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

Cross-merge networking fixes after downstream PR.

No conflicts (or adjacent changes of note).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 106 insertions, 48 deletions

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 4f6c795588fb..eaf9f2ed0067 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1435,7 +1435,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
 	sin.sin_addr.s_addr  = addr;
 	sin.sin_port         = 0;
 
-	return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin));
+	return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin));
 }
 
 static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
@@ -1501,8 +1501,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id,
 	}
 
 	get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id);
-	result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr,
-				    salen, 0);
+	result = kernel_connect(sock, (struct sockaddr *)&mcast_addr,
+				salen, 0);
 	if (result < 0) {
 		pr_err("Error connecting to the multicast addr\n");
 		goto error;
@@ -1542,7 +1542,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id,
 
 	get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
 	sock->sk->sk_bound_dev_if = dev->ifindex;
-	result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
+	result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen);
 	if (result < 0) {
 		pr_err("Error binding to the multicast addr\n");
 		goto error;
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index b6bcc8f2f46b..c6bd533983c1 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA},
 /* error        */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/
 /* cookie_echo  */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */
-/* cookie_ack   */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
+/* cookie_ack   */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
 /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL},
 /* heartbeat    */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
 /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
@@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /* shutdown     */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV},
 /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV},
 /* error        */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV},
-/* cookie_echo  */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
+/* cookie_echo  */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
 /* cookie_ack   */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV},
 /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV},
 /* heartbeat    */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
@@ -412,6 +412,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 			/* (D) vtag must be same as init_vtag as found in INIT_ACK */
 			if (sh->vtag != ct->proto.sctp.vtag[dir])
 				goto out_unlock;
+		} else if (sch->type == SCTP_CID_COOKIE_ACK) {
+			ct->proto.sctp.init[dir] = 0;
+			ct->proto.sctp.init[!dir] = 0;
 		} else if (sch->type == SCTP_CID_HEARTBEAT) {
 			if (ct->proto.sctp.vtag[dir] == 0) {
 				pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir);
@@ -461,16 +464,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 		}
 
 		/* If it is an INIT or an INIT ACK note down the vtag */
-		if (sch->type == SCTP_CID_INIT ||
-		    sch->type == SCTP_CID_INIT_ACK) {
-			struct sctp_inithdr _inithdr, *ih;
+		if (sch->type == SCTP_CID_INIT) {
+			struct sctp_inithdr _ih, *ih;
 
-			ih = skb_header_pointer(skb, offset + sizeof(_sch),
-						sizeof(_inithdr), &_inithdr);
-			if (ih == NULL)
+			ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih);
+			if (!ih)
 				goto out_unlock;
-			pr_debug("Setting vtag %x for dir %d\n",
-				 ih->init_tag, !dir);
+
+			if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir])
+				ct->proto.sctp.init[!dir] = 0;
+			ct->proto.sctp.init[dir] = 1;
+
+			pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir);
 			ct->proto.sctp.vtag[!dir] = ih->init_tag;
 
 			/* don't renew timeout on init retransmit so
@@ -481,6 +486,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 			    old_state == SCTP_CONNTRACK_CLOSED &&
 			    nf_ct_is_confirmed(ct))
 				ignore = true;
+		} else if (sch->type == SCTP_CID_INIT_ACK) {
+			struct sctp_inithdr _ih, *ih;
+			__be32 vtag;
+
+			ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih);
+			if (!ih)
+				goto out_unlock;
+
+			vtag = ct->proto.sctp.vtag[!dir];
+			if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag)
+				goto out_unlock;
+			/* collision */
+			if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] &&
+			    vtag != ih->init_tag)
+				goto out_unlock;
+
+			pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir);
+			ct->proto.sctp.vtag[!dir] = ih->init_tag;
 		}
 
 		ct->proto.sctp.state = new_state;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 7e2e76086d25..b4405db710b0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7879,24 +7879,14 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info,
 	return nft_delobj(&ctx, obj);
 }
 
-void nft_obj_notify(struct net *net, const struct nft_table *table,
-		    struct nft_object *obj, u32 portid, u32 seq, int event,
-		    u16 flags, int family, int report, gfp_t gfp)
+static void
+__nft_obj_notify(struct net *net, const struct nft_table *table,
+		 struct nft_object *obj, u32 portid, u32 seq, int event,
+		 u16 flags, int family, int report, gfp_t gfp)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 	struct sk_buff *skb;
 	int err;
-	char *buf = kasprintf(gfp, "%s:%u",
-			      table->name, nft_net->base_seq);
-
-	audit_log_nfcfg(buf,
-			family,
-			obj->handle,
-			event == NFT_MSG_NEWOBJ ?
-				 AUDIT_NFT_OP_OBJ_REGISTER :
-				 AUDIT_NFT_OP_OBJ_UNREGISTER,
-			gfp);
-	kfree(buf);
 
 	if (!report &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
@@ -7919,13 +7909,35 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 err:
 	nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
+
+void nft_obj_notify(struct net *net, const struct nft_table *table,
+		    struct nft_object *obj, u32 portid, u32 seq, int event,
+		    u16 flags, int family, int report, gfp_t gfp)
+{
+	struct nftables_pernet *nft_net = nft_pernet(net);
+	char *buf = kasprintf(gfp, "%s:%u",
+			      table->name, nft_net->base_seq);
+
+	audit_log_nfcfg(buf,
+			family,
+			obj->handle,
+			event == NFT_MSG_NEWOBJ ?
+				 AUDIT_NFT_OP_OBJ_REGISTER :
+				 AUDIT_NFT_OP_OBJ_UNREGISTER,
+			gfp);
+	kfree(buf);
+
+	__nft_obj_notify(net, table, obj, portid, seq, event,
+			 flags, family, report, gfp);
+}
 EXPORT_SYMBOL_GPL(nft_obj_notify);
 
 static void nf_tables_obj_notify(const struct nft_ctx *ctx,
 				 struct nft_object *obj, int event)
 {
-	nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event,
-		       ctx->flags, ctx->family, ctx->report, GFP_KERNEL);
+	__nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid,
+			 ctx->seq, event, ctx->flags, ctx->family,
+			 ctx->report, GFP_KERNEL);
 }
 
 /*
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 8cb800989947..120f6d395b98 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -154,6 +154,17 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
 	return pkt->inneroff;
 }
 
+static bool nft_payload_need_vlan_copy(const struct nft_payload *priv)
+{
+	unsigned int len = priv->offset + priv->len;
+
+	/* data past ether src/dst requested, copy needed */
+	if (len > offsetof(struct ethhdr, h_proto))
+		return true;
+
+	return false;
+}
+
 void nft_payload_eval(const struct nft_expr *expr,
 		      struct nft_regs *regs,
 		      const struct nft_pktinfo *pkt)
@@ -172,7 +183,7 @@ void nft_payload_eval(const struct nft_expr *expr,
 			goto err;
 
 		if (skb_vlan_tag_present(skb) &&
-		    priv->offset >= offsetof(struct ethhdr, h_proto)) {
+		    nft_payload_need_vlan_copy(priv)) {
 			if (!nft_payload_copy_vlan(dest, skb,
 						   priv->offset, priv->len))
 				goto err;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 487572dcd614..2660ceab3759 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -233,10 +233,9 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set,
 	rb_erase(&rbe->node, &priv->root);
 }
 
-static int nft_rbtree_gc_elem(const struct nft_set *__set,
-			      struct nft_rbtree *priv,
-			      struct nft_rbtree_elem *rbe,
-			      u8 genmask)
+static const struct nft_rbtree_elem *
+nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
+		   struct nft_rbtree_elem *rbe, u8 genmask)
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
@@ -246,7 +245,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 
 	gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC);
 	if (!gc)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* search for end interval coming before this element.
 	 * end intervals don't carry a timeout extension, they
@@ -261,6 +260,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 		prev = rb_prev(prev);
 	}
 
+	rbe_prev = NULL;
 	if (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
 		nft_rbtree_gc_remove(net, set, priv, rbe_prev);
@@ -272,7 +272,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 		 */
 		gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
 		if (WARN_ON_ONCE(!gc))
-			return -ENOMEM;
+			return ERR_PTR(-ENOMEM);
 
 		nft_trans_gc_elem_add(gc, rbe_prev);
 	}
@@ -280,13 +280,13 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set,
 	nft_rbtree_gc_remove(net, set, priv, rbe);
 	gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
 	if (WARN_ON_ONCE(!gc))
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	nft_trans_gc_elem_add(gc, rbe);
 
 	nft_trans_gc_queue_sync_done(gc);
 
-	return 0;
+	return rbe_prev;
 }
 
 static bool nft_rbtree_update_first(const struct nft_set *set,
@@ -314,7 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
-	int d, err;
+	int d;
 
 	/* Descend the tree to search for an existing element greater than the
 	 * key value to insert that is greater than the new element. This is the
@@ -363,9 +363,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		 */
 		if (nft_set_elem_expired(&rbe->ext) &&
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
-			err = nft_rbtree_gc_elem(set, priv, rbe, genmask);
-			if (err < 0)
-				return err;
+			const struct nft_rbtree_elem *removed_end;
+
+			removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask);
+			if (IS_ERR(removed_end))
+				return PTR_ERR(removed_end);
+
+			if (removed_end == rbe_le || removed_end == rbe_ge)
+				return -EAGAIN;
 
 			continue;
 		}
@@ -486,11 +491,18 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree_elem *rbe = elem->priv;
 	int err;
 
-	write_lock_bh(&priv->lock);
-	write_seqcount_begin(&priv->count);
-	err = __nft_rbtree_insert(net, set, rbe, ext);
-	write_seqcount_end(&priv->count);
-	write_unlock_bh(&priv->lock);
+	do {
+		if (fatal_signal_pending(current))
+			return -EINTR;
+
+		cond_resched();
+
+		write_lock_bh(&priv->lock);
+		write_seqcount_begin(&priv->count);
+		err = __nft_rbtree_insert(net, set, rbe, ext);
+		write_seqcount_end(&priv->count);
+		write_unlock_bh(&priv->lock);
+	} while (err == -EAGAIN);
 
 	return err;
 }