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

Merge in late fixes to prepare for the 6.11 net-next PR.

Conflicts:
  93c3a96c30 ("net: pse-pd: Do not return EOPNOSUPP if config is null")
  4cddb0f15e ("net: ethtool: pse-pd: Fix possible null-deref")
  30d7b67277 ("net: ethtool: Add new power limit get and set features")
https://lore.kernel.org/20240715123204.623520bb@canb.auug.org.au/

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

drivers/net/netconsole.c

@@ -973,6 +973,7 @@ restart:
 				/* rtnl_lock already held
 				 * we might sleep in __netpoll_cleanup()
 				 */
+				nt->enabled = false;
 				spin_unlock_irqrestore(&target_list_lock, flags);
 
 				__netpoll_cleanup(&nt->np);
@@ -980,7 +981,6 @@ restart:
 				spin_lock_irqsave(&target_list_lock, flags);
 				netdev_put(nt->np.dev, &nt->np.dev_tracker);
 				nt->np.dev = NULL;
-				nt->enabled = false;
 				stopped = true;
 				netconsole_target_put(nt);
 				goto restart;

drivers/net/pse-pd/pse_core.c

@@ -832,13 +832,13 @@ int pse_ethtool_set_config(struct pse_control *psec,
 {
 	int err = 0;
 
-	if (pse_has_c33(psec)) {
+	if (pse_has_c33(psec) && config->c33_admin_control) {
 		err = pse_ethtool_c33_set_config(psec, config);
 		if (err)
 			return err;
 	}
 
-	if (pse_has_podl(psec))
+	if (pse_has_podl(psec) && config->podl_admin_control)
 		err = pse_ethtool_podl_set_config(psec, config);
 
 	return err;

include/net/ip6_route.h

@@ -127,18 +127,26 @@ void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
 
 static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i,
 				      const struct in6_addr *daddr,
-				      unsigned int prefs,
+				      unsigned int prefs, int l3mdev_index,
 				      struct in6_addr *saddr)
 {
+	struct net_device *l3mdev;
+	struct net_device *dev;
+	bool same_vrf;
 	int err = 0;
 
-	if (f6i && f6i->fib6_prefsrc.plen) {
+	rcu_read_lock();
-		*saddr = f6i->fib6_prefsrc.addr;
-	} else {
-		struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
 
-		err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr);
+	l3mdev = dev_get_by_index_rcu(net, l3mdev_index);
-	}
+	if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev)
+		dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
+	same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev;
+	if (f6i && f6i->fib6_prefsrc.plen && same_vrf)
+		*saddr = f6i->fib6_prefsrc.addr;
+	else
+		err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr);
+
+	rcu_read_unlock();
 
 	return err;
 }

include/net/xfrm.h

@@ -178,7 +178,10 @@ struct xfrm_state {
 		struct hlist_node	gclist;
 		struct hlist_node	bydst;
 	};
+	union {
+		struct hlist_node	dev_gclist;
 		struct hlist_node	bysrc;
+	};
 	struct hlist_node	byspi;
 	struct hlist_node	byseq;
 
@@ -1592,7 +1595,7 @@ void xfrm_state_update_stats(struct net *net);
 static inline void xfrm_dev_state_update_stats(struct xfrm_state *x)
 {
 	struct xfrm_dev_offload *xdo = &x->xso;
-	struct net_device *dev = xdo->dev;
+	struct net_device *dev = READ_ONCE(xdo->dev);
 
 	if (dev && dev->xfrmdev_ops &&
 	    dev->xfrmdev_ops->xdo_dev_state_update_stats)
@@ -1950,13 +1953,16 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
 			struct xfrm_user_offload *xuo, u8 dir,
 			struct netlink_ext_ack *extack);
 bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
+void xfrm_dev_state_delete(struct xfrm_state *x);
+void xfrm_dev_state_free(struct xfrm_state *x);
 
 static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x)
 {
 	struct xfrm_dev_offload *xso = &x->xso;
+	struct net_device *dev = READ_ONCE(xso->dev);
 
-	if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn)
+	if (dev && dev->xfrmdev_ops->xdo_dev_state_advance_esn)
-		xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x);
+		dev->xfrmdev_ops->xdo_dev_state_advance_esn(x);
 }
 
 static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
@@ -1977,28 +1983,6 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
 	return false;
 }
 
-static inline void xfrm_dev_state_delete(struct xfrm_state *x)
-{
-	struct xfrm_dev_offload *xso = &x->xso;
-
-	if (xso->dev)
-		xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
-}
-
-static inline void xfrm_dev_state_free(struct xfrm_state *x)
-{
-	struct xfrm_dev_offload *xso = &x->xso;
-	struct net_device *dev = xso->dev;
-
-	if (dev && dev->xfrmdev_ops) {
-		if (dev->xfrmdev_ops->xdo_dev_state_free)
-			dev->xfrmdev_ops->xdo_dev_state_free(x);
-		xso->dev = NULL;
-		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
-		netdev_put(dev, &xso->dev_tracker);
-	}
-}
-
 static inline void xfrm_dev_policy_delete(struct xfrm_policy *x)
 {
 	struct xfrm_dev_offload *xdo = &x->xdo;

net/bridge/br_forward.c

@@ -25,8 +25,8 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 	vg = nbp_vlan_group_rcu(p);
 	return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
-		p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
+		(br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) &&
-		nbp_switchdev_allowed_egress(p, skb) &&
+		br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) &&
 		!br_skb_isolated(p, skb);
 }
 

net/core/xdp.c

@@ -127,10 +127,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem)
 		return;
 
 	if (type == MEM_TYPE_PAGE_POOL) {
-		rcu_read_lock();
+		xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
 		page_pool_destroy(xa->page_pool);
-		rcu_read_unlock();
 	}
 }
 EXPORT_SYMBOL_GPL(xdp_unreg_mem_model);

net/ethtool/pse-pd.c

@@ -277,17 +277,21 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 	    tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) {
 		struct pse_control_config config = {};
 
-		if (pse_has_podl(phydev->psec))
+		if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL])
 			config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]);
-		if (pse_has_c33(phydev->psec))
+		if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL])
 			config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]);
 
+		/* pse_ethtool_set_config() will do nothing if the config
+		 * is zero
+		 */
 		ret = pse_ethtool_set_config(phydev->psec, info->extack,
 					     &config);
 		if (ret)
 			return ret;
 	}
 
+	/* Return errno or zero - PSE has no notification */
 	return ret;
 }
 

net/ipv4/esp4.c

@@ -239,8 +239,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
 #else
 static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
 {
-	kfree_skb(skb);
+	WARN_ON(1);
-
 	return -EOPNOTSUPP;
 }
 #endif

net/ipv4/esp4_offload.c

@@ -56,6 +56,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ip_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET);
+
+		if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
+			/* non-offload path will record the error and audit log */
+			xfrm_state_put(x);
+			x = NULL;
+		}
+
 		if (!x)
 			goto out_reset;
 

net/ipv4/fib_semantics.c

@@ -2269,6 +2269,15 @@ void fib_select_path(struct net *net, struct fib_result *res,
 		fib_select_default(fl4, res);
 
 check_saddr:
-	if (!fl4->saddr)
+	if (!fl4->saddr) {
+		struct net_device *l3mdev;
+
+		l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev);
+
+		if (!l3mdev ||
+		    l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev)
 			fl4->saddr = fib_result_prefsrc(net, res);
+		else
+			fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
+	}
 }

net/ipv6/addrconf.c

@@ -1873,7 +1873,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 							    master, &dst,
 							    scores, hiscore_idx);
 
-			if (scores[hiscore_idx].ifa)
+			if (scores[hiscore_idx].ifa &&
+			    scores[hiscore_idx].scopedist >= 0)
 				goto out;
 		}
 

net/ipv6/esp6.c

@@ -256,8 +256,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
 #else
 static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
 {
-	kfree_skb(skb);
+	WARN_ON(1);
-
 	return -EOPNOTSUPP;
 }
 #endif

net/ipv6/esp6_offload.c

@@ -83,6 +83,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET6);
+
+		if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
+			/* non-offload path will record the error and audit log */
+			xfrm_state_put(x);
+			x = NULL;
+		}
+
 		if (!x)
 			goto out_reset;
 

net/ipv6/ip6_output.c

@@ -1124,6 +1124,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		from = rt ? rcu_dereference(rt->from) : NULL;
 		err = ip6_route_get_saddr(net, from, &fl6->daddr,
 					  sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0,
+					  fl6->flowi6_l3mdev,
 					  &fl6->saddr);
 		rcu_read_unlock();
 

net/ipv6/route.c

@@ -5687,7 +5687,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				goto nla_put_failure;
 	} else if (dest) {
 		struct in6_addr saddr_buf;
-		if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
+		if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
 		    nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}

net/packet/af_packet.c

@@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po,
 	return packet_lookup_frame(po, rb, rb->head, status);
 }
 
+static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev)
+{
+	u8 *skb_orig_data = skb->data;
+	int skb_orig_len = skb->len;
+	struct vlan_hdr vhdr, *vh;
+	unsigned int header_len;
+
+	if (!dev)
+		return 0;
+
+	/* In the SOCK_DGRAM scenario, skb data starts at the network
+	 * protocol, which is after the VLAN headers. The outer VLAN
+	 * header is at the hard_header_len offset in non-variable
+	 * length link layer headers. If it's a VLAN device, the
+	 * min_header_len should be used to exclude the VLAN header
+	 * size.
+	 */
+	if (dev->min_header_len == dev->hard_header_len)
+		header_len = dev->hard_header_len;
+	else if (is_vlan_dev(dev))
+		header_len = dev->min_header_len;
+	else
+		return 0;
+
+	skb_push(skb, skb->data - skb_mac_header(skb));
+	vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr);
+	if (skb_orig_data != skb->data) {
+		skb->data = skb_orig_data;
+		skb->len = skb_orig_len;
+	}
+	if (unlikely(!vh))
+		return 0;
+
+	return ntohs(vh->h_vlan_TCI);
+}
+
+static __be16 vlan_get_protocol_dgram(struct sk_buff *skb)
+{
+	__be16 proto = skb->protocol;
+
+	if (unlikely(eth_type_vlan(proto))) {
+		u8 *skb_orig_data = skb->data;
+		int skb_orig_len = skb->len;
+
+		skb_push(skb, skb->data - skb_mac_header(skb));
+		proto = __vlan_get_protocol(skb, proto, NULL);
+		if (skb_orig_data != skb->data) {
+			skb->data = skb_orig_data;
+			skb->len = skb_orig_len;
+		}
+	}
+
+	return proto;
+}
+
 static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
 {
 	del_timer_sync(&pkc->retire_blk_timer);
@@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
 static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
+	struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc);
+
 	if (skb_vlan_tag_present(pkc->skb)) {
 		ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
 		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
 		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+	} else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) {
+		ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev);
+		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol);
+		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
 		ppd->hv1.tp_vlan_tci = 0;
 		ppd->hv1.tp_vlan_tpid = 0;
@@ -2427,6 +2488,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
 			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
 			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+		} else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
+			h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev);
+			h.h2->tp_vlan_tpid = ntohs(skb->protocol);
+			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			h.h2->tp_vlan_tci = 0;
 			h.h2->tp_vlan_tpid = 0;
@@ -2456,7 +2521,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
 	sll->sll_family = AF_PACKET;
 	sll->sll_hatype = dev->type;
-	sll->sll_protocol = skb->protocol;
+	sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ?
+		vlan_get_protocol_dgram(skb) : skb->protocol;
 	sll->sll_pkttype = skb->pkt_type;
 	if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
 		sll->sll_ifindex = orig_dev->ifindex;
@@ -3481,7 +3547,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		/* Original length was stored in sockaddr_ll fields */
 		origlen = PACKET_SKB_CB(skb)->sa.origlen;
 		sll->sll_family = AF_PACKET;
-		sll->sll_protocol = skb->protocol;
+		sll->sll_protocol = (sock->type == SOCK_DGRAM) ?
+			vlan_get_protocol_dgram(skb) : skb->protocol;
 	}
 
 	sock_recv_cmsgs(msg, sk, skb);
@@ -3538,6 +3605,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			aux.tp_vlan_tci = skb_vlan_tag_get(skb);
 			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
 			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+		} else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
+			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+			struct net_device *dev;
+
+			rcu_read_lock();
+			dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex);
+			if (dev) {
+				aux.tp_vlan_tci = vlan_get_tci(skb, dev);
+				aux.tp_vlan_tpid = ntohs(skb->protocol);
+				aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+			} else {
+				aux.tp_vlan_tci = 0;
+				aux.tp_vlan_tpid = 0;
+			}
+			rcu_read_unlock();
 		} else {
 			aux.tp_vlan_tci = 0;
 			aux.tp_vlan_tpid = 0;

net/xfrm/xfrm_input.c

@@ -475,11 +475,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 				      encap_type == UDP_ENCAP_ESPINUDP))) {
 		x = xfrm_input_state(skb);
 
-		if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR);
-			goto drop;
-		}
-
 		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
 			if (x->km.state == XFRM_STATE_ACQ)
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
@@ -586,8 +581,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		}
 
 		if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) {
+			secpath_reset(skb);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR);
+			xfrm_audit_state_notfound(skb, family, spi, seq);
 			xfrm_state_put(x);
+			x = NULL;
 			goto drop;
 		}
 

net/xfrm/xfrm_policy.c

@@ -452,6 +452,8 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
 
 static void xfrm_policy_kill(struct xfrm_policy *policy)
 {
+	xfrm_dev_policy_delete(policy);
+
 	write_lock_bh(&policy->lock);
 	policy->walk.dead = 1;
 	write_unlock_bh(&policy->lock);
@@ -1850,7 +1852,6 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -1891,7 +1892,6 @@ again:
 
 		__xfrm_policy_unlink(pol, dir);
 		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-		xfrm_dev_policy_delete(pol);
 		cnt++;
 		xfrm_audit_policy_delete(pol, 1, task_valid);
 		xfrm_policy_kill(pol);
@@ -2342,7 +2342,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 	pol = __xfrm_policy_unlink(pol, dir);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	if (pol) {
-		xfrm_dev_policy_delete(pol);
 		xfrm_policy_kill(pol);
 		return 0;
 	}

net/xfrm/xfrm_state.c

@@ -49,6 +49,7 @@ static struct kmem_cache *xfrm_state_cache __ro_after_init;
 
 static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
 static HLIST_HEAD(xfrm_state_gc_list);
+static HLIST_HEAD(xfrm_state_dev_gc_list);
 
 static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
 {
@@ -214,6 +215,7 @@ static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
 static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
 
 static DEFINE_SPINLOCK(xfrm_state_gc_lock);
+static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock);
 
 int __xfrm_state_delete(struct xfrm_state *x);
 
@@ -683,6 +685,41 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 }
 EXPORT_SYMBOL(xfrm_state_alloc);
 
+#ifdef CONFIG_XFRM_OFFLOAD
+void xfrm_dev_state_delete(struct xfrm_state *x)
+{
+	struct xfrm_dev_offload *xso = &x->xso;
+	struct net_device *dev = READ_ONCE(xso->dev);
+
+	if (dev) {
+		dev->xfrmdev_ops->xdo_dev_state_delete(x);
+		spin_lock_bh(&xfrm_state_dev_gc_lock);
+		hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list);
+		spin_unlock_bh(&xfrm_state_dev_gc_lock);
+	}
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_state_delete);
+
+void xfrm_dev_state_free(struct xfrm_state *x)
+{
+	struct xfrm_dev_offload *xso = &x->xso;
+	struct net_device *dev = READ_ONCE(xso->dev);
+
+	if (dev && dev->xfrmdev_ops) {
+		spin_lock_bh(&xfrm_state_dev_gc_lock);
+		if (!hlist_unhashed(&x->dev_gclist))
+			hlist_del(&x->dev_gclist);
+		spin_unlock_bh(&xfrm_state_dev_gc_lock);
+
+		if (dev->xfrmdev_ops->xdo_dev_state_free)
+			dev->xfrmdev_ops->xdo_dev_state_free(x);
+		WRITE_ONCE(xso->dev, NULL);
+		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+		netdev_put(dev, &xso->dev_tracker);
+	}
+}
+#endif
+
 void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
 {
 	WARN_ON(x->km.state != XFRM_STATE_DEAD);
@@ -849,6 +886,9 @@ EXPORT_SYMBOL(xfrm_state_flush);
 
 int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid)
 {
+	struct xfrm_state *x;
+	struct hlist_node *tmp;
+	struct xfrm_dev_offload *xso;
 	int i, err = 0, cnt = 0;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -858,8 +898,6 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
 
 	err = -ESRCH;
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
-		struct xfrm_state *x;
-		struct xfrm_dev_offload *xso;
 restart:
 		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
 			xso = &x->xso;
@@ -869,6 +907,8 @@ restart:
 				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 				err = xfrm_state_delete(x);
+				xfrm_dev_state_free(x);
+
 				xfrm_audit_state_delete(x, err ? 0 : 1,
 							task_valid);
 				xfrm_state_put(x);
@@ -885,6 +925,24 @@ restart:
 
 out:
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	spin_lock_bh(&xfrm_state_dev_gc_lock);
+restart_gc:
+	hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) {
+		xso = &x->xso;
+
+		if (xso->dev == dev) {
+			spin_unlock_bh(&xfrm_state_dev_gc_lock);
+			xfrm_dev_state_free(x);
+			spin_lock_bh(&xfrm_state_dev_gc_lock);
+			goto restart_gc;
+		}
+
+	}
+	spin_unlock_bh(&xfrm_state_dev_gc_lock);
+
+	xfrm_flush_gc();
+
 	return err;
 }
 EXPORT_SYMBOL(xfrm_dev_state_flush);
@@ -1274,8 +1332,7 @@ found:
 			xso->dev = xdo->dev;
 			xso->real_dev = xdo->real_dev;
 			xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
-			netdev_tracker_alloc(xso->dev, &xso->dev_tracker,
+			netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC);
-					     GFP_ATOMIC);
 			error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL);
 			if (error) {
 				xso->dir = 0;

net/xfrm/xfrm_user.c

@@ -2466,7 +2466,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 					    NETLINK_CB(skb).portid);
 		}
 	} else {
-		xfrm_dev_policy_delete(xp);
 		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err != 0)

tools/testing/selftests/net/forwarding/devlink_lib.sh

@@ -122,6 +122,8 @@ devlink_reload()
 	still_pending=$(devlink resource show "$DEVLINK_DEV" | \
 			grep -c "size_new")
 	check_err $still_pending "Failed reload - There are still unset sizes"
+
+	udevadm settle
 }
 
 declare -A DEVLINK_ORIG

tools/testing/selftests/net/vrf_route_leaking.sh

@@ -59,6 +59,7 @@
 # while it is forwarded between different vrfs.
 
 source lib.sh
+PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH
 VERBOSE=0
 PAUSE_ON_FAIL=no
 DEFAULT_TTYPE=sym
@@ -533,6 +534,86 @@ ipv6_ping_frag_asym()
 	ipv6_ping_frag asym
 }
 
+ipv4_ping_local()
+{
+	log_section "IPv4 (sym route): VRF ICMP local error route lookup ping"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd ip netns exec $r1 ip vrf exec blue ping -c1 -w1 ${H2_N2_IP}
+	log_test $? 0 "VRF ICMP local IPv4"
+}
+
+ipv4_tcp_local()
+{
+	log_section "IPv4 (sym route): VRF tcp local connection"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd nettest -s -O "$h2" -l ${H2_N2_IP} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -N "$r1" -d blue -r ${H2_N2_IP}
+	log_test $? 0 "VRF tcp local connection IPv4"
+}
+
+ipv4_udp_local()
+{
+	log_section "IPv4 (sym route): VRF udp local connection"
+
+	setup_sym
+
+	check_connectivity || return
+
+	run_cmd nettest -s -D -O "$h2" -l ${H2_N2_IP} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -D -N "$r1" -d blue -r ${H2_N2_IP}
+	log_test $? 0 "VRF udp local connection IPv4"
+}
+
+ipv6_ping_local()
+{
+	log_section "IPv6 (sym route): VRF ICMP local error route lookup ping"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd ip netns exec $r1 ip vrf exec blue ${ping6} -c1 -w1 ${H2_N2_IP6}
+	log_test $? 0 "VRF ICMP local IPv6"
+}
+
+ipv6_tcp_local()
+{
+	log_section "IPv6 (sym route): VRF tcp local connection"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd nettest -s -6 -O "$h2" -l ${H2_N2_IP6} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -6 -N "$r1" -d blue -r ${H2_N2_IP6}
+	log_test $? 0 "VRF tcp local connection IPv6"
+}
+
+ipv6_udp_local()
+{
+	log_section "IPv6 (sym route): VRF udp local connection"
+
+	setup_sym
+
+	check_connectivity6 || return
+
+	run_cmd nettest -s -6 -D -O "$h2" -l ${H2_N2_IP6} -I eth0 -3 eth0 &
+	sleep 1
+	run_cmd nettest -6 -D -N "$r1" -d blue -r ${H2_N2_IP6}
+	log_test $? 0 "VRF udp local connection IPv6"
+}
+
 ################################################################################
 # usage
 
@@ -555,8 +636,10 @@ EOF
 # Some systems don't have a ping6 binary anymore
 command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping)
 
-TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_ttl_asym ipv4_traceroute_asym"
+TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local
-TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_ttl_asym ipv6_traceroute_asym"
+ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym"
+TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local
+ipv6_ping_ttl_asym ipv6_traceroute_asym"
 
 ret=0
 nsuccess=0
@@ -594,12 +677,18 @@ do
 	ipv4_traceroute|traceroute)      ipv4_traceroute;;&
 	ipv4_traceroute_asym|traceroute) ipv4_traceroute_asym;;&
 	ipv4_ping_frag|ping)             ipv4_ping_frag;;&
+	ipv4_ping_local|ping)            ipv4_ping_local;;&
+	ipv4_tcp_local)                  ipv4_tcp_local;;&
+	ipv4_udp_local)                  ipv4_udp_local;;&
 
 	ipv6_ping_ttl|ping)              ipv6_ping_ttl;;&
 	ipv6_ping_ttl_asym|ping)         ipv6_ping_ttl_asym;;&
 	ipv6_traceroute|traceroute)      ipv6_traceroute;;&
 	ipv6_traceroute_asym|traceroute) ipv6_traceroute_asym;;&
 	ipv6_ping_frag|ping)             ipv6_ping_frag;;&
+	ipv6_ping_local|ping)            ipv6_ping_local;;&
+	ipv6_tcp_local)                  ipv6_tcp_local;;&
+	ipv6_udp_local)                  ipv6_udp_local;;&
 
 	# setup namespaces and config, but do not run any tests
 	setup_sym|setup)                 setup_sym; exit 0;;