Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 65 insertions, 12 deletions

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e013d33f1c7c..2b48b204205e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -307,16 +307,18 @@ struct net_bridge_port {
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	struct bridge_mcast_own_query	ip4_own_query;
+	struct timer_list		ip4_mc_router_timer;
+	struct hlist_node		ip4_rlist;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct bridge_mcast_own_query	ip6_own_query;
+	struct timer_list		ip6_mc_router_timer;
+	struct hlist_node		ip6_rlist;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 	u32				multicast_eht_hosts_limit;
 	u32				multicast_eht_hosts_cnt;
 	unsigned char			multicast_router;
 	struct bridge_mcast_stats	__percpu *mcast_stats;
-	struct timer_list		multicast_router_timer;
 	struct hlist_head		mglist;
-	struct hlist_node		rlist;
 #endif
 
 #ifdef CONFIG_SYSFS
@@ -449,14 +451,16 @@ struct net_bridge {
 
 	struct hlist_head		mcast_gc_list;
 	struct hlist_head		mdb_list;
-	struct hlist_head		router_list;
 
-	struct timer_list		multicast_router_timer;
+	struct hlist_head		ip4_mc_router_list;
+	struct timer_list		ip4_mc_router_timer;
 	struct bridge_mcast_other_query	ip4_other_query;
 	struct bridge_mcast_own_query	ip4_own_query;
 	struct bridge_mcast_querier	ip4_querier;
 	struct bridge_mcast_stats	__percpu *mcast_stats;
 #if IS_ENABLED(CONFIG_IPV6)
+	struct hlist_head		ip6_mc_router_list;
+	struct timer_list		ip6_mc_router_timer;
 	struct bridge_mcast_other_query	ip6_other_query;
 	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
@@ -864,11 +868,58 @@ static inline bool br_group_is_l2(const struct br_ip *group)
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
 
-static inline bool br_multicast_is_router(struct net_bridge *br)
+static inline struct hlist_node *
+br_multicast_get_first_rport_node(struct net_bridge *b, struct sk_buff *skb) {
+#if IS_ENABLED(CONFIG_IPV6)
+	if (skb->protocol == htons(ETH_P_IPV6))
+		return rcu_dereference(hlist_first_rcu(&b->ip6_mc_router_list));
+#endif
+	return rcu_dereference(hlist_first_rcu(&b->ip4_mc_router_list));
+}
+
+static inline struct net_bridge_port *
+br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) {
+#if IS_ENABLED(CONFIG_IPV6)
+	if (skb->protocol == htons(ETH_P_IPV6))
+		return hlist_entry_safe(rp, struct net_bridge_port, ip6_rlist);
+#endif
+	return hlist_entry_safe(rp, struct net_bridge_port, ip4_rlist);
+}
+
+static inline bool br_ip4_multicast_is_router(struct net_bridge *br)
+{
+	return timer_pending(&br->ip4_mc_router_timer);
+}
+
+static inline bool br_ip6_multicast_is_router(struct net_bridge *br)
 {
-	return br->multicast_router == 2 ||
-	       (br->multicast_router == 1 &&
-		timer_pending(&br->multicast_router_timer));
+#if IS_ENABLED(CONFIG_IPV6)
+	return timer_pending(&br->ip6_mc_router_timer);
+#else
+	return false;
+#endif
+}
+
+static inline bool
+br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb)
+{
+	switch (br->multicast_router) {
+	case MDB_RTR_TYPE_PERM:
+		return true;
+	case MDB_RTR_TYPE_TEMP_QUERY:
+		if (skb) {
+			if (skb->protocol == htons(ETH_P_IP))
+				return br_ip4_multicast_is_router(br);
+			else if (skb->protocol == htons(ETH_P_IPV6))
+				return br_ip6_multicast_is_router(br);
+		} else {
+			return br_ip4_multicast_is_router(br) ||
+			       br_ip6_multicast_is_router(br);
+		}
+		fallthrough;
+	default:
+		return false;
+	}
 }
 
 static inline bool
@@ -1017,7 +1068,8 @@ static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 {
 }
 
-static inline bool br_multicast_is_router(struct net_bridge *br)
+static inline bool br_multicast_is_router(struct net_bridge *br,
+					  struct sk_buff *skb)
 {
 	return false;
 }
@@ -1602,8 +1654,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
 			       unsigned long flags,
 			       unsigned long mask,
 			       struct netlink_ext_ack *extack);
-void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb,
-			     int type);
+void br_switchdev_fdb_notify(struct net_bridge *br,
+			     const struct net_bridge_fdb_entry *fdb, int type);
 int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
 			       struct netlink_ext_ack *extack);
 int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid);
@@ -1650,7 +1702,8 @@ static inline int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
 }
 
 static inline void
-br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
+br_switchdev_fdb_notify(struct net_bridge *br,
+			const struct net_bridge_fdb_entry *fdb, int type)
 {
 }