21 files changed, 261 insertions, 102 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6926d0ca6c71..747bba0a584a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2225,7 +2225,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		padding = true;
 		goto skip_init_addrs;
 	}
-	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
+	addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
 		goto out_addrs;
@@ -2317,7 +2317,7 @@ out_image:
 		if (image)
 			bpf_prog_fill_jited_linfo(prog, addrs + 1);
 out_addrs:
-		kfree(addrs);
+		kvfree(addrs);
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index f277df922fcd..4dedd6e0b11b 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -114,7 +114,10 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
 		reg |= (MII_SW_OR | LINK_STS);
-		reg &= ~GMII_SPEED_UP_2G;
+		if (priv->type == BCM4908_DEVICE_ID)
+			reg |= GMII_SPEED_UP_2G;
+		else
+			reg &= ~GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index d1e4d42e497d..3712e1786091 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1544,8 +1544,8 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	clk_disable_unprepare(pep->clk);
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
-	unregister_netdev(dev);
 	cancel_work_sync(&pep->tx_timeout_task);
+	unregister_netdev(dev);
 	free_netdev(dev);
 	return 0;
 }
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index aa1a66ad2ce5..34e49c75db42 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -302,8 +302,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (rxq < rcv->real_num_rx_queues) {
 		rq = &rcv_priv->rq[rxq];
 		rcv_xdp = rcu_access_pointer(rq->xdp_prog);
-		if (rcv_xdp)
-			skb_record_rx_queue(skb, rxq);
+		skb_record_rx_queue(skb, rxq);
 	}
 
 	skb_tx_timestamp(skb);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cccaef1088ea..d7e0f479a5b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1093,7 +1093,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		_ret;							\
 	 })
 
-#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage)	\
 	({						\
 		struct bpf_prog_array_item *_item;	\
 		struct bpf_prog *_prog;			\
@@ -1106,7 +1106,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			goto _out;			\
 		_item = &_array->items[0];		\
 		while ((_prog = READ_ONCE(_item->prog))) {		\
-			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			if (set_cg_storage)		\
+				bpf_cgroup_storage_set(_item->cgroup_storage);	\
 			_ret &= func(_prog, ctx);	\
 			_item++;			\
 		}					\
@@ -1153,10 +1154,10 @@ _out:							\
 	})
 
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, false, true)
 
 #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, true, false)
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 96556c64c95d..10c94a3936ca 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -43,13 +43,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 	if (likely(success)) {
 		struct vlan_pcpu_stats *pcpu_stats;
 
-		pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
+		pcpu_stats = get_cpu_ptr(vlan->pcpu_stats);
 		u64_stats_update_begin(&pcpu_stats->syncp);
 		pcpu_stats->rx_packets++;
 		pcpu_stats->rx_bytes += len;
 		if (multicast)
 			pcpu_stats->rx_multicast++;
 		u64_stats_update_end(&pcpu_stats->syncp);
+		put_cpu_ptr(vlan->pcpu_stats);
 	} else {
 		this_cpu_inc(vlan->pcpu_stats->rx_errors);
 	}
diff --git a/include/net/dst.h b/include/net/dst.h
index 26f134ad3a25..75b1e734e9c2 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -550,4 +550,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 }
 
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu, bool confirm_neigh);
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb);
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old);
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr);
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst);
+
 #endif /* _NET_DST_H */
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 7bc057aee40b..a10a319d7eb2 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -410,6 +410,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel)
 int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 		       struct netlink_ext_ack *extack);
 
+/* Caller should either hold rcu_read_lock(), or RTNL. */
 static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 {
 	struct nh_info *nhi;
@@ -430,6 +431,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 	return NULL;
 }
 
+/* Variant of nexthop_fib6_nh().
+ * Caller should either hold rcu_read_lock_bh(), or RTNL.
+ */
+static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp);
+		nh = nexthop_mpath_select(nh_grp, 0);
+		if (!nh)
+			return NULL;
+	}
+
+	nhi = rcu_dereference_bh_rtnl(nh->nh_info);
+	if (nhi->family == AF_INET6)
+		return &nhi->fib6_nh;
+
+	return NULL;
+}
+
 static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i)
 {
 	struct fib6_nh *fib6_nh;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 79c893310492..4ba4ef0ff63a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3850,7 +3850,7 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
- *		Check ctx packet size against exceeding MTU of net device (based
+ *		Check packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
  *
@@ -3867,6 +3867,14 @@ union bpf_attr {
  *		against the current net device.  This is practical if this isn't
  *		used prior to redirect.
  *
+ *		On input *mtu_len* must be a valid pointer, else verifier will
+ *		reject BPF program.  If the value *mtu_len* is initialized to
+ *		zero then the ctx packet size is use.  When value *mtu_len* is
+ *		provided as input this specify the L3 length that the MTU check
+ *		is done against. Remember XDP and TC length operate at L2, but
+ *		this value is L3 as this correlate to MTU and IP-header tot_len
+ *		values which are L3 (similar behavior as bpf_fib_lookup).
+ *
  *		The Linux kernel route table can configure MTUs on a more
  *		specific per route level, which is not provided by this helper.
  *		For route level MTU checks use the **bpf_fib_lookup**\ ()
@@ -3891,11 +3899,9 @@ union bpf_attr {
  *
  *		On return *mtu_len* pointer contains the MTU value of the net
  *		device.  Remember the net device configured MTU is the L3 size,
- *		which is returned here and XDP and TX length operate at L2.
+ *		which is returned here and XDP and TC length operate at L2.
  *		Helper take this into account for you, but remember when using
- *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
- *		pointer and be initialized (to zero), else verifier will reject
- *		BPF program.
+ *		MTU value in your BPF-code.
  *
  *	Return
  *		* 0 on success, and populate MTU value in *mtu_len* pointer.
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 6639640523c0..b58b2efb9b43 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -109,7 +109,7 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	f = fget_raw(fd);
 	if (!f)
-		return NULL;
+		return ERR_PTR(-EBADF);
 
 	sdata = inode_storage_lookup(f->f_inode, map, true);
 	fput(f);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c859bc46d06c..250503482cda 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -854,6 +854,11 @@ static int map_create(union bpf_attr *attr)
 			err = PTR_ERR(btf);
 			goto free_map;
 		}
+		if (btf_is_kernel(btf)) {
+			btf_put(btf);
+			err = -EACCES;
+			goto free_map;
+		}
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c56e3fcb5f1a..4192a9e56654 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9056,6 +9056,10 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
 		return PTR_ERR(btf);
+	if (btf_is_kernel(btf)) {
+		btf_put(btf);
+		return -EACCES;
+	}
 	env->prog->aux->btf = btf;
 
 	err = check_btf_func(env, attr, uattr);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 571f191c06d9..db65ce62b625 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 	return 0;
 
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&hw_data->send_timer);
+		cancel_work_sync(&hw_data->dm_alert_work);
+		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+			struct devlink_trap_metadata *hw_metadata;
+
+			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+			net_dm_hw_metadata_free(hw_metadata);
+			consume_skb(skb);
+		}
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
@@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
 err_unregister_trace:
 	unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		while ((skb = __skb_dequeue(&data->drop_queue)))
+			consume_skb(skb);
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
diff --git a/net/core/dst.c b/net/core/dst.c
index 0c01bd8d9d81..fb3bcba87744 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-static struct dst_ops md_dst_ops = {
-	.family =		AF_UNSPEC,
-};
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
 
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
-	WARN_ONCE(1, "Attempting to call output on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
 }
 
-static int dst_md_discard(struct sk_buff *skb)
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr)
 {
-	WARN_ONCE(1, "Attempting to call input on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
+static struct dst_ops dst_blackhole_ops = {
+	.family		= AF_UNSPEC,
+	.neigh_lookup	= dst_blackhole_neigh_lookup,
+	.check		= dst_blackhole_check,
+	.cow_metrics	= dst_blackhole_cow_metrics,
+	.update_pmtu	= dst_blackhole_update_pmtu,
+	.redirect	= dst_blackhole_redirect,
+	.mtu		= dst_blackhole_mtu,
+};
 
 static void __metadata_dst_init(struct metadata_dst *md_dst,
 				enum metadata_type type, u8 optslen)
-
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
-	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+	dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
 		 DST_METADATA | DST_NOCOUNT);
-
-	dst->input = dst_md_discard;
-	dst->output = dst_md_discard_out;
-
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
 	md_dst->type = type;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index adfdad234674..9323d34d34cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5658,7 +5658,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
 		return -EINVAL;
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
 		return -EINVAL;
 
 	dev = __dev_via_ifindex(dev, ifindex);
@@ -5668,7 +5668,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	mtu = READ_ONCE(dev->mtu);
 
 	dev_len = mtu + dev->hard_header_len;
-	skb_len = skb->len + len_diff; /* minus result pass check */
+
+	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+	skb_len += len_diff; /* minus result pass check */
 	if (skb_len <= dev_len) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
 		goto out;
@@ -5713,6 +5717,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
+	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	if (*mtu_len)
+		xdp_len = *mtu_len + dev->hard_header_len;
+
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02d81d79deeb..bba150fdd265 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2687,44 +2687,15 @@ out:
 	return rth;
 }
 
-static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
-{
-	return NULL;
-}
-
-static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
-{
-	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
-	return mtu ? : dst->dev->mtu;
-}
-
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu,
-					  bool confirm_neigh)
-{
-}
-
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
-				       struct sk_buff *skb)
-{
-}
-
-static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
-					  unsigned long old)
-{
-	return NULL;
-}
-
 static struct dst_ops ipv4_dst_blackhole_ops = {
-	.family			=	AF_INET,
-	.check			=	ipv4_blackhole_dst_check,
-	.mtu			=	ipv4_blackhole_mtu,
-	.default_advmss		=	ipv4_default_advmss,
-	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
-	.redirect		=	ipv4_rt_blackhole_redirect,
-	.cow_metrics		=	ipv4_rt_blackhole_cow_metrics,
-	.neigh_lookup		=	ipv4_neigh_lookup,
+	.family			= AF_INET,
+	.default_advmss		= ipv4_default_advmss,
+	.neigh_lookup		= ipv4_neigh_lookup,
+	.check			= dst_blackhole_check,
+	.cow_metrics		= dst_blackhole_cow_metrics,
+	.update_pmtu		= dst_blackhole_update_pmtu,
+	.redirect		= dst_blackhole_redirect,
+	.mtu			= dst_blackhole_mtu,
 };
 
 struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef9d022e693f..679699e953f1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2486,7 +2486,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v)
 	const struct net_device *dev;
 
 	if (rt->nh)
-		fib6_nh = nexthop_fib6_nh(rt->nh);
+		fib6_nh = nexthop_fib6_nh_bh(rt->nh);
 
 	seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1536f4948e86..1056b0229ffd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -260,34 +260,16 @@ static struct dst_ops ip6_dst_ops_template = {
 	.confirm_neigh		=	ip6_confirm_neigh,
 };
 
-static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
-{
-	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
-	return mtu ? : dst->dev->mtu;
-}
-
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu,
-					 bool confirm_neigh)
-{
-}
-
-static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
-				      struct sk_buff *skb)
-{
-}
-
 static struct dst_ops ip6_dst_blackhole_ops = {
-	.family			=	AF_INET6,
-	.destroy		=	ip6_dst_destroy,
-	.check			=	ip6_dst_check,
-	.mtu			=	ip6_blackhole_mtu,
-	.default_advmss		=	ip6_default_advmss,
-	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
-	.redirect		=	ip6_rt_blackhole_redirect,
-	.cow_metrics		=	dst_cow_metrics_generic,
-	.neigh_lookup		=	ip6_dst_neigh_lookup,
+	.family			= AF_INET6,
+	.default_advmss		= ip6_default_advmss,
+	.neigh_lookup		= ip6_dst_neigh_lookup,
+	.check			= ip6_dst_check,
+	.destroy		= ip6_dst_destroy,
+	.cow_metrics		= dst_cow_metrics_generic,
+	.update_pmtu		= dst_blackhole_update_pmtu,
+	.redirect		= dst_blackhole_redirect,
+	.mtu			= dst_blackhole_mtu,
 };
 
 static const u32 ip6_template_metrics[RTAX_MAX] = {
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 887a494ad5fc..e9eb6a6e80d2 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -215,7 +215,7 @@ define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
 	fi;						\
-	$(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
 install_lib: all_cmd
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 36af1c138faf..b62a39315336 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -128,6 +128,8 @@ static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu);
 
 cleanup:
 	test_check_mtu__destroy(skel);
@@ -187,6 +189,8 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
 cleanup:
 	test_check_mtu__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index b7787b43f9db..c4a9bae96e75 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -105,6 +105,54 @@ int xdp_minus_delta(struct xdp_md *ctx)
 	return retval;
 }
 
+SEC("xdp")
+int xdp_input_len(struct xdp_md *ctx)
+{
+	int retval = XDP_PASS; /* Expected retval on successful test */
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	__u32 data_len = data_end - data;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input len is L3, like MTU and iph->tot_len.
+	 * Remember XDP data_len is L2.
+	 */
+	__u32 mtu_len = data_len - ETH_HLEN;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = XDP_ABORTED;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("xdp")
+int xdp_input_len_exceed(struct xdp_md *ctx)
+{
+	int retval = XDP_ABORTED; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = XDP_PASS ; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
 SEC("classifier")
 int tc_use_helper(struct __sk_buff *ctx)
 {
@@ -196,3 +244,47 @@ int tc_minus_delta(struct __sk_buff *ctx)
 	global_bpf_mtu_xdp = mtu_len;
 	return retval;
 }
+
+SEC("classifier")
+int tc_input_len(struct __sk_buff *ctx)
+{
+	int retval = BPF_OK; /* Expected retval on successful test */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = BPF_DROP;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("classifier")
+int tc_input_len_exceed(struct __sk_buff *ctx)
+{
+	int retval = BPF_DROP; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = BPF_OK; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}