Merge branch 'Link-based-attach-to-netns'

Jakub Sitnicki says:

====================
One of the pieces of feedback from recent review of BPF hooks for socket
lookup [0] was that new program types should use bpf_link-based
attachment.

This series introduces new bpf_link type for attaching to network
namespace. All link operations are supported. Errors returned from ops
follow cgroup example. Patch 4 description goes into error semantics.

The major change in v2 is a switch away from RCU to mutex-only
synchronization. Andrii pointed out that it is not needed, and it makes
sense to keep locking straightforward.

Also, there were a couple of bugs in update_prog and fill_info initial
implementation, one picked up by kbuild. Those are now fixed. Tests have
been extended to cover them. Full changelog below.

Series is organized as so:

Patches 1-3 prepare a space in struct net to keep state for attached BPF
programs, and massage the code in flow_dissector to make it attach type
agnostic, to finally move it under kernel/bpf/.

Patch 4, the most important one, introduces new bpf_link link type for
attaching to network namespace.

Patch 5 unifies the update error (ENOLINK) between BPF cgroup and netns.

Patches 6-8 make libbpf and bpftool aware of the new link type.

Patches 9-12 Add and extend tests to check that link low- and high-level
API for operating on links to netns works as intended.

Thanks to Alexei, Andrii, Lorenz, Marek, and Stanislav for feedback.

-jkbs

[0] https://lore.kernel.org/bpf/20200511185218.1422406-1-jakub@cloudflare.com/

Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Cc: Marek Majkowski <marek@cloudflare.com>
Cc: Stanislav Fomichev <sdf@google.com>

v1 -> v2:

- Switch to mutex-only synchronization. Don't rely on RCU grace period
  guarantee when accessing struct net from link release / update /
  fill_info, and when accessing bpf_link from pernet pre_exit
  callback. (Andrii)
- Drop patch 1, no longer needed with mutex-only synchronization.
- Don't leak uninitialized variable contents from fill_info callback
  when link is in defunct state. (kbuild)
- Make fill_info treat the link as defunct (i.e. no attached netns) when
  struct net refcount is 0, but link has not been yet auto-detached.
- Add missing BPF_LINK_TYPE define in bpf_types.h for new link type.
- Fix link update_prog callback to update the prog that will run, and
  not just the link itself.
- Return EEXIST on prog attach when link already exists, and on link
  create when prog is already attached directly. (Andrii)
- Return EINVAL on prog detach when link is attached. (Andrii)
- Fold __netns_bpf_link_attach into its only caller. (Stanislav)
- Get rid of a wrapper around container_of() (Andrii)
- Use rcu_dereference_protected instead of rcu_access_pointer on
  update-side. (Stanislav)
- Make return-on-success from netns_bpf_link_create less
  confusing. (Andrii)
- Adapt bpf_link for cgroup to return ENOLINK when updating a defunct
  link. (Andrii, Alexei)
- Order new exported symbols in libbpf.map alphabetically (Andrii)
- Keep libbpf's "failed to attach link" warning message clear as to what
  we failed to attach to (cgroup vs netns). (Andrii)
- Extract helpers for printing link attach type. (bpftool, Andrii)
- Switch flow_dissector tests to BPF skeleton and extend them to
  exercise link-based flow dissector attachment. (Andrii)
- Harden flow dissector attachment tests with prog query checks after
  prog attach/detach, or link create/update/close.
- Extend flow dissector tests to cover fill_info for defunct links.
- Rebase onto recent bpf-next
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf-netns.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BPF_NETNS_H
+#define _BPF_NETNS_H
+
+#include <linux/mutex.h>
+#include <uapi/linux/bpf.h>
+
+enum netns_bpf_attach_type {
+	NETNS_BPF_INVALID = -1,
+	NETNS_BPF_FLOW_DISSECTOR = 0,
+	MAX_NETNS_BPF_ATTACH_TYPE
+};
+
+static inline enum netns_bpf_attach_type
+to_netns_bpf_attach_type(enum bpf_attach_type attach_type)
+{
+	switch (attach_type) {
+	case BPF_FLOW_DISSECTOR:
+		return NETNS_BPF_FLOW_DISSECTOR;
+	default:
+		return NETNS_BPF_INVALID;
+	}
+}
+
+/* Protects updates to netns_bpf */
+extern struct mutex netns_bpf_mutex;
+
+union bpf_attr;
+struct bpf_prog;
+
+#ifdef CONFIG_NET
+int netns_bpf_prog_query(const union bpf_attr *attr,
+			 union bpf_attr __user *uattr);
+int netns_bpf_prog_attach(const union bpf_attr *attr,
+			  struct bpf_prog *prog);
+int netns_bpf_prog_detach(const union bpf_attr *attr);
+int netns_bpf_link_create(const union bpf_attr *attr,
+			  struct bpf_prog *prog);
+#else
+static inline int netns_bpf_prog_query(const union bpf_attr *attr,
+				       union bpf_attr __user *uattr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int netns_bpf_prog_attach(const union bpf_attr *attr,
+					struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int netns_bpf_prog_detach(const union bpf_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int netns_bpf_link_create(const union bpf_attr *attr,
+					struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif /* _BPF_NETNS_H */

include/linux/bpf_types.h

@@ -126,3 +126,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
 BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
+#ifdef CONFIG_NET
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
+#endif

include/linux/skbuff.h

@@ -1283,32 +1283,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     const struct flow_dissector_key *key,
 			     unsigned int key_count);
 
-#ifdef CONFIG_NET
-int skb_flow_dissector_prog_query(const union bpf_attr *attr,
-				  union bpf_attr __user *uattr);
-int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
-				       struct bpf_prog *prog);
-
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr);
-#else
-static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr,
-						union bpf_attr __user *uattr)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
-						     struct bpf_prog *prog)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-
 struct bpf_flow_dissector;
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 		      __be16 proto, int nhoff, int hlen, unsigned int flags);

include/net/flow_dissector.h

@@ -8,6 +8,8 @@
 #include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
+struct bpf_prog;
+struct net;
 struct sk_buff;
 
 /**
@@ -369,4 +371,8 @@ flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
 	memset(key_basic, 0, sizeof(*key_basic));
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog);
+#endif /* CONFIG_BPF_SYSCALL */
+
 #endif

include/net/net_namespace.h

@@ -33,6 +33,7 @@
 #include <net/netns/mpls.h>
 #include <net/netns/can.h>
 #include <net/netns/xdp.h>
+#include <net/netns/bpf.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
@@ -162,7 +163,8 @@ struct net {
 #endif
 	struct net_generic __rcu	*gen;
 
-	struct bpf_prog __rcu	*flow_dissector_prog;
+	/* Used to store attached BPF programs */
+	struct netns_bpf	bpf;
 
 	/* Note : following structs are cache line aligned */
 #ifdef CONFIG_XFRM

include/net/netns/bpf.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF programs attached to network namespace
+ */
+
+#ifndef __NETNS_BPF_H__
+#define __NETNS_BPF_H__
+
+#include <linux/bpf-netns.h>
+
+struct bpf_prog;
+
+struct netns_bpf {
+	struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE];
+	struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE];
+};
+
+#endif /* __NETNS_BPF_H__ */

include/uapi/linux/bpf.h

@@ -237,6 +237,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
+	BPF_LINK_TYPE_NETNS = 5,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -3839,6 +3840,10 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct  {
+			__u32 netns_ino;
+			__u32 attach_type;
+		} netns;
 	};
 } __attribute__((aligned(8)));
 

kernel/bpf/Makefile

@@ -13,6 +13,7 @@ ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
+obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
 endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o

kernel/bpf/cgroup.c

@@ -595,7 +595,7 @@ static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog,
 	mutex_lock(&cgroup_mutex);
 	/* link might have been auto-released by dying cgroup, so fail */
 	if (!cg_link->cgroup) {
-		ret = -EINVAL;
+		ret = -ENOLINK;
 		goto out_unlock;
 	}
 	if (old_prog && link->prog != old_prog) {

kernel/bpf/net_namespace.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <net/net_namespace.h>
+
+/*
+ * Functions to manage BPF programs attached to netns
+ */
+
+struct bpf_netns_link {
+	struct bpf_link	link;
+	enum bpf_attach_type type;
+	enum netns_bpf_attach_type netns_type;
+
+	/* We don't hold a ref to net in order to auto-detach the link
+	 * when netns is going away. Instead we rely on pernet
+	 * pre_exit callback to clear this pointer. Must be accessed
+	 * with netns_bpf_mutex held.
+	 */
+	struct net *net;
+};
+
+/* Protects updates to netns_bpf */
+DEFINE_MUTEX(netns_bpf_mutex);
+
+/* Must be called with netns_bpf_mutex held. */
+static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+
+	net_link->net = NULL;
+}
+
+static void bpf_netns_link_release(struct bpf_link *link)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct net *net;
+
+	/* Link auto-detached by dying netns. */
+	if (!net_link->net)
+		return;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	/* Recheck after potential sleep. We can race with cleanup_net
+	 * here, but if we see a non-NULL struct net pointer pre_exit
+	 * has not happened yet and will block on netns_bpf_mutex.
+	 */
+	net = net_link->net;
+	if (!net)
+		goto out_unlock;
+
+	net->bpf.links[type] = NULL;
+	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+}
+
+static void bpf_netns_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+
+	kfree(net_link);
+}
+
+static int bpf_netns_link_update_prog(struct bpf_link *link,
+				      struct bpf_prog *new_prog,
+				      struct bpf_prog *old_prog)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct net *net;
+	int ret = 0;
+
+	if (old_prog && old_prog != link->prog)
+		return -EPERM;
+	if (new_prog->type != link->prog->type)
+		return -EINVAL;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	net = net_link->net;
+	if (!net || !check_net(net)) {
+		/* Link auto-detached or netns dying */
+		ret = -ENOLINK;
+		goto out_unlock;
+	}
+
+	old_prog = xchg(&link->prog, new_prog);
+	rcu_assign_pointer(net->bpf.progs[type], new_prog);
+	bpf_prog_put(old_prog);
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+	return ret;
+}
+
+static int bpf_netns_link_fill_info(const struct bpf_link *link,
+				    struct bpf_link_info *info)
+{
+	const struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	unsigned int inum = 0;
+	struct net *net;
+
+	mutex_lock(&netns_bpf_mutex);
+	net = net_link->net;
+	if (net && check_net(net))
+		inum = net->ns.inum;
+	mutex_unlock(&netns_bpf_mutex);
+
+	info->netns.netns_ino = inum;
+	info->netns.attach_type = net_link->type;
+	return 0;
+}
+
+static void bpf_netns_link_show_fdinfo(const struct bpf_link *link,
+				       struct seq_file *seq)
+{
+	struct bpf_link_info info = {};
+
+	bpf_netns_link_fill_info(link, &info);
+	seq_printf(seq,
+		   "netns_ino:\t%u\n"
+		   "attach_type:\t%u\n",
+		   info.netns.netns_ino,
+		   info.netns.attach_type);
+}
+
+static const struct bpf_link_ops bpf_netns_link_ops = {
+	.release = bpf_netns_link_release,
+	.dealloc = bpf_netns_link_dealloc,
+	.update_prog = bpf_netns_link_update_prog,
+	.fill_link_info = bpf_netns_link_fill_info,
+	.show_fdinfo = bpf_netns_link_show_fdinfo,
+};
+
+int netns_bpf_prog_query(const union bpf_attr *attr,
+			 union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	u32 prog_id, prog_cnt = 0, flags = 0;
+	enum netns_bpf_attach_type type;
+	struct bpf_prog *attached;
+	struct net *net;
+
+	if (attr->query.query_flags)
+		return -EINVAL;
+
+	type = to_netns_bpf_attach_type(attr->query.attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	net = get_net_ns_by_fd(attr->query.target_fd);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	rcu_read_lock();
+	attached = rcu_dereference(net->bpf.progs[type]);
+	if (attached) {
+		prog_cnt = 1;
+		prog_id = attached->aux->id;
+	}
+	rcu_read_unlock();
+
+	put_net(net);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		return -EFAULT;
+
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		return 0;
+
+	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	enum netns_bpf_attach_type type;
+	struct net *net;
+	int ret;
+
+	type = to_netns_bpf_attach_type(attr->attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	net = current->nsproxy->net_ns;
+	mutex_lock(&netns_bpf_mutex);
+
+	/* Attaching prog directly is not compatible with links */
+	if (net->bpf.links[type]) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		ret = flow_dissector_bpf_prog_attach(net, prog);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+
+	return ret;
+}
+
+/* Must be called with netns_bpf_mutex held. */
+static int __netns_bpf_prog_detach(struct net *net,
+				   enum netns_bpf_attach_type type)
+{
+	struct bpf_prog *attached;
+
+	/* Progs attached via links cannot be detached */
+	if (net->bpf.links[type])
+		return -EINVAL;
+
+	attached = rcu_dereference_protected(net->bpf.progs[type],
+					     lockdep_is_held(&netns_bpf_mutex));
+	if (!attached)
+		return -ENOENT;
+	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+	bpf_prog_put(attached);
+	return 0;
+}
+
+int netns_bpf_prog_detach(const union bpf_attr *attr)
+{
+	enum netns_bpf_attach_type type;
+	int ret;
+
+	type = to_netns_bpf_attach_type(attr->attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	mutex_lock(&netns_bpf_mutex);
+	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type);
+	mutex_unlock(&netns_bpf_mutex);
+
+	return ret;
+}
+
+static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
+				 enum netns_bpf_attach_type type)
+{
+	struct bpf_prog *prog;
+	int err;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	/* Allow attaching only one prog or link for now */
+	if (net->bpf.links[type]) {
+		err = -E2BIG;
+		goto out_unlock;
+	}
+	/* Links are not compatible with attaching prog directly */
+	prog = rcu_dereference_protected(net->bpf.progs[type],
+					 lockdep_is_held(&netns_bpf_mutex));
+	if (prog) {
+		err = -EEXIST;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		err = flow_dissector_bpf_prog_attach(net, link->prog);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+	if (err)
+		goto out_unlock;
+
+	net->bpf.links[type] = link;
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+	return err;
+}
+
+int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	enum netns_bpf_attach_type netns_type;
+	struct bpf_link_primer link_primer;
+	struct bpf_netns_link *net_link;
+	enum bpf_attach_type type;
+	struct net *net;
+	int err;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	type = attr->link_create.attach_type;
+	netns_type = to_netns_bpf_attach_type(type);
+	if (netns_type < 0)
+		return -EINVAL;
+
+	net = get_net_ns_by_fd(attr->link_create.target_fd);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	net_link = kzalloc(sizeof(*net_link), GFP_USER);
+	if (!net_link) {
+		err = -ENOMEM;
+		goto out_put_net;
+	}
+	bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS,
+		      &bpf_netns_link_ops, prog);
+	net_link->net = net;
+	net_link->type = type;
+	net_link->netns_type = netns_type;
+
+	err = bpf_link_prime(&net_link->link, &link_primer);
+	if (err) {
+		kfree(net_link);
+		goto out_put_net;
+	}
+
+	err = netns_bpf_link_attach(net, &net_link->link, netns_type);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_net;
+	}
+
+	put_net(net);
+	return bpf_link_settle(&link_primer);
+
+out_put_net:
+	put_net(net);
+	return err;
+}
+
+static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
+{
+	enum netns_bpf_attach_type type;
+	struct bpf_link *link;
+
+	mutex_lock(&netns_bpf_mutex);
+	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
+		link = net->bpf.links[type];
+		if (link)
+			bpf_netns_link_auto_detach(link);
+		else
+			__netns_bpf_prog_detach(net, type);
+	}
+	mutex_unlock(&netns_bpf_mutex);
+}
+
+static struct pernet_operations netns_bpf_pernet_ops __net_initdata = {
+	.pre_exit = netns_bpf_pernet_pre_exit,
+};
+
+static int __init netns_bpf_init(void)
+{
+	return register_pernet_subsys(&netns_bpf_pernet_ops);
+}
+
+subsys_initcall(netns_bpf_init);

kernel/bpf/syscall.c

@@ -27,6 +27,7 @@
 #include <uapi/linux/btf.h>
 #include <linux/bpf_lsm.h>
 #include <linux/poll.h>
+#include <linux/bpf-netns.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -2868,7 +2869,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		ret = lirc_prog_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		ret = skb_flow_dissector_bpf_prog_attach(attr, prog);
+		ret = netns_bpf_prog_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -2908,7 +2909,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-		return skb_flow_dissector_bpf_prog_detach(attr);
+		return netns_bpf_prog_detach(attr);
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -2961,7 +2962,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
 	case BPF_FLOW_DISSECTOR:
-		return skb_flow_dissector_prog_query(attr, uattr);
+		return netns_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
@@ -3886,6 +3887,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_TRACING:
 		ret = tracing_bpf_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+		ret = netns_bpf_link_create(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}

net/core/flow_dissector.c

@@ -31,8 +31,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #endif
-
-static DEFINE_MUTEX(flow_dissector_mutex);
+#include <linux/bpf-netns.h>
 
 static void dissector_set_key(struct flow_dissector *flow_dissector,
 			      enum flow_dissector_key_id key_id)
@@ -70,54 +69,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 }
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
-int skb_flow_dissector_prog_query(const union bpf_attr *attr,
-				  union bpf_attr __user *uattr)
+#ifdef CONFIG_BPF_SYSCALL
+int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
 {
-	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
-	u32 prog_id, prog_cnt = 0, flags = 0;
+	enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
 	struct bpf_prog *attached;
-	struct net *net;
-
-	if (attr->query.query_flags)
-		return -EINVAL;
-
-	net = get_net_ns_by_fd(attr->query.target_fd);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	rcu_read_lock();
-	attached = rcu_dereference(net->flow_dissector_prog);
-	if (attached) {
-		prog_cnt = 1;
-		prog_id = attached->aux->id;
-	}
-	rcu_read_unlock();
-
-	put_net(net);
-
-	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
-		return -EFAULT;
-	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
-		return -EFAULT;
-
-	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
-		return 0;
-
-	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
-		return -EFAULT;
-
-	return 0;
-}
-
-int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
-				       struct bpf_prog *prog)
-{
-	struct bpf_prog *attached;
-	struct net *net;
-	int ret = 0;
-
-	net = current->nsproxy->net_ns;
-	mutex_lock(&flow_dissector_mutex);
 
 	if (net == &init_net) {
 		/* BPF flow dissector in the root namespace overrides
@@ -130,70 +86,29 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 		for_each_net(ns) {
 			if (ns == &init_net)
 				continue;
-			if (rcu_access_pointer(ns->flow_dissector_prog)) {
-				ret = -EEXIST;
-				goto out;
-			}
+			if (rcu_access_pointer(ns->bpf.progs[type]))
+				return -EEXIST;
 		}
 	} else {
 		/* Make sure root flow dissector is not attached
 		 * when attaching to the non-root namespace.
 		 */
-		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
-			ret = -EEXIST;
-			goto out;
-		}
+		if (rcu_access_pointer(init_net.bpf.progs[type]))
+			return -EEXIST;
 	}
 
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached == prog) {
+	attached = rcu_dereference_protected(net->bpf.progs[type],
+					     lockdep_is_held(&netns_bpf_mutex));
+	if (attached == prog)
 		/* The same program cannot be attached twice */
-		ret = -EINVAL;
-		goto out;
-	}
-	rcu_assign_pointer(net->flow_dissector_prog, prog);
-	if (attached)
-		bpf_prog_put(attached);
-out:
-	mutex_unlock(&flow_dissector_mutex);
-	return ret;
-}
-
-static int flow_dissector_bpf_prog_detach(struct net *net)
-{
-	struct bpf_prog *attached;
+		return -EINVAL;
 
-	mutex_lock(&flow_dissector_mutex);
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (!attached) {
-		mutex_unlock(&flow_dissector_mutex);
-		return -ENOENT;
-	}
-	RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
+	rcu_assign_pointer(net->bpf.progs[type], prog);
+	if (attached)
 		bpf_prog_put(attached);
-	mutex_unlock(&flow_dissector_mutex);
 	return 0;
 }
-
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
-{
-	return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
-}
-
-static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
-{
-	/* We're not racing with attach/detach because there are no
-	 * references to netns left when pre_exit gets called.
-	 */
-	if (rcu_access_pointer(net->flow_dissector_prog))
-		flow_dissector_bpf_prog_detach(net);
-}
-
-static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
-	.pre_exit = flow_dissector_pernet_pre_exit,
-};
+#endif /* CONFIG_BPF_SYSCALL */
 
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
@@ -1044,11 +959,13 @@ bool __skb_flow_dissect(const struct net *net,
 
 	WARN_ON_ONCE(!net);
 	if (net) {
+		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+
 		rcu_read_lock();
-		attached = rcu_dereference(init_net.flow_dissector_prog);
+		attached = rcu_dereference(init_net.bpf.progs[type]);
 
 		if (!attached)
-			attached = rcu_dereference(net->flow_dissector_prog);
+			attached = rcu_dereference(net->bpf.progs[type]);
 
 		if (attached) {
 			struct bpf_flow_keys flow_keys;
@@ -1869,7 +1786,6 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_basic_dissector,
 				flow_keys_basic_dissector_keys,
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
-
-	return register_pernet_subsys(&flow_dissector_pernet_ops);
+	return 0;
 }
 core_initcall(init_default_flow_dissectors);

tools/bpf/bpftool/link.c

@@ -17,6 +17,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_TRACING]			= "tracing",
 	[BPF_LINK_TYPE_CGROUP]			= "cgroup",
 	[BPF_LINK_TYPE_ITER]			= "iter",
+	[BPF_LINK_TYPE_NETNS]			= "netns",
 };
 
 static int link_parse_fd(int *argc, char ***argv)
@@ -62,6 +63,15 @@ show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_uint_field(json_wtr, "prog_id", info->prog_id);
 }
 
+static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr)
+{
+	if (attach_type < ARRAY_SIZE(attach_type_name))
+		jsonw_string_field(wtr, "attach_type",
+				   attach_type_name[attach_type]);
+	else
+		jsonw_uint_field(wtr, "attach_type", attach_type);
+}
+
 static int get_prog_info(int prog_id, struct bpf_prog_info *info)
 {
 	__u32 len = sizeof(*info);
@@ -105,22 +115,18 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 			jsonw_uint_field(json_wtr, "prog_type",
 					 prog_info.type);
 
-		if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name))
-			jsonw_string_field(json_wtr, "attach_type",
-			       attach_type_name[info->tracing.attach_type]);
-		else
-			jsonw_uint_field(json_wtr, "attach_type",
-					 info->tracing.attach_type);
+		show_link_attach_type_json(info->tracing.attach_type,
+					   json_wtr);
 		break;
 	case BPF_LINK_TYPE_CGROUP:
 		jsonw_lluint_field(json_wtr, "cgroup_id",
 				   info->cgroup.cgroup_id);
-		if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name))
-			jsonw_string_field(json_wtr, "attach_type",
-			       attach_type_name[info->cgroup.attach_type]);
-		else
-			jsonw_uint_field(json_wtr, "attach_type",
-					 info->cgroup.attach_type);
+		show_link_attach_type_json(info->cgroup.attach_type, json_wtr);
+		break;
+	case BPF_LINK_TYPE_NETNS:
+		jsonw_uint_field(json_wtr, "netns_ino",
+				 info->netns.netns_ino);
+		show_link_attach_type_json(info->netns.attach_type, json_wtr);
 		break;
 	default:
 		break;
@@ -153,6 +159,14 @@ static void show_link_header_plain(struct bpf_link_info *info)
 	printf("prog %u  ", info->prog_id);
 }
 
+static void show_link_attach_type_plain(__u32 attach_type)
+{
+	if (attach_type < ARRAY_SIZE(attach_type_name))
+		printf("attach_type %s  ", attach_type_name[attach_type]);
+	else
+		printf("attach_type %u  ", attach_type);
+}
+
 static int show_link_close_plain(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -176,19 +190,15 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		else
 			printf("\n\tprog_type %u  ", prog_info.type);
 
-		if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name))
-			printf("attach_type %s  ",
-			       attach_type_name[info->tracing.attach_type]);
-		else
-			printf("attach_type %u  ", info->tracing.attach_type);
+		show_link_attach_type_plain(info->tracing.attach_type);
 		break;
 	case BPF_LINK_TYPE_CGROUP:
 		printf("\n\tcgroup_id %zu  ", (size_t)info->cgroup.cgroup_id);
-		if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name))
-			printf("attach_type %s  ",
-			       attach_type_name[info->cgroup.attach_type]);
-		else
-			printf("attach_type %u  ", info->cgroup.attach_type);
+		show_link_attach_type_plain(info->cgroup.attach_type);
+		break;
+	case BPF_LINK_TYPE_NETNS:
+		printf("\n\tnetns_ino %u  ", info->netns.netns_ino);
+		show_link_attach_type_plain(info->netns.attach_type);
 		break;
 	default:
 		break;

tools/include/uapi/linux/bpf.h

@@ -237,6 +237,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
+	BPF_LINK_TYPE_NETNS = 5,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -3839,6 +3840,10 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct  {
+			__u32 netns_ino;
+			__u32 attach_type;
+		} netns;
 	};
 } __attribute__((aligned(8)));
 

tools/lib/bpf/libbpf.c

@@ -7896,8 +7896,9 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
 	return bpf_program__attach_iter(prog, NULL);
 }
 
-struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+static struct bpf_link *
+bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
+		       const char *target_name)
 {
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
@@ -7917,12 +7918,12 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
-	link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL);
+	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, NULL);
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to cgroup: %s\n",
-			bpf_program__title(prog, false),
+		pr_warn("program '%s': failed to attach to %s: %s\n",
+			bpf_program__title(prog, false), target_name,
 			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(link_fd);
 	}
@@ -7930,6 +7931,18 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 	return link;
 }
 
+struct bpf_link *
+bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+{
+	return bpf_program__attach_fd(prog, cgroup_fd, "cgroup");
+}
+
+struct bpf_link *
+bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
+{
+	return bpf_program__attach_fd(prog, netns_fd, "netns");
+}
+
 struct bpf_link *
 bpf_program__attach_iter(struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts)

tools/lib/bpf/libbpf.h

@@ -253,6 +253,8 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_lsm(struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
 
 struct bpf_map;
 

tools/lib/bpf/libbpf.map

@@ -262,6 +262,7 @@ LIBBPF_0.0.9 {
 		bpf_link_get_fd_by_id;
 		bpf_link_get_next_id;
 		bpf_program__attach_iter;
+		bpf_program__attach_netns;
 		perf_buffer__consume;
 		ring_buffer__add;
 		ring_buffer__consume;

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -6,6 +6,8 @@
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
+#include "bpf_flow.skel.h"
+
 #ifndef IP_MF
 #define IP_MF 0x2000
 #endif
@@ -101,6 +103,7 @@ struct test {
 
 #define VLAN_HLEN	4
 
+static __u32 duration;
 struct test tests[] = {
 	{
 		.name = "ipv4",
@@ -444,17 +447,130 @@ static int ifup(const char *ifname)
 	return 0;
 }
 
+static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
+{
+	int i, err, map_fd, prog_fd;
+	struct bpf_program *prog;
+	char prog_name[32];
+
+	map_fd = bpf_map__fd(prog_array);
+	if (map_fd < 0)
+		return -1;
+
+	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+		snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i);
+
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		if (!prog)
+			return -1;
+
+		prog_fd = bpf_program__fd(prog);
+		if (prog_fd < 0)
+			return -1;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (err)
+			return -1;
+	}
+	return 0;
+}
+
+static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
+{
+	int i, err, keys_fd;
+
+	keys_fd = bpf_map__fd(keys);
+	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		/* Keep in sync with 'flags' from eth_get_headlen. */
+		__u32 eth_get_headlen_flags =
+			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
+		struct bpf_prog_test_run_attr tattr = {};
+		struct bpf_flow_keys flow_keys = {};
+		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
+			    tests[i].keys.dport;
+
+		/* For skb-less case we can't pass input flags; run
+		 * only the tests that have a matching set of flags.
+		 */
+
+		if (tests[i].flags != eth_get_headlen_flags)
+			continue;
+
+		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
+		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
+
+		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
+
+		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
+		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+
+		err = bpf_map_delete_elem(keys_fd, &key);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
+	}
+}
+
+static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
+{
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+		return;
+
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno))
+		return;
+
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+	err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
+	CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno);
+}
+
+static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
+{
+	struct bpf_link *link;
+	int err, net_fd;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno))
+		return;
+
+	link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
+	if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link)))
+		goto out_close;
+
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+	err = bpf_link__destroy(link);
+	CHECK(err, "bpf_link__destroy", "err %d\n", err);
+out_close:
+	close(net_fd);
+}
+
 void test_flow_dissector(void)
 {
 	int i, err, prog_fd, keys_fd = -1, tap_fd;
-	struct bpf_object *obj;
-	__u32 duration = 0;
+	struct bpf_flow *skel;
 
-	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
-			    "jmp_table", "last_dissection", &prog_fd, &keys_fd);
-	if (CHECK_FAIL(err))
+	skel = bpf_flow__open_and_load();
+	if (CHECK(!skel, "skel", "failed to open/load skeleton\n"))
 		return;
 
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+		goto out_destroy_skel;
+	keys_fd = bpf_map__fd(skel->maps.last_dissection);
+	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+		goto out_destroy_skel;
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (CHECK(err, "init_prog_array", "err %d\n", err))
+		goto out_destroy_skel;
+
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_flow_keys flow_keys;
 		struct bpf_prog_test_run_attr tattr = {
@@ -487,43 +603,17 @@ void test_flow_dissector(void)
 	 * via BPF map in this case.
 	 */
 
-	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
-	CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno);
-
 	tap_fd = create_tap("tap0");
 	CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno);
 	err = ifup("tap0");
 	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
 
-	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		/* Keep in sync with 'flags' from eth_get_headlen. */
-		__u32 eth_get_headlen_flags =
-			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
-		struct bpf_prog_test_run_attr tattr = {};
-		struct bpf_flow_keys flow_keys = {};
-		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
-			    tests[i].keys.dport;
-
-		/* For skb-less case we can't pass input flags; run
-		 * only the tests that have a matching set of flags.
-		 */
-
-		if (tests[i].flags != eth_get_headlen_flags)
-			continue;
-
-		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
-		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
-
-		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
-		CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
-
-		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
-
-		err = bpf_map_delete_elem(keys_fd, &key);
-		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
-	}
+	/* Test direct prog attachment */
+	test_skb_less_prog_attach(skel, tap_fd);
+	/* Test indirect prog attachment via link */
+	test_skb_less_link_create(skel, tap_fd);
 
-	bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
-	bpf_object__close(obj);
+	close(tap_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
 }

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -20,20 +20,20 @@
 #include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
-#define PROG(F) SEC(#F) int bpf_func_##F
+#define PROG(F) PROG_(F, _##F)
+#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME
 
 /* These are the identifiers of the BPF programs that will be used in tail
  * calls. Name is limited to 16 characters, with the terminating character and
  * bpf_func_ above, we have only 6 to work with, anything after will be cropped.
  */
-enum {
-	IP,
-	IPV6,
-	IPV6OP,	/* Destination/Hop-by-Hop Options IPv6 Extension header */
-	IPV6FR,	/* Fragmentation IPv6 Extension Header */
-	MPLS,
-	VLAN,
-};
+#define IP		0
+#define IPV6		1
+#define IPV6OP		2 /* Destination/Hop-by-Hop Options IPv6 Ext. Header */
+#define IPV6FR		3 /* Fragmentation IPv6 Extension Header */
+#define MPLS		4
+#define VLAN		5
+#define MAX_PROG	6
 
 #define IP_MF		0x2000
 #define IP_OFFSET	0x1FFF
@@ -59,7 +59,7 @@ struct frag_hdr {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
-	__uint(max_entries, 8);
+	__uint(max_entries, MAX_PROG);
 	__uint(key_size, sizeof(__u32));
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");