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

Pull networking fixes from David Miller:

 1) The wireless rate info fix from Johannes Berg.

 2) When a RAW socket is in hdrincl mode, we need to make sure that the
    user provided at least a minimally sized ipv4/ipv6 header. Fix from
    Alexander Potapenko.

 3) We must emit IFLA_PHYS_PORT_NAME netlink attributes using
    nla_put_string() so that it is NULL terminated.

 4) Fix a bug in TCP fastopen handling, wherein child sockets
    erroneously inherit the fastopen_req from the parent, and later can
    end up derefencing freed memory or doing a double free. From Eric
    Dumazet.

 5) Don't clear out netdev stats at close time in tg3 driver, from
    YueHaibing.

 6) Fix refcount leak in xt_CT, from Gao Feng.

 7) In nft_set_bitmap() don't leak dummy elements, from Liping Zhang.

 8) Fix deadlock due to taking the expectation lock twice, also from
    Liping Zhang.

 9) Make xt_socket work again with ipv6, from Peter Tirsek.

10) Don't allow IPV6 to be used with IPVS if ipv6.disable=1, from Paolo
    Abeni.

11) Make the BPF loader more flexible wrt. changes to the bpf MAP entry
    layout. From Jesper Dangaard Brouer.

12) Fix ethtool reported device name in aquantia driver, from Pavel
    Belous.

13) Fix build failures due to the compile time size test not working in
    netfilter conntrack. From Geert Uytterhoeven.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (52 commits)
  cfg80211: make RATE_INFO_BW_20 the default
  ipv6: initialize route null entry in addrconf_init()
  qede: Fix possible misconfiguration of advertised autoneg value.
  qed: Fix overriding of supported autoneg value.
  qed*: Fix possible overflow for status block id field.
  rtnetlink: NUL-terminate IFLA_PHYS_PORT_NAME string
  netvsc: make sure napi enabled before vmbus_open
  aquantia: Fix driver name reported by ethtool
  ipv4, ipv6: ensure raw socket message is big enough to hold an IP header
  net/sched: remove redundant null check on head
  tcp: do not inherit fastopen_req from parent
  forcedeth: remove unnecessary carrier status check
  ibmvnic: Move queue restarting in ibmvnic_tx_complete
  ibmvnic: Record SKB RX queue during poll
  ibmvnic: Continue skb processing after skb completion error
  ibmvnic: Check for driver reset first in ibmvnic_xmit
  ibmvnic: Wait for any pending scrqs entries at driver close
  ibmvnic: Clean up tx pools when closing
  ibmvnic: Whitespace correction in release_rx_pools
  ibmvnic: Delete napi's when releasing driver resources
  ...

10 files changed, 113 insertions, 58 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 668d9643f0cc..1fa3c2307b6e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3078,6 +3078,17 @@ nla_put_failure:
 	return skb->len;
 }
 
+static bool ip_vs_is_af_valid(int af)
+{
+	if (af == AF_INET)
+		return true;
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6 && ipv6_mod_enabled())
+		return true;
+#endif
+	return false;
+}
+
 static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
 				    struct ip_vs_service_user_kern *usvc,
 				    struct nlattr *nla, int full_entry,
@@ -3105,11 +3116,7 @@ static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
 	memset(usvc, 0, sizeof(*usvc));
 
 	usvc->af = nla_get_u16(nla_af);
-#ifdef CONFIG_IP_VS_IPV6
-	if (usvc->af != AF_INET && usvc->af != AF_INET6)
-#else
-	if (usvc->af != AF_INET)
-#endif
+	if (!ip_vs_is_af_valid(usvc->af))
 		return -EAFNOSUPPORT;
 
 	if (nla_fwmark) {
@@ -3612,6 +3619,11 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		if (udest.af == 0)
 			udest.af = svc->af;
 
+		if (!ip_vs_is_af_valid(udest.af)) {
+			ret = -EAFNOSUPPORT;
+			goto out;
+		}
+
 		if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) {
 			/* The synchronization protocol is incompatible
 			 * with mixed family services
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f9245dbfe435..3c8f1ed2f555 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1853,7 +1853,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
 		  &nf_conntrack_htable_size, 0600);
 
-static unsigned int total_extension_size(void)
+static __always_inline unsigned int total_extension_size(void)
 {
 	/* remember to add new extensions below */
 	BUILD_BUG_ON(NF_CT_EXT_NUM > 9);
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 4b9dfe3eef62..3a60efa7799b 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -385,7 +385,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 	struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
 	unsigned int h = helper_hash(&me->tuple);
 	struct nf_conntrack_helper *cur;
-	int ret = 0;
+	int ret = 0, i;
 
 	BUG_ON(me->expect_policy == NULL);
 	BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
@@ -395,10 +395,26 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 		return -EINVAL;
 
 	mutex_lock(&nf_ct_helper_mutex);
-	hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
-		if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
-			ret = -EEXIST;
-			goto out;
+	for (i = 0; i < nf_ct_helper_hsize; i++) {
+		hlist_for_each_entry(cur, &nf_ct_helper_hash[i], hnode) {
+			if (!strcmp(cur->name, me->name) &&
+			    (cur->tuple.src.l3num == NFPROTO_UNSPEC ||
+			     cur->tuple.src.l3num == me->tuple.src.l3num) &&
+			    cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+				ret = -EEXIST;
+				goto out;
+			}
+		}
+	}
+
+	/* avoid unpredictable behaviour for auto_assign_helper */
+	if (!(me->flags & NF_CT_HELPER_F_USERSPACE)) {
+		hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
+			if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple,
+						     &mask)) {
+				ret = -EEXIST;
+				goto out;
+			}
 		}
 	}
 	hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 5f6f2f388928..dcf561b5c97a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -417,8 +417,7 @@ nla_put_failure:
 	return -1;
 }
 
-static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb,
-				     const struct nf_conn *ct)
+static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct)
 {
 	struct nf_conn_seqadj *seqadj = nfct_seqadj(ct);
 	struct nf_ct_seqadj *seq;
@@ -426,15 +425,20 @@ static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb,
 	if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj)
 		return 0;
 
+	spin_lock_bh(&ct->lock);
 	seq = &seqadj->seq[IP_CT_DIR_ORIGINAL];
 	if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1)
-		return -1;
+		goto err;
 
 	seq = &seqadj->seq[IP_CT_DIR_REPLY];
 	if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1)
-		return -1;
+		goto err;
 
+	spin_unlock_bh(&ct->lock);
 	return 0;
+err:
+	spin_unlock_bh(&ct->lock);
+	return -1;
 }
 
 static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
@@ -1417,6 +1421,24 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 }
 #endif
 
+static void
+__ctnetlink_change_status(struct nf_conn *ct, unsigned long on,
+			  unsigned long off)
+{
+	unsigned int bit;
+
+	/* Ignore these unchangable bits */
+	on &= ~IPS_UNCHANGEABLE_MASK;
+	off &= ~IPS_UNCHANGEABLE_MASK;
+
+	for (bit = 0; bit < __IPS_MAX_BIT; bit++) {
+		if (on & (1 << bit))
+			set_bit(bit, &ct->status);
+		else if (off & (1 << bit))
+			clear_bit(bit, &ct->status);
+	}
+}
+
 static int
 ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
 {
@@ -1436,10 +1458,7 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
 		/* ASSURED bit can only be set */
 		return -EBUSY;
 
-	/* Be careful here, modifying NAT bits can screw up things,
-	 * so don't let users modify them directly if they don't pass
-	 * nf_nat_range. */
-	ct->status |= status & ~(IPS_NAT_DONE_MASK | IPS_NAT_MASK);
+	__ctnetlink_change_status(ct, status, 0);
 	return 0;
 }
 
@@ -1508,23 +1527,11 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
 		return 0;
 	}
 
+	rcu_read_lock();
 	helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
 					    nf_ct_protonum(ct));
 	if (helper == NULL) {
-#ifdef CONFIG_MODULES
-		spin_unlock_bh(&nf_conntrack_expect_lock);
-
-		if (request_module("nfct-helper-%s", helpname) < 0) {
-			spin_lock_bh(&nf_conntrack_expect_lock);
-			return -EOPNOTSUPP;
-		}
-
-		spin_lock_bh(&nf_conntrack_expect_lock);
-		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
-						    nf_ct_protonum(ct));
-		if (helper)
-			return -EAGAIN;
-#endif
+		rcu_read_unlock();
 		return -EOPNOTSUPP;
 	}
 
@@ -1533,13 +1540,16 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
 			/* update private helper data if allowed. */
 			if (helper->from_nlattr)
 				helper->from_nlattr(helpinfo, ct);
-			return 0;
+			err = 0;
 		} else
-			return -EBUSY;
+			err = -EBUSY;
+	} else {
+		/* we cannot set a helper for an existing conntrack */
+		err = -EOPNOTSUPP;
 	}
 
-	/* we cannot set a helper for an existing conntrack */
-	return -EOPNOTSUPP;
+	rcu_read_unlock();
+	return err;
 }
 
 static int ctnetlink_change_timeout(struct nf_conn *ct,
@@ -1630,25 +1640,30 @@ ctnetlink_change_seq_adj(struct nf_conn *ct,
 	if (!seqadj)
 		return 0;
 
+	spin_lock_bh(&ct->lock);
 	if (cda[CTA_SEQ_ADJ_ORIG]) {
 		ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL],
 				     cda[CTA_SEQ_ADJ_ORIG]);
 		if (ret < 0)
-			return ret;
+			goto err;
 
-		ct->status |= IPS_SEQ_ADJUST;
+		set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 	}
 
 	if (cda[CTA_SEQ_ADJ_REPLY]) {
 		ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY],
 				     cda[CTA_SEQ_ADJ_REPLY]);
 		if (ret < 0)
-			return ret;
+			goto err;
 
-		ct->status |= IPS_SEQ_ADJUST;
+		set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 	}
 
+	spin_unlock_bh(&ct->lock);
 	return 0;
+err:
+	spin_unlock_bh(&ct->lock);
+	return ret;
 }
 
 static int
@@ -1959,9 +1974,7 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl,
 	err = -EEXIST;
 	ct = nf_ct_tuplehash_to_ctrack(h);
 	if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
-		spin_lock_bh(&nf_conntrack_expect_lock);
 		err = ctnetlink_change_conntrack(ct, cda);
-		spin_unlock_bh(&nf_conntrack_expect_lock);
 		if (err == 0) {
 			nf_conntrack_eventmask_report((1 << IPCT_REPLY) |
 						      (1 << IPCT_ASSURED) |
@@ -2294,10 +2307,10 @@ ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[])
 	/* This check is less strict than ctnetlink_change_status()
 	 * because callers often flip IPS_EXPECTED bits when sending
 	 * an NFQA_CT attribute to the kernel.  So ignore the
-	 * unchangeable bits but do not error out.
+	 * unchangeable bits but do not error out. Also user programs
+	 * are allowed to clear the bits that they are allowed to change.
 	 */
-	ct->status = (status & ~IPS_UNCHANGEABLE_MASK) |
-		     (ct->status & IPS_UNCHANGEABLE_MASK);
+	__ctnetlink_change_status(ct, status, ~status);
 	return 0;
 }
 
@@ -2351,11 +2364,7 @@ ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct)
 	if (ret < 0)
 		return ret;
 
-	spin_lock_bh(&nf_conntrack_expect_lock);
-	ret = ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct);
-	spin_unlock_bh(&nf_conntrack_expect_lock);
-
-	return ret;
+	return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct);
 }
 
 static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1c6482d2c4dc..559225029740 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3778,6 +3778,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	err = set->ops->insert(ctx->net, set, &elem, &ext2);
 	if (err) {
 		if (err == -EEXIST) {
+			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^
+			    nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) ||
+			    nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^
+			    nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF))
+				return -EBUSY;
 			if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
 			     nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
 			     memcmp(nft_set_ext_data(ext),
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 3948da380259..66221ad891a9 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -82,8 +82,7 @@ static void nft_dynset_eval(const struct nft_expr *expr,
 		    nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
 			timeout = priv->timeout ? : set->timeout;
 			*nft_set_ext_expiration(ext) = jiffies + timeout;
-		} else if (sexpr == NULL)
-			goto out;
+		}
 
 		if (sexpr != NULL)
 			sexpr->ops->eval(sexpr, regs, pkt);
@@ -92,7 +91,7 @@ static void nft_dynset_eval(const struct nft_expr *expr,
 			regs->verdict.code = NFT_BREAK;
 		return;
 	}
-out:
+
 	if (!priv->invert)
 		regs->verdict.code = NFT_BREAK;
 }
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 8ebbc2940f4c..b988162b5b15 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -257,6 +257,11 @@ static int nft_bitmap_init(const struct nft_set *set,
 
 static void nft_bitmap_destroy(const struct nft_set *set)
 {
+	struct nft_bitmap *priv = nft_set_priv(set);
+	struct nft_bitmap_elem *be, *n;
+
+	list_for_each_entry_safe(be, n, &priv->list, head)
+		nft_set_elem_destroy(set, be, true);
 }
 
 static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 14857afc9937..f134d384852f 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1051,8 +1051,10 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
 	list_for_each_entry(t, &init_net.xt.tables[af], list) {
 		if (strcmp(t->name, name))
 			continue;
-		if (!try_module_get(t->me))
+		if (!try_module_get(t->me)) {
+			mutex_unlock(&xt[af].mutex);
 			return NULL;
+		}
 
 		mutex_unlock(&xt[af].mutex);
 		if (t->table_init(net) != 0) {
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 3cbe1bcf6a74..bb7ad82dcd56 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -168,8 +168,10 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par,
 		goto err_put_timeout;
 	}
 	timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC);
-	if (timeout_ext == NULL)
+	if (!timeout_ext) {
 		ret = -ENOMEM;
+		goto err_put_timeout;
+	}
 
 	rcu_read_unlock();
 	return ret;
@@ -201,6 +203,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			  struct xt_ct_target_info_v1 *info)
 {
 	struct nf_conntrack_zone zone;
+	struct nf_conn_help *help;
 	struct nf_conn *ct;
 	int ret = -EOPNOTSUPP;
 
@@ -249,7 +252,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	if (info->timeout[0]) {
 		ret = xt_ct_set_timeout(ct, par, info->timeout);
 		if (ret < 0)
-			goto err3;
+			goto err4;
 	}
 	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
 	nf_conntrack_get(&ct->ct_general);
@@ -257,6 +260,10 @@ out:
 	info->ct = ct;
 	return 0;
 
+err4:
+	help = nfct_help(ct);
+	if (help)
+		module_put(help->helper->me);
 err3:
 	nf_ct_tmpl_free(ct);
 err2:
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 770bbec878f1..e75ef39669c5 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -152,7 +152,7 @@ static int socket_mt_enable_defrag(struct net *net, int family)
 	switch (family) {
 	case NFPROTO_IPV4:
 		return nf_defrag_ipv4_enable(net);
-#ifdef XT_SOCKET_HAVE_IPV6
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	case NFPROTO_IPV6:
 		return nf_defrag_ipv6_enable(net);
 #endif