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

Cross-merge networking fixes after downstream PR.

Conflicts:

include/linux/mlx5/driver.h
  617f5db1a626 ("RDMA/mlx5: Fix affinity assignment")
  dc13180824b7 ("net/mlx5: Enable devlink port for embedded cpu VF vports")
https://lore.kernel.org/all/20230613125939.595e50b8@canb.auug.org.au/

tools/testing/selftests/net/mptcp/mptcp_join.sh
  47867f0a7e83 ("selftests: mptcp: join: skip check if MIB counter not supported")
  425ba803124b ("selftests: mptcp: join: support RM_ADDR for used endpoints or not")
  45b1a1227a7a ("mptcp: introduces more address related mibs")
  0639fa230a21 ("selftests: mptcp: add explicit check for new mibs")
https://lore.kernel.org/netdev/20230609-upstream-net-20230610-mptcp-selftests-support-old-kernels-part-3-v1-0-2896fe2ee8a3@tessares.net/

No adjacent changes.

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

7 files changed, 113 insertions, 35 deletions

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 9cc0bc7c71ed7..abc71a06d634a 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -610,6 +610,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	struct flow_offload_tuple tuple = {};
 	enum ip_conntrack_info ctinfo;
 	struct tcphdr *tcph = NULL;
+	bool force_refresh = false;
 	struct flow_offload *flow;
 	struct nf_conn *ct;
 	u8 dir;
@@ -647,6 +648,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 			 * established state, then don't refresh.
 			 */
 			return false;
+		force_refresh = true;
 	}
 
 	if (tcph && (unlikely(tcph->fin || tcph->rst))) {
@@ -660,7 +662,12 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	else
 		ctinfo = IP_CT_ESTABLISHED_REPLY;
 
-	flow_offload_refresh(nf_ft, flow);
+	flow_offload_refresh(nf_ft, flow, force_refresh);
+	if (!test_bit(IPS_ASSURED_BIT, &ct->status)) {
+		/* Process this flow in SW to allow promoting to ASSURED */
+		return false;
+	}
+
 	nf_conntrack_get(&ct->ct_general);
 	nf_ct_set(skb, ct, ctinfo);
 	if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 8c4e7fddddbf9..b562fc2bb5b19 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -13,7 +13,10 @@
 #include <linux/rtnetlink.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/slab.h>
+#include <net/ipv6.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <linux/tc_act/tc_pedit.h>
@@ -325,28 +328,58 @@ static bool offset_valid(struct sk_buff *skb, int offset)
 	return true;
 }
 
-static void pedit_skb_hdr_offset(struct sk_buff *skb,
+static int pedit_l4_skb_offset(struct sk_buff *skb, int *hoffset, const int header_type)
+{
+	const int noff = skb_network_offset(skb);
+	int ret = -EINVAL;
+	struct iphdr _iph;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP): {
+		const struct iphdr *iph = skb_header_pointer(skb, noff, sizeof(_iph), &_iph);
+
+		if (!iph)
+			goto out;
+		*hoffset = noff + iph->ihl * 4;
+		ret = 0;
+		break;
+	}
+	case htons(ETH_P_IPV6):
+		ret = ipv6_find_hdr(skb, hoffset, header_type, NULL, NULL) == header_type ? 0 : -EINVAL;
+		break;
+	}
+out:
+	return ret;
+}
+
+static int pedit_skb_hdr_offset(struct sk_buff *skb,
 				 enum pedit_header_type htype, int *hoffset)
 {
+	int ret = -EINVAL;
 	/* 'htype' is validated in the netlink parsing */
 	switch (htype) {
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
-		if (skb_mac_header_was_set(skb))
+		if (skb_mac_header_was_set(skb)) {
 			*hoffset = skb_mac_offset(skb);
+			ret = 0;
+		}
 		break;
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK:
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
 		*hoffset = skb_network_offset(skb);
+		ret = 0;
 		break;
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+		ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_TCP);
+		break;
 	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
-		if (skb_transport_header_was_set(skb))
-			*hoffset = skb_transport_offset(skb);
+		ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_UDP);
 		break;
 	default:
 		break;
 	}
+	return ret;
 }
 
 TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
@@ -382,6 +415,7 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 		int hoffset = 0;
 		u32 *ptr, hdata;
 		u32 val;
+		int rc;
 
 		if (tkey_ex) {
 			htype = tkey_ex->htype;
@@ -390,7 +424,11 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 			tkey_ex++;
 		}
 
-		pedit_skb_hdr_offset(skb, htype, &hoffset);
+		rc = pedit_skb_hdr_offset(skb, htype, &hoffset);
+		if (rc) {
+			pr_info_ratelimited("tc action pedit unable to extract header offset for header type (0x%x)\n", htype);
+			goto bad;
+		}
 
 		if (tkey->offmask) {
 			u8 *d, _d;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c877a6343fd47..a193cc7b32418 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -657,8 +657,8 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
 {
 	struct tcf_block *block = chain->block;
 	const struct tcf_proto_ops *tmplt_ops;
+	unsigned int refcnt, non_act_refcnt;
 	bool free_block = false;
-	unsigned int refcnt;
 	void *tmplt_priv;
 
 	mutex_lock(&block->lock);
@@ -678,13 +678,15 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act,
 	 * save these to temporary variables.
 	 */
 	refcnt = --chain->refcnt;
+	non_act_refcnt = refcnt - chain->action_refcnt;
 	tmplt_ops = chain->tmplt_ops;
 	tmplt_priv = chain->tmplt_priv;
 
-	/* The last dropped non-action reference will trigger notification. */
-	if (refcnt - chain->action_refcnt == 0 && !by_act) {
-		tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain->index,
-				       block, NULL, 0, 0, false);
+	if (non_act_refcnt == chain->explicitly_created && !by_act) {
+		if (non_act_refcnt == 0)
+			tc_chain_notify_delete(tmplt_ops, tmplt_priv,
+					       chain->index, block, NULL, 0, 0,
+					       false);
 		/* Last reference to chain, no need to lock. */
 		chain->flushing = false;
 	}
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4e2e269f121f8..d15d50de79802 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -718,13 +718,19 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 			 struct nlattr *est, u32 flags, u32 fl_flags,
 			 struct netlink_ext_ack *extack)
 {
-	int err;
+	int err, ifindex = -1;
 
 	err = tcf_exts_validate_ex(net, tp, tb, est, &n->exts, flags,
 				   fl_flags, extack);
 	if (err < 0)
 		return err;
 
+	if (tb[TCA_U32_INDEV]) {
+		ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
+		if (ifindex < 0)
+			return -EINVAL;
+	}
+
 	if (tb[TCA_U32_LINK]) {
 		u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
 		struct tc_u_hnode *ht_down = NULL, *ht_old;
@@ -759,13 +765,9 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 		tcf_bind_filter(tp, &n->res, base);
 	}
 
-	if (tb[TCA_U32_INDEV]) {
-		int ret;
-		ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
-		if (ret < 0)
-			return -EINVAL;
-		n->ifindex = ret;
-	}
+	if (ifindex >= 0)
+		n->ifindex = ifindex;
+
 	return 0;
 }
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e4b6452318c0a..aa6b1fe651519 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1079,17 +1079,29 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 
 	if (parent == NULL) {
 		unsigned int i, num_q, ingress;
+		struct netdev_queue *dev_queue;
 
 		ingress = 0;
 		num_q = dev->num_tx_queues;
 		if ((q && q->flags & TCQ_F_INGRESS) ||
 		    (new && new->flags & TCQ_F_INGRESS)) {
-			num_q = 1;
 			ingress = 1;
-			if (!dev_ingress_queue(dev)) {
+			dev_queue = dev_ingress_queue(dev);
+			if (!dev_queue) {
 				NL_SET_ERR_MSG(extack, "Device does not have an ingress queue");
 				return -ENOENT;
 			}
+
+			q = rtnl_dereference(dev_queue->qdisc_sleeping);
+
+			/* This is the counterpart of that qdisc_refcount_inc_nz() call in
+			 * __tcf_qdisc_find() for filter requests.
+			 */
+			if (!qdisc_refcount_dec_if_one(q)) {
+				NL_SET_ERR_MSG(extack,
+					       "Current ingress or clsact Qdisc has ongoing filter requests");
+				return -EBUSY;
+			}
 		}
 
 		if (dev->flags & IFF_UP)
@@ -1100,18 +1112,26 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (new && new->ops->attach && !ingress)
 			goto skip;
 
-		for (i = 0; i < num_q; i++) {
-			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
-
-			if (!ingress)
+		if (!ingress) {
+			for (i = 0; i < num_q; i++) {
 				dev_queue = netdev_get_tx_queue(dev, i);
+				old = dev_graft_qdisc(dev_queue, new);
 
-			old = dev_graft_qdisc(dev_queue, new);
-			if (new && i > 0)
-				qdisc_refcount_inc(new);
-
-			if (!ingress)
+				if (new && i > 0)
+					qdisc_refcount_inc(new);
 				qdisc_put(old);
+			}
+		} else {
+			old = dev_graft_qdisc(dev_queue, NULL);
+
+			/* {ingress,clsact}_destroy() @old before grafting @new to avoid
+			 * unprotected concurrent accesses to net_device::miniq_{in,e}gress
+			 * pointer(s) in mini_qdisc_pair_swap().
+			 */
+			qdisc_notify(net, skb, n, classid, old, new, extack);
+			qdisc_destroy(old);
+
+			dev_graft_qdisc(dev_queue, new);
 		}
 
 skip:
@@ -1125,8 +1145,6 @@ skip:
 
 			if (new && new->ops->attach)
 				new->ops->attach(new);
-		} else {
-			notify_and_destroy(net, skb, n, classid, old, new, extack);
 		}
 
 		if (dev->flags & IFF_UP)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3248259eba32a..5d7e23f4cc0ee 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1046,7 +1046,7 @@ static void qdisc_free_cb(struct rcu_head *head)
 	qdisc_free(q);
 }
 
-static void qdisc_destroy(struct Qdisc *qdisc)
+static void __qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
 
@@ -1070,6 +1070,14 @@ static void qdisc_destroy(struct Qdisc *qdisc)
 	call_rcu(&qdisc->rcu, qdisc_free_cb);
 }
 
+void qdisc_destroy(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN)
+		return;
+
+	__qdisc_destroy(qdisc);
+}
+
 void qdisc_put(struct Qdisc *qdisc)
 {
 	if (!qdisc)
@@ -1079,7 +1087,7 @@ void qdisc_put(struct Qdisc *qdisc)
 	    !refcount_dec_and_test(&qdisc->refcnt))
 		return;
 
-	qdisc_destroy(qdisc);
+	__qdisc_destroy(qdisc);
 }
 EXPORT_SYMBOL(qdisc_put);
 
@@ -1094,7 +1102,7 @@ void qdisc_put_unlocked(struct Qdisc *qdisc)
 	    !refcount_dec_and_rtnl_lock(&qdisc->refcnt))
 		return;
 
-	qdisc_destroy(qdisc);
+	__qdisc_destroy(qdisc);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(qdisc_put_unlocked);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c6627f5abdfa2..717ae51d94a0a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -800,6 +800,9 @@ static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch,
 
 			taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]);
 
+			if (q->cur_txq[tc] >= dev->num_tx_queues)
+				q->cur_txq[tc] = first_txq;
+
 			if (skb)
 				return skb;
 		} while (q->cur_txq[tc] != first_txq);