bpf: add bpf_link support for BPF_NETFILTER programs

Add bpf_link support skeleton. To keep this reviewable, no bpf program
can be invoked yet, if a program is attached only a c-stub is called and
not the actual bpf program.

Defaults to 'y' if both netfilter and bpf syscall are enabled in kconfig.

Uapi example usage:
union bpf_attr attr = { };

attr.link_create.prog_fd = progfd;
attr.link_create.attach_type = 0; /* unused */
attr.link_create.netfilter.pf = PF_INET;
attr.link_create.netfilter.hooknum = NF_INET_LOCAL_IN;
attr.link_create.netfilter.priority = -128;

err = bpf(BPF_LINK_CREATE, &attr, sizeof(attr));

... this would attach progfd to ipv4:input hook.

Such hook gets removed automatically if the calling program exits.

BPF_NETFILTER program invocation is added in followup change.

NF_HOOK_OP_BPF enum will eventually be read from nfnetlink_hook, it
allows to tell userspace which program is attached at the given hook
when user runs 'nft hook list' command rather than just the priority
and not-very-helpful 'this hook runs a bpf prog but I can't tell which
one'.

Will also be used to disallow registration of two bpf programs with
same priority in a followup patch.

v4: arm32 cmpxchg only supports 32bit operand
s/prio/priority/
v3: restrict prog attachment to ip/ip6 for now, lets lift restrictions if
more use cases pop up (arptables, ebtables, netdev ingress/egress etc).

Signed-off-by: Florian Westphal <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

include/linux/netfilter.h

···
 enum nf_hook_ops_type {
 	NF_HOOK_OP_UNDEFINED,
 	NF_HOOK_OP_NF_TABLES,
+	NF_HOOK_OP_BPF,
 };
 
 struct nf_hook_ops {

include/net/netfilter/nf_bpf_link.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#if IS_ENABLED(CONFIG_NETFILTER_BPF_LINK)
+int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+#else
+static inline int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+#endif

include/uapi/linux/bpf.h

···
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
+	BPF_PROG_TYPE_NETFILTER,
 };
 
 enum bpf_attach_type {
···
 	BPF_LINK_TYPE_PERF_EVENT = 7,
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
+	BPF_LINK_TYPE_NETFILTER = 10,
 
 	MAX_BPF_LINK_TYPE,
 };
···
 				 */
 				__u64		cookie;
 			} tracing;
+			struct {
+				__u32		pf;
+				__u32		hooknum;
+				__s32		priority;
+				__u32		flags;
+			} netfilter;
 		};
 	} link_create;
 
···
 		struct {
 			__u32 map_id;
 		} struct_ops;
+		struct {
+			__u32 pf;
+			__u32 hooknum;
+			__s32 priority;
+			__u32 flags;
+		} netfilter;
 	};
 } __attribute__((aligned(8)));
 

kernel/bpf/syscall.c

···
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
 #include <linux/trace_events.h>
+#include <net/netfilter/nf_bpf_link.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
···
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_EXT: /* extends any prog */
+	case BPF_PROG_TYPE_NETFILTER:
 		return true;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		/* always unpriv */
···
 
 	switch (prog->type) {
 	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_NETFILTER:
 		break;
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_TRACEPOINT:
···
 #ifdef CONFIG_NET
 	case BPF_PROG_TYPE_XDP:
 		ret = bpf_xdp_link_attach(attr, prog);
+		break;
+	case BPF_PROG_TYPE_NETFILTER:
+		ret = bpf_nf_link_attach(attr, prog);
 		break;
 #endif
 	case BPF_PROG_TYPE_PERF_EVENT:

net/netfilter/Kconfig

···
 config NETFILTER_FAMILY_ARP
 	bool
 
+config NETFILTER_BPF_LINK
+	def_bool BPF_SYSCALL
+
 config NETFILTER_NETLINK_HOOK
 	tristate "Netfilter base hook dump support"
 	depends on NETFILTER_ADVANCED

net/netfilter/Makefile

···
 endif
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
+obj-$(CONFIG_NETFILTER_BPF_LINK) += nf_bpf_link.o
 
 obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
 obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o

net/netfilter/nf_bpf_link.c

···
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/netfilter.h>
+
+#include <net/netfilter/nf_bpf_link.h>
+#include <uapi/linux/netfilter_ipv4.h>
+
+static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb,
+				    const struct nf_hook_state *s)
+{
+	return NF_ACCEPT;
+}
+
+struct bpf_nf_link {
+	struct bpf_link link;
+	struct nf_hook_ops hook_ops;
+	struct net *net;
+	u32 dead;
+};
+
+static void bpf_nf_link_release(struct bpf_link *link)
+{
+	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
+
+	if (nf_link->dead)
+		return;
+
+	/* prevent hook-not-found warning splat from netfilter core when
+	 * .detach was already called
+	 */
+	if (!cmpxchg(&nf_link->dead, 0, 1))
+		nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops);
+}
+
+static void bpf_nf_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
+
+	kfree(nf_link);
+}
+
+static int bpf_nf_link_detach(struct bpf_link *link)
+{
+	bpf_nf_link_release(link);
+	return 0;
+}
+
+static void bpf_nf_link_show_info(const struct bpf_link *link,
+				  struct seq_file *seq)
+{
+	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
+
+	seq_printf(seq, "pf:\t%u\thooknum:\t%u\tprio:\t%d\n",
+		   nf_link->hook_ops.pf, nf_link->hook_ops.hooknum,
+		   nf_link->hook_ops.priority);
+}
+
+static int bpf_nf_link_fill_link_info(const struct bpf_link *link,
+				      struct bpf_link_info *info)
+{
+	struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link);
+
+	info->netfilter.pf = nf_link->hook_ops.pf;
+	info->netfilter.hooknum = nf_link->hook_ops.hooknum;
+	info->netfilter.priority = nf_link->hook_ops.priority;
+	info->netfilter.flags = 0;
+
+	return 0;
+}
+
+static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
+			      struct bpf_prog *old_prog)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct bpf_link_ops bpf_nf_link_lops = {
+	.release = bpf_nf_link_release,
+	.dealloc = bpf_nf_link_dealloc,
+	.detach = bpf_nf_link_detach,
+	.show_fdinfo = bpf_nf_link_show_info,
+	.fill_link_info = bpf_nf_link_fill_link_info,
+	.update_prog = bpf_nf_link_update,
+};
+
+static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr)
+{
+	switch (attr->link_create.netfilter.pf) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+		if (attr->link_create.netfilter.hooknum >= NF_INET_NUMHOOKS)
+			return -EPROTO;
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	if (attr->link_create.netfilter.flags)
+		return -EOPNOTSUPP;
+
+	/* make sure conntrack confirm is always last.
+	 *
+	 * In the future, if userspace can e.g. request defrag, then
+	 * "defrag_requested && prio before NF_IP_PRI_CONNTRACK_DEFRAG"
+	 * should fail.
+	 */
+	switch (attr->link_create.netfilter.priority) {
+	case NF_IP_PRI_FIRST: return -ERANGE; /* sabotage_in and other warts */
+	case NF_IP_PRI_LAST: return -ERANGE; /* e.g. conntrack confirm */
+	}
+
+	return 0;
+}
+
+int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_link_primer link_primer;
+	struct bpf_nf_link *link;
+	int err;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	err = bpf_nf_check_pf_and_hooks(attr);
+	if (err)
+		return err;
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link)
+		return -ENOMEM;
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog);
+
+	link->hook_ops.hook = nf_hook_run_bpf;
+	link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF;
+	link->hook_ops.priv = prog;
+
+	link->hook_ops.pf = attr->link_create.netfilter.pf;
+	link->hook_ops.priority = attr->link_create.netfilter.priority;
+	link->hook_ops.hooknum = attr->link_create.netfilter.hooknum;
+
+	link->net = net;
+	link->dead = false;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		return err;
+	}
+
+	err = nf_register_net_hook(net, &link->hook_ops);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+}