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

Cross-merge networking fixes after downstream PR.

No conflicts.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>

16 files changed, 77 insertions, 65 deletions

diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index b5c406a6e765..abb090f94ed2 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
-	int err;
+	int err = 0;
 
 	/* for offloaded checksums cleanup checksum before fragmentation */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d548431f3fa..af53f6d838ce 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1119,7 +1119,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res)
 	if (i == max_netdevices)
 		return -ENFILE;
 
-	snprintf(res, IFNAMSIZ, name, i);
+	/* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
+	strscpy(buf, name, IFNAMSIZ);
+	snprintf(res, IFNAMSIZ, buf, i);
 	return i;
 }
 
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index ceb684be4cbf..4c2e77bd12f4 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -180,18 +180,17 @@ static void gso_test_func(struct kunit *test)
 	}
 
 	if (tcase->frag_skbs) {
-		unsigned int total_size = 0, total_true_size = 0, alloc_size = 0;
+		unsigned int total_size = 0, total_true_size = 0;
 		struct sk_buff *frag_skb, *prev = NULL;
 
-		page = alloc_page(GFP_KERNEL);
-		KUNIT_ASSERT_NOT_NULL(test, page);
-		page_ref_add(page, tcase->nr_frag_skbs - 1);
-
 		for (i = 0; i < tcase->nr_frag_skbs; i++) {
 			unsigned int frag_size;
 
+			page = alloc_page(GFP_KERNEL);
+			KUNIT_ASSERT_NOT_NULL(test, page);
+
 			frag_size = tcase->frag_skbs[i];
-			frag_skb = build_skb(page_address(page) + alloc_size,
+			frag_skb = build_skb(page_address(page),
 					     frag_size + shinfo_size);
 			KUNIT_ASSERT_NOT_NULL(test, frag_skb);
 			__skb_put(frag_skb, frag_size);
@@ -204,11 +203,8 @@ static void gso_test_func(struct kunit *test)
 
 			total_size += frag_size;
 			total_true_size += frag_skb->truesize;
-			alloc_size += frag_size + shinfo_size;
 		}
 
-		KUNIT_ASSERT_LE(test, alloc_size, PAGE_SIZE);
-
 		skb->len += total_size;
 		skb->data_len += total_size;
 		skb->truesize += total_true_size;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 598c1b114d2c..a532f749e477 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -751,12 +751,12 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 		if (err)
 			goto unlock;
 	}
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
 		__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
 	else
 		__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
-	sock_set_flag(sk, SOCK_RCU_FREE);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 unlock:
 	spin_unlock(&ilb2->lock);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1529ec358815..bf4d96f6f99a 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1515,8 +1515,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		remove_anno_list_by_saddr(msk, &entry->addr);
-		if (alist.nr < MPTCP_RM_IDS_MAX)
+		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+		    alist.nr < MPTCP_RM_IDS_MAX)
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a0b8356cd8c5..bc81ea53a049 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1230,6 +1230,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	mptcp_do_fallback(ssk);
 }
 
+#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)
@@ -1256,6 +1258,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		return -EAGAIN;
 
 	/* compute send limit */
+	if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE))
+		ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE;
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
 	copy = info->size_goal;
 
@@ -3398,10 +3402,11 @@ static void mptcp_release_cb(struct sock *sk)
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
 	if (unlikely(msk->cb_flags)) {
-		/* be sure to set the current sk state before tacking actions
-		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
+		/* be sure to set the current sk state before taking actions
+		 * depending on sk_state (MPTCP_ERROR_REPORT)
+		 * On sk release avoid actions depending on the first subflow
 		 */
-		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
+		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags) && msk->first)
 			__mptcp_set_connected(sk);
 		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
 			__mptcp_error_report(sk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 77f5e8932abf..353680733700 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -738,8 +738,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow;
 
+		slow = lock_sock_fast(ssk);
 		__ip_sock_set_tos(ssk, val);
+		unlock_sock_fast(ssk, slow);
 	}
 	release_sock(sk);
 
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index f8854bff286c..62fb1031763d 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (had_link)
-		netif_carrier_off(ndp->ndev.dev);
-	else
-		netif_carrier_on(ndp->ndev.dev);
-
 	if (!ndp->multi_package && !nc->package->multi_channel) {
 		if (had_link) {
 			ndp->flags |= NCSI_DEV_RESHUFFLE;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 35d2f9c9ada0..4c133e06be1d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 	ip_set_dereference((inst)->ip_set_list)[id]
 #define ip_set_ref_netlink(inst,id)	\
 	rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p)	\
+	rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set)
 static struct ip_set *
 ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
-	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	rcu_read_lock();
-	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(inst->ip_set_list)[index];
-	rcu_read_unlock();
-
-	return set;
+	/* ip_set_list and the set pointer need to be protected */
+	return ip_set_dereference_nfnl(inst->ip_set_list)[index];
 }
 
 static inline void
@@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
+	/* Make sure all readers of the old set pointers are completed. */
+	synchronize_rcu();
+
 	return 0;
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a761ee6796f6..c0a42989b982 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7263,10 +7263,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
-			break;
+			return err;
 		}
 	}
-	return err;
+
+	return 0;
 }
 
 /*
@@ -9679,16 +9680,14 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans)
 	call_rcu(&trans->rcu, nft_trans_gc_trans_free);
 }
 
-static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
-						  unsigned int gc_seq,
-						  bool sync)
+struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
+						 unsigned int gc_seq)
 {
-	struct nft_set_elem_catchall *catchall, *next;
+	struct nft_set_elem_catchall *catchall;
 	const struct nft_set *set = gc->set;
-	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
 
-	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
 		if (!nft_set_elem_expired(ext))
@@ -9698,35 +9697,42 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
 
 		nft_set_elem_dead(ext);
 dead_elem:
-		if (sync)
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
-		else
-			gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
-
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
 		if (!gc)
 			return NULL;
 
-		elem_priv = catchall->elem;
-		if (sync) {
-			nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
-			nft_setelem_catchall_destroy(catchall);
-		}
-
-		nft_trans_gc_elem_add(gc, elem_priv);
+		nft_trans_gc_elem_add(gc, catchall->elem);
 	}
 
 	return gc;
 }
 
-struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
-						 unsigned int gc_seq)
-{
-	return nft_trans_gc_catchall(gc, gc_seq, false);
-}
-
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
-	return nft_trans_gc_catchall(gc, 0, true);
+	struct nft_set_elem_catchall *catchall, *next;
+	const struct nft_set *set = gc->set;
+	struct nft_elem_priv *elem_priv;
+	struct nft_set_ext *ext;
+
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net));
+
+	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+
+		if (!nft_set_elem_expired(ext))
+			continue;
+
+		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
+		if (!gc)
+			return NULL;
+
+		elem_priv = catchall->elem;
+		nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
+		nft_setelem_catchall_destroy(catchall);
+		nft_trans_gc_elem_add(gc, elem_priv);
+	}
+
+	return gc;
 }
 
 static void nf_tables_module_autoload_cleanup(struct net *net)
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index e596d1a842f7..f6e791a68101 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 
 	switch (priv->size) {
 	case 8: {
+		u64 *dst64 = (void *)dst;
 		u64 src64;
 
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = nft_reg_load64(&src[i]);
-				nft_reg_store64(&dst[i],
+				nft_reg_store64(&dst64[i],
 						be64_to_cpu((__force __be64)src64));
 			}
 			break;
@@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = (__force __u64)
 					cpu_to_be64(nft_reg_load64(&src[i]));
-				nft_reg_store64(&dst[i], src64);
+				nft_reg_store64(&dst64[i], src64);
 			}
 			break;
 		}
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index f7da7c43333b..ba0d3683a45d 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key,
 {
 	switch (key) {
 	case NFT_META_TIME_NS:
-		nft_reg_store64(dest, ktime_get_real_ns());
+		nft_reg_store64((u64 *)dest, ktime_get_real_ns());
 		break;
 	case NFT_META_TIME_DAY:
 		nft_reg_store8(dest, nft_meta_weekday());
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 6f1186abd47b..baa3fea4fe65 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -624,14 +624,12 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
-	struct nftables_pernet *nft_net;
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
 	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	nft_net = nft_pernet(net);
 
 	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (!gc)
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0db0ecf1d110..b3f4a503ee2b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1549,6 +1549,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
 	if (bind) {
 		struct flow_action_entry *entry = entry_data;
 
+		if (tcf_ct_helper(act))
+			return -EOPNOTSUPP;
+
 		entry->id = FLOW_ACTION_CT;
 		entry->ct.action = tcf_ct_action(act);
 		entry->ct.zone = tcf_ct_zone(act);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 5bc076f2fa74..c763008a8adb 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -102,6 +102,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
 		return -EMSGSIZE;
 
 	skb_put(skb, TLV_SPACE(len));
+	memset(tlv, 0, TLV_SPACE(len));
 	tlv->tlv_type = htons(type);
 	tlv->tlv_len = htons(TLV_LENGTH(len));
 	if (len && data)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 45506a95b25f..a357dc5f2404 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2581,15 +2581,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	if (!(state->flags & MSG_PEEK))
 		WRITE_ONCE(u->oob_skb, NULL);
-
+	else
+		skb_get(oob_skb);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
 
-	if (!(state->flags & MSG_PEEK)) {
+	if (!(state->flags & MSG_PEEK))
 		UNIXCB(oob_skb).consumed += 1;
-		kfree_skb(oob_skb);
-	}
+
+	consume_skb(oob_skb);
 
 	mutex_unlock(&u->iolock);