libbpf: Add low level TC-BPF management API

This adds functions that wrap the netlink API used for adding, manipulating,
and removing traffic control filters.

The API summary:

A bpf_tc_hook represents a location where a TC-BPF filter can be attached.
This means that creating a hook leads to creation of the backing qdisc,
while destruction either removes all filters attached to a hook, or destroys
qdisc if requested explicitly (as discussed below).

The TC-BPF API functions operate on this bpf_tc_hook to attach, replace,
query, and detach tc filters. All functions return 0 on success, and a
negative error code on failure.

bpf_tc_hook_create - Create a hook
Parameters:
	@hook - Cannot be NULL, ifindex > 0, attach_point must be set to
		proper enum constant. Note that parent must be unset when
		attach_point is one of BPF_TC_INGRESS or BPF_TC_EGRESS. Note
		that as an exception BPF_TC_INGRESS|BPF_TC_EGRESS is also a
		valid value for attach_point.

		Returns -EOPNOTSUPP when hook has attach_point as BPF_TC_CUSTOM.

bpf_tc_hook_destroy - Destroy a hook
Parameters:
	@hook - Cannot be NULL. The behaviour depends on value of
		attach_point. If BPF_TC_INGRESS, all filters attached to
		the ingress hook will be detached. If BPF_TC_EGRESS, all
		filters attached to the egress hook will be detached. If
		BPF_TC_INGRESS|BPF_TC_EGRESS, the clsact qdisc will be
		deleted, also detaching all filters. As before, parent must
		be unset for these attach_points, and set for BPF_TC_CUSTOM.

		It is advised that if the qdisc is operated on by many programs,
		then the program at least check that there are no other existing
		filters before deleting the clsact qdisc. An example is shown
		below:

		DECLARE_LIBBPF_OPTS(bpf_tc_hook, .ifindex = if_nametoindex("lo"),
				    .attach_point = BPF_TC_INGRESS);
		/* set opts as NULL, as we're not really interested in
		 * getting any info for a particular filter, but just
	 	 * detecting its presence.
		 */
		r = bpf_tc_query(&hook, NULL);
		if (r == -ENOENT) {
			/* no filters */
			hook.attach_point = BPF_TC_INGRESS|BPF_TC_EGREESS;
			return bpf_tc_hook_destroy(&hook);
		} else {
			/* failed or r == 0, the latter means filters do exist */
			return r;
		}

		Note that there is a small race between checking for no
		filters and deleting the qdisc. This is currently unavoidable.

		Returns -EOPNOTSUPP when hook has attach_point as BPF_TC_CUSTOM.

bpf_tc_attach - Attach a filter to a hook
Parameters:
	@hook - Cannot be NULL. Represents the hook the filter will be
		attached to. Requirements for ifindex and attach_point are
		same as described in bpf_tc_hook_create, but BPF_TC_CUSTOM
		is also supported.  In that case, parent must be set to the
		handle where the filter will be attached (using BPF_TC_PARENT).
		E.g. to set parent to 1:16 like in tc command line, the
		equivalent would be BPF_TC_PARENT(1, 16).

	@opts - Cannot be NULL. The following opts are optional:
		* handle   - The handle of the filter
		* priority - The priority of the filter
			     Must be >= 0 and <= UINT16_MAX
		Note that when left unset, they will be auto-allocated by
		the kernel. The following opts must be set:
		* prog_fd - The fd of the loaded SCHED_CLS prog
		The following opts must be unset:
		* prog_id - The ID of the BPF prog
		The following opts are optional:
		* flags - Currently only BPF_TC_F_REPLACE is allowed. It
			  allows replacing an existing filter instead of
			  failing with -EEXIST.
		The following opts will be filled by bpf_tc_attach on a
		successful attach operation if they are unset:
		* handle   - The handle of the attached filter
		* priority - The priority of the attached filter
		* prog_id  - The ID of the attached SCHED_CLS prog
		This way, the user can know what the auto allocated values
		for optional opts like handle and priority are for the newly
		attached filter, if they were unset.

		Note that some other attributes are set to fixed default
		values listed below (this holds for all bpf_tc_* APIs):
		protocol as ETH_P_ALL, direct action mode, chain index of 0,
		and class ID of 0 (this can be set by writing to the
		skb->tc_classid field from the BPF program).

bpf_tc_detach
Parameters:
	@hook - Cannot be NULL. Represents the hook the filter will be
		detached from. Requirements are same as described above
		in bpf_tc_attach.

	@opts - Cannot be NULL. The following opts must be set:
		* handle, priority
		The following opts must be unset:
		* prog_fd, prog_id, flags

bpf_tc_query
Parameters:
	@hook - Cannot be NULL. Represents the hook where the filter lookup will
		be performed. Requirements are same as described above in
		bpf_tc_attach().

	@opts - Cannot be NULL. The following opts must be set:
		* handle, priority
		The following opts must be unset:
		* prog_fd, prog_id, flags
		The following fields will be filled by bpf_tc_query upon a
		successful lookup:
		* prog_id

Some usage examples (using BPF skeleton infrastructure):

BPF program (test_tc_bpf.c):

	#include <linux/bpf.h>
	#include <bpf/bpf_helpers.h>

	SEC("classifier")
	int cls(struct __sk_buff *skb)
	{
		return 0;
	}

Userspace loader:

	struct test_tc_bpf *skel = NULL;
	int fd, r;

	skel = test_tc_bpf__open_and_load();
	if (!skel)
		return -ENOMEM;

	fd = bpf_program__fd(skel->progs.cls);

	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex =
			    if_nametoindex("lo"), .attach_point =
			    BPF_TC_INGRESS);
	/* Create clsact qdisc */
	r = bpf_tc_hook_create(&hook);
	if (r < 0)
		goto end;

	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .prog_fd = fd);
	r = bpf_tc_attach(&hook, &opts);
	if (r < 0)
		goto end;
	/* Print the auto allocated handle and priority */
	printf("Handle=%u", opts.handle);
	printf("Priority=%u", opts.priority);

	opts.prog_fd = opts.prog_id = 0;
	bpf_tc_detach(&hook, &opts);
end:
	test_tc_bpf__destroy(skel);

This is equivalent to doing the following using tc command line:
  # tc qdisc add dev lo clsact
  # tc filter add dev lo ingress bpf obj foo.o sec classifier da
  # tc filter del dev lo ingress handle <h> prio <p> bpf
... where the handle and priority can be found using:
  # tc filter show dev lo ingress

Another example replacing a filter (extending prior example):

	/* We can also choose both (or one), let's try replacing an
	 * existing filter.
	 */
	DECLARE_LIBBPF_OPTS(bpf_tc_opts, replace_opts, .handle =
			    opts.handle, .priority = opts.priority,
			    .prog_fd = fd);
	r = bpf_tc_attach(&hook, &replace_opts);
	if (r == -EEXIST) {
		/* Expected, now use BPF_TC_F_REPLACE to replace it */
		replace_opts.flags = BPF_TC_F_REPLACE;
		return bpf_tc_attach(&hook, &replace_opts);
	} else if (r < 0) {
		return r;
	}
	/* There must be no existing filter with these
	 * attributes, so cleanup and return an error.
	 */
	replace_opts.prog_fd = replace_opts.prog_id = 0;
	bpf_tc_detach(&hook, &replace_opts);
	return -1;

To obtain info of a particular filter:

	/* Find info for filter with handle 1 and priority 50 */
	DECLARE_LIBBPF_OPTS(bpf_tc_opts, info_opts, .handle = 1,
			    .priority = 50);
	r = bpf_tc_query(&hook, &info_opts);
	if (r == -ENOENT)
		printf("Filter not found");
	else if (r < 0)
		return r;
	printf("Prog ID: %u", info_opts.prog_id);
	return 0;

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net> # libbpf API design
[ Daniel: also did major patch cleanup ]
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210512103451.989420-3-memxor@gmail.com

1 files changed, 44 insertions, 0 deletions

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3f3a24763459..cc51dc4465f2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -498,6 +498,7 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
 			     struct bpf_object **pobj, int *prog_fd);
 
+/* XDP related API */
 struct xdp_link_info {
 	__u32 prog_id;
 	__u32 drv_prog_id;
@@ -520,6 +521,49 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);
 
+/* TC related API */
+enum bpf_tc_attach_point {
+	BPF_TC_INGRESS = 1 << 0,
+	BPF_TC_EGRESS  = 1 << 1,
+	BPF_TC_CUSTOM  = 1 << 2,
+};
+
+#define BPF_TC_PARENT(a, b) 	\
+	((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU))
+
+enum bpf_tc_flags {
+	BPF_TC_F_REPLACE = 1 << 0,
+};
+
+struct bpf_tc_hook {
+	size_t sz;
+	int ifindex;
+	enum bpf_tc_attach_point attach_point;
+	__u32 parent;
+	size_t :0;
+};
+#define bpf_tc_hook__last_field parent
+
+struct bpf_tc_opts {
+	size_t sz;
+	int prog_fd;
+	__u32 flags;
+	__u32 prog_id;
+	__u32 handle;
+	__u32 priority;
+	size_t :0;
+};
+#define bpf_tc_opts__last_field priority
+
+LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook,
+			     struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook,
+			     const struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
+			    struct bpf_tc_opts *opts);
+
 /* Ring buffer APIs */
 struct ring_buffer;