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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 154 insertions, 54 deletions

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 213baf7aaa93..216018c76018 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -20,6 +20,7 @@
 #include <net/route.h>
 #include <net/ip6_fib.h>
 #include <linux/if_vlan.h>
+#include <linux/rhashtable.h>
 
 #define BR_HASH_BITS 8
 #define BR_HASH_SIZE (1 << BR_HASH_BITS)
@@ -28,7 +29,6 @@
 
 #define BR_PORT_BITS	10
 #define BR_MAX_PORTS	(1<<BR_PORT_BITS)
-#define BR_VLAN_BITMAP_LEN	BITS_TO_LONGS(VLAN_N_VID)
 
 #define BR_VERSION	"2.3"
 
@@ -77,17 +77,61 @@ struct bridge_mcast_querier {
 };
 #endif
 
-struct net_port_vlans {
-	u16				port_idx;
-	u16				pvid;
+/**
+ * struct net_bridge_vlan - per-vlan entry
+ *
+ * @vnode: rhashtable member
+ * @vid: VLAN id
+ * @flags: bridge vlan flags
+ * @br: if MASTER flag set, this points to a bridge struct
+ * @port: if MASTER flag unset, this points to a port struct
+ * @refcnt: if MASTER flag set, this is bumped for each port referencing it
+ * @brvlan: if MASTER flag unset, this points to the global per-VLAN context
+ *          for this VLAN entry
+ * @vlist: sorted list of VLAN entries
+ * @rcu: used for entry destruction
+ *
+ * This structure is shared between the global per-VLAN entries contained in
+ * the bridge rhashtable and the local per-port per-VLAN entries contained in
+ * the port's rhashtable. The union entries should be interpreted depending on
+ * the entry flags that are set.
+ */
+struct net_bridge_vlan {
+	struct rhash_head		vnode;
+	u16				vid;
+	u16				flags;
 	union {
-		struct net_bridge_port		*port;
-		struct net_bridge		*br;
-	}				parent;
+		struct net_bridge	*br;
+		struct net_bridge_port	*port;
+	};
+	union {
+		atomic_t		refcnt;
+		struct net_bridge_vlan	*brvlan;
+	};
+	struct list_head		vlist;
+
 	struct rcu_head			rcu;
-	unsigned long			vlan_bitmap[BR_VLAN_BITMAP_LEN];
-	unsigned long			untagged_bitmap[BR_VLAN_BITMAP_LEN];
+};
+
+/**
+ * struct net_bridge_vlan_group
+ *
+ * @vlan_hash: VLAN entry rhashtable
+ * @vlan_list: sorted VLAN entry list
+ * @num_vlans: number of total VLAN entries
+ * @pvid: PVID VLAN id
+ *
+ * IMPORTANT: Be careful when checking if there're VLAN entries using list
+ *            primitives because the bridge can have entries in its list which
+ *            are just for global context but not for filtering, i.e. they have
+ *            the master flag set but not the brentry flag. If you have to check
+ *            if there're "real" entries in the bridge please test @num_vlans
+ */
+struct net_bridge_vlan_group {
+	struct rhashtable		vlan_hash;
+	struct list_head		vlan_list;
 	u16				num_vlans;
+	u16				pvid;
 };
 
 struct net_bridge_fdb_entry
@@ -185,7 +229,7 @@ struct net_bridge_port
 	struct netpoll			*np;
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
-	struct net_port_vlans __rcu	*vlan_info;
+	struct net_bridge_vlan_group	__rcu *vlgrp;
 #endif
 };
 
@@ -293,10 +337,10 @@ struct net_bridge
 	struct kobject			*ifobj;
 	u32				auto_cnt;
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	struct net_bridge_vlan_group	__rcu *vlgrp;
 	u8				vlan_enabled;
 	__be16				vlan_proto;
 	u16				default_pvid;
-	struct net_port_vlans __rcu	*vlan_info;
 #endif
 };
 
@@ -344,6 +388,31 @@ static inline int br_is_root_bridge(const struct net_bridge *br)
 	return !memcmp(&br->bridge_id, &br->designated_root, 8);
 }
 
+/* check if a VLAN entry is global */
+static inline bool br_vlan_is_master(const struct net_bridge_vlan *v)
+{
+	return v->flags & BRIDGE_VLAN_INFO_MASTER;
+}
+
+/* check if a VLAN entry is used by the bridge */
+static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v)
+{
+	return v->flags & BRIDGE_VLAN_INFO_BRENTRY;
+}
+
+/* check if we should use the vlan entry, returns false if it's only context */
+static inline bool br_vlan_should_use(const struct net_bridge_vlan *v)
+{
+	if (br_vlan_is_master(v)) {
+		if (br_vlan_is_brentry(v))
+			return true;
+		else
+			return false;
+	}
+
+	return true;
+}
+
 /* br_device.c */
 void br_dev_setup(struct net_device *dev);
 void br_dev_delete(struct net_device *dev, struct list_head *list);
@@ -413,10 +482,10 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
 
 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
-int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb);
+int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb);
 void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb, struct sk_buff *skb0);
-int br_forward_finish(struct sock *sk, struct sk_buff *skb);
+int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
 void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast);
 void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
 		      struct sk_buff *skb2, bool unicast);
@@ -434,7 +503,7 @@ void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
 void br_manage_promisc(struct net_bridge *br);
 
 /* br_input.c */
-int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);
+int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
 rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
 
 static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
@@ -601,18 +670,19 @@ static inline void br_mdb_uninit(void)
 
 /* br_vlan.c */
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
-bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
-			struct sk_buff *skb, u16 *vid);
-bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
+bool br_allowed_ingress(const struct net_bridge *br,
+			struct net_bridge_vlan_group *vg, struct sk_buff *skb,
+			u16 *vid);
+bool br_allowed_egress(struct net_bridge_vlan_group *vg,
 		       const struct sk_buff *skb);
 bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
-			       const struct net_port_vlans *v,
+			       struct net_bridge_vlan_group *vg,
 			       struct sk_buff *skb);
 int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
-bool br_vlan_find(struct net_bridge *br, u16 vid);
+struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
 void br_recalculate_fwd_mask(struct net_bridge *br);
 int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
@@ -620,22 +690,35 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto);
 int br_vlan_set_proto(struct net_bridge *br, unsigned long val);
 int br_vlan_init(struct net_bridge *br);
 int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
+int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
-bool nbp_vlan_find(struct net_bridge_port *port, u16 vid);
 int nbp_vlan_init(struct net_bridge_port *port);
+int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
+
+static inline struct net_bridge_vlan_group *br_vlan_group(
+					const struct net_bridge *br)
+{
+	return rtnl_dereference(br->vlgrp);
+}
 
-static inline struct net_port_vlans *br_get_vlan_info(
-						const struct net_bridge *br)
+static inline struct net_bridge_vlan_group *nbp_vlan_group(
+					const struct net_bridge_port *p)
 {
-	return rcu_dereference_rtnl(br->vlan_info);
+	return rtnl_dereference(p->vlgrp);
 }
 
-static inline struct net_port_vlans *nbp_get_vlan_info(
-						const struct net_bridge_port *p)
+static inline struct net_bridge_vlan_group *br_vlan_group_rcu(
+					const struct net_bridge *br)
 {
-	return rcu_dereference_rtnl(p->vlan_info);
+	return rcu_dereference(br->vlgrp);
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
+					const struct net_bridge_port *p)
+{
+	return rcu_dereference(p->vlgrp);
 }
 
 /* Since bridge now depends on 8021Q module, but the time bridge sees the
@@ -645,9 +728,9 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 {
 	int err = 0;
 
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		*vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
-	else {
+	} else {
 		*vid = 0;
 		err = -EINVAL;
 	}
@@ -655,13 +738,13 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 	return err;
 }
 
-static inline u16 br_get_pvid(const struct net_port_vlans *v)
+static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg)
 {
-	if (!v)
+	if (!vg)
 		return 0;
 
 	smp_rmb();
-	return v->pvid;
+	return vg->pvid;
 }
 
 static inline int br_vlan_enabled(struct net_bridge *br)
@@ -669,16 +752,15 @@ static inline int br_vlan_enabled(struct net_bridge *br)
 	return br->vlan_enabled;
 }
 #else
-static inline bool br_allowed_ingress(struct net_bridge *br,
-				      struct net_port_vlans *v,
+static inline bool br_allowed_ingress(const struct net_bridge *br,
+				      struct net_bridge_vlan_group *vg,
 				      struct sk_buff *skb,
 				      u16 *vid)
 {
 	return true;
 }
 
-static inline bool br_allowed_egress(struct net_bridge *br,
-				     const struct net_port_vlans *v,
+static inline bool br_allowed_egress(struct net_bridge_vlan_group *vg,
 				     const struct sk_buff *skb)
 {
 	return true;
@@ -691,7 +773,7 @@ static inline bool br_should_learn(struct net_bridge_port *p,
 }
 
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
-					     const struct net_port_vlans *v,
+					     struct net_bridge_vlan_group *vg,
 					     struct sk_buff *skb)
 {
 	return skb;
@@ -711,11 +793,6 @@ static inline void br_vlan_flush(struct net_bridge *br)
 {
 }
 
-static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
-{
-	return false;
-}
-
 static inline void br_recalculate_fwd_mask(struct net_bridge *br)
 {
 }
@@ -739,22 +816,12 @@ static inline void nbp_vlan_flush(struct net_bridge_port *port)
 {
 }
 
-static inline struct net_port_vlans *br_get_vlan_info(
-						const struct net_bridge *br)
-{
-	return NULL;
-}
-static inline struct net_port_vlans *nbp_get_vlan_info(
-						const struct net_bridge_port *p)
+static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg,
+						   u16 vid)
 {
 	return NULL;
 }
 
-static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid)
-{
-	return false;
-}
-
 static inline int nbp_vlan_init(struct net_bridge_port *port)
 {
 	return 0;
@@ -764,7 +831,8 @@ static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag)
 {
 	return 0;
 }
-static inline u16 br_get_pvid(const struct net_port_vlans *v)
+
+static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg)
 {
 	return 0;
 }
@@ -779,6 +847,37 @@ static inline int __br_vlan_filter_toggle(struct net_bridge *br,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p,
+					 u32 filter_mask)
+{
+	return 0;
+}
+
+static inline struct net_bridge_vlan_group *br_vlan_group(
+					const struct net_bridge *br)
+{
+	return NULL;
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group(
+					const struct net_bridge_port *p)
+{
+	return NULL;
+}
+
+static inline struct net_bridge_vlan_group *br_vlan_group_rcu(
+					const struct net_bridge *br)
+{
+	return NULL;
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
+					const struct net_bridge_port *p)
+{
+	return NULL;
+}
+
 #endif
 
 struct nf_br_ops {
@@ -808,6 +907,7 @@ void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
 int br_set_forward_delay(struct net_bridge *br, unsigned long x);
 int br_set_hello_time(struct net_bridge *br, unsigned long x);
 int br_set_max_age(struct net_bridge *br, unsigned long x);
+int br_set_ageing_time(struct net_bridge *br, u32 ageing_time);
 
 
 /* br_stp_if.c */