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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 75 insertions, 22 deletions

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 1b6896896fff..333ec5f298fe 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -24,11 +24,12 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/ipv6_frag.h>
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 #include <net/netfilter/nf_nat.h>
 #endif
 
@@ -73,7 +74,8 @@ struct ovs_conntrack_info {
 	u32 eventmask;              /* Mask of 1 << IPCT_*. */
 	struct md_mark mark;
 	struct md_labels labels;
-#ifdef CONFIG_NF_NAT_NEEDED
+	char timeout[CTNL_TIMEOUT_NAME_MAX];
+#if IS_ENABLED(CONFIG_NF_NAT)
 	struct nf_nat_range2 range;  /* Only present for SRC NAT and DST NAT. */
 #endif
 };
@@ -719,7 +721,7 @@ static bool skb_nfct_cached(struct net *net,
 	return ct_executed;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 /* Modelled after nf_nat_ipv[46]_fn().
  * range is only used for new, uninitialized NAT state.
  * Returns either NF_ACCEPT or NF_DROP.
@@ -901,7 +903,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 
 	return err;
 }
-#else /* !CONFIG_NF_NAT_NEEDED */
+#else /* !CONFIG_NF_NAT */
 static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 		      const struct ovs_conntrack_info *info,
 		      struct sk_buff *skb, struct nf_conn *ct,
@@ -990,6 +992,12 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 							    GFP_ATOMIC);
 			if (err)
 				return err;
+
+			/* helper installed, add seqadj if NAT is required */
+			if (info->nat && !nfct_seqadj(ct)) {
+				if (!nfct_seqadj_ext_add(ct))
+					return -EINVAL;
+			}
 		}
 
 		/* Call the helper only if:
@@ -1299,6 +1307,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
 {
 	struct nf_conntrack_helper *helper;
 	struct nf_conn_help *help;
+	int ret = 0;
 
 	helper = nf_conntrack_helper_try_module_get(name, info->family,
 						    key->ip.proto);
@@ -1313,16 +1322,24 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
 		return -ENOMEM;
 	}
 
+#ifdef CONFIG_NF_NAT_NEEDED
+	if (info->nat) {
+		ret = nf_nat_helper_try_module_get(name, info->family,
+						   key->ip.proto);
+		if (ret) {
+			nf_conntrack_helper_put(helper);
+			OVS_NLERR(log, "Failed to load \"%s\" NAT helper, error: %d",
+				  name, ret);
+			return ret;
+		}
+	}
+#endif
 	rcu_assign_pointer(help->helper, helper);
 	info->helper = helper;
-
-	if (info->nat)
-		request_module("ip_nat_%s", name);
-
-	return 0;
+	return ret;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 static int parse_nat(const struct nlattr *attr,
 		     struct ovs_conntrack_info *info, bool log)
 {
@@ -1459,12 +1476,14 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
 				    .maxlen = sizeof(struct md_labels) },
 	[OVS_CT_ATTR_HELPER]	= { .minlen = 1,
 				    .maxlen = NF_CT_HELPER_NAME_LEN },
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	/* NAT length is checked when parsing the nested attributes. */
 	[OVS_CT_ATTR_NAT]	= { .minlen = 0, .maxlen = INT_MAX },
 #endif
 	[OVS_CT_ATTR_EVENTMASK]	= { .minlen = sizeof(u32),
 				    .maxlen = sizeof(u32) },
+	[OVS_CT_ATTR_TIMEOUT] = { .minlen = 1,
+				  .maxlen = CTNL_TIMEOUT_NAME_MAX },
 };
 
 static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
@@ -1537,7 +1556,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				return -EINVAL;
 			}
 			break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 		case OVS_CT_ATTR_NAT: {
 			int err = parse_nat(a, info, log);
 
@@ -1550,6 +1569,15 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 			info->have_eventmask = true;
 			info->eventmask = nla_get_u32(a);
 			break;
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+		case OVS_CT_ATTR_TIMEOUT:
+			memcpy(info->timeout, nla_data(a), nla_len(a));
+			if (!memchr(info->timeout, '\0', nla_len(a))) {
+				OVS_NLERR(log, "Invalid conntrack helper");
+				return -EINVAL;
+			}
+			break;
+#endif
 
 		default:
 			OVS_NLERR(log, "Unknown conntrack attr (%d)",
@@ -1631,6 +1659,14 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		OVS_NLERR(log, "Failed to allocate conntrack template");
 		return -ENOMEM;
 	}
+
+	if (ct_info.timeout[0]) {
+		if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
+				      ct_info.timeout))
+			pr_info_ratelimited("Failed to associated timeout "
+					    "policy `%s'\n", ct_info.timeout);
+	}
+
 	if (helper) {
 		err = ovs_ct_add_helper(&ct_info, helper, key, log);
 		if (err)
@@ -1650,13 +1686,13 @@ err_free_ct:
 	return err;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 			       struct sk_buff *skb)
 {
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, OVS_CT_ATTR_NAT);
+	start = nla_nest_start_noflag(skb, OVS_CT_ATTR_NAT);
 	if (!start)
 		return false;
 
@@ -1723,7 +1759,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 {
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, OVS_ACTION_ATTR_CT);
+	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CT);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -1751,8 +1787,12 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 	if (ct_info->have_eventmask &&
 	    nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask))
 		return -EMSGSIZE;
+	if (ct_info->timeout[0]) {
+		if (nla_put_string(skb, OVS_CT_ATTR_TIMEOUT, ct_info->timeout))
+			return -EMSGSIZE;
+	}
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
 		return -EMSGSIZE;
 #endif
@@ -1770,10 +1810,18 @@ void ovs_ct_free_action(const struct nlattr *a)
 
 static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
 {
-	if (ct_info->helper)
+	if (ct_info->helper) {
+#ifdef CONFIG_NF_NAT_NEEDED
+		if (ct_info->nat)
+			nf_nat_helper_put(ct_info->helper);
+#endif
 		nf_conntrack_helper_put(ct_info->helper);
-	if (ct_info->ct)
+	}
+	if (ct_info->ct) {
+		if (ct_info->timeout[0])
+			nf_ct_destroy_timeout(ct_info->ct);
 		nf_ct_tmpl_free(ct_info->ct);
+	}
 }
 
 #if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
@@ -2126,7 +2174,11 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	if (IS_ERR(reply))
 		return PTR_ERR(reply);
 
-	nla_reply = nla_nest_start(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT);
+	nla_reply = nla_nest_start_noflag(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT);
+	if (!nla_reply) {
+		err = -EMSGSIZE;
+		goto exit_err;
+	}
 
 	if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) {
 		err = ovs_ct_limit_get_zone_limit(
@@ -2152,20 +2204,20 @@ exit_err:
 
 static struct genl_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_set,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_del,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_get,
 	},
 };
@@ -2179,6 +2231,7 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 	.name = OVS_CT_LIMIT_FAMILY,
 	.version = OVS_CT_LIMIT_VERSION,
 	.maxattr = OVS_CT_LIMIT_ATTR_MAX,
+	.policy = ct_limit_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = ct_limit_genl_ops,