1 files changed, 122 insertions, 135 deletions

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 81d03acf68d4..7562b215b932 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -58,6 +58,12 @@
 
 MODULE_LICENSE("GPL");
 
+struct ctnetlink_list_dump_ctx {
+	struct nf_conn *last;
+	unsigned int cpu;
+	bool done;
+};
+
 static int ctnetlink_dump_tuples_proto(struct sk_buff *skb,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_l4proto *l4proto)
@@ -508,7 +514,7 @@ nla_put_failure:
 
 static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use))))
+	if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use))))
 		goto nla_put_failure;
 	return 0;
 
@@ -1195,12 +1201,11 @@ restart:
 		}
 		hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]],
 					   hnnode) {
-			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
-				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (nf_ct_is_expired(ct)) {
+				/* need to defer nf_ct_kill() until lock is released */
 				if (i < ARRAY_SIZE(nf_ct_evict) &&
-				    atomic_inc_not_zero(&ct->ct_general.use))
+				    refcount_inc_not_zero(&ct->ct_general.use))
 					nf_ct_evict[i++] = ct;
 				continue;
 			}
@@ -1208,6 +1213,9 @@ restart:
 			if (!net_eq(net, nf_ct_net(ct)))
 				continue;
 
+			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+
 			if (cb->args[1]) {
 				if (ct != last)
 					continue;
@@ -1552,6 +1560,11 @@ static int ctnetlink_flush_conntrack(struct net *net,
 				     u32 portid, int report, u8 family)
 {
 	struct ctnetlink_filter *filter = NULL;
+	struct nf_ct_iter_data iter = {
+		.net		= net,
+		.portid		= portid,
+		.report		= report,
+	};
 
 	if (ctnetlink_needs_filter(family, cda)) {
 		if (cda[CTA_FILTER])
@@ -1560,10 +1573,11 @@ static int ctnetlink_flush_conntrack(struct net *net,
 		filter = ctnetlink_alloc_filter(cda, family);
 		if (IS_ERR(filter))
 			return PTR_ERR(filter);
+
+		iter.data = filter;
 	}
 
-	nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter,
-				  portid, report);
+	nf_ct_iterate_cleanup_net(ctnetlink_flush_iterate, &iter);
 	kfree(filter);
 
 	return 0;
@@ -1693,87 +1707,109 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 
 static int ctnetlink_done_list(struct netlink_callback *cb)
 {
-	if (cb->args[1])
-		nf_ct_put((struct nf_conn *)cb->args[1]);
+	struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx;
+
+	if (ctx->last)
+		nf_ct_put(ctx->last);
+
 	return 0;
 }
 
-static int
-ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+static int ctnetlink_dump_one_entry(struct sk_buff *skb,
+				    struct netlink_callback *cb,
+				    struct nf_conn *ct,
+				    bool dying)
 {
-	struct nf_conn *ct, *last;
-	struct nf_conntrack_tuple_hash *h;
-	struct hlist_nulls_node *n;
+	struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx;
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
-	u_int8_t l3proto = nfmsg->nfgen_family;
+	u8 l3proto = nfmsg->nfgen_family;
 	int res;
-	int cpu;
-	struct hlist_nulls_head *list;
-	struct net *net = sock_net(skb->sk);
 
-	if (cb->args[2])
+	if (l3proto && nf_ct_l3num(ct) != l3proto)
 		return 0;
 
-	last = (struct nf_conn *)cb->args[1];
-
-	for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
-		struct ct_pcpu *pcpu;
+	if (ctx->last) {
+		if (ct != ctx->last)
+			return 0;
 
-		if (!cpu_possible(cpu))
-			continue;
+		ctx->last = NULL;
+	}
 
-		pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
-		spin_lock_bh(&pcpu->lock);
-		list = dying ? &pcpu->dying : &pcpu->unconfirmed;
-restart:
-		hlist_nulls_for_each_entry(h, n, list, hnnode) {
-			ct = nf_ct_tuplehash_to_ctrack(h);
-			if (l3proto && nf_ct_l3num(ct) != l3proto)
-				continue;
-			if (cb->args[1]) {
-				if (ct != last)
-					continue;
-				cb->args[1] = 0;
-			}
+	/* We can't dump extension info for the unconfirmed
+	 * list because unconfirmed conntracks can have
+	 * ct->ext reallocated (and thus freed).
+	 *
+	 * In the dying list case ct->ext can't be free'd
+	 * until after we drop pcpu->lock.
+	 */
+	res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
+				  cb->nlh->nlmsg_seq,
+				  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+				  ct, dying, 0);
+	if (res < 0) {
+		if (!refcount_inc_not_zero(&ct->ct_general.use))
+			return 0;
 
-			/* We can't dump extension info for the unconfirmed
-			 * list because unconfirmed conntracks can have
-			 * ct->ext reallocated (and thus freed).
-			 *
-			 * In the dying list case ct->ext can't be free'd
-			 * until after we drop pcpu->lock.
-			 */
-			res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
-						  cb->nlh->nlmsg_seq,
-						  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
-						  ct, dying ? true : false, 0);
-			if (res < 0) {
-				if (!atomic_inc_not_zero(&ct->ct_general.use))
-					continue;
-				cb->args[0] = cpu;
-				cb->args[1] = (unsigned long)ct;
-				spin_unlock_bh(&pcpu->lock);
-				goto out;
-			}
-		}
-		if (cb->args[1]) {
-			cb->args[1] = 0;
-			goto restart;
-		}
-		spin_unlock_bh(&pcpu->lock);
+		ctx->last = ct;
 	}
-	cb->args[2] = 1;
-out:
-	if (last)
-		nf_ct_put(last);
 
-	return skb->len;
+	return res;
+}
+#endif
+
+static int
+ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return 0;
 }
 
 static int
 ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	return ctnetlink_dump_list(skb, cb, true);
+	struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx;
+	struct nf_conn *last = ctx->last;
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	const struct net *net = sock_net(skb->sk);
+	struct nf_conntrack_net_ecache *ecache_net;
+	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_node *n;
+#endif
+
+	if (ctx->done)
+		return 0;
+
+	ctx->last = NULL;
+
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	ecache_net = nf_conn_pernet_ecache(net);
+	spin_lock_bh(&ecache_net->dying_lock);
+
+	hlist_nulls_for_each_entry(h, n, &ecache_net->dying_list, hnnode) {
+		struct nf_conn *ct;
+		int res;
+
+		ct = nf_ct_tuplehash_to_ctrack(h);
+		if (last && last != ct)
+			continue;
+
+		res = ctnetlink_dump_one_entry(skb, cb, ct, true);
+		if (res < 0) {
+			spin_unlock_bh(&ecache_net->dying_lock);
+			nf_ct_put(last);
+			return skb->len;
+		}
+
+		nf_ct_put(last);
+		last = NULL;
+	}
+
+	spin_unlock_bh(&ecache_net->dying_lock);
+#endif
+	ctx->done = true;
+	nf_ct_put(last);
+
+	return skb->len;
 }
 
 static int ctnetlink_get_ct_dying(struct sk_buff *skb,
@@ -1791,12 +1827,6 @@ static int ctnetlink_get_ct_dying(struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
-static int
-ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	return ctnetlink_dump_list(skb, cb, false);
-}
-
 static int ctnetlink_get_ct_unconfirmed(struct sk_buff *skb,
 					const struct nfnl_info *info,
 					const struct nlattr * const cda[])
@@ -1819,7 +1849,7 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 			  const struct nlattr *attr)
 	__must_hold(RCU)
 {
-	struct nf_nat_hook *nat_hook;
+	const struct nf_nat_hook *nat_hook;
 	int err;
 
 	nat_hook = rcu_dereference(nf_nat_hook);
@@ -1861,45 +1891,10 @@ 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[])
 {
-	unsigned long d;
-	unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS]));
-	d = ct->status ^ status;
-
-	if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING))
-		/* unchangeable */
-		return -EBUSY;
-
-	if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY))
-		/* SEEN_REPLY bit can only be set */
-		return -EBUSY;
-
-	if (d & IPS_ASSURED && !(status & IPS_ASSURED))
-		/* ASSURED bit can only be set */
-		return -EBUSY;
-
-	__ctnetlink_change_status(ct, status, 0);
-	return 0;
+	return nf_ct_change_status_common(ct, ntohl(nla_get_be32(cda[CTA_STATUS])));
 }
 
 static int
@@ -1975,7 +1970,7 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
 	}
 
 	if (help) {
-		if (help->helper == helper) {
+		if (rcu_access_pointer(help->helper) == helper) {
 			/* update private helper data if allowed. */
 			if (helper->from_nlattr)
 				helper->from_nlattr(helpinfo, ct);
@@ -1994,16 +1989,7 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
 static int ctnetlink_change_timeout(struct nf_conn *ct,
 				    const struct nlattr * const cda[])
 {
-	u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ;
-
-	if (timeout > INT_MAX)
-		timeout = INT_MAX;
-	WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
-
-	if (test_bit(IPS_DYING_BIT, &ct->status))
-		return -ETIME;
-
-	return 0;
+	return __nf_ct_change_timeout(ct, (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ);
 }
 
 #if defined(CONFIG_NF_CONNTRACK_MARK)
@@ -2263,9 +2249,7 @@ ctnetlink_create_conntrack(struct net *net,
 		goto err1;
 
 	timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ;
-	if (timeout > INT_MAX)
-		timeout = INT_MAX;
-	ct->timeout = (u32)timeout + nfct_time_stamp;
+	__nf_ct_set_timeout(ct, timeout);
 
 	rcu_read_lock();
  	if (cda[CTA_HELP]) {
@@ -2310,14 +2294,10 @@ ctnetlink_create_conntrack(struct net *net,
 			if (helper->from_nlattr)
 				helper->from_nlattr(helpinfo, ct);
 
-			/* not in hash table yet so not strictly necessary */
+			/* disable helper auto-assignment for this entry */
+			ct->status |= IPS_HELPER;
 			RCU_INIT_POINTER(help->helper, helper);
 		}
-	} else {
-		/* try an implicit helper assignation */
-		err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
-		if (err < 0)
-			goto err2;
 	}
 
 	err = ctnetlink_setup_nat(ct, cda);
@@ -2806,7 +2786,7 @@ ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[])
 	 * unchangeable bits but do not error out. Also user programs
 	 * are allowed to clear the bits that they are allowed to change.
 	 */
-	__ctnetlink_change_status(ct, status, ~status);
+	__nf_ct_change_status(ct, status, ~status);
 	return 0;
 }
 
@@ -2921,7 +2901,7 @@ static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct,
 	nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff);
 }
 
-static struct nfnl_ct_hook ctnetlink_glue_hook = {
+static const struct nfnl_ct_hook ctnetlink_glue_hook = {
 	.build_size	= ctnetlink_glue_build_size,
 	.build		= ctnetlink_glue_build,
 	.parse		= ctnetlink_glue_parse,
@@ -2995,7 +2975,7 @@ static const union nf_inet_addr any_addr;
 
 static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
 {
-	static __read_mostly siphash_key_t exp_id_seed;
+	static siphash_aligned_key_t exp_id_seed;
 	unsigned long a, b, c, d;
 
 	net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
@@ -3382,12 +3362,17 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 
 static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data)
 {
+	struct nf_conntrack_helper *helper;
 	const struct nf_conn_help *m_help;
 	const char *name = data;
 
 	m_help = nfct_help(exp->master);
 
-	return strcmp(m_help->helper->name, name) == 0;
+	helper = rcu_dereference(m_help->helper);
+	if (!helper)
+		return false;
+
+	return strcmp(helper->name, name) == 0;
 }
 
 static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data)
@@ -3876,6 +3861,8 @@ static int __init ctnetlink_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx));
+
 	ret = nfnetlink_subsys_register(&ctnl_subsys);
 	if (ret < 0) {
 		pr_err("ctnetlink_init: cannot register with nfnetlink.\n");