bpf: Support consuming XDP HW metadata from fext programs

Instead of rejecting the attaching of PROG_TYPE_EXT programs to XDP
programs that consume HW metadata, implement support for propagating the
offload information. The extension program doesn't need to set a flag or
ifindex, these will just be propagated from the target by the verifier.
We need to create a separate offload object for the extension program,
though, since it can be reattached to a different program later (which
means we can't just inherit the offload information from the target).

An additional check is added on attach that the new target is compatible
with the offload information in the extension prog.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230119221536.3349901-9-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

1 files changed, 82 insertions, 30 deletions

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 3e173c694bbb..e87cab2ed710 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -187,43 +187,24 @@ static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
 	kfree(ondev);
 }
 
-int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
+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;
 
-	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;
-
 	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;
-
-	prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY);
-
-	down_write(&bpf_devs_lock);
 	ondev = bpf_offload_find_netdev(offload->netdev);
 	if (!ondev) {
 		if (bpf_prog_is_offloaded(prog->aux)) {
 			err = -EINVAL;
-			goto err_unlock;
+			goto err_free;
 		}
 
 		/* When only binding to the device, explicitly
@@ -231,25 +212,80 @@ int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
 		 */
 		err = __bpf_offload_dev_netdev_register(NULL, offload->netdev);
 		if (err)
-			goto err_unlock;
+			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;
@@ -675,6 +711,22 @@ 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;