Merge branch 'bpf-link-support-for-tc-bpf-programs'

Daniel Borkmann says:

====================
BPF link support for tc BPF programs

This series adds BPF link support for tc BPF programs. We initially
presented the motivation, related work and design at last year's LPC
conference in the networking & BPF track [0], and a recent update on
our progress of the rework during this year's LSF/MM/BPF summit [1].
The main changes are in first two patches and the last two have an
extensive batch of test cases we developed along with it, please see
individual patches for details. We tested this series with tc-testing
selftest suite as well as BPF CI/selftests. Thanks!

v5 -> v6:
  - Remove export symbol on tcx_inc/dec (Jakub)
  - Treat fd==0 as invalid (Stan, Alexei)
v4 -> v5:
  - Updated bpftool docs and usage of bpftool net (Quentin)
  - Consistent dump "prog id"/"link id" -> "prog_id"/"link_id" (Quentin)
  - Reworked bpftool flag output handling (Quentin)
  - LIBBPF_OPTS_RESET() macro with varargs for reinit (Andrii)
  - libbpf opts/link bail out on relative_fd && relative_id (Andrii)
  - libbpf improvements for assigning attr.relative_{id,fd} (Andrii)
  - libbpf sorting in libbpf.map (Andrii)
  - libbpf move ifindex to bpf_program__attach_tcx param (Andrii)
  - libbpf move BPF_F_ID flag handling to bpf_link_create (Andrii)
  - bpf_program_attach_fd with tcx instead of tc (Andrii)
  - Reworking kernel-internal bpf_mprog API (Alexei, Andrii)
  - Change "object" notation to "id_or_fd" (Andrii)
  - Remove on stack cpp[BPF_MPROG_MAX] and switch to memmove (Andrii)
  - Simplify bpf_mprog_{insert,delete} and add comment on internals
  - Get rid of BPF_MPROG_* return codes (Alexei, Andrii)
v3 -> v4:
  - Fix bpftool output to display tcx/{ingress,egress} (Stan)
  - Documentation around API, BPF_MPROG_* return codes and locking
    expectations (Stan, Alexei)
  - Change _after and _before to have the same semantics for return
    value (Alexei)
  - Rework mprog initialization and move allocation/free one layer
    up into tcx to simplify the code (Stan)
  - Add comment on synchronize_rcu and parent->ref (Stan)
  - Add comment on bpf_mprog_pos_() helpers wrt target position (Stan)
v2 -> v3:
  - Removal of BPF_F_FIRST/BPF_F_LAST from control UAPI (Toke, Stan)
  - Along with that full rework of bpf_mprog internals to simplify
    dependency management, looks much nicer now imho
  - Just single bpf_mprog_cp instead of two (Andrii)
  - atomic64_t for revision counter (Andrii)
  - Evaluate target position and reject on conflicts (Andrii)
  - Keep track of actual count in bpf_mprob_bundle (Andrii)
  - Make combo of REPLACE and BEFORE/AFTER work (Andrii)
  - Moved miniq as first struct member (Jamal)
  - Rework tcx_link_attach with regards to rtnl (Jakub, Andrii)
  - Moved wrappers after bpf_prog_detach_ops (Andrii)
  - Removed union for relative_fd and friends for opts and link in
    libbpf (Andrii)
  - Add doc comments to attach/detach/query libbpf APIs (Andrii)
  - Dropped SEC_ATTACHABLE_OPT (Andrii)
  - Add an OPTS_ZEROED check to bpf_link_create (Andrii)
  - Keep opts as the last argument in bpf_program_attach_fd (Andrii)
  - Rework bpf_program_attach_fd (Andrii)
  - Remove OPTS_GET before we checked OPTS_VALID in
    bpf_program__attach_tcx (Andrii)
  - Add `size_t :0;` to prevent compiler from leaving garbage (Andrii)
  - Add helper macro to clear opts structs which I found useful
    when writing tests
  - Rework of both opts and link test cases to accommodate for changes
v1 -> v2:
  - Rework of almost entire series to remove prio from UAPI and switch
    to better control directives BPF_F_FIRST/BPF_F_LAST/BPF_F_BEFORE/
    BPF_F_AFTER (Alexei, Toke, Stan, Andrii)
  - Addition of big test suite to cover all corner cases

  [0] https://lpc.events/event/16/contributions/1353/
  [1] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf
====================

Link: https://lore.kernel.org/r/20230719140858.13224-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 93 insertions, 5 deletions

diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 26a49965bf71..66a8ce8ae012 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -76,6 +76,11 @@ static const char * const attach_type_strings[] = {
 	[NET_ATTACH_TYPE_XDP_OFFLOAD]	= "xdpoffload",
 };
 
+static const char * const attach_loc_strings[] = {
+	[BPF_TCX_INGRESS]		= "tcx/ingress",
+	[BPF_TCX_EGRESS]		= "tcx/egress",
+};
+
 const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings);
 
 static enum net_attach_type parse_attach_type(const char *str)
@@ -422,8 +427,89 @@ static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 			      filter_info->devname, filter_info->ifindex);
 }
 
-static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
-			   struct ip_devname_ifindex *dev)
+static int __show_dev_tc_bpf_name(__u32 id, char *name, size_t len)
+{
+	struct bpf_prog_info info = {};
+	__u32 ilen = sizeof(info);
+	int fd, ret;
+
+	fd = bpf_prog_get_fd_by_id(id);
+	if (fd < 0)
+		return fd;
+	ret = bpf_obj_get_info_by_fd(fd, &info, &ilen);
+	if (ret < 0)
+		goto out;
+	ret = -ENOENT;
+	if (info.name[0]) {
+		get_prog_full_name(&info, fd, name, len);
+		ret = 0;
+	}
+out:
+	close(fd);
+	return ret;
+}
+
+static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev,
+			      const enum bpf_attach_type loc)
+{
+	__u32 prog_flags[64] = {}, link_flags[64] = {}, i, j;
+	__u32 prog_ids[64] = {}, link_ids[64] = {};
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	char prog_name[MAX_PROG_FULL_NAME];
+	int ret;
+
+	optq.prog_ids = prog_ids;
+	optq.prog_attach_flags = prog_flags;
+	optq.link_ids = link_ids;
+	optq.link_attach_flags = link_flags;
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	ret = bpf_prog_query_opts(dev->ifindex, loc, &optq);
+	if (ret)
+		return;
+	for (i = 0; i < optq.count; i++) {
+		NET_START_OBJECT;
+		NET_DUMP_STR("devname", "%s", dev->devname);
+		NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex);
+		NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]);
+		ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name,
+					     sizeof(prog_name));
+		if (!ret)
+			NET_DUMP_STR("name", " %s", prog_name);
+		NET_DUMP_UINT("prog_id", " prog_id %u ", prog_ids[i]);
+		if (prog_flags[i] || json_output) {
+			NET_START_ARRAY("prog_flags", "%s ");
+			for (j = 0; prog_flags[i] && j < 32; j++) {
+				if (!(prog_flags[i] & (1 << j)))
+					continue;
+				NET_DUMP_UINT_ONLY(1 << j);
+			}
+			NET_END_ARRAY("");
+		}
+		if (link_ids[i] || json_output) {
+			NET_DUMP_UINT("link_id", "link_id %u ", link_ids[i]);
+			if (link_flags[i] || json_output) {
+				NET_START_ARRAY("link_flags", "%s ");
+				for (j = 0; link_flags[i] && j < 32; j++) {
+					if (!(link_flags[i] & (1 << j)))
+						continue;
+					NET_DUMP_UINT_ONLY(1 << j);
+				}
+				NET_END_ARRAY("");
+			}
+		}
+		NET_END_OBJECT_FINAL;
+	}
+}
+
+static void show_dev_tc_bpf(struct ip_devname_ifindex *dev)
+{
+	__show_dev_tc_bpf(dev, BPF_TCX_INGRESS);
+	__show_dev_tc_bpf(dev, BPF_TCX_EGRESS);
+}
+
+static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid,
+				   struct ip_devname_ifindex *dev)
 {
 	struct bpf_filter_t filter_info;
 	struct bpf_tcinfo_t tcinfo;
@@ -790,8 +876,9 @@ static int do_show(int argc, char **argv)
 	if (!ret) {
 		NET_START_ARRAY("tc", "%s:\n");
 		for (i = 0; i < dev_array.used_len; i++) {
-			ret = show_dev_tc_bpf(sock, nl_pid,
-					      &dev_array.devices[i]);
+			show_dev_tc_bpf(&dev_array.devices[i]);
+			ret = show_dev_tc_bpf_classic(sock, nl_pid,
+						      &dev_array.devices[i]);
 			if (ret)
 				break;
 		}
@@ -839,7 +926,8 @@ static int do_help(int argc, char **argv)
 		"       ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n"
 		"       " HELP_SPEC_OPTIONS " }\n"
 		"\n"
-		"Note: Only xdp and tc attachments are supported now.\n"
+		"Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n"
+		"      are currently supported.\n"
 		"      For progs attached to cgroups, use \"bpftool cgroup\"\n"
 		"      to dump program attachments. For program types\n"
 		"      sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n"