);
 int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value);
-int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
-			    u16 value_len);
 
 int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name,
 			       bool value);
@@ -931,7 +983,7 @@ int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name,
 int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name,
 				 const char *value);
 int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
-				 const void *value, u16 value_len);
+				 const void *value, u32 value_len);
 
 struct devlink_health_reporter *
 devlink_health_reporter_create(struct devlink *devlink,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 541fb514e31d..6767dc3f66c0 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -42,6 +42,7 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_8021Q_VALUE		12
 #define DSA_TAG_PROTO_SJA1105_VALUE		13
 #define DSA_TAG_PROTO_KSZ8795_VALUE		14
+#define DSA_TAG_PROTO_OCELOT_VALUE		15
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
@@ -59,6 +60,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_8021Q		= DSA_TAG_PROTO_8021Q_VALUE,
 	DSA_TAG_PROTO_SJA1105		= DSA_TAG_PROTO_SJA1105_VALUE,
 	DSA_TAG_PROTO_KSZ8795		= DSA_TAG_PROTO_KSZ8795_VALUE,
+	DSA_TAG_PROTO_OCELOT		= DSA_TAG_PROTO_OCELOT_VALUE,
 };
 
 struct packet_type;
@@ -94,8 +96,6 @@ struct __dsa_skb_cb {
 	u8 priv[48 - sizeof(struct dsa_skb_cb)];
 };
 
-#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb))
-
 #define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb))
 
 #define DSA_SKB_CB_PRIV(skb)			\
@@ -122,15 +122,11 @@ struct dsa_switch_tree {
 	 */
 	struct dsa_platform_data	*pd;
 
-	/*
-	 * The switch port to which the CPU is attached.
-	 */
-	struct dsa_port		*cpu_dp;
+	/* List of switch ports */
+	struct list_head ports;
 
-	/*
-	 * Data for the individual switch chips.
-	 */
-	struct dsa_switch	*ds[DSA_MAX_SWITCHES];
+	/* List of DSA links composing the routing table */
+	struct list_head rtable;
 };
 
 /* TC matchall action types, only mirroring for now */
@@ -197,6 +193,8 @@ struct dsa_port {
 	struct work_struct	xmit_work;
 	struct sk_buff_head	xmit_queue;
 
+	struct list_head list;
+
 	/*
 	 * Give the switch driver somewhere to hang its per-port private data
 	 * structures (accessible from the tagger).
@@ -212,9 +210,24 @@ struct dsa_port {
 	 * Original copy of the master netdev net_device_ops
 	 */
 	const struct net_device_ops *orig_ndo_ops;
+
+	bool setup;
+};
+
+/* TODO: ideally DSA ports would have a single dp->link_dp member,
+ * and no dst->rtable nor this struct dsa_link would be needed,
+ * but this would require some more complex tree walking,
+ * so keep it stupid at the moment and list them all.
+ */
+struct dsa_link {
+	struct dsa_port *dp;
+	struct dsa_port *link_dp;
+	struct list_head list;
 };
 
 struct dsa_switch {
+	bool setup;
+
 	struct device *dev;
 
 	/*
@@ -243,13 +256,6 @@ struct dsa_switch {
 	const struct dsa_switch_ops	*ops;
 
 	/*
-	 * An array of which element [a] indicates which port on this
-	 * switch should be used to send packets to that are destined
-	 * for switch a. Can be NULL if there is only one switch chip.
-	 */
-	s8		rtable[DSA_MAX_SWITCHES];
-
-	/*
 	 * Slave mii_bus and devices for the individual ports.
 	 */
 	u32			phys_mii_mask;
@@ -275,14 +281,19 @@ struct dsa_switch {
 	 */
 	bool			vlan_filtering;
 
-	/* Dynamically allocated ports, keep last */
 	size_t num_ports;
-	struct dsa_port ports[];
 };
 
-static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
+static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
 {
-	return &ds->ports[p];
+	struct dsa_switch_tree *dst = ds->dst;
+	struct dsa_port *dp;
+
+	list_for_each_entry(dp, &dst->ports, list)
+		if (dp->ds == ds && dp->index == p)
+			return dp;
+
+	return NULL;
 }
 
 static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
@@ -317,6 +328,19 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds)
 	return mask;
 }
 
+/* Return the local port used to reach an arbitrary switch device */
+static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device)
+{
+	struct dsa_switch_tree *dst = ds->dst;
+	struct dsa_link *dl;
+
+	list_for_each_entry(dl, &dst->rtable, list)
+		if (dl->dp->ds == ds && dl->link_dp->ds->index == device)
+			return dl->dp->index;
+
+	return ds->num_ports;
+}
+
 /* Return the local port used to reach an arbitrary switch port */
 static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device,
 					    int port)
@@ -324,7 +348,7 @@ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device,
 	if (device == ds->index)
 		return port;
 	else
-		return ds->rtable[device];
+		return dsa_routing_port(ds, device);
 }
 
 /* Return the local port used to reach the dedicated CPU port */
@@ -543,6 +567,45 @@ struct dsa_switch_ops {
 	 */
 	netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port,
 					  struct sk_buff *skb);
+	/* Devlink parameters */
+	int	(*devlink_param_get)(struct dsa_switch *ds, u32 id,
+				     struct devlink_param_gset_ctx *ctx);
+	int	(*devlink_param_set)(struct dsa_switch *ds, u32 id,
+				     struct devlink_param_gset_ctx *ctx);
+};
+
+#define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes)		\
+	DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes,		\
+			     dsa_devlink_param_get, dsa_devlink_param_set, NULL)
+
+int dsa_devlink_param_get(struct devlink *dl, u32 id,
+			  struct devlink_param_gset_ctx *ctx);
+int dsa_devlink_param_set(struct devlink *dl, u32 id,
+			  struct devlink_param_gset_ctx *ctx);
+int dsa_devlink_params_register(struct dsa_switch *ds,
+				const struct devlink_param *params,
+				size_t params_count);
+void dsa_devlink_params_unregister(struct dsa_switch *ds,
+				   const struct devlink_param *params,
+				   size_t params_count);
+int dsa_devlink_resource_register(struct dsa_switch *ds,
+				  const char *resource_name,
+				  u64 resource_size,
+				  u64 resource_id,
+				  u64 parent_resource_id,
+				  const struct devlink_resource_size_params *size_params);
+
+void dsa_devlink_resources_unregister(struct dsa_switch *ds);
+
+void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds,
+					   u64 resource_id,
+					   devlink_resource_occ_get_t *occ_get,
+					   void *occ_get_priv);
+void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
+					     u64 resource_id);
+
+struct dsa_devlink_priv {
+	struct dsa_switch *ds;
 };
 
 struct dsa_switch_driver {
@@ -570,7 +633,6 @@ static inline bool dsa_can_decode(const struct sk_buff *skb,
 	return false;
 }
 
-struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
 void dsa_unregister_switch(struct dsa_switch *ds);
 int dsa_register_switch(struct dsa_switch *ds);
 #ifdef CONFIG_PM_SLEEP
diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h
index c49d7bfb5c30..6d59221ff05a 100644
--- a/include/net/fib_notifier.h
+++ b/include/net/fib_notifier.h
@@ -8,7 +8,6 @@
 struct module;
 
 struct fib_notifier_info {
-	struct net *net;
 	int family;
 	struct netlink_ext_ack  *extack;
 };
@@ -30,19 +29,21 @@ struct fib_notifier_ops {
 	int family;
 	struct list_head list;
 	unsigned int (*fib_seq_read)(struct net *net);
-	int (*fib_dump)(struct net *net, struct notifier_block *nb);
+	int (*fib_dump)(struct net *net, struct notifier_block *nb,
+			struct netlink_ext_ack *extack);
 	struct module *owner;
 	struct rcu_head rcu;
 };
 
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
+int call_fib_notifier(struct notifier_block *nb,
 		      enum fib_event_type event_type,
 		      struct fib_notifier_info *info);
 int call_fib_no