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, 36 insertions, 160 deletions

diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 8899b51aad44..ee9ab10a32e4 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -48,24 +48,25 @@ static const unsigned int gre_timeouts[GRE_CT_MAX] = {
 	[GRE_CT_REPLIED]	= 180*HZ,
 };
 
-static unsigned int proto_gre_net_id __read_mostly;
+/* used when expectation is added */
+static DEFINE_SPINLOCK(keymap_lock);
 
-static inline struct netns_proto_gre *gre_pernet(struct net *net)
+static inline struct nf_gre_net *gre_pernet(struct net *net)
 {
-	return net_generic(net, proto_gre_net_id);
+	return &net->ct.nf_ct_proto.gre;
 }
 
-static void nf_ct_gre_keymap_flush(struct net *net)
+void nf_ct_gre_keymap_flush(struct net *net)
 {
-	struct netns_proto_gre *net_gre = gre_pernet(net);
+	struct nf_gre_net *net_gre = gre_pernet(net);
 	struct nf_ct_gre_keymap *km, *tmp;
 
-	write_lock_bh(&net_gre->keymap_lock);
+	spin_lock_bh(&keymap_lock);
 	list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) {
-		list_del(&km->list);
-		kfree(km);
+		list_del_rcu(&km->list);
+		kfree_rcu(km, rcu);
 	}
-	write_unlock_bh(&net_gre->keymap_lock);
+	spin_unlock_bh(&keymap_lock);
 }
 
 static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
@@ -81,18 +82,16 @@ static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
 /* look up the source key for a given tuple */
 static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t)
 {
-	struct netns_proto_gre *net_gre = gre_pernet(net);
+	struct nf_gre_net *net_gre = gre_pernet(net);
 	struct nf_ct_gre_keymap *km;
 	__be16 key = 0;
 
-	read_lock_bh(&net_gre->keymap_lock);
-	list_for_each_entry(km, &net_gre->keymap_list, list) {
+	list_for_each_entry_rcu(km, &net_gre->keymap_list, list) {
 		if (gre_key_cmpfn(km, t)) {
 			key = km->tuple.src.u.gre.key;
 			break;
 		}
 	}
-	read_unlock_bh(&net_gre->keymap_lock);
 
 	pr_debug("lookup src key 0x%x for ", key);
 	nf_ct_dump_tuple(t);
@@ -105,21 +104,17 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 			 struct nf_conntrack_tuple *t)
 {
 	struct net *net = nf_ct_net(ct);
-	struct netns_proto_gre *net_gre = gre_pernet(net);
+	struct nf_gre_net *net_gre = gre_pernet(net);
 	struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
 	struct nf_ct_gre_keymap **kmp, *km;
 
 	kmp = &ct_pptp_info->keymap[dir];
 	if (*kmp) {
 		/* check whether it's a retransmission */
-		read_lock_bh(&net_gre->keymap_lock);
-		list_for_each_entry(km, &net_gre->keymap_list, list) {
-			if (gre_key_cmpfn(km, t) && km == *kmp) {
-				read_unlock_bh(&net_gre->keymap_lock);
+		list_for_each_entry_rcu(km, &net_gre->keymap_list, list) {
+			if (gre_key_cmpfn(km, t) && km == *kmp)
 				return 0;
-			}
 		}
-		read_unlock_bh(&net_gre->keymap_lock);
 		pr_debug("trying to override keymap_%s for ct %p\n",
 			 dir == IP_CT_DIR_REPLY ? "reply" : "orig", ct);
 		return -EEXIST;
@@ -134,9 +129,9 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 	pr_debug("adding new entry %p: ", km);
 	nf_ct_dump_tuple(&km->tuple);
 
-	write_lock_bh(&net_gre->keymap_lock);
+	spin_lock_bh(&keymap_lock);
 	list_add_tail(&km->list, &net_gre->keymap_list);
-	write_unlock_bh(&net_gre->keymap_lock);
+	spin_unlock_bh(&keymap_lock);
 
 	return 0;
 }
@@ -145,32 +140,30 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_add);
 /* destroy the keymap entries associated with specified master ct */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct)
 {
-	struct net *net = nf_ct_net(ct);
-	struct netns_proto_gre *net_gre = gre_pernet(net);
 	struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
 	enum ip_conntrack_dir dir;
 
 	pr_debug("entering for ct %p\n", ct);
 
-	write_lock_bh(&net_gre->keymap_lock);
+	spin_lock_bh(&keymap_lock);
 	for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) {
 		if (ct_pptp_info->keymap[dir]) {
 			pr_debug("removing %p from list\n",
 				 ct_pptp_info->keymap[dir]);
-			list_del(&ct_pptp_info->keymap[dir]->list);
-			kfree(ct_pptp_info->keymap[dir]);
+			list_del_rcu(&ct_pptp_info->keymap[dir]->list);
+			kfree_rcu(ct_pptp_info->keymap[dir], rcu);
 			ct_pptp_info->keymap[dir] = NULL;
 		}
 	}
-	write_unlock_bh(&net_gre->keymap_lock);
+	spin_unlock_bh(&keymap_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy);
 
 /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */
 
 /* gre hdr info to tuple */
-static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			     struct net *net, struct nf_conntrack_tuple *tuple)
+bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
+		      struct net *net, struct nf_conntrack_tuple *tuple)
 {
 	const struct pptp_gre_header *pgrehdr;
 	struct pptp_gre_header _pgrehdr;
@@ -216,15 +209,15 @@ static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 
 static unsigned int *gre_get_timeouts(struct net *net)
 {
-	return gre_pernet(net)->gre_timeouts;
+	return gre_pernet(net)->timeouts;
 }
 
 /* Returns verdict for packet, and may modify conntrack */
-static int gre_packet(struct nf_conn *ct,
-		      struct sk_buff *skb,
-		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      const struct nf_hook_state *state)
+int nf_conntrack_gre_packet(struct nf_conn *ct,
+			    struct sk_buff *skb,
+			    unsigned int dataoff,
+			    enum ip_conntrack_info ctinfo,
+			    const struct nf_hook_state *state)
 {
 	if (state->pf != NFPROTO_IPV4)
 		return -NF_ACCEPT;
@@ -256,19 +249,6 @@ static int gre_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 }
 
-/* Called when a conntrack entry has already been removed from the hashes
- * and is about to be deleted from memory */
-static void gre_destroy(struct nf_conn *ct)
-{
-	struct nf_conn *master = ct->master;
-	pr_debug(" entering\n");
-
-	if (!master)
-		pr_debug("no master !?!\n");
-	else
-		nf_ct_gre_keymap_destroy(master);
-}
-
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 
 #include <linux/netfilter/nfnetlink.h>
@@ -278,13 +258,13 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[],
 				     struct net *net, void *data)
 {
 	unsigned int *timeouts = data;
-	struct netns_proto_gre *net_gre = gre_pernet(net);
+	struct nf_gre_net *net_gre = gre_pernet(net);
 
 	if (!timeouts)
 		timeouts = gre_get_timeouts(net);
 	/* set default timeouts for GRE. */
-	timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED];
-	timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED];
+	timeouts[GRE_CT_UNREPLIED] = net_gre->timeouts[GRE_CT_UNREPLIED];
+	timeouts[GRE_CT_REPLIED] = net_gre->timeouts[GRE_CT_REPLIED];
 
 	if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) {
 		timeouts[GRE_CT_UNREPLIED] =
@@ -320,69 +300,22 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = {
 };
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table gre_sysctl_table[] = {
-	{
-		.procname       = "nf_conntrack_gre_timeout",
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec_jiffies,
-	},
-	{
-		.procname       = "nf_conntrack_gre_timeout_stream",
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec_jiffies,
-	},
-	{}
-};
-#endif
-
-static int gre_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *nf,
-				    struct netns_proto_gre *net_gre)
-{
-#ifdef CONFIG_SYSCTL
-	int i;
-
-	if (nf->ctl_table)
-		return 0;
-
-	nf->ctl_table = kmemdup(gre_sysctl_table,
-				sizeof(gre_sysctl_table),
-				GFP_KERNEL);
-	if (!nf->ctl_table)
-		return -ENOMEM;
-
-	for (i = 0; i < GRE_CT_MAX; i++)
-		nf->ctl_table[i].data = &net_gre->gre_timeouts[i];
-#endif
-	return 0;
-}
-
-static int gre_init_net(struct net *net)
+void nf_conntrack_gre_init_net(struct net *net)
 {
-	struct netns_proto_gre *net_gre = gre_pernet(net);
-	struct nf_proto_net *nf = &net_gre->nf;
+	struct nf_gre_net *net_gre = gre_pernet(net);
 	int i;
 
-	rwlock_init(&net_gre->keymap_lock);
 	INIT_LIST_HEAD(&net_gre->keymap_list);
 	for (i = 0; i < GRE_CT_MAX; i++)
-		net_gre->gre_timeouts[i] = gre_timeouts[i];
-
-	return gre_kmemdup_sysctl_table(net, nf, net_gre);
+		net_gre->timeouts[i] = gre_timeouts[i];
 }
 
 /* protocol helper struct */
-static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = {
 	.l4proto	 = IPPROTO_GRE,
-	.pkt_to_tuple	 = gre_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif
-	.packet		 = gre_packet,
-	.destroy	 = gre_destroy,
-	.me 		 = THIS_MODULE,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
 	.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
@@ -398,61 +331,4 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
 		.nla_policy	= gre_timeout_nla_policy,
 	},
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
-	.net_id		= &proto_gre_net_id,
-	.init_net	= gre_init_net,
 };
-
-static int proto_gre_net_init(struct net *net)
-{
-	int ret = 0;
-
-	ret = nf_ct_l4proto_pernet_register_one(net,
-						&nf_conntrack_l4proto_gre4);
-	if (ret < 0)
-		pr_err("nf_conntrack_gre4: pernet registration failed.\n");
-	return ret;
-}
-
-static void proto_gre_net_exit(struct net *net)
-{
-	nf_ct_l4proto_pernet_unregister_one(net, &nf_conntrack_l4proto_gre4);
-	nf_ct_gre_keymap_flush(net);
-}
-
-static struct pernet_operations proto_gre_net_ops = {
-	.init = proto_gre_net_init,
-	.exit = proto_gre_net_exit,
-	.id   = &proto_gre_net_id,
-	.size = sizeof(struct netns_proto_gre),
-};
-
-static int __init nf_ct_proto_gre_init(void)
-{
-	int ret;
-
-	BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0);
-
-	ret = register_pernet_subsys(&proto_gre_net_ops);
-	if (ret < 0)
-		goto out_pernet;
-	ret = nf_ct_l4proto_register_one(&nf_conntrack_l4proto_gre4);
-	if (ret < 0)
-		goto out_gre4;
-
-	return 0;
-out_gre4:
-	unregister_pernet_subsys(&proto_gre_net_ops);
-out_pernet:
-	return ret;
-}
-
-static void __exit nf_ct_proto_gre_fini(void)
-{
-	nf_ct_l4proto_unregister_one(&nf_conntrack_l4proto_gre4);
-	unregister_pernet_subsys(&proto_gre_net_ops);
-}
-
-module_init(nf_ct_proto_gre_init);
-module_exit(nf_ct_proto_gre_fini);
-
-MODULE_LICENSE("GPL");