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

Cross-merge networking fixes after downstream PR.

Conflicts:

net/sched/act_ct.c
  26488172b029 ("net/sched: Fix UAF when resolving a clash")
  3abbd7ed8b76 ("act_ct: prepare for stolen verdict coming from conntrack and nat engine")

No adjacent changes.

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

11 files changed, 93 insertions, 173 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b2f391edb9e8..a40f733b37d7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -423,11 +423,12 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 			if (copy > len)
 				copy = len;
 
+			n = 0;
 			skb_frag_foreach_page(frag,
 					      skb_frag_off(frag) + offset - start,
 					      copy, p, p_off, p_len, copied) {
 				vaddr = kmap_local_page(p);
-				n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+				n += INDIRECT_CALL_1(cb, simple_copy_to_iter,
 					vaddr + p_off, p_len, data, to);
 				kunmap_local(vaddr);
 			}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index fd20aae30be2..bbf40b999713 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 			page = sg_page(sge);
 			if (copied + copy > len)
 				copy = len - copied;
-			copy = copy_page_to_iter(page, sge->offset, copy, iter);
+			if (copy)
+				copy = copy_page_to_iter(page, sge->offset, copy, iter);
 			if (!copy) {
 				copied = copied ? copied : -EFAULT;
 				goto out;
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index b2de2108b356..34d76e87847d 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -37,6 +37,8 @@ static int linkstate_get_sqi(struct net_device *dev)
 	mutex_lock(&phydev->lock);
 	if (!phydev->drv || !phydev->drv->get_sqi)
 		ret = -EOPNOTSUPP;
+	else if (!phydev->link)
+		ret = -ENETDOWN;
 	else
 		ret = phydev->drv->get_sqi(phydev);
 	mutex_unlock(&phydev->lock);
@@ -55,6 +57,8 @@ static int linkstate_get_sqi_max(struct net_device *dev)
 	mutex_lock(&phydev->lock);
 	if (!phydev->drv || !phydev->drv->get_sqi_max)
 		ret = -EOPNOTSUPP;
+	else if (!phydev->link)
+		ret = -ENETDOWN;
 	else
 		ret = phydev->drv->get_sqi_max(phydev);
 	mutex_unlock(&phydev->lock);
@@ -62,6 +66,17 @@ static int linkstate_get_sqi_max(struct net_device *dev)
 	return ret;
 };
 
+static bool linkstate_sqi_critical_error(int sqi)
+{
+	return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN;
+}
+
+static bool linkstate_sqi_valid(struct linkstate_reply_data *data)
+{
+	return data->sqi >= 0 && data->sqi_max >= 0 &&
+	       data->sqi <= data->sqi_max;
+}
+
 static int linkstate_get_link_ext_state(struct net_device *dev,
 					struct linkstate_reply_data *data)
 {
@@ -93,12 +108,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 	data->link = __ethtool_get_link(dev);
 
 	ret = linkstate_get_sqi(dev);
-	if (ret < 0 && ret != -EOPNOTSUPP)
+	if (linkstate_sqi_critical_error(ret))
 		goto out;
 	data->sqi = ret;
 
 	ret = linkstate_get_sqi_max(dev);
-	if (ret < 0 && ret != -EOPNOTSUPP)
+	if (linkstate_sqi_critical_error(ret))
 		goto out;
 	data->sqi_max = ret;
 
@@ -136,11 +151,10 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base,
 	len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */
 		+ 0;
 
-	if (data->sqi != -EOPNOTSUPP)
-		len += nla_total_size(sizeof(u32));
-
-	if (data->sqi_max != -EOPNOTSUPP)
-		len += nla_total_size(sizeof(u32));
+	if (linkstate_sqi_valid(data)) {
+		len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */
+		len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */
+	}
 
 	if (data->link_ext_state_provided)
 		len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */
@@ -164,13 +178,14 @@ static int linkstate_fill_reply(struct sk_buff *skb,
 	    nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link))
 		return -EMSGSIZE;
 
-	if (data->sqi != -EOPNOTSUPP &&
-	    nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi))
-		return -EMSGSIZE;
+	if (linkstate_sqi_valid(data)) {
+		if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi))
+			return -EMSGSIZE;
 
-	if (data->sqi_max != -EOPNOTSUPP &&
-	    nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max))
-		return -EMSGSIZE;
+		if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX,
+				data->sqi_max))
+			return -EMSGSIZE;
+	}
 
 	if (data->link_ext_state_provided) {
 		if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 47dacb575f74..e0f54b9be850 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2129,8 +2129,16 @@ void tcp_clear_retrans(struct tcp_sock *tp)
 static inline void tcp_init_undo(struct tcp_sock *tp)
 {
 	tp->undo_marker = tp->snd_una;
+
 	/* Retransmission still in flight may cause DSACKs later. */
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	/* First, account for regular retransmits in flight: */
+	tp->undo_retrans = tp->retrans_out;
+	/* Next, account for TLP retransmits in flight: */
+	if (tp->tlp_high_seq && tp->tlp_retrans)
+		tp->undo_retrans++;
+	/* Finally, avoid 0, because undo_retrans==0 means "can undo now": */
+	if (!tp->undo_retrans)
+		tp->undo_retrans = -1;
 }
 
 static bool tcp_is_rack(const struct sock *sk)
@@ -2209,6 +2217,7 @@ void tcp_enter_loss(struct sock *sk)
 
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = 0;
 	tcp_ecn_queue_cwr(tp);
 
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index ab4b6de0e069..4d40615dc8fc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -479,15 +479,26 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
 				     const struct sk_buff *skb,
 				     u32 rtx_delta)
 {
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	const int timeout = TCP_RTO_MAX * 2;
+	int timeout = TCP_RTO_MAX * 2;
 	s32 rcv_delta;
 
+	if (user_timeout) {
+		/* If user application specified a TCP_USER_TIMEOUT,
+		 * it does not want win 0 packets to 'reset the timer'
+		 * while retransmits are not making progress.
+		 */
+		if (rtx_delta > user_timeout)
+			return true;
+		timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
+	}
 	/* Note: timer interrupt might have been delayed by at least one jiffy,
 	 * and tp->rcv_tstamp might very well have been written recently.
 	 * rcv_delta can thus be negative.
 	 */
-	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
 	if (rcv_delta <= timeout)
 		return false;
 
@@ -532,8 +543,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (WARN_ON_ONCE(!skb))
 		return;
 
-	tp->tlp_high_seq = 0;
-
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
 		/* Receiver dastardly shrinks window. Our retransmits
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ed97df6af14d..49c622e743e8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -326,6 +326,8 @@ found:
 			goto fail_unlock;
 		}
 
+		sock_set_flag(sk, SOCK_RCU_FREE);
+
 		sk_add_node_rcu(sk, &hslot->head);
 		hslot->count++;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -342,7 +344,7 @@ found:
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
-	sock_set_flag(sk, SOCK_RCU_FREE);
+
 	error = 0;
 fail_unlock:
 	spin_unlock_bh(&hslot->lock);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4a07834809bb..481ee78e77bc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3866,6 +3866,15 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r
 	nf_tables_rule_destroy(ctx, rule);
 }
 
+/** nft_chain_validate - loop detection and hook validation
+ *
+ * @ctx: context containing call depth and base chain
+ * @chain: chain to validate
+ *
+ * Walk through the rules of the given chain and chase all jumps/gotos
+ * and set lookups until either the jump limit is hit or all reachable
+ * chains have been validated.
+ */
 int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 {
 	struct nft_expr *expr, *last;
@@ -3887,6 +3896,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 			if (!expr->ops->validate)
 				continue;
 
+			/* This may call nft_chain_validate() recursively,
+			 * callers that do so must increment ctx->level.
+			 */
 			err = expr->ops->validate(ctx, expr, &data);
 			if (err < 0)
 				return err;
@@ -10879,150 +10891,6 @@ int nft_chain_validate_hooks(const struct nft_chain *chain,
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
 
-/*
- * Loop detection - walk through the ruleset beginning at the destination chain
- * of a new jump until either the source chain is reached (loop) or all
- * reachable chains have been traversed.
- *
- * The loop check is performed whenever a new jump verdict is added to an
- * expression or verdict map or a verdict map is bound to a new chain.
- */
-
-static int nf_tables_check_loops(const struct nft_ctx *ctx,
-				 const struct nft_chain *chain);
-
-static int nft_check_loops(const struct nft_ctx *ctx,
-			   const struct nft_set_ext *ext)
-{
-	const struct nft_data *data;
-	int ret;
-
-	data = nft_set_ext_data(ext);
-	switch (data->verdict.code) {
-	case NFT_JUMP:
-	case NFT_GOTO:
-		ret = nf_tables_check_loops(ctx, data->verdict.chain);
-		break;
-	default:
-		ret = 0;
-		break;
-	}
-
-	return ret;
-}
-
-static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
-					struct nft_set *set,
-					const struct nft_set_iter *iter,
-					struct nft_elem_priv *elem_priv)
-{
-	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
-
-	if (!nft_set_elem_active(ext, iter->genmask))
-		return 0;
-
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
-	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
-		return 0;
-
-	return nft_check_loops(ctx, ext);
-}
-
-static int nft_set_catchall_loops(const struct nft_ctx *ctx,
-				  struct nft_set *set)
-{
-	u8 genmask = nft_genmask_next(ctx->net);
-	struct nft_set_elem_catchall *catchall;
-	struct nft_set_ext *ext;
-	int ret = 0;
-
-	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
-		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_set_elem_active(ext, genmask))
-			continue;
-
-		ret = nft_check_loops(ctx, ext);
-		if (ret < 0)
-			return ret;
-	}
-
-	return ret;
-}
-
-static int nf_tables_check_loops(const struct nft_ctx *ctx,
-				 const struct nft_chain *chain)
-{
-	const struct nft_rule *rule;
-	const struct nft_expr *expr, *last;
-	struct nft_set *set;
-	struct nft_set_binding *binding;
-	struct nft_set_iter iter;
-
-	if (ctx->chain == chain)
-		return -ELOOP;
-
-	if (fatal_signal_pending(current))
-		return -EINTR;
-
-	list_for_each_entry(rule, &chain->rules, list) {
-		nft_rule_for_each_expr(expr, last, rule) {
-			struct nft_immediate_expr *priv;
-			const struct nft_data *data;
-			int err;
-
-			if (strcmp(expr->ops->type->name, "immediate"))
-				continue;
-
-			priv = nft_expr_priv(expr);
-			if (priv->dreg != NFT_REG_VERDICT)
-				continue;
-
-			data = &priv->data;
-			switch (data->verdict.code) {
-			case NFT_JUMP:
-			case NFT_GOTO:
-				err = nf_tables_check_loops(ctx,
-							data->verdict.chain);
-				if (err < 0)
-					return err;
-				break;
-			default:
-				break;
-			}
-		}
-	}
-
-	list_for_each_entry(set, &ctx->table->sets, list) {
-		if (!nft_is_active_next(ctx->net, set))
-			continue;
-		if (!(set->flags & NFT_SET_MAP) ||
-		    set->dtype != NFT_DATA_VERDICT)
-			continue;
-
-		list_for_each_entry(binding, &set->bindings, list) {
-			if (!(binding->flags & NFT_SET_MAP) ||
-			    binding->chain != chain)
-				continue;
-
-			iter.genmask	= nft_genmask_next(ctx->net);
-			iter.type	= NFT_ITER_UPDATE;
-			iter.skip 	= 0;
-			iter.count	= 0;
-			iter.err	= 0;
-			iter.fn		= nf_tables_loop_check_setelem;
-
-			set->ops->walk(ctx, set, &iter);
-			if (!iter.err)
-				iter.err = nft_set_catchall_loops(ctx, set);
-
-			if (iter.err < 0)
-				return iter.err;
-		}
-	}
-
-	return 0;
-}
-
 /**
  *	nft_parse_u32_check - fetch u32 attribute and check for maximum value
  *
@@ -11135,7 +11003,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 		if (data != NULL &&
 		    (data->verdict.code == NFT_GOTO ||
 		     data->verdict.code == NFT_JUMP)) {
-			err = nf_tables_check_loops(ctx, data->verdict.chain);
+			err = nft_chain_validate(ctx, data->verdict.chain);
 			if (err < 0)
 				return err;
 		}
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index f1c31757e496..55e28e1da66e 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -325,7 +325,7 @@ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	hooks = nf_hook_entries_head(net, pf, entry->state.hook);
 
 	i = entry->hook_index;
-	if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) {
+	if (!hooks || i >= hooks->num_hook_entries) {
 		kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP);
 		nf_queue_entry_free(entry);
 		return;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index a6b7c514a181..113b907da0f7 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1081,6 +1081,14 @@ do_nat:
 		err = nf_conntrack_confirm(skb);
 		if (err != NF_ACCEPT)
 			goto nf_error;
+
+		/* The ct may be dropped if a clash has been resolved,
+		 * so it's necessary to retrieve it from skb again to
+		 * prevent UAF.
+		 */
+		ct = nf_ct_get(skb, &ctinfo);
+		if (!ct)
+			skip_add = true;
 	}
 
 	if (!skip_add)
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index c2ef9dcf91d2..cc6051d4f2ef 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -91,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 	entry = tcx_entry_fetch_or_create(dev, true, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, true);
@@ -121,7 +121,7 @@ static void ingress_destroy(struct Qdisc *sch)
 	tcf_block_put_ext(q->block, sch, &q->block_info);
 
 	if (entry) {
-		tcx_miniq_set_active(entry, false);
+		tcx_miniq_dec(entry);
 		if (!tcx_entry_is_active(entry)) {
 			tcx_entry_update(dev, NULL, true);
 			tcx_entry_free(entry);
@@ -257,7 +257,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	entry = tcx_entry_fetch_or_create(dev, true, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, true);
@@ -276,7 +276,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	entry = tcx_entry_fetch_or_create(dev, false, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, false);
@@ -302,7 +302,7 @@ static void clsact_destroy(struct Qdisc *sch)
 	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 
 	if (ingress_entry) {
-		tcx_miniq_set_active(ingress_entry, false);
+		tcx_miniq_dec(ingress_entry);
 		if (!tcx_entry_is_active(ingress_entry)) {
 			tcx_entry_update(dev, NULL, true);
 			tcx_entry_free(ingress_entry);
@@ -310,7 +310,7 @@ static void clsact_destroy(struct Qdisc *sch)
 	}
 
 	if (egress_entry) {
-		tcx_miniq_set_active(egress_entry, false);
+		tcx_miniq_dec(egress_entry);
 		if (!tcx_entry_is_active(egress_entry)) {
 			tcx_entry_update(dev, NULL, false);
 			tcx_entry_free(egress_entry);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index dfc353eea8ed..0e1691316f42 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2441,6 +2441,13 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		transport->srcport = 0;
 		status = -EAGAIN;
 		break;
+	case -EPERM:
+		/* Happens, for instance, if a BPF program is preventing
+		 * the connect. Remap the error so upper layers can better
+		 * deal with it.
+		 */
+		status = -ECONNREFUSED;
+		fallthrough;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link
 		 * local IPv6 address without a scope-id.