Merge branch 'xdp: hints via kfuncs'

Stanislav Fomichev says:

====================

Please see the first patch in the series for the overall
design and use-cases.

See the following email from Toke for the per-packet metadata overhead:
https://lore.kernel.org/bpf/20221206024554.3826186-1-sdf@google.com/T/#m49d48ea08d525ec88360c7d14c4d34fb0e45e798

Recent changes:
- Keep new functions in en/xdp.c, do 'extern mlx5_xdp_metadata_ops' (Tariq)

- Remove mxbuf pointer and use xsk_buff_to_mxbuf (Tariq)

- Clarify xdp_buff vs 'XDP frame' (Jesper)

- Explicitly mention that AF_XDP RX descriptor lacks metadata size (Jesper)

- Drop libbpf_flags/xdp_flags from selftests and use ifindex instead
  of ifname (due to recent xsk.h refactoring)

Prior art (to record pros/cons for different approaches):

- Stable UAPI approach:
  https://lore.kernel.org/bpf/20220628194812.1453059-1-alexandr.lobakin@intel.com/
- Metadata+BTF_ID appoach:
  https://lore.kernel.org/bpf/166256538687.1434226.15760041133601409770.stgit@firesoul/
- v7:
  https://lore.kernel.org/bpf/20230112003230.3779451-1-sdf@google.com/
- v6:
  https://lore.kernel.org/bpf/20230104215949.529093-1-sdf@google.com/
- v5:
  https://lore.kernel.org/bpf/20221220222043.3348718-1-sdf@google.com/
- v4:
  https://lore.kernel.org/bpf/20221213023605.737383-1-sdf@google.com/
- v3:
  https://lore.kernel.org/bpf/20221206024554.3826186-1-sdf@google.com/
- v2:
  https://lore.kernel.org/bpf/20221121182552.2152891-1-sdf@google.com/
- v1:
  https://lore.kernel.org/bpf/20221115030210.3159213-1-sdf@google.com/
- kfuncs v2 RFC:
  https://lore.kernel.org/bpf/20221027200019.4106375-1-sdf@google.com/
- kfuncs v1 RFC:
  https://lore.kernel.org/bpf/20221104032532.1615099-1-sdf@google.com/

Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org

Stanislav Fomichev (13):
  bpf: Document XDP RX metadata
  bpf: Rename bpf_{prog,map}_is_dev_bound to is_offloaded
  bpf: Move offload initialization into late_initcall
  bpf: Reshuffle some parts of bpf/offload.c
  bpf: Introduce device-bound XDP programs
  selftests/bpf: Update expected test_offload.py messages
  bpf: XDP metadata RX kfuncs
  veth: Introduce veth_xdp_buff wrapper for xdp_buff
  veth: Support RX XDP metadata
  selftests/bpf: Verify xdp_metadata xdp->af_xdp path
  net/mlx4_en: Introduce wrapper for xdp_buff
  net/mlx4_en: Support RX XDP metadata
  selftests/bpf: Simple program to dump XDP RX metadata
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

4 files changed, 351 insertions, 164 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ba3fff17e2f9..16da51093aff 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2096,6 +2096,14 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
 	if (fp->kprobe_override)
 		return false;
 
+	/* XDP programs inserted into maps are not guaranteed to run on
+	 * a particular netdev (and can run outside driver context entirely
+	 * in the case of devmap and cpumap). Until device checks
+	 * are implemented, prohibit adding dev-bound programs to program maps.
+	 */
+	if (bpf_prog_is_dev_bound(fp->aux))
+		return false;
+
 	spin_lock(&map->owner.lock);
 	if (!map->owner.type) {
 		/* There's no owner yet where we could check for
@@ -2182,7 +2190,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	 * valid program, which in this case would simply not
 	 * be JITed, but falls back to the interpreter.
 	 */
-	if (!bpf_prog_is_dev_bound(fp->aux)) {
+	if (!bpf_prog_is_offloaded(fp->aux)) {
 		*err = bpf_prog_alloc_jited_linfo(fp);
 		if (*err)
 			return fp;
@@ -2554,7 +2562,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	bpf_free_used_maps(aux);
 	bpf_free_used_btfs(aux);
 	if (bpf_prog_is_dev_bound(aux))
-		bpf_prog_offload_destroy(aux->prog);
+		bpf_prog_dev_bound_destroy(aux->prog);
 #ifdef CONFIG_PERF_EVENTS
 	if (aux->prog->has_callchain_buf)
 		put_callchain_buffers();
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 13e4efc971e6..e87cab2ed710 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -41,7 +41,7 @@ struct bpf_offload_dev {
 struct bpf_offload_netdev {
 	struct rhash_head l;
 	struct net_device *netdev;
-	struct bpf_offload_dev *offdev;
+	struct bpf_offload_dev *offdev; /* NULL when bound-only */
 	struct list_head progs;
 	struct list_head maps;
 	struct list_head offdev_netdevs;
@@ -56,7 +56,6 @@ static const struct rhashtable_params offdevs_params = {
 };
 
 static struct rhashtable offdevs;
-static bool offdevs_inited;
 
 static int bpf_dev_offload_check(struct net_device *netdev)
 {
@@ -72,58 +71,221 @@ bpf_offload_find_netdev(struct net_device *netdev)
 {
 	lockdep_assert_held(&bpf_devs_lock);
 
-	if (!offdevs_inited)
-		return NULL;
 	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
 }
 
-int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
+static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+					     struct net_device *netdev)
 {
 	struct bpf_offload_netdev *ondev;
-	struct bpf_prog_offload *offload;
 	int err;
 
-	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
-	    attr->prog_type != BPF_PROG_TYPE_XDP)
-		return -EINVAL;
+	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+	if (!ondev)
+		return -ENOMEM;
 
-	if (attr->prog_flags)
-		return -EINVAL;
+	ondev->netdev = netdev;
+	ondev->offdev = offdev;
+	INIT_LIST_HEAD(&ondev->progs);
+	INIT_LIST_HEAD(&ondev->maps);
+
+	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+	if (err) {
+		netdev_warn(netdev, "failed to register for BPF offload\n");
+		goto err_free;
+	}
+
+	if (offdev)
+		list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+	return 0;
+
+err_free:
+	kfree(ondev);
+	return err;
+}
+
+static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	struct bpf_prog_offload *offload = prog->aux->offload;
+
+	if (offload->dev_state)
+		offload->offdev->ops->destroy(prog);
+
+	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
+	bpf_prog_free_id(prog, true);
+
+	list_del_init(&offload->offloads);
+	kfree(offload);
+	prog->aux->offload = NULL;
+}
+
+static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
+			       enum bpf_netdev_command cmd)
+{
+	struct netdev_bpf data = {};
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	data.command = cmd;
+	data.offmap = offmap;
+	/* Caller must make sure netdev is valid */
+	netdev = offmap->netdev;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, &data);
+}
+
+static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
+{
+	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
+	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
+	bpf_map_free_id(&offmap->map, true);
+	list_del_init(&offmap->offloads);
+	offmap->netdev = NULL;
+}
+
+static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+						struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev, *altdev = NULL;
+	struct bpf_offloaded_map *offmap, *mtmp;
+	struct bpf_prog_offload *offload, *ptmp;
+
+	ASSERT_RTNL();
+
+	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+	if (WARN_ON(!ondev))
+		return;
+
+	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+
+	/* Try to move the objects to another netdev of the device */
+	if (offdev) {
+		list_del(&ondev->offdev_netdevs);
+		altdev = list_first_entry_or_null(&offdev->netdevs,
+						  struct bpf_offload_netdev,
+						  offdev_netdevs);
+	}
+
+	if (altdev) {
+		list_for_each_entry(offload, &ondev->progs, offloads)
+			offload->netdev = altdev->netdev;
+		list_splice_init(&ondev->progs, &altdev->progs);
+
+		list_for_each_entry(offmap, &ondev->maps, offloads)
+			offmap->netdev = altdev->netdev;
+		list_splice_init(&ondev->maps, &altdev->maps);
+	} else {
+		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+			__bpf_prog_offload_destroy(offload->prog);
+		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+			__bpf_map_offload_destroy(offmap);
+	}
+
+	WARN_ON(!list_empty(&ondev->progs));
+	WARN_ON(!list_empty(&ondev->maps));
+	kfree(ondev);
+}
+
+static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev;
+	struct bpf_prog_offload *offload;
+	int err;
 
 	offload = kzalloc(sizeof(*offload), GFP_USER);
 	if (!offload)
 		return -ENOMEM;
 
 	offload->prog = prog;
+	offload->netdev = netdev;
 
-	offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
-					   attr->prog_ifindex);
-	err = bpf_dev_offload_check(offload->netdev);
-	if (err)
-		goto err_maybe_put;
-
-	down_write(&bpf_devs_lock);
 	ondev = bpf_offload_find_netdev(offload->netdev);
 	if (!ondev) {
-		err = -EINVAL;
-		goto err_unlock;
+		if (bpf_prog_is_offloaded(prog->aux)) {
+			err = -EINVAL;
+			goto err_free;
+		}
+
+		/* When only binding to the device, explicitly
+		 * create an entry in the hashtable.
+		 */
+		err = __bpf_offload_dev_netdev_register(NULL, offload->netdev);
+		if (err)
+			goto err_free;
+		ondev = bpf_offload_find_netdev(offload->netdev);
 	}
 	offload->offdev = ondev->offdev;
 	prog->aux->offload = offload;
 	list_add_tail(&offload->offloads, &ondev->progs);
-	dev_put(offload->netdev);
-	up_write(&bpf_devs_lock);
 
 	return 0;
-err_unlock:
-	up_write(&bpf_devs_lock);
-err_maybe_put:
-	if (offload->netdev)
-		dev_put(offload->netdev);
+err_free:
 	kfree(offload);
 	return err;
 }
 
+int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
+{
+	struct net_device *netdev;
+	int err;
+
+	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_type != BPF_PROG_TYPE_XDP)
+		return -EINVAL;
+
+	if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY)
+		return -EINVAL;
+
+	if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY)
+		return -EINVAL;
+
+	netdev = dev_get_by_index(current->nsproxy->net_ns, attr->prog_ifindex);
+	if (!netdev)
+		return -EINVAL;
+
+	err = bpf_dev_offload_check(netdev);
+	if (err)
+		goto out;
+
+	prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY);
+
+	down_write(&bpf_devs_lock);
+	err = __bpf_prog_dev_bound_init(prog, netdev);
+	up_write(&bpf_devs_lock);
+
+out:
+	dev_put(netdev);
+	return err;
+}
+
+int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog)
+{
+	int err;
+
+	if (!bpf_prog_is_dev_bound(old_prog->aux))
+		return 0;
+
+	if (bpf_prog_is_offloaded(old_prog->aux))
+		return -EINVAL;
+
+	new_prog->aux->dev_bound = old_prog->aux->dev_bound;
+	new_prog->aux->offload_requested = old_prog->aux->offload_requested;
+
+	down_write(&bpf_devs_lock);
+	if (!old_prog->aux->offload) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = __bpf_prog_dev_bound_init(new_prog, old_prog->aux->offload->netdev);
+
+out:
+	up_write(&bpf_devs_lock);
+	return err;
+}
+
 int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload;
@@ -209,27 +371,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
 	up_read(&bpf_devs_lock);
 }
 
-static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+void bpf_prog_dev_bound_destroy(struct bpf_prog *prog)
 {
-	struct bpf_prog_offload *offload = prog->aux->offload;
-
-	if (offload->dev_state)
-		offload->offdev->ops->destroy(prog);
-
-	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
-	bpf_prog_free_id(prog, true);
-
-	list_del_init(&offload->offloads);
-	kfree(offload);
-	prog->aux->offload = NULL;
-}
+	struct bpf_offload_netdev *ondev;
+	struct net_device *netdev;
 
-void bpf_prog_offload_destroy(struct bpf_prog *prog)
-{
+	rtnl_lock();
 	down_write(&bpf_devs_lock);
-	if (prog->aux->offload)
+	if (prog->aux->offload) {
+		list_del_init(&prog->aux->offload->offloads);
+
+		netdev = prog->aux->offload->netdev;
 		__bpf_prog_offload_destroy(prog);
+
+		ondev = bpf_offload_find_netdev(netdev);
+		if (!ondev->offdev && list_empty(&ondev->progs))
+			__bpf_offload_dev_netdev_unregister(NULL, netdev);
+	}
 	up_write(&bpf_devs_lock);
+	rtnl_unlock();
 }
 
 static int bpf_prog_offload_translate(struct bpf_prog *prog)
@@ -343,22 +503,6 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 const struct bpf_prog_ops bpf_offload_prog_ops = {
 };
 
-static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
-			       enum bpf_netdev_command cmd)
-{
-	struct netdev_bpf data = {};
-	struct net_device *netdev;
-
-	ASSERT_RTNL();
-
-	data.command = cmd;
-	data.offmap = offmap;
-	/* Caller must make sure netdev is valid */
-	netdev = offmap->netdev;
-
-	return netdev->netdev_ops->ndo_bpf(netdev, &data);
-}
-
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -408,15 +552,6 @@ err_unlock:
 	return ERR_PTR(err);
 }
 
-static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
-{
-	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
-	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
-	bpf_map_free_id(&offmap->map, true);
-	list_del_init(&offmap->offloads);
-	offmap->netdev = NULL;
-}
-
 void bpf_map_offload_map_free(struct bpf_map *map)
 {
 	struct bpf_offloaded_map *offmap = map_to_offmap(map);
@@ -576,12 +711,28 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
 
+bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs)
+{
+	bool ret;
+
+	if (bpf_prog_is_offloaded(lhs->aux) != bpf_prog_is_offloaded(rhs->aux))
+		return false;
+
+	down_read(&bpf_devs_lock);
+	ret = lhs->aux->offload && rhs->aux->offload &&
+	      lhs->aux->offload->netdev &&
+	      lhs->aux->offload->netdev == rhs->aux->offload->netdev;
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 {
 	struct bpf_offloaded_map *offmap;
 	bool ret;
 
-	if (!bpf_map_is_dev_bound(map))
+	if (!bpf_map_is_offloaded(map))
 		return bpf_map_offload_neutral(map);
 	offmap = map_to_offmap(map);
 
@@ -595,32 +746,11 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
 				    struct net_device *netdev)
 {
-	struct bpf_offload_netdev *ondev;
 	int err;
 
-	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
-	if (!ondev)
-		return -ENOMEM;
-
-	ondev->netdev = netdev;
-	ondev->offdev = offdev;
-	INIT_LIST_HEAD(&ondev->progs);
-	INIT_LIST_HEAD(&ondev->maps);
-
 	down_write(&bpf_devs_lock);
-	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
-	if (err) {
-		netdev_warn(netdev, "failed to register for BPF offload\n");
-		goto err_unlock_free;
-	}
-
-	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
-	up_write(&bpf_devs_lock);
-	return 0;
-
-err_unlock_free:
+	err = __bpf_offload_dev_netdev_register(offdev, netdev);
 	up_write(&bpf_devs_lock);
-	kfree(ondev);
 	return err;
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
@@ -628,43 +758,8 @@ EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
 void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
 				       struct net_device *netdev)
 {
-	struct bpf_offload_netdev *ondev, *altdev;
-	struct bpf_offloaded_map *offmap, *mtmp;
-	struct bpf_prog_offload *offload, *ptmp;
-
-	ASSERT_RTNL();
-
 	down_write(&bpf_devs_lock);
-	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
-	if (WARN_ON(!ondev))
-		goto unlock;
-
-	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
-	list_del(&ondev->offdev_netdevs);
-
-	/* Try to move the objects to another netdev of the device */
-	altdev = list_first_entry_or_null(&offdev->netdevs,
-					  struct bpf_offload_netdev,
-					  offdev_netdevs);
-	if (altdev) {
-		list_for_each_entry(offload, &ondev->progs, offloads)
-			offload->netdev = altdev->netdev;
-		list_splice_init(&ondev->progs, &altdev->progs);
-
-		list_for_each_entry(offmap, &ondev->maps, offloads)
-			offmap->netdev = altdev->netdev;
-		list_splice_init(&ondev->maps, &altdev->maps);
-	} else {
-		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
-			__bpf_prog_offload_destroy(offload->prog);
-		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
-			__bpf_map_offload_destroy(offmap);
-	}
-
-	WARN_ON(!list_empty(&ondev->progs));
-	WARN_ON(!list_empty(&ondev->maps));
-	kfree(ondev);
-unlock:
+	__bpf_offload_dev_netdev_unregister(offdev, netdev);
 	up_write(&bpf_devs_lock);
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
@@ -673,18 +768,6 @@ struct bpf_offload_dev *
 bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv)
 {
 	struct bpf_offload_dev *offdev;
-	int err;
-
-	down_write(&bpf_devs_lock);
-	if (!offdevs_inited) {
-		err = rhashtable_init(&offdevs, &offdevs_params);
-		if (err) {
-			up_write(&bpf_devs_lock);
-			return ERR_PTR(err);
-		}
-		offdevs_inited = true;
-	}
-	up_write(&bpf_devs_lock);
 
 	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
 	if (!offdev)
@@ -710,3 +793,67 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev)
 	return offdev->priv;
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_priv);
+
+void bpf_dev_bound_netdev_unregister(struct net_device *dev)
+{
+	struct bpf_offload_netdev *ondev;
+
+	ASSERT_RTNL();
+
+	down_write(&bpf_devs_lock);
+	ondev = bpf_offload_find_netdev(dev);
+	if (ondev && !ondev->offdev)
+		__bpf_offload_dev_netdev_unregister(NULL, ondev->netdev);
+	up_write(&bpf_devs_lock);
+}
+
+int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
+			      struct bpf_prog_aux *prog_aux)
+{
+	if (!bpf_prog_is_dev_bound(prog_aux)) {
+		bpf_log(log, "metadata kfuncs require device-bound program\n");
+		return -EINVAL;
+	}
+
+	if (bpf_prog_is_offloaded(prog_aux)) {
+		bpf_log(log, "metadata kfuncs can't be offloaded\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
+{
+	const struct xdp_metadata_ops *ops;
+	void *p = NULL;
+
+	/* We don't hold bpf_devs_lock while resolving several
+	 * kfuncs and can race with the unregister_netdevice().
+	 * We rely on bpf_dev_bound_match() check at attach
+	 * to render this program unusable.
+	 */
+	down_read(&bpf_devs_lock);
+	if (!prog->aux->offload)
+		goto out;
+
+	ops = prog->aux->offload->netdev->xdp_metadata_ops;
+	if (!ops)
+		goto out;
+
+	if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
+		p = ops->xmo_rx_timestamp;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
+		p = ops->xmo_rx_hash;
+out:
+	up_read(&bpf_devs_lock);
+
+	return p;
+}
+
+static int __init bpf_offload_init(void)
+{
+	return rhashtable_init(&offdevs, &offdevs_params);
+}
+
+late_initcall(bpf_offload_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35ffd808f281..d5ffa7a01dfb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -181,7 +181,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 	int err;
 
 	/* Need to create a kthread, thus must support schedule */
-	if (bpf_map_is_dev_bound(map)) {
+	if (bpf_map_is_offloaded(map)) {
 		return bpf_map_offload_update_elem(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
 		   map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
@@ -238,7 +238,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	void *ptr;
 	int err;
 
-	if (bpf_map_is_dev_bound(map))
+	if (bpf_map_is_offloaded(map))
 		return bpf_map_offload_lookup_elem(map, key, value);
 
 	bpf_disable_instrumentation();
@@ -1483,7 +1483,7 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
 		goto err_put;
 	}
 
-	if (bpf_map_is_dev_bound(map)) {
+	if (bpf_map_is_offloaded(map)) {
 		err = bpf_map_offload_delete_elem(map, key);
 		goto out;
 	} else if (IS_FD_PROG_ARRAY(map) ||
@@ -1547,7 +1547,7 @@ static int map_get_next_key(union bpf_attr *attr)
 	if (!next_key)
 		goto free_key;
 
-	if (bpf_map_is_dev_bound(map)) {
+	if (bpf_map_is_offloaded(map)) {
 		err = bpf_map_offload_get_next_key(map, key, next_key);
 		goto out;
 	}
@@ -1605,7 +1605,7 @@ int generic_map_delete_batch(struct bpf_map *map,
 				   map->key_size))
 			break;
 
-		if (bpf_map_is_dev_bound(map)) {
+		if (bpf_map_is_offloaded(map)) {
 			err = bpf_map_offload_delete_elem(map, key);
 			break;
 		}
@@ -1851,7 +1851,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 		   map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 		   map->map_type == BPF_MAP_TYPE_LRU_HASH ||
 		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
-		if (!bpf_map_is_dev_bound(map)) {
+		if (!bpf_map_is_offloaded(map)) {
 			bpf_disable_instrumentation();
 			rcu_read_lock();
 			err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags);
@@ -1944,7 +1944,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 	if (!ops)
 		return -EINVAL;
 
-	if (!bpf_prog_is_dev_bound(prog->aux))
+	if (!bpf_prog_is_offloaded(prog->aux))
 		prog->aux->ops = ops;
 	else
 		prog->aux->ops = &bpf_offload_prog_ops;
@@ -2255,7 +2255,7 @@ bool bpf_prog_get_ok(struct bpf_prog *prog,
 
 	if (prog->type != *attach_type)
 		return false;
-	if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv)
+	if (bpf_prog_is_offloaded(prog->aux) && !attach_drv)
 		return false;
 
 	return true;
@@ -2491,7 +2491,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 				 BPF_F_TEST_STATE_FREQ |
 				 BPF_F_SLEEPABLE |
 				 BPF_F_TEST_RND_HI32 |
-				 BPF_F_XDP_HAS_FRAGS))
+				 BPF_F_XDP_HAS_FRAGS |
+				 BPF_F_XDP_DEV_BOUND_ONLY))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -2575,7 +2576,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	prog->aux->attach_btf = attach_btf;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
 	prog->aux->dst_prog = dst_prog;
-	prog->aux->offload_requested = !!attr->prog_ifindex;
+	prog->aux->dev_bound = !!attr->prog_ifindex;
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 	prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
 
@@ -2599,7 +2600,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
 	if (bpf_prog_is_dev_bound(prog->aux)) {
-		err = bpf_prog_offload_init(prog, attr);
+		err = bpf_prog_dev_bound_init(prog, attr);
+		if (err)
+			goto free_prog_sec;
+	}
+
+	if (type == BPF_PROG_TYPE_EXT && dst_prog &&
+	    bpf_prog_is_dev_bound(dst_prog->aux)) {
+		err = bpf_prog_dev_bound_inherit(prog, dst_prog);
 		if (err)
 			goto free_prog_sec;
 	}
@@ -3997,7 +4005,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 			return -EFAULT;
 	}
 
-	if (bpf_prog_is_dev_bound(prog->aux)) {
+	if (bpf_prog_is_offloaded(prog->aux)) {
 		err = bpf_prog_offload_info_fill(&info, prog);
 		if (err)
 			return err;
@@ -4225,7 +4233,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	}
 	info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
 
-	if (bpf_map_is_dev_bound(map)) {
+	if (bpf_map_is_offloaded(map)) {
 		err = bpf_map_offload_info_fill(&info, map);
 		if (err)
 			return err;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ecf7fed7881c..800488289297 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2333,6 +2333,12 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
 		return -EINVAL;
 	}
 
+	if (bpf_dev_bound_kfunc_id(func_id)) {
+		err = bpf_dev_bound_kfunc_check(&env->log, prog_aux);
+		if (err)
+			return err;
+	}
+
 	desc = &tab->descs[tab->nr_descs++];
 	desc->func_id = func_id;
 	desc->imm = call_imm;
@@ -14099,7 +14105,7 @@ static int do_check(struct bpf_verifier_env *env)
 			env->prev_log_len = env->log.len_used;
 		}
 
-		if (bpf_prog_is_dev_bound(env->prog->aux)) {
+		if (bpf_prog_is_offloaded(env->prog->aux)) {
 			err = bpf_prog_offload_verify_insn(env, env->insn_idx,
 							   env->prev_insn_idx);
 			if (err)
@@ -14579,7 +14585,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		}
 	}
 
-	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
+	if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) &&
 	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
 		return -EINVAL;
@@ -15060,7 +15066,7 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
 	unsigned int orig_prog_len = env->prog->len;
 	int err;
 
-	if (bpf_prog_is_dev_bound(env->prog->aux))
+	if (bpf_prog_is_offloaded(env->prog->aux))
 		bpf_prog_offload_remove_insns(env, off, cnt);
 
 	err = bpf_remove_insns(env->prog, off, cnt);
@@ -15141,7 +15147,7 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
 		else
 			continue;
 
-		if (bpf_prog_is_dev_bound(env->prog->aux))
+		if (bpf_prog_is_offloaded(env->prog->aux))
 			bpf_prog_offload_replace_insn(env, i, &ja);
 
 		memcpy(insn, &ja, sizeof(ja));
@@ -15328,7 +15334,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 	}
 
-	if (bpf_prog_is_dev_bound(env->prog->aux))
+	if (bpf_prog_is_offloaded(env->prog->aux))
 		return 0;
 
 	insn = env->prog->insnsi + delta;
@@ -15728,7 +15734,7 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 	int err = 0;
 
 	if (env->prog->jit_requested &&
-	    !bpf_prog_is_dev_bound(env->prog->aux)) {
+	    !bpf_prog_is_offloaded(env->prog->aux)) {
 		err = jit_subprogs(env);
 		if (err == 0)
 			return 0;
@@ -15772,12 +15778,25 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			    struct bpf_insn *insn_buf, int insn_idx, int *cnt)
 {
 	const struct bpf_kfunc_desc *desc;
+	void *xdp_kfunc;
 
 	if (!insn->imm) {
 		verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
 		return -EINVAL;
 	}
 
+	*cnt = 0;
+
+	if (bpf_dev_bound_kfunc_id(insn->imm)) {
+		xdp_kfunc = bpf_dev_bound_resolve_kfunc(env->prog, insn->imm);
+		if (xdp_kfunc) {
+			insn->imm = BPF_CALL_IMM(xdp_kfunc);
+			return 0;
+		}
+
+		/* fallback to default kfunc when not supported by netdev */
+	}
+
 	/* insn->imm has the btf func_id. Replace it with
 	 * an address (relative to __bpf_call_base).
 	 */
@@ -15788,7 +15807,6 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EFAULT;
 	}
 
-	*cnt = 0;
 	insn->imm = desc->imm;
 	if (insn->off)
 		return 0;
@@ -16795,6 +16813,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 	if (tgt_prog) {
 		struct bpf_prog_aux *aux = tgt_prog->aux;
 
+		if (bpf_prog_is_dev_bound(prog->aux) &&
+		    !bpf_prog_dev_bound_match(prog, tgt_prog)) {
+			bpf_log(log, "Target program bound device mismatch");
+			return -EINVAL;
+		}
+
 		for (i = 0; i < aux->func_info_cnt; i++)
 			if (aux->func_info[i].type_id == btf_id) {
 				subprog = i;
@@ -17231,7 +17255,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
 	if (ret < 0)
 		goto skip_full_check;
 
-	if (bpf_prog_is_dev_bound(env->prog->aux)) {
+	if (bpf_prog_is_offloaded(env->prog->aux)) {
 		ret = bpf_prog_offload_verifier_prep(env->prog);
 		if (ret)
 			goto skip_full_check;
@@ -17244,7 +17268,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
 	ret = do_check_subprogs(env);
 	ret = ret ?: do_check_main(env);
 
-	if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
+	if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
 		ret = bpf_prog_offload_finalize(env);
 
 skip_full_check:
@@ -17279,7 +17303,7 @@ skip_full_check:
 	/* do 32-bit optimization after insn patching has done so those patched
 	 * insns could be handled correctly.
 	 */
-	if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) {
+	if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) {
 		ret = opt_subreg_zext_lo32_rnd_hi32(env, attr);
 		env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret
 								     : false;