[PATCHv4 bpf-next 0/3] bpf: tracing_multi link info support

[PATCHv4 bpf-next 0/3] bpf: tracing_multi link info support

[Jiri Olsa]

hi,
adding link info support for tracing_multi link.

Adding the kernel support with related selftests and bpftool support
to display the tracing_multi link info, the output looks like:

  # bpftool link
  ...
  61: tracing_multi  prog 167
          attach_type trace_fentry_multi  btf_obj_id 1  count 3
          btf_id           addr             cookie           func [module]
          92598            ffffffff825017c4 10               bpf_fentry_test1
          92600            ffffffff82503814 30               bpf_fentry_test2
          92601            ffffffff82503824 20               bpf_fentry_test3
          pids test_progs(1540)

thanks,
jirka


v1: https://lore.kernel.org/bpf/20260621204524.61067-1-jolsa@kernel.org/
v2: https://lore.kernel.org/bpf/20260623142417.275892-1-jolsa@kernel.org/
v3: https://lore.kernel.org/bpf/20260629143844.862369-1-jolsa@kernel.org/

v4 changes:
- fix wrong allocation check [Alexei]

v3 changes:
- added acks [Andrii, Leon]
- display cookies as decimal numbers [Andrii]
- renamed obj_id to btf_obj_id [Andrii]
- several fixes in bpftool change [Andrii]

v2 changes:
- fix kernel symbol search logic [sashiko]
- typo fixes [bots]


---
Jiri Olsa (3):
      bpf: Add tracing_multi link info support
      selftests/bpf: Add tracing_multi link info tests
      bpftool: Add tracing_multi link info output

 include/uapi/linux/bpf.h                                |   9 +++
 kernel/trace/bpf_trace.c                                |  55 +++++++++++++++++
 tools/bpf/bpftool/link.c                                | 133 ++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h                          |   9 +++
 tools/testing/selftests/bpf/prog_tests/fill_link_info.c | 242 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_fill_link_info.c |   6 ++
 6 files changed, 454 insertions(+)

[PATCHv4 bpf-next 1/3] bpf: Add tracing_multi link info support

[Jiri Olsa]

Adding BPF_OBJ_GET_INFO_BY_FD support for tracing_multi links.

We expose following tracing_multi link data:
- attach_type of the program
- number of ids
- array of BTF ids
- array of its related kernel addresses
- array of cookies

The change follows the kprobe_multi and uprobe_multi link-info convention
of optional output arrays with an in/out count,

On top of standard tracing link data we also expose addresses, because they
are useful info for user (especially when the attachment was done via pattern).
This data is hidden when kallsyms does not allow exposing kernel pointer values.

Assisted-by: Codex:GPT-5
Acked-by: Leon Hwang <leon.hwang@linux.dev>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 include/uapi/linux/bpf.h       |  9 ++++++
 kernel/trace/bpf_trace.c       | 55 ++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 ++++++
 3 files changed, 73 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 89b36de5fdbb..4180262814e7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6839,6 +6839,15 @@ struct bpf_link_info {
 			__u32 flags;
 			__u32 pid;
 		} uprobe_multi;
+		struct {
+			__u32 attach_type;
+			__u32 count; /* in/out: tracing_multi target count */
+			__u32 btf_obj_id;
+			__u32 :32;
+			__aligned_u64 ids;
+			__aligned_u64 addrs;
+			__aligned_u64 cookies;
+		} tracing_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 82f8feea6931..0711810f4562 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3699,6 +3699,60 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link)
 	kvfree(tr_link);
 }
 
+static int bpf_tracing_multi_link_fill_link_info(const struct bpf_link *link,
+						 struct bpf_link_info *info)
+{
+	u64 __user *ucookies = u64_to_user_ptr(info->tracing_multi.cookies);
+	u64 __user *uaddrs = u64_to_user_ptr(info->tracing_multi.addrs);
+	u32 __user *uids = u64_to_user_ptr(info->tracing_multi.ids);
+	struct bpf_tracing_multi_link *tr_link;
+	u32 ucount = info->tracing_multi.count;
+	bool has_cookies, show_addrs;
+	int err = 0;
+
+	if ((uids || ucookies || uaddrs) && !ucount)
+		return -EINVAL;
+
+	tr_link = container_of(link, struct bpf_tracing_multi_link, link);
+
+	info->tracing_multi.attach_type = tr_link->link.attach_type;
+	info->tracing_multi.count = tr_link->nodes_cnt;
+	info->tracing_multi.btf_obj_id = btf_obj_id(tr_link->link.prog->aux->attach_btf);
+
+	if (!uids && !ucookies && !uaddrs)
+		return 0;
+
+	if (ucount < tr_link->nodes_cnt)
+		err = -ENOSPC;
+	else
+		ucount = tr_link->nodes_cnt;
+
+	has_cookies = !!tr_link->cookies;
+	show_addrs = kallsyms_show_value(current_cred());
+
+	for (int i = 0; i < ucount; i++) {
+		struct bpf_tracing_multi_node *mnode = &tr_link->nodes[i];
+		u64 addr, cookie;
+		u32 id;
+
+		bpf_trampoline_unpack_key(mnode->trampoline->key, NULL, &id);
+
+		addr = show_addrs ? mnode->trampoline->ip : 0;
+		cookie = has_cookies ? tr_link->cookies[i] : 0;
+
+		if (uids && put_user(id, uids + i))
+			return -EFAULT;
+		if (uaddrs && put_user(addr, uaddrs + i))
+			return -EFAULT;
+		if (ucookies && put_user(cookie, ucookies + i))
+			return -EFAULT;
+
+		cond_resched();
+	}
+
+	return err;
+}
+
 #ifdef CONFIG_PROC_FS
 static void bpf_tracing_multi_show_fdinfo(const struct bpf_link *link,
 					  struct seq_file *seq)
@@ -3729,6 +3783,7 @@ static void bpf_tracing_multi_show_fdinfo(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_tracing_multi_link_lops = {
 	.release = bpf_tracing_multi_link_release,
 	.dealloc_deferred = bpf_tracing_multi_link_dealloc,
+	.fill_link_info = bpf_tracing_multi_link_fill_link_info,
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo = bpf_tracing_multi_show_fdinfo,
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 89b36de5fdbb..4180262814e7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6839,6 +6839,15 @@ struct bpf_link_info {
 			__u32 flags;
 			__u32 pid;
 		} uprobe_multi;
+		struct {
+			__u32 attach_type;
+			__u32 count; /* in/out: tracing_multi target count */
+			__u32 btf_obj_id;
+			__u32 :32;
+			__aligned_u64 ids;
+			__aligned_u64 addrs;
+			__aligned_u64 cookies;
+		} tracing_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
-- 
2.54.0

[PATCHv4 bpf-next 2/3] selftests/bpf: Add tracing_multi link info tests

[Jiri Olsa]

Adding tracing_multi link info tests that follow the kprobe_multi
and uprobe_multi tests logic.

Assisted-by: Codex:GPT-5
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 .../selftests/bpf/prog_tests/fill_link_info.c | 242 ++++++++++++++++++
 .../selftests/bpf/progs/test_fill_link_info.c |   6 +
 2 files changed, 248 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index f589eefbf9fb..0918321c8e63 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -4,6 +4,7 @@
 #include <string.h>
 #include <linux/bpf.h>
 #include <linux/limits.h>
+#include <bpf/btf.h>
 #include <test_progs.h>
 #include "trace_helpers.h"
 #include "test_fill_link_info.skel.h"
@@ -24,6 +25,22 @@ static __u64 kmulti_cookies[] = { 3, 1, 2 };
 #define KPROBE_FUNC "bpf_fentry_test1"
 static __u64 kprobe_addr;
 
+static const char * const tmulti_syms[] = {
+	"bpf_fentry_test2",
+	"bpf_fentry_test1",
+	"bpf_fentry_test3",
+};
+
+static __u64 tmulti_cookies[] = { 30, 10, 20 };
+#define TRACING_MULTI_CNT ARRAY_SIZE(tmulti_syms)
+
+struct tmulti_target {
+	const char *name;
+	__u64 addr;
+	__u64 cookie;
+	__u32 id;
+};
+
 #define UPROBE_FILE "/proc/self/exe"
 static ssize_t uprobe_offset;
 /* uprobe attach point */
@@ -396,6 +413,224 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
 	bpf_link__destroy(link);
 }
 
+static int tmulti_target_cmp(const void *a, const void *b)
+{
+	const struct tmulti_target *ta = a;
+	const struct tmulti_target *tb = b;
+
+	return (ta->id > tb->id) - (ta->id < tb->id);
+}
+
+static int setup_tmulti_targets(const struct bpf_program *prog,
+				struct tmulti_target *targets,
+				__u32 *btf_obj_id)
+{
+	struct bpf_prog_info prog_info;
+	__u32 len = sizeof(prog_info);
+	struct btf *btf;
+	int err, i;
+	__s32 id;
+
+	btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(btf, "btf__load_vmlinux_btf"))
+		return -1;
+
+	for (i = 0; i < TRACING_MULTI_CNT; i++) {
+		id = btf__find_by_name_kind(btf, tmulti_syms[i], BTF_KIND_FUNC);
+		if (!ASSERT_GT(id, 0, "btf__find_by_name_kind"))
+			goto error;
+
+		targets[i].name = tmulti_syms[i];
+		targets[i].addr = ksym_get_addr(tmulti_syms[i]);
+		targets[i].cookie = tmulti_cookies[i];
+		targets[i].id = id;
+	}
+
+	memset(&prog_info, 0, len);
+	err = bpf_prog_get_info_by_fd(bpf_program__fd(prog), &prog_info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		goto error;
+	if (!ASSERT_GT(prog_info.attach_btf_obj_id, 0, "attach_btf_obj_id"))
+		goto error;
+	*btf_obj_id = prog_info.attach_btf_obj_id;
+
+	/*
+	 * The kernel tracing multi attach sorts ids. We sort as well,
+	 * so we can easily compare ids and cookies later.
+	 */
+	qsort(targets, TRACING_MULTI_CNT, sizeof(targets[0]), tmulti_target_cmp);
+	btf__free(btf);
+	return 0;
+
+error:
+	btf__free(btf);
+	return -1;
+}
+
+static int verify_tracing_multi_link_info(int fd, const struct bpf_program *prog,
+					  const struct tmulti_target *targets,
+					  __u32 btf_obj_id, bool has_cookies)
+{
+	enum bpf_attach_type attach_type = bpf_program__expected_attach_type(prog);
+	__u64 addrs[TRACING_MULTI_CNT], cookies[TRACING_MULTI_CNT];
+	__u32 ids[TRACING_MULTI_CNT];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err, i;
+
+	memset(&info, 0, sizeof(info));
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING_MULTI, "info.type"))
+		return -1;
+
+	ASSERT_EQ(info.tracing_multi.attach_type, attach_type, "info.tracing_multi.attach_type");
+	ASSERT_EQ(info.tracing_multi.count, TRACING_MULTI_CNT, "info.tracing_multi.count");
+
+	memset(ids, 0, sizeof(ids));
+	memset(cookies, 0, sizeof(cookies));
+	memset(addrs, 0, sizeof(addrs));
+
+	info.tracing_multi.ids = ptr_to_u64(ids);
+	info.tracing_multi.addrs = ptr_to_u64(addrs);
+	info.tracing_multi.cookies = has_cookies ? ptr_to_u64(cookies) : 0;
+	info.tracing_multi.count = TRACING_MULTI_CNT;
+
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING_MULTI, "info.type"))
+		return -1;
+
+	ASSERT_EQ(info.tracing_multi.attach_type, attach_type, "info.tracing_multi.attach_type");
+	ASSERT_EQ(info.tracing_multi.count, TRACING_MULTI_CNT, "info.tracing_multi.count");
+	ASSERT_EQ(info.tracing_multi.btf_obj_id, btf_obj_id, "tracing_multi.btf_obj_id");
+
+	for (i = 0; i < TRACING_MULTI_CNT; i++) {
+		ASSERT_EQ(ids[i], targets[i].id, "tracing_multi.ids");
+		ASSERT_EQ(cookies[i], has_cookies ? targets[i].cookie : 0, "tracing_multi.cookies");
+
+		if (targets[i].addr) {
+			struct ksym *ksym;
+
+			if (!ASSERT_NEQ(addrs[i], 0, "tracing_multi.addrs"))
+				return -1;
+			ksym = ksym_search(addrs[i]);
+			if (!ASSERT_OK_PTR(ksym, "ksym_search"))
+				return -1;
+			ASSERT_STREQ(ksym->name, targets[i].name, "tracing_multi.addr_name");
+		} else {
+			ASSERT_EQ(addrs[i], 0, "tracing_multi.addrs");
+		}
+	}
+
+	return 0;
+}
+
+static void verify_tracing_multi_invalid_user_buffer(int fd, const struct tmulti_target *targets)
+{
+	__u32 ids[TRACING_MULTI_CNT] = {};
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err, i;
+
+	/* Wrong info setup (ids != NULL and cnt == 0) -> EINVAL */
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.ids = ptr_to_u64(ids);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "tracing_multi.invalid_count");
+
+	/* Smaller than actual count provided -> ENOSPC */
+	memset(ids, 0, sizeof(ids));
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.ids = ptr_to_u64(ids);
+	info.tracing_multi.count = TRACING_MULTI_CNT - 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "tracing_multi.small_count");
+	for (i = 0; i < TRACING_MULTI_CNT - 1; i++)
+		ASSERT_EQ(ids[i], targets[i].id, "tracing_multi.partial_ids");
+	/* check that the last entry is not populated */
+	ASSERT_EQ(ids[i], 0, "tracing_multi.partial_ids");
+
+	/* Bigger than actual count provided -> OK */
+	memset(ids, 0, sizeof(ids));
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.ids = ptr_to_u64(ids);
+	info.tracing_multi.count = TRACING_MULTI_CNT + 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_OK(err, "tracing_multi.big_count");
+	for (i = 0; i < TRACING_MULTI_CNT; i++)
+		ASSERT_EQ(ids[i], targets[i].id, "tracing_multi.ids");
+
+	/* Invalid ids pointer -> EFAULT */
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.ids = 0x1;
+	info.tracing_multi.count = TRACING_MULTI_CNT;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "tracing_multi.bad_btf_ids");
+
+	/* Invalid cookies pointer -> EFAULT */
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.cookies = 0x1;
+	info.tracing_multi.count = TRACING_MULTI_CNT;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "tracing_multi.bad_cookies");
+
+	/* Invalid addrs pointer -> EFAULT */
+	memset(&info, 0, sizeof(info));
+	info.tracing_multi.addrs = 0x1;
+	info.tracing_multi.count = TRACING_MULTI_CNT;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "tracing_multi.bad_addrs");
+}
+
+static void test_tracing_multi_fill_link_info(struct test_fill_link_info *skel,
+					      bool has_cookies, bool invalid)
+{
+	LIBBPF_OPTS(bpf_tracing_multi_opts, opts);
+	struct tmulti_target targets[TRACING_MULTI_CNT];
+	__u32 ids[TRACING_MULTI_CNT], btf_obj_id;
+	__u64 cookies[TRACING_MULTI_CNT];
+	struct bpf_link *link;
+	int link_fd, err, i;
+
+#ifndef __x86_64__
+	test__skip();
+	return;
+#endif
+
+	if (setup_tmulti_targets(skel->progs.tmulti_run, targets, &btf_obj_id))
+		return;
+
+	for (i = 0; i < TRACING_MULTI_CNT; i++) {
+		ids[i] = targets[i].id;
+		cookies[i] = targets[i].cookie;
+	}
+
+	opts.ids = ids;
+	opts.cnt = TRACING_MULTI_CNT;
+	if (has_cookies)
+		opts.cookies = cookies;
+
+	link = bpf_program__attach_tracing_multi(skel->progs.tmulti_run, NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_tracing_multi"))
+		return;
+
+	link_fd = bpf_link__fd(link);
+	if (invalid) {
+		verify_tracing_multi_invalid_user_buffer(link_fd, targets);
+	} else {
+		err = verify_tracing_multi_link_info(link_fd, skel->progs.tmulti_run,
+						     targets, btf_obj_id, has_cookies);
+		ASSERT_OK(err, "verify_tracing_multi_link_info");
+	}
+
+	bpf_link__destroy(link);
+}
+
 #define SEC(name) __attribute__((section(name), used))
 
 static short uprobe_link_info_sema_1 SEC(".probes");
@@ -640,6 +875,13 @@ void test_fill_link_info(void)
 	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
 		test_kprobe_multi_fill_link_info(skel, true, true, true);
 
+	if (test__start_subtest("tracing_multi_link_info")) {
+		test_tracing_multi_fill_link_info(skel, false, false);
+		test_tracing_multi_fill_link_info(skel, true, false);
+	}
+	if (test__start_subtest("tracing_multi_invalid_ubuff"))
+		test_tracing_multi_fill_link_info(skel, true, true);
+
 	if (test__start_subtest("uprobe_multi_link_info"))
 		test_uprobe_multi_fill_link_info(skel, false, false);
 	if (test__start_subtest("uretprobe_multi_link_info"))
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
index 137bd6292163..c85081538e93 100644
--- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -58,4 +58,10 @@ int BPF_PROG(umulti_run)
 	return 0;
 }
 
+SEC("fentry.multi")
+int BPF_PROG(tmulti_run)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
2.54.0

[PATCHv4 bpf-next 3/3] bpftool: Add tracing_multi link info output

[Jiri Olsa]

Adding bpftool support to show tracing_multi link details,
the new output looks like:

  # bpftool link
  ...
  61: tracing_multi  prog 167
          attach_type trace_fentry_multi  btf_obj_id 1  count 3
          btf_id           addr             cookie           func [module]
          92598            ffffffff825017c4 10               bpf_fentry_test1
          92600            ffffffff82503814 30               bpf_fentry_test2
          92601            ffffffff82503824 20               bpf_fentry_test3
          pids test_progs(1540)

Assisted-by: Codex:GPT-5
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/bpf/bpftool/link.c | 133 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 133 insertions(+)

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index bdcd717b0348..088d1d206065 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -377,6 +377,25 @@ static __u64 *u64_to_arr(__u64 val)
 	return (__u64 *) u64_to_ptr(val);
 }
 
+static __u32 *u64_to_u32_arr(__u64 val)
+{
+	return (__u32 *)u64_to_ptr(val);
+}
+
+static struct kernel_sym *find_kernel_sym_by_addr(__u64 addr, bool is_ibt_enabled)
+{
+	struct kernel_sym *sym;
+
+	if (!addr)
+		return NULL;
+
+	sym = kernel_syms_search(&dd, addr);
+	if (!sym && is_ibt_enabled && addr >= 4)
+		sym = kernel_syms_search(&dd, addr - 4);
+
+	return sym;
+}
+
 static void
 show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
 {
@@ -403,6 +422,52 @@ show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_end_array(json_wtr);
 }
 
+static void
+show_tracing_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	bool is_ibt_enabled = is_x86_ibt_enabled(), show_symbol;
+	__u64 *addrs, *cookies;
+	__u32 i, *ids;
+
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	show_symbol = !!dd.sym_count;
+
+	show_link_attach_type_json(info->tracing_multi.attach_type, wtr);
+	jsonw_uint_field(wtr, "func_cnt", info->tracing_multi.count);
+	jsonw_uint_field(wtr, "btf_obj_id", info->tracing_multi.btf_obj_id);
+	jsonw_name(wtr, "funcs");
+
+	jsonw_start_array(wtr);
+
+	ids = u64_to_u32_arr(info->tracing_multi.ids);
+	addrs = u64_to_arr(info->tracing_multi.addrs);
+	cookies = u64_to_arr(info->tracing_multi.cookies);
+
+	for (i = 0; i < info->tracing_multi.count; i++) {
+		struct kernel_sym *sym;
+		__u64 addr = addrs[i];
+
+		sym = show_symbol ? find_kernel_sym_by_addr(addr, is_ibt_enabled) : NULL;
+
+		jsonw_start_object(wtr);
+		jsonw_uint_field(wtr, "id", ids[i]);
+		jsonw_uint_field(wtr, "addr", addr);
+		if (sym) {
+			jsonw_string_field(wtr, "func", sym->name);
+			if (sym->module[0] == '\0') {
+				jsonw_name(wtr, "module");
+				jsonw_null(wtr);
+			} else {
+				jsonw_string_field(wtr, "module", sym->module);
+			}
+		}
+		jsonw_uint_field(wtr, "cookie", cookies[i]);
+		jsonw_end_object(wtr);
+	}
+	jsonw_end_array(wtr);
+}
+
 static void
 show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
 {
@@ -589,6 +654,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_UPROBE_MULTI:
 		show_uprobe_multi_json(info, json_wtr);
 		break;
+	case BPF_LINK_TYPE_TRACING_MULTI:
+		show_tracing_multi_json(info, json_wtr);
+		break;
 	case BPF_LINK_TYPE_PERF_EVENT:
 		switch (info->perf_event.type) {
 		case BPF_PERF_EVENT_EVENT:
@@ -833,6 +901,46 @@ static void show_uprobe_multi_plain(struct bpf_link_info *info)
 	}
 }
 
+static void show_tracing_multi_plain(struct bpf_link_info *info)
+{
+	bool is_ibt_enabled = is_x86_ibt_enabled(), show_symbol;
+	__u64 *addrs, *cookies;
+	__u32 i, *ids;
+
+	if (!info->tracing_multi.count)
+		return;
+
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	show_symbol = !!dd.sym_count;
+
+	printf("\n\t");
+	show_link_attach_type_plain(info->tracing_multi.attach_type);
+	printf("btf_obj_id %u  ", info->tracing_multi.btf_obj_id);
+	printf("count %u  ", info->tracing_multi.count);
+
+	printf("\n\t%-16s %-16s %-16s %s",
+	       "btf_id", "addr", "cookie", "func [module]");
+
+	ids = u64_to_u32_arr(info->tracing_multi.ids);
+	addrs = u64_to_arr(info->tracing_multi.addrs);
+	cookies = u64_to_arr(info->tracing_multi.cookies);
+
+	for (i = 0; i < info->tracing_multi.count; i++) {
+		__u64 addr = addrs[i];
+		struct kernel_sym *sym;
+
+		sym = show_symbol ? find_kernel_sym_by_addr(addr, is_ibt_enabled) : NULL;
+
+		printf("\n\t%-16u %016llx %-16llu", ids[i], addr, cookies[i]);
+		if (sym) {
+			printf(" %s", sym->name);
+			if (sym->module[0] != '\0')
+				printf(" [%s]", sym->module);
+		}
+	}
+}
+
 static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
 {
 	const char *buf;
@@ -989,6 +1097,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_UPROBE_MULTI:
 		show_uprobe_multi_plain(info);
 		break;
+	case BPF_LINK_TYPE_TRACING_MULTI:
+		show_tracing_multi_plain(info);
+		break;
 	case BPF_LINK_TYPE_PERF_EVENT:
 		switch (info->perf_event.type) {
 		case BPF_PERF_EVENT_EVENT:
@@ -1029,6 +1140,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 static int do_show_link(int fd)
 {
 	__u64 *ref_ctr_offsets = NULL, *offsets = NULL, *cookies = NULL;
+	__u32 *ids = NULL;
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
 	char path_buf[PATH_MAX];
@@ -1114,6 +1226,26 @@ static int do_show_link(int fd)
 			goto again;
 		}
 	}
+	if (info.type == BPF_LINK_TYPE_TRACING_MULTI && !info.tracing_multi.ids) {
+		count = info.tracing_multi.count;
+		if (count) {
+			ids = calloc(count, sizeof(__u32));
+			addrs = calloc(count, sizeof(__u64));
+			cookies = calloc(count, sizeof(__u64));
+			if (!ids || !addrs || !cookies) {
+				p_err("mem alloc failed");
+				close(fd);
+				free(cookies);
+				free(addrs);
+				free(ids);
+				return -ENOMEM;
+			}
+			info.tracing_multi.ids = ptr_to_u64(ids);
+			info.tracing_multi.addrs = ptr_to_u64(addrs);
+			info.tracing_multi.cookies = ptr_to_u64(cookies);
+			goto again;
+		}
+	}
 	if (info.type == BPF_LINK_TYPE_PERF_EVENT) {
 		switch (info.perf_event.type) {
 		case BPF_PERF_EVENT_TRACEPOINT:
@@ -1153,6 +1285,7 @@ static int do_show_link(int fd)
 	free(cookies);
 	free(offsets);
 	free(addrs);
+	free(ids);
 	close(fd);
 	return 0;
 }
-- 
2.54.0

Re: [PATCHv4 bpf-next 3/3] bpftool: Add tracing_multi link info output

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Medium] bpftool uses a non-existent `tracing_multi` union member in `struct bpf_link_info`.
- [Medium] The kernel-side `bpf_tracing_multi_link_lops` is missing the `.fill_link_info` callback.
- [Low] Memory allocated for `ids`, `addrs`, and `cookies` is leaked on the error path of the `bpf_link_get_info_by_fd` syscall.
--

commit 3c4bad76286f49adf87a7b01dc7042ac6368c5ce
Author: Jiri Olsa <jolsa@kernel.org>

bpftool: Add tracing_multi link info output

Adding bpftool support to show tracing_multi link details. The new output will
display attach types, counts, BTF IDs, addresses, cookies, and functions.

> diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
> index bdcd717b0348f..088d1d206065f 100644
> --- a/tools/bpf/bpftool/link.c
> +++ b/tools/bpf/bpftool/link.c

[ ... ]

> @@ -403,6 +422,52 @@ show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
>  	jsonw_end_array(json_wtr);
>  }
>  
> +static void
> +show_tracing_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
> +{
> +	bool is_ibt_enabled = is_x86_ibt_enabled(), show_symbol;
> +	__u64 *addrs, *cookies;
> +	__u32 i, *ids;
> +
> +	if (!dd.sym_count)
> +		kernel_syms_load(&dd);
> +	show_symbol = !!dd.sym_count;
> +
> +	show_link_attach_type_json(info->tracing_multi.attach_type, wtr);

[Severity: Medium]
Does `struct bpf_link_info` in `include/uapi/linux/bpf.h` include a
`tracing_multi` member?

It looks like the `tracing_multi` struct is missing from `struct bpf_link_info`
in the UAPI, which causes a compile error here when trying to access
`info->tracing_multi.attach_type`.

Additionally, the kernel-side implementation in `kernel/trace/bpf_trace.c`
appears to be missing the `.fill_link_info` callback in
`bpf_tracing_multi_link_lops`.

Without it, will the kernel silently return unpopulated link details when
queried via `bpf_obj_get_info_by_fd()`?

[ ... ]

> @@ -1114,6 +1226,26 @@ static int do_show_link(int fd)
>  			goto again;
>  		}
>  	}
> +	if (info.type == BPF_LINK_TYPE_TRACING_MULTI && !info.tracing_multi.ids) {
> +		count = info.tracing_multi.count;
> +		if (count) {
> +			ids = calloc(count, sizeof(__u32));
> +			addrs = calloc(count, sizeof(__u64));
> +			cookies = calloc(count, sizeof(__u64));
> +			if (!ids || !addrs || !cookies) {
> +				p_err("mem alloc failed");
> +				close(fd);
> +				free(cookies);
> +				free(addrs);
> +				free(ids);
> +				return -ENOMEM;
> +			}
> +			info.tracing_multi.ids = ptr_to_u64(ids);
> +			info.tracing_multi.addrs = ptr_to_u64(addrs);
> +			info.tracing_multi.cookies = ptr_to_u64(cookies);
> +			goto again;

[Severity: Low]
Do we leak the memory allocated for `ids`, `addrs`, and `cookies` if the
subsequent `bpf_link_get_info_by_fd()` syscall fails?

When jumping to `again:`, if `bpf_link_get_info_by_fd()` returns an error, the
function returns early without freeing these arrays:

tools/bpf/bpftool/link.c:do_show_link() {
    ...
    again:
	err = bpf_link_get_info_by_fd(fd, &info, &len);
	if (err) {
		p_err("can't get link info: %s",
		      strerror(errno));
		close(fd);
		return err;
	}
    ...
}

Should the error path free these arrays before returning?

> +		}
> +	}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629212208.895962-4-jolsa@kernel.org?part=1

Re: [PATCHv4 bpf-next 2/3] selftests/bpf: Add tracing_multi link info tests

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Missing UAPI and kernel implementation for 'tracing_multi' link info.
- [Medium] Flawed negative testing logic for 'tracing_multi' invalid user buffers.
--

commit 10d5275538071b94b5cfb747b2b37b5cb2e5d158
Author: Jiri Olsa <jolsa@kernel.org>

selftests/bpf: Add tracing_multi link info tests

Adding tracing_multi link info tests that follow the kprobe_multi
and uprobe_multi tests logic.

> diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
> index f589eefbf9fbd..0918321c8e63d 100644
> --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
> +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
[ ... ]
> @@ -396,6 +413,224 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
[ ... ]
> +static int verify_tracing_multi_link_info(int fd, const struct bpf_program *prog,
> +					  const struct tmulti_target *targets,
> +					  __u32 btf_obj_id, bool has_cookies)
> +{
> +	enum bpf_attach_type attach_type = bpf_program__expected_attach_type(prog);
> +	__u64 addrs[TRACING_MULTI_CNT], cookies[TRACING_MULTI_CNT];
> +	__u32 ids[TRACING_MULTI_CNT];
> +	struct bpf_link_info info;
> +	__u32 len = sizeof(info);
> +	int err, i;
> +
> +	memset(&info, 0, sizeof(info));
> +	err = bpf_link_get_info_by_fd(fd, &info, &len);
> +	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
> +		return -1;
> +
> +	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING_MULTI, "info.type"))
> +		return -1;
> +
> +	ASSERT_EQ(info.tracing_multi.attach_type, attach_type, "info.tracing_multi.attach_type");
> +	ASSERT_EQ(info.tracing_multi.count, TRACING_MULTI_CNT, "info.tracing_multi.count");

[Severity: Medium]
Does struct bpf_link_info currently have a tracing_multi member? It appears
this might cause a compilation failure because the UAPI header doesn't include
it. Also, does the kernel side implement the .fill_link_info callback in
bpf_tracing_multi_link_lops?

> +
> +	memset(ids, 0, sizeof(ids));
> +	memset(cookies, 0, sizeof(cookies));
> +	memset(addrs, 0, sizeof(addrs));
[ ... ]
> +static void verify_tracing_multi_invalid_user_buffer(int fd, const struct tmulti_target *targets)
> +{
> +	__u32 ids[TRACING_MULTI_CNT] = {};
> +	struct bpf_link_info info;
> +	__u32 len = sizeof(info);
> +	int err, i;
[ ... ]
> +	/* Invalid addrs pointer -> EFAULT */
> +	memset(&info, 0, sizeof(info));
> +	info.tracing_multi.addrs = 0x1;
> +	info.tracing_multi.count = TRACING_MULTI_CNT;
> +	err = bpf_link_get_info_by_fd(fd, &info, &len);
> +	ASSERT_EQ(err, -EFAULT, "tracing_multi.bad_addrs");

[Severity: Medium]
Will this test actually return -EFAULT?

By zeroing out the info struct before these checks, the mandatory ids
pointer is left as NULL while count is non-zero. If the kernel validation
logic eagerly rejects the missing ids array with -EINVAL before reaching
the -EFAULT paths, won't this assertion fail?

> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629212208.895962-3-jolsa@kernel.org?part=1

Re: [PATCHv4 bpf-next 3/3] bpftool: Add tracing_multi link info output

[Jiri Olsa]

On Mon, Jun 29, 2026 at 09:33:29PM +0000, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
> - [Medium] bpftool uses a non-existent `tracing_multi` union member in `struct bpf_link_info`.
> - [Medium] The kernel-side `bpf_tracing_multi_link_lops` is missing the `.fill_link_info` callback.
> - [Low] Memory allocated for `ids`, `addrs`, and `cookies` is leaked on the error path of the `bpf_link_get_info_by_fd` syscall.
> --
> 
> commit 3c4bad76286f49adf87a7b01dc7042ac6368c5ce
> Author: Jiri Olsa <jolsa@kernel.org>
> 
> bpftool: Add tracing_multi link info output
> 
> Adding bpftool support to show tracing_multi link details. The new output will
> display attach types, counts, BTF IDs, addresses, cookies, and functions.
> 
> > diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
> > index bdcd717b0348f..088d1d206065f 100644
> > --- a/tools/bpf/bpftool/link.c
> > +++ b/tools/bpf/bpftool/link.c
> 
> [ ... ]
> 
> > @@ -403,6 +422,52 @@ show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
> >  	jsonw_end_array(json_wtr);
> >  }
> >  
> > +static void
> > +show_tracing_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
> > +{
> > +	bool is_ibt_enabled = is_x86_ibt_enabled(), show_symbol;
> > +	__u64 *addrs, *cookies;
> > +	__u32 i, *ids;
> > +
> > +	if (!dd.sym_count)
> > +		kernel_syms_load(&dd);
> > +	show_symbol = !!dd.sym_count;
> > +
> > +	show_link_attach_type_json(info->tracing_multi.attach_type, wtr);
> 
> [Severity: Medium]
> Does `struct bpf_link_info` in `include/uapi/linux/bpf.h` include a
> `tracing_multi` member?
> 
> It looks like the `tracing_multi` struct is missing from `struct bpf_link_info`
> in the UAPI, which causes a compile error here when trying to access
> `info->tracing_multi.attach_type`.
> 
> Additionally, the kernel-side implementation in `kernel/trace/bpf_trace.c`
> appears to be missing the `.fill_link_info` callback in
> `bpf_tracing_multi_link_lops`.
> 
> Without it, will the kernel silently return unpopulated link details when
> queried via `bpf_obj_get_info_by_fd()`?
> 
> [ ... ]
> 
> > @@ -1114,6 +1226,26 @@ static int do_show_link(int fd)
> >  			goto again;
> >  		}
> >  	}
> > +	if (info.type == BPF_LINK_TYPE_TRACING_MULTI && !info.tracing_multi.ids) {
> > +		count = info.tracing_multi.count;
> > +		if (count) {
> > +			ids = calloc(count, sizeof(__u32));
> > +			addrs = calloc(count, sizeof(__u64));
> > +			cookies = calloc(count, sizeof(__u64));
> > +			if (!ids || !addrs || !cookies) {
> > +				p_err("mem alloc failed");
> > +				close(fd);
> > +				free(cookies);
> > +				free(addrs);
> > +				free(ids);
> > +				return -ENOMEM;
> > +			}
> > +			info.tracing_multi.ids = ptr_to_u64(ids);
> > +			info.tracing_multi.addrs = ptr_to_u64(addrs);
> > +			info.tracing_multi.cookies = ptr_to_u64(cookies);
> > +			goto again;
> 
> [Severity: Low]
> Do we leak the memory allocated for `ids`, `addrs`, and `cookies` if the
> subsequent `bpf_link_get_info_by_fd()` syscall fails?
> 
> When jumping to `again:`, if `bpf_link_get_info_by_fd()` returns an error, the
> function returns early without freeing these arrays:
> 
> tools/bpf/bpftool/link.c:do_show_link() {
>     ...
>     again:
> 	err = bpf_link_get_info_by_fd(fd, &info, &len);
> 	if (err) {
> 		p_err("can't get link info: %s",
> 		      strerror(errno));
> 		close(fd);
> 		return err;
> 	}
>     ...
> }
> 
> Should the error path free these arrays before returning?

right, that's pre-existing issue, I think we could do something like
below.. will send a separate fix

jirka


---
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 088d1d206065..3f5b3b12a404 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -1156,8 +1156,7 @@ static int do_show_link(int fd)
 	if (err) {
 		p_err("can't get link info: %s",
 		      strerror(errno));
-		close(fd);
-		return err;
+		goto out;
 	}
 	if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT &&
 	    !info.raw_tracepoint.tp_name) {
@@ -1281,13 +1280,14 @@ static int do_show_link(int fd)
 	else
 		show_link_close_plain(fd, &info);
 
+out:
 	free(ref_ctr_offsets);
 	free(cookies);
 	free(offsets);
 	free(addrs);
 	free(ids);
 	close(fd);
-	return 0;
+	return err;
 }
 
 static int do_show(int argc, char **argv)

Re: [PATCHv4 bpf-next 2/3] selftests/bpf: Add tracing_multi link info tests

[Jiri Olsa]

On Mon, Jun 29, 2026 at 09:34:06PM +0000, sashiko-bot@kernel.org wrote:

SNIP

> > +static void verify_tracing_multi_invalid_user_buffer(int fd, const struct tmulti_target *targets)
> > +{
> > +	__u32 ids[TRACING_MULTI_CNT] = {};
> > +	struct bpf_link_info info;
> > +	__u32 len = sizeof(info);
> > +	int err, i;
> [ ... ]
> > +	/* Invalid addrs pointer -> EFAULT */
> > +	memset(&info, 0, sizeof(info));
> > +	info.tracing_multi.addrs = 0x1;
> > +	info.tracing_multi.count = TRACING_MULTI_CNT;
> > +	err = bpf_link_get_info_by_fd(fd, &info, &len);
> > +	ASSERT_EQ(err, -EFAULT, "tracing_multi.bad_addrs");
> 
> [Severity: Medium]
> Will this test actually return -EFAULT?
> 
> By zeroing out the info struct before these checks, the mandatory ids
> pointer is left as NULL while count is non-zero. If the kernel validation
> logic eagerly rejects the missing ids array with -EINVAL before reaching
> the -EFAULT paths, won't this assertion fail?

there's no such eager reject in bpf_tracing_multi_link_fill_link_info,
the test passes

jirka

Re: [PATCHv4 bpf-next 3/3] bpftool: Add tracing_multi link info output

[Andrii Nakryiko]

On Mon, Jun 29, 2026 at 2:22 PM Jiri Olsa <jolsa@kernel.org> wrote:
>
> Adding bpftool support to show tracing_multi link details,
> the new output looks like:
>
>   # bpftool link
>   ...
>   61: tracing_multi  prog 167
>           attach_type trace_fentry_multi  btf_obj_id 1  count 3
>           btf_id           addr             cookie           func [module]
>           92598            ffffffff825017c4 10               bpf_fentry_test1
>           92600            ffffffff82503814 30               bpf_fentry_test2
>           92601            ffffffff82503824 20               bpf_fentry_test3
>           pids test_progs(1540)
>
> Assisted-by: Codex:GPT-5
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  tools/bpf/bpftool/link.c | 133 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 133 insertions(+)
>

[...]

>  static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
>  {
>         const char *buf;
> @@ -989,6 +1097,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
>         case BPF_LINK_TYPE_UPROBE_MULTI:
>                 show_uprobe_multi_plain(info);
>                 break;
> +       case BPF_LINK_TYPE_TRACING_MULTI:
> +               show_tracing_multi_plain(info);
> +               break;
>         case BPF_LINK_TYPE_PERF_EVENT:
>                 switch (info->perf_event.type) {
>                 case BPF_PERF_EVENT_EVENT:
> @@ -1029,6 +1140,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
>  static int do_show_link(int fd)
>  {
>         __u64 *ref_ctr_offsets = NULL, *offsets = NULL, *cookies = NULL;
> +       __u32 *ids = NULL;
>         struct bpf_link_info info;
>         __u32 len = sizeof(info);
>         char path_buf[PATH_MAX];
> @@ -1114,6 +1226,26 @@ static int do_show_link(int fd)
>                         goto again;
>                 }
>         }
> +       if (info.type == BPF_LINK_TYPE_TRACING_MULTI && !info.tracing_multi.ids) {

`&& info.tracing_multi.count` and avoid that nested if (just use
info.tracing_multi.count directly for callocs())


just a nit for maybe a follow up, if you care

> +               count = info.tracing_multi.count;
> +               if (count) {
> +                       ids = calloc(count, sizeof(__u32));
> +                       addrs = calloc(count, sizeof(__u64));
> +                       cookies = calloc(count, sizeof(__u64));
> +                       if (!ids || !addrs || !cookies) {
> +                               p_err("mem alloc failed");
> +                               close(fd);
> +                               free(cookies);
> +                               free(addrs);
> +                               free(ids);
> +                               return -ENOMEM;
> +                       }
> +                       info.tracing_multi.ids = ptr_to_u64(ids);
> +                       info.tracing_multi.addrs = ptr_to_u64(addrs);
> +                       info.tracing_multi.cookies = ptr_to_u64(cookies);
> +                       goto again;
> +               }
> +       }
>         if (info.type == BPF_LINK_TYPE_PERF_EVENT) {
>                 switch (info.perf_event.type) {
>                 case BPF_PERF_EVENT_TRACEPOINT:
> @@ -1153,6 +1285,7 @@ static int do_show_link(int fd)
>         free(cookies);
>         free(offsets);
>         free(addrs);
> +       free(ids);
>         close(fd);
>         return 0;
>  }
> --
> 2.54.0
>

Re: [PATCHv4 bpf-next 0/3] bpf: tracing_multi link info support

[patchwork-bot+netdevbpf]

Hello:

This series was applied to bpf/bpf-next.git (master)
by Andrii Nakryiko <andrii@kernel.org>:

On Mon, 29 Jun 2026 23:22:05 +0200 you wrote:
> hi,
> adding link info support for tracing_multi link.
> 
> Adding the kernel support with related selftests and bpftool support
> to display the tracing_multi link info, the output looks like:
> 
>   # bpftool link
>   ...
>   61: tracing_multi  prog 167
>           attach_type trace_fentry_multi  btf_obj_id 1  count 3
>           btf_id           addr             cookie           func [module]
>           92598            ffffffff825017c4 10               bpf_fentry_test1
>           92600            ffffffff82503814 30               bpf_fentry_test2
>           92601            ffffffff82503824 20               bpf_fentry_test3
>           pids test_progs(1540)
> 
> [...]

Here is the summary with links:
  - [PATCHv4,bpf-next,1/3] bpf: Add tracing_multi link info support
    https://git.kernel.org/bpf/bpf-next/c/859055e07697
  - [PATCHv4,bpf-next,2/3] selftests/bpf: Add tracing_multi link info tests
    https://git.kernel.org/bpf/bpf-next/c/d36e4dd547bb
  - [PATCHv4,bpf-next,3/3] bpftool: Add tracing_multi link info output
    https://git.kernel.org/bpf/bpf-next/c/37c1e353c9fd

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html