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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 87 insertions, 44 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 083f3f0bf37f..3d9bcc957f7d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -468,14 +468,19 @@ static u32 eth_vni_hash(const unsigned char *addr, __be32 vni)
 	return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1);
 }
 
+static u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni)
+{
+	if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)
+		return eth_vni_hash(mac, vni);
+	else
+		return eth_hash(mac);
+}
+
 /* Hash chain to use given mac address */
 static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
 						const u8 *mac, __be32 vni)
 {
-	if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)
-		return &vxlan->fdb_head[eth_vni_hash(mac, vni)];
-	else
-		return &vxlan->fdb_head[eth_hash(mac)];
+	return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)];
 }
 
 /* Look up Ethernet address in forwarding table */
@@ -590,8 +595,8 @@ int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
 		return -EINVAL;
 	vxlan = netdev_priv(dev);
 
-	spin_lock_bh(&vxlan->hash_lock);
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		spin_lock_bh(&vxlan->hash_lock[h]);
 		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) {
 			if (f->vni == vni) {
 				list_for_each_entry(rdst, &f->remotes, list) {
@@ -599,14 +604,16 @@ int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
 								  f, rdst,
 								  extack);
 					if (rc)
-						goto out;
+						goto unlock;
 				}
 			}
 		}
+		spin_unlock_bh(&vxlan->hash_lock[h]);
 	}
+	return 0;
 
-out:
-	spin_unlock_bh(&vxlan->hash_lock);
+unlock:
+	spin_unlock_bh(&vxlan->hash_lock[h]);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_replay);
@@ -622,14 +629,15 @@ void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni)
 		return;
 	vxlan = netdev_priv(dev);
 
-	spin_lock_bh(&vxlan->hash_lock);
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		spin_lock_bh(&vxlan->hash_lock[h]);
 		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist)
 			if (f->vni == vni)
 				list_for_each_entry(rdst, &f->remotes, list)
 					rdst->offloaded = false;
+		spin_unlock_bh(&vxlan->hash_lock[h]);
 	}
-	spin_unlock_bh(&vxlan->hash_lock);
+
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload);
 
@@ -804,6 +812,14 @@ static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
 	return f;
 }
 
+static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
+			     __be32 src_vni, struct vxlan_fdb *f)
+{
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __be16 port, __be32 src_vni,
@@ -829,18 +845,13 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		return rc;
 	}
 
-	++vxlan->addrcnt;
-	hlist_add_head_rcu(&f->hlist,
-			   vxlan_fdb_head(vxlan, mac, src_vni));
-
 	*fdb = f;
 
 	return 0;
 }
 
-static void vxlan_fdb_free(struct rcu_head *head)
+static void __vxlan_fdb_free(struct vxlan_fdb *f)
 {
-	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
 	struct vxlan_rdst *rd, *nd;
 
 	list_for_each_entry_safe(rd, nd, &f->remotes, list) {
@@ -850,6 +861,13 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
+static void vxlan_fdb_free(struct rcu_head *head)
+{
+	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+
+	__vxlan_fdb_free(f);
+}
+
 static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 			      bool do_notify, bool swdev_notify)
 {
@@ -977,6 +995,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 	if (rc < 0)
 		return rc;
 
+	vxlan_fdb_insert(vxlan, mac, src_vni, f);
 	rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
 			      swdev_notify, extack);
 	if (rc)
@@ -1105,6 +1124,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	__be16 port;
 	__be32 src_vni, vni;
 	u32 ifindex;
+	u32 hash_index;
 	int err;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
@@ -1123,12 +1143,13 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
 		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&vxlan->hash_lock);
+	hash_index = fdb_head_index(vxlan, addr, src_vni);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex,
 			       ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER,
 			       true, extack);
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
 }
@@ -1176,16 +1197,18 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	__be32 src_vni, vni;
 	__be16 port;
 	u32 ifindex;
+	u32 hash_index;
 	int err;
 
 	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex);
 	if (err)
 		return err;
 
-	spin_lock_bh(&vxlan->hash_lock);
+	hash_index = fdb_head_index(vxlan, addr, src_vni);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex,
 				 true);
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
 }
@@ -1297,8 +1320,10 @@ static bool vxlan_snoop(struct net_device *dev,
 		f->updated = jiffies;
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
+		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);
+
 		/* learned new entry */
-		spin_lock(&vxlan->hash_lock);
+		spin_lock(&vxlan->hash_lock[hash_index]);
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
@@ -1309,7 +1334,7 @@ static bool vxlan_snoop(struct net_device *dev,
 					 vni,
 					 vxlan->default_dst.remote_vni,
 					 ifindex, NTF_SELF, true, NULL);
-		spin_unlock(&vxlan->hash_lock);
+		spin_unlock(&vxlan->hash_lock[hash_index]);
 	}
 
 	return false;
@@ -2219,7 +2244,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device
 	fl4.fl4_sport = sport;
 
 	rt = ip_route_output_key(vxlan->net, &fl4);
-	if (likely(!IS_ERR(rt))) {
+	if (!IS_ERR(rt)) {
 		if (rt->dst.dev == dev) {
 			netdev_dbg(dev, "circular route to %pI4\n", &daddr);
 			ip_rt_put(rt);
@@ -2699,7 +2724,7 @@ static void vxlan_cleanup(struct timer_list *t)
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct hlist_node *p, *n;
 
-		spin_lock(&vxlan->hash_lock);
+		spin_lock(&vxlan->hash_lock[h]);
 		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
 			struct vxlan_fdb *f
 				= container_of(p, struct vxlan_fdb, hlist);
@@ -2721,7 +2746,7 @@ static void vxlan_cleanup(struct timer_list *t)
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
-		spin_unlock(&vxlan->hash_lock);
+		spin_unlock(&vxlan->hash_lock[h]);
 	}
 
 	mod_timer(&vxlan->age_timer, next_timer);
@@ -2764,12 +2789,13 @@ static int vxlan_init(struct net_device *dev)
 static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 {
 	struct vxlan_fdb *f;
+	u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni);
 
-	spin_lock_bh(&vxlan->hash_lock);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
 		vxlan_fdb_destroy(vxlan, f, true, true);
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 }
 
 static void vxlan_uninit(struct net_device *dev)
@@ -2814,9 +2840,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 {
 	unsigned int h;
 
-	spin_lock_bh(&vxlan->hash_lock);
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct hlist_node *p, *n;
+
+		spin_lock_bh(&vxlan->hash_lock[h]);
 		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
 			struct vxlan_fdb *f
 				= container_of(p, struct vxlan_fdb, hlist);
@@ -2826,8 +2853,8 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 			if (!is_zero_ether_addr(f->eth_addr))
 				vxlan_fdb_destroy(vxlan, f, true, true);
 		}
+		spin_unlock_bh(&vxlan->hash_lock[h]);
 	}
-	spin_unlock_bh(&vxlan->hash_lock);
 }
 
 /* Cleanup timer and forwarding table on shutdown */
@@ -3011,7 +3038,6 @@ static void vxlan_setup(struct net_device *dev)
 	dev->max_mtu = ETH_MAX_MTU;
 
 	INIT_LIST_HEAD(&vxlan->next);
-	spin_lock_init(&vxlan->hash_lock);
 
 	timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE);
 
@@ -3019,8 +3045,10 @@ static void vxlan_setup(struct net_device *dev)
 
 	gro_cells_init(&vxlan->gro_cells, dev);
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h)
+	for (h = 0; h < FDB_HASH_SIZE; ++h) {
+		spin_lock_init(&vxlan->hash_lock[h]);
 		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
+	}
 }
 
 static void vxlan_ether_setup(struct net_device *dev)
@@ -3571,12 +3599,17 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	if (err)
 		goto errout;
 
-	/* notify default fdb entry */
 	if (f) {
+		vxlan_fdb_insert(vxlan, all_zeros_mac,
+				 vxlan->default_dst.remote_vni, f);
+
+		/* notify default fdb entry */
 		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
 				       RTM_NEWNEIGH, true, extack);
-		if (err)
-			goto errout;
+		if (err) {
+			vxlan_fdb_destroy(vxlan, f, false, false);
+			goto unregister;
+		}
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
@@ -3588,7 +3621,8 @@ errout:
 	 * destroy the entry by hand here.
 	 */
 	if (f)
-		vxlan_fdb_destroy(vxlan, f, false, false);
+		__vxlan_fdb_free(f);
+unregister:
 	if (unregister)
 		unregister_netdevice(dev);
 	return err;
@@ -3914,7 +3948,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 
 	/* handle default dst entry */
 	if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) {
-		spin_lock_bh(&vxlan->hash_lock);
+		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
+
+		spin_lock_bh(&vxlan->hash_lock[hash_index]);
 		if (!vxlan_addr_any(&conf.remote_ip)) {
 			err = vxlan_fdb_update(vxlan, all_zeros_mac,
 					       &conf.remote_ip,
@@ -3925,7 +3961,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       conf.remote_ifindex,
 					       NTF_SELF, true, extack);
 			if (err) {
-				spin_unlock_bh(&vxlan->hash_lock);
+				spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 				return err;
 			}
 		}
@@ -3937,7 +3973,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   dst->remote_vni,
 					   dst->remote_ifindex,
 					   true);
-		spin_unlock_bh(&vxlan->hash_lock);
+		spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 	}
 
 	if (conf.age_interval != vxlan->cfg.age_interval)
@@ -4192,8 +4228,11 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *rdst;
 	struct vxlan_fdb *f;
+	u32 hash_index;
+
+	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 
-	spin_lock_bh(&vxlan->hash_lock);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
 	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
@@ -4209,7 +4248,7 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 	rdst->offloaded = fdb_info->offloaded;
 
 out:
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 }
 
 static int
@@ -4218,11 +4257,13 @@ vxlan_fdb_external_learn_add(struct net_device *dev,
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct netlink_ext_ack *extack;
+	u32 hash_index;
 	int err;
 
+	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	extack = switchdev_notifier_info_to_extack(&fdb_info->info);
 
-	spin_lock_bh(&vxlan->hash_lock);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 	err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip,
 			       NUD_REACHABLE,
 			       NLM_F_CREATE | NLM_F_REPLACE,
@@ -4232,7 +4273,7 @@ vxlan_fdb_external_learn_add(struct net_device *dev,
 			       fdb_info->remote_ifindex,
 			       NTF_USE | NTF_SELF | NTF_EXT_LEARNED,
 			       false, extack);
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
 }
@@ -4243,9 +4284,11 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb *f;
+	u32 hash_index;
 	int err = 0;
 
-	spin_lock_bh(&vxlan->hash_lock);
+	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
 	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
@@ -4259,7 +4302,7 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 					 fdb_info->remote_ifindex,
 					 false);
 
-	spin_unlock_bh(&vxlan->hash_lock);
+	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
 }