libbpf: Add link-based API for tcx

Implement tcx BPF link support for libbpf.

The bpf_program__attach_fd() API has been refactored slightly in order to pass
bpf_link_create_opts pointer as input.

A new bpf_program__attach_tcx() has been added on top of this which allows for
passing all relevant data via extensible struct bpf_tcx_opts.

The program sections tcx/ingress and tcx/egress correspond to the hook locations
for tc ingress and egress, respectively.

For concrete usage examples, see the extensive selftests that have been
developed as part of this series.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230719140858.13224-5-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: borkmann

tools/lib/bpf/bpf.c

@@ -719,9 +719,9 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    const struct bpf_link_create_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
-	__u32 target_btf_id, iter_info_len;
+	__u32 target_btf_id, iter_info_len, relative_id;
+	int fd, err, relative_fd;
 	union bpf_attr attr;
-	int fd, err;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return libbpf_err(-EINVAL);
@@ -783,6 +783,22 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, netfilter))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		relative_fd = OPTS_GET(opts, tcx.relative_fd, 0);
+		relative_id = OPTS_GET(opts, tcx.relative_id, 0);
+		if (relative_fd && relative_id)
+			return libbpf_err(-EINVAL);
+		if (relative_id) {
+			attr.link_create.tcx.relative_id = relative_id;
+			attr.link_create.flags |= BPF_F_ID;
+		} else {
+			attr.link_create.tcx.relative_fd = relative_fd;
+		}
+		attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0);
+		if (!OPTS_ZEROED(opts, tcx))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);

tools/lib/bpf/bpf.h

@@ -401,6 +401,11 @@ struct bpf_link_create_opts {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} tcx;
 	};
 	size_t :0;
 };

tools/lib/bpf/libbpf.c

@@ -134,6 +134,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_KPROBE_MULTI]		= "kprobe_multi",
 	[BPF_LINK_TYPE_STRUCT_OPS]		= "struct_ops",
 	[BPF_LINK_TYPE_NETFILTER]		= "netfilter",
+	[BPF_LINK_TYPE_TCX]			= "tcx",
 };
 
 static const char * const map_type_name[] = {
@@ -11854,11 +11855,10 @@ static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_li
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id,
-		       const char *target_name)
+bpf_program_attach_fd(const struct bpf_program *prog,
+		      int target_fd, const char *target_name,
+		      const struct bpf_link_create_opts *opts)
 {
-	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
-			    .target_btf_id = btf_id);
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -11876,7 +11876,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__expected_attach_type(prog);
-	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts);
+	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, opts);
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
@@ -11892,19 +11892,54 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id
 struct bpf_link *
 bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd)
 {
-	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
+	return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", NULL);
 }
 
 struct bpf_link *
 bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd)
 {
-	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
+	return bpf_program_attach_fd(prog, netns_fd, "netns", NULL);
 }
 
 struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
-	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
+	return bpf_program_attach_fd(prog, ifindex, "xdp", NULL);
+}
+
+struct bpf_link *
+bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
+			const struct bpf_tcx_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+	__u32 relative_id;
+	int relative_fd;
+
+	if (!OPTS_VALID(opts, bpf_tcx_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	relative_id = OPTS_GET(opts, relative_id, 0);
+	relative_fd = OPTS_GET(opts, relative_fd, 0);
+
+	/* validate we don't have unexpected combinations of non-zero fields */
+	if (!ifindex) {
+		pr_warn("prog '%s': target netdevice ifindex cannot be zero\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+	if (relative_fd && relative_id) {
+		pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link_create_opts.tcx.expected_revision = OPTS_GET(opts, expected_revision, 0);
+	link_create_opts.tcx.relative_fd = relative_fd;
+	link_create_opts.tcx.relative_id = relative_id;
+	link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+	/* target_fd/target_ifindex use the same field in LINK_CREATE */
+	return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts);
 }
 
 struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
@@ -11926,11 +11961,16 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 	}
 
 	if (target_fd) {
+		LIBBPF_OPTS(bpf_link_create_opts, target_opts);
+
 		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
 		if (btf_id < 0)
 			return libbpf_err_ptr(btf_id);
 
-		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
+		target_opts.target_btf_id = btf_id;
+
+		return bpf_program_attach_fd(prog, target_fd, "freplace",
+					     &target_opts);
 	} else {
 		/* no target, so use raw_tracepoint_open for compatibility
 		 * with old kernels

tools/lib/bpf/libbpf.h

@@ -733,6 +733,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netfilter(const struct bpf_program *prog,
 			      const struct bpf_netfilter_opts *opts);
 
+struct bpf_tcx_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+	__u32 flags;
+	__u32 relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_tcx_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
+			const struct bpf_tcx_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);

tools/lib/bpf/libbpf.map

@@ -397,4 +397,5 @@ LIBBPF_1.3.0 {
 		bpf_obj_pin_opts;
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
+		bpf_program__attach_tcx;
 } LIBBPF_1.2.0;