From 3903802bb99a263a3c26422c3d30a121b1f6f939 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 25 Aug 2023 13:21:52 -0700
Subject: libbpf: Add basic BTF sanity validation

Implement a simple and straightforward BTF sanity check when parsing BTF
data. Right now it's very basic and just validates that all the string
offsets and type IDs are within valid range. For FUNC we also check that
it points to FUNC_PROTO kinds.

Even with such simple checks it fixes a bunch of crashes found by OSS
fuzzer ([0]-[5]) and will allow fuzzer to make further progress.

Some other invariants will be checked in follow up patches (like
ensuring there is no infinite type loops), but this seems like a good
start already.

Adding FUNC -> FUNC_PROTO check revealed that one of selftests has
a problem with FUNC pointing to VAR instead, so fix it up in the same
commit.

  [0] https://github.com/libbpf/libbpf/issues/482
  [1] https://github.com/libbpf/libbpf/issues/483
  [2] https://github.com/libbpf/libbpf/issues/485
  [3] https://github.com/libbpf/libbpf/issues/613
  [4] https://github.com/libbpf/libbpf/issues/618
  [5] https://github.com/libbpf/libbpf/issues/619

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Reviewed-by: Song Liu <song@kernel.org>
Closes: https://github.com/libbpf/libbpf/issues/617
Link: https://lore.kernel.org/bpf/20230825202152.1813394-1-andrii@kernel.org
---
 tools/lib/bpf/btf.c                          | 160 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/prog_tests/btf.c |   4 +-
 2 files changed, 162 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 8484b563b53d..ee95fd379d4d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -448,6 +448,165 @@ static int btf_parse_type_sec(struct btf *btf)
 	return 0;
 }
 
+static int btf_validate_str(const struct btf *btf, __u32 str_off, const char *what, __u32 type_id)
+{
+	const char *s;
+
+	s = btf__str_by_offset(btf, str_off);
+	if (!s) {
+		pr_warn("btf: type [%u]: invalid %s (string offset %u)\n", type_id, what, str_off);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_validate_id(const struct btf *btf, __u32 id, __u32 ctx_id)
+{
+	const struct btf_type *t;
+
+	t = btf__type_by_id(btf, id);
+	if (!t) {
+		pr_warn("btf: type [%u]: invalid referenced type ID %u\n", ctx_id, id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_validate_type(const struct btf *btf, const struct btf_type *t, __u32 id)
+{
+	__u32 kind = btf_kind(t);
+	int err, i, n;
+
+	err = btf_validate_str(btf, t->name_off, "type name", id);
+	if (err)
+		return err;
+
+	switch (kind) {
+	case BTF_KIND_UNKN:
+	case BTF_KIND_INT:
+	case BTF_KIND_FWD:
+	case BTF_KIND_FLOAT:
+		break;
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_VAR:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
+		err = btf_validate_id(btf, t->type, id);
+		if (err)
+			return err;
+		break;
+	case BTF_KIND_ARRAY: {
+		const struct btf_array *a = btf_array(t);
+
+		err = btf_validate_id(btf, a->type, id);
+		err = err ?: btf_validate_id(btf, a->index_type, id);
+		if (err)
+			return err;
+		break;
+	}
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		const struct btf_member *m = btf_members(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "field name", id);
+			err = err ?: btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_ENUM: {
+		const struct btf_enum *m = btf_enum(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "enum name", id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_ENUM64: {
+		const struct btf_enum64 *m = btf_enum64(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "enum name", id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_FUNC: {
+		const struct btf_type *ft;
+
+		err = btf_validate_id(btf, t->type, id);
+		if (err)
+			return err;
+		ft = btf__type_by_id(btf, t->type);
+		if (btf_kind(ft) != BTF_KIND_FUNC_PROTO) {
+			pr_warn("btf: type [%u]: referenced type [%u] is not FUNC_PROTO\n", id, t->type);
+			return -EINVAL;
+		}
+		break;
+	}
+	case BTF_KIND_FUNC_PROTO: {
+		const struct btf_param *m = btf_params(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "param name", id);
+			err = err ?: btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_DATASEC: {
+		const struct btf_var_secinfo *m = btf_var_secinfos(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	default:
+		pr_warn("btf: type [%u]: unrecognized kind %u\n", id, kind);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Validate basic sanity of BTF. It's intentionally less thorough than
+ * kernel's validation and validates only properties of BTF that libbpf relies
+ * on to be correct (e.g., valid type IDs, valid string offsets, etc)
+ */
+static int btf_sanity_check(const struct btf *btf)
+{
+	const struct btf_type *t;
+	__u32 i, n = btf__type_cnt(btf);
+	int err;
+
+	for (i = 1; i < n; i++) {
+		t = btf_type_by_id(btf, i);
+		err = btf_validate_type(btf, t, i);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 __u32 btf__type_cnt(const struct btf *btf)
 {
 	return btf->start_id + btf->nr_types;
@@ -902,6 +1061,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	err = btf_parse_str_sec(btf);
 	err = err ?: btf_parse_type_sec(btf);
+	err = err ?: btf_sanity_check(btf);
 	if (err)
 		goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 4e0cdb593318..92d51f377fe5 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -7296,7 +7296,7 @@ static struct btf_dedup_test dedup_tests[] = {
 			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
-			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			BTF_FUNC_ENC(NAME_NTH(4), 3),			/* [4] */
 			/* tag -> t */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
@@ -7317,7 +7317,7 @@ static struct btf_dedup_test dedup_tests[] = {
 			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
-			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			BTF_FUNC_ENC(NAME_NTH(4), 3),			/* [4] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [7] */
-- 
cgit v1.2.3


From 96fc99d3d56ff094db7fc5d211183bb3d5c2caaa Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:27:54 -0700
Subject: selftests/bpf: Update error message in negative linked_list test

Some error messages are changed due to the addition of
percpu kptr support. Fix linked_list test with changed
error messages.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152754.1997769-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/linked_list.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index 18cf7b17463d..db3bf6bbe01a 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -65,8 +65,8 @@ static struct {
 	{ "map_compat_raw_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
 	{ "map_compat_raw_tp_w", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
 	{ "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" },
-	{ "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" },
-	{ "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" },
+	{ "obj_new_no_composite", "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct" },
+	{ "obj_new_no_struct", "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct" },
 	{ "obj_drop_non_zero_off", "R1 must have zero offset when passed to release func" },
 	{ "new_null_ret", "R0 invalid mem access 'ptr_or_null_'" },
 	{ "obj_new_acq", "Unreleased reference id=" },
-- 
cgit v1.2.3


From ed5285a1482f81f031183286e98edfe76fd9ac3b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:00 -0700
Subject: libbpf: Add __percpu_kptr macro definition

Add __percpu_kptr macro definition in bpf_helpers.h.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152800.1998492-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf_helpers.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index bbab9ad9dc5a..77ceea575dc7 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -181,6 +181,7 @@ enum libbpf_tristate {
 #define __ksym __attribute__((section(".ksyms")))
 #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
 #define __kptr __attribute__((btf_type_tag("kptr")))
+#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
 
 #define bpf_ksym_exists(sym) ({									\
 	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
-- 
cgit v1.2.3


From 968c76cb3dc6cc86e8099ecaa5c30dc0d4738a30 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:05 -0700
Subject: selftests/bpf: Add bpf_percpu_obj_{new,drop}() macro in
 bpf_experimental.h

The new macro bpf_percpu_obj_{new/drop}() is very similar to bpf_obj_{new,drop}()
as they both take a type as the argument.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152805.1999417-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_experimental.h | 31 ++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 209811b1993a..4494eaa9937e 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -131,4 +131,35 @@ extern int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *nod
  */
 extern struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym;
 
+/* Description
+ *	Allocates a percpu object of the type represented by 'local_type_id' in
+ *	program BTF. User may use the bpf_core_type_id_local macro to pass the
+ *	type ID of a struct in program BTF.
+ *
+ *	The 'local_type_id' parameter must be a known constant.
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
+ * Returns
+ *	A pointer to a percpu object of the type corresponding to the passed in
+ *	'local_type_id', or NULL on failure.
+ */
+extern void *bpf_percpu_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
+
+/* Convenience macro to wrap over bpf_percpu_obj_new_impl */
+#define bpf_percpu_obj_new(type) ((type __percpu_kptr *)bpf_percpu_obj_new_impl(bpf_core_type_id_local(type), NULL))
+
+/* Description
+ *	Free an allocated percpu object. All fields of the object that require
+ *	destruction will be destructed before the storage is freed.
+ *
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
+ * Returns
+ *	Void.
+ */
+extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
+
+/* Convenience macro to wrap over bpf_obj_drop_impl */
+#define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL)
+
 #endif
-- 
cgit v1.2.3


From 6adf82a4398d774398b4538dad561958c2c9521e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:11 -0700
Subject: selftests/bpf: Add tests for array map with local percpu kptr

Add non-sleepable and sleepable tests with percpu kptr. For
non-sleepable test, four programs are executed in the order of:
  1. allocate percpu data.
  2. assign values to percpu data.
  3. retrieve percpu data.
  4. de-allocate percpu data.

The sleepable prog tried to exercise all above 4 steps in a
single prog. Also for sleepable prog, rcu_read_lock is needed
to protect direct percpu ptr access (from map value) and
following bpf_this_cpu_ptr() and bpf_per_cpu_ptr() helpers.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152811.2000125-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/percpu_alloc.c        |  78 +++++++++
 .../selftests/bpf/progs/percpu_alloc_array.c       | 187 +++++++++++++++++++++
 2 files changed, 265 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
 create mode 100644 tools/testing/selftests/bpf/progs/percpu_alloc_array.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
new file mode 100644
index 000000000000..0fb536822f14
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "percpu_alloc_array.skel.h"
+
+static void test_array(void)
+{
+	struct percpu_alloc_array *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.test_array_map_1, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_2, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_3, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_4, true);
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__load"))
+		goto out;
+
+	err = percpu_alloc_array__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__attach"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.test_array_map_1);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run array_map 1-4");
+	ASSERT_EQ(topts.retval, 0, "test_run array_map 1-4");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+out:
+	percpu_alloc_array__destroy(skel);
+}
+
+static void test_array_sleepable(void)
+{
+	struct percpu_alloc_array *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc__open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.test_array_map_10, true);
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__load"))
+		goto out;
+
+	err = percpu_alloc_array__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__attach"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.test_array_map_10);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run array_map_10");
+	ASSERT_EQ(topts.retval, 0, "test_run array_map_10");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+out:
+	percpu_alloc_array__destroy(skel);
+}
+
+void test_percpu_alloc(void)
+{
+	if (test__start_subtest("array"))
+		test_array();
+	if (test__start_subtest("array_sleepable"))
+		test_array_sleepable();
+}
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
new file mode 100644
index 000000000000..3bd7d47870a9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -0,0 +1,187 @@
+#include "bpf_experimental.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+const volatile int nr_cpus;
+
+/* Initialize the percpu object */
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test_array_map_1)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+/* Update percpu data */
+SEC("?fentry/bpf_fentry_test2")
+int BPF_PROG(test_array_map_2)
+{
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		return 0;
+	v->c = 1;
+	v->d = 2;
+
+	return 0;
+}
+
+int cpu0_field_d, sum_field_c;
+
+/* Summarize percpu data */
+SEC("?fentry/bpf_fentry_test3")
+int BPF_PROG(test_array_map_3)
+{
+	struct val_t __percpu_kptr *p;
+	int i, index = 0;
+	struct val_t *v;
+	struct elem *e;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	return 0;
+}
+
+/* Explicitly free allocated percpu data */
+SEC("?fentry/bpf_fentry_test4")
+int BPF_PROG(test_array_map_4)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	/* delete */
+	p = bpf_kptr_xchg(&e->pc, NULL);
+	if (p) {
+		bpf_percpu_obj_drop(p);
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+int BPF_PROG(test_array_map_10)
+{
+	struct val_t __percpu_kptr *p, *p1;
+	int i, index = 0;
+	struct val_t *v;
+	struct elem *e;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	bpf_rcu_read_lock();
+	p = e->pc;
+	if (!p) {
+		p = bpf_percpu_obj_new(struct val_t);
+		if (!p)
+			goto out;
+
+		p1 = bpf_kptr_xchg(&e->pc, p);
+		if (p1) {
+			/* race condition */
+			bpf_percpu_obj_drop(p1);
+		}
+
+		p = e->pc;
+		if (!p)
+			goto out;
+	}
+
+	v = bpf_this_cpu_ptr(p);
+	v->c = 3;
+	v = bpf_this_cpu_ptr(p);
+	v->c = 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		goto out;
+	v->c = 1;
+	v->d = 2;
+
+	/* delete */
+	p1 = bpf_kptr_xchg(&e->pc, NULL);
+	if (!p1)
+		goto out;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	/* finally release p */
+	bpf_percpu_obj_drop(p1);
+out:
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 46200d6da544a624ad4a6f5745defed7e318f73d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:21 -0700
Subject: selftests/bpf: Remove unnecessary direct read of local percpu kptr

For the second argument of bpf_kptr_xchg(), if the reg type contains
MEM_ALLOC and MEM_PERCPU, which means a percpu allocation,
after bpf_kptr_xchg(), the argument is marked as MEM_RCU and MEM_PERCPU
if in rcu critical section. This way, re-reading from the map value
is not needed. Remove it from the percpu_alloc_array.c selftest.

Without previous kernel change, the test will fail like below:

  0: R1=ctx(off=0,imm=0) R10=fp0
  ; int BPF_PROG(test_array_map_10, int a)
  0: (b4) w1 = 0                        ; R1_w=0
  ; int i, index = 0;
  1: (63) *(u32 *)(r10 -4) = r1         ; R1_w=0 R10=fp0 fp-8=0000????
  2: (bf) r2 = r10                      ; R2_w=fp0 R10=fp0
  ;
  3: (07) r2 += -4                      ; R2_w=fp-4
  ; e = bpf_map_lookup_elem(&array, &index);
  4: (18) r1 = 0xffff88810e771800       ; R1_w=map_ptr(off=0,ks=4,vs=16,imm=0)
  6: (85) call bpf_map_lookup_elem#1    ; R0_w=map_value_or_null(id=1,off=0,ks=4,vs=16,imm=0)
  7: (bf) r6 = r0                       ; R0_w=map_value_or_null(id=1,off=0,ks=4,vs=16,imm=0) R6_w=map_value_or_null(id=1,off=0,ks=4,vs=16,imm=0)
  ; if (!e)
  8: (15) if r6 == 0x0 goto pc+81       ; R6_w=map_value(off=0,ks=4,vs=16,imm=0)
  ; bpf_rcu_read_lock();
  9: (85) call bpf_rcu_read_lock#87892          ;
  ; p = e->pc;
  10: (bf) r7 = r6                      ; R6=map_value(off=0,ks=4,vs=16,imm=0) R7_w=map_value(off=0,ks=4,vs=16,imm=0)
  11: (07) r7 += 8                      ; R7_w=map_value(off=8,ks=4,vs=16,imm=0)
  12: (79) r6 = *(u64 *)(r6 +8)         ; R6_w=percpu_rcu_ptr_or_null_val_t(id=2,off=0,imm=0)
  ; if (!p) {
  13: (55) if r6 != 0x0 goto pc+13      ; R6_w=0
  ; p = bpf_percpu_obj_new(struct val_t);
  14: (18) r1 = 0x12                    ; R1_w=18
  16: (b7) r2 = 0                       ; R2_w=0
  17: (85) call bpf_percpu_obj_new_impl#87883   ; R0_w=percpu_ptr_or_null_val_t(id=4,ref_obj_id=4,off=0,imm=0) refs=4
  18: (bf) r6 = r0                      ; R0=percpu_ptr_or_null_val_t(id=4,ref_obj_id=4,off=0,imm=0) R6=percpu_ptr_or_null_val_t(id=4,ref_obj_id=4,off=0,imm=0) refs=4
  ; if (!p)
  19: (15) if r6 == 0x0 goto pc+69      ; R6=percpu_ptr_val_t(ref_obj_id=4,off=0,imm=0) refs=4
  ; p1 = bpf_kptr_xchg(&e->pc, p);
  20: (bf) r1 = r7                      ; R1_w=map_value(off=8,ks=4,vs=16,imm=0) R7=map_value(off=8,ks=4,vs=16,imm=0) refs=4
  21: (bf) r2 = r6                      ; R2_w=percpu_ptr_val_t(ref_obj_id=4,off=0,imm=0) R6=percpu_ptr_val_t(ref_obj_id=4,off=0,imm=0) refs=4
  22: (85) call bpf_kptr_xchg#194       ; R0_w=percpu_ptr_or_null_val_t(id=6,ref_obj_id=6,off=0,imm=0) refs=6
  ; if (p1) {
  23: (15) if r0 == 0x0 goto pc+3       ; R0_w=percpu_ptr_val_t(ref_obj_id=6,off=0,imm=0) refs=6
  ; bpf_percpu_obj_drop(p1);
  24: (bf) r1 = r0                      ; R0_w=percpu_ptr_val_t(ref_obj_id=6,off=0,imm=0) R1_w=percpu_ptr_val_t(ref_obj_id=6,off=0,imm=0) refs=6
  25: (b7) r2 = 0                       ; R2_w=0 refs=6
  26: (85) call bpf_percpu_obj_drop_impl#87882          ;
  ; v = bpf_this_cpu_ptr(p);
  27: (bf) r1 = r6                      ; R1_w=scalar(id=7) R6=scalar(id=7)
  28: (85) call bpf_this_cpu_ptr#154
  R1 type=scalar expected=percpu_ptr_, percpu_rcu_ptr_, percpu_trusted_ptr_

The R1 which gets its value from R6 is a scalar. But before insn 22, R6 is
  R6=percpu_ptr_val_t(ref_obj_id=4,off=0,imm=0)
Its type is changed to a scalar at insn 22 without previous patch.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152821.2001129-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/percpu_alloc_array.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
index 3bd7d47870a9..bbc45346e006 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -146,10 +146,6 @@ int BPF_PROG(test_array_map_10)
 			/* race condition */
 			bpf_percpu_obj_drop(p1);
 		}
-
-		p = e->pc;
-		if (!p)
-			goto out;
 	}
 
 	v = bpf_this_cpu_ptr(p);
-- 
cgit v1.2.3


From dfae1eeee9baa12e27f24a223d699326133e366b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:27 -0700
Subject: selftests/bpf: Add tests for cgrp_local_storage with local percpu
 kptr

Add a non-sleepable cgrp_local_storage test with percpu kptr. The
test does allocation of percpu data, assigning values to percpu
data and retrieval of percpu data. The de-allocation of percpu
data is done when the map is freed.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152827.2001784-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/percpu_alloc.c        |  40 ++++++++
 .../bpf/progs/percpu_alloc_cgrp_local_storage.c    | 105 +++++++++++++++++++++
 2 files changed, 145 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 0fb536822f14..41bf784a4bb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "percpu_alloc_array.skel.h"
+#include "percpu_alloc_cgrp_local_storage.skel.h"
 
 static void test_array(void)
 {
@@ -69,10 +70,49 @@ out:
 	percpu_alloc_array__destroy(skel);
 }
 
+static void test_cgrp_local_storage(void)
+{
+	struct percpu_alloc_cgrp_local_storage *skel;
+	int err, cgroup_fd, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	cgroup_fd = test__join_cgroup("/percpu_alloc");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /percpu_alloc"))
+		return;
+
+	skel = percpu_alloc_cgrp_local_storage__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_cgrp_local_storage__open"))
+		goto close_fd;
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_cgrp_local_storage__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_cgrp_local_storage__load"))
+		goto destroy_skel;
+
+	err = percpu_alloc_cgrp_local_storage__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_cgrp_local_storage__attach"))
+		goto destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs.test_cgrp_local_storage_1);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run cgrp_local_storage 1-3");
+	ASSERT_EQ(topts.retval, 0, "test_run cgrp_local_storage 1-3");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+
+destroy_skel:
+	percpu_alloc_cgrp_local_storage__destroy(skel);
+close_fd:
+	close(cgroup_fd);
+}
+
 void test_percpu_alloc(void)
 {
 	if (test__start_subtest("array"))
 		test_array();
 	if (test__start_subtest("array_sleepable"))
 		test_array_sleepable();
+	if (test__start_subtest("cgrp_local_storage"))
+		test_cgrp_local_storage();
 }
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
new file mode 100644
index 000000000000..1c36a241852c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
@@ -0,0 +1,105 @@
+#include "bpf_experimental.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGRP_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct elem);
+} cgrp SEC(".maps");
+
+const volatile int nr_cpus;
+
+/* Initialize the percpu object */
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test_cgrp_local_storage_1)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+/* Percpu data collection */
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test_cgrp_local_storage_2)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		return 0;
+	v->c = 1;
+	v->d = 2;
+	return 0;
+}
+
+int cpu0_field_d, sum_field_c;
+
+/* Summarize percpu data collection */
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG(test_cgrp_local_storage_3)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+	int i;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 1bd7931728718bc463c43b78ab74954452e099e3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:32 -0700
Subject: selftests/bpf: Add some negative tests

Add a few negative tests for common mistakes with using percpu kptr
including:
  - store to percpu kptr.
  - type mistach in bpf_kptr_xchg arguments.
  - sleepable prog with untrusted arg for bpf_this_cpu_ptr().
  - bpf_percpu_obj_new && bpf_obj_drop, and bpf_obj_new && bpf_percpu_obj_drop
  - struct with ptr for bpf_percpu_obj_new
  - struct with special field (e.g., bpf_spin_lock) for bpf_percpu_obj_new

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152832.2002421-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/percpu_alloc.c        |   7 +
 .../selftests/bpf/progs/percpu_alloc_fail.c        | 164 +++++++++++++++++++++
 2 files changed, 171 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/percpu_alloc_fail.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 41bf784a4bb3..9541e9b3a034 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -2,6 +2,7 @@
 #include <test_progs.h>
 #include "percpu_alloc_array.skel.h"
 #include "percpu_alloc_cgrp_local_storage.skel.h"
+#include "percpu_alloc_fail.skel.h"
 
 static void test_array(void)
 {
@@ -107,6 +108,10 @@ close_fd:
 	close(cgroup_fd);
 }
 
+static void test_failure(void) {
+	RUN_TESTS(percpu_alloc_fail);
+}
+
 void test_percpu_alloc(void)
 {
 	if (test__start_subtest("array"))
@@ -115,4 +120,6 @@ void test_percpu_alloc(void)
 		test_array_sleepable();
 	if (test__start_subtest("cgrp_local_storage"))
 		test_cgrp_local_storage();
+	if (test__start_subtest("failure_tests"))
+		test_failure();
 }
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
new file mode 100644
index 000000000000..1a891d30f1fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -0,0 +1,164 @@
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct val2_t {
+	long b;
+};
+
+struct val_with_ptr_t {
+	char *p;
+};
+
+struct val_with_rb_root_t {
+	struct bpf_spin_lock lock;
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+long ret;
+
+SEC("?fentry/bpf_fentry_test1")
+__failure __msg("store to referenced kptr disallowed")
+int BPF_PROG(test_array_map_1)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	e->pc = (struct val_t __percpu_kptr *)ret;
+	return 0;
+}
+
+SEC("?fentry/bpf_fentry_test1")
+__failure __msg("invalid kptr access, R2 type=percpu_ptr_val2_t expected=ptr_val_t")
+int BPF_PROG(test_array_map_2)
+{
+	struct val2_t __percpu_kptr *p2;
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p2 = bpf_percpu_obj_new(struct val2_t);
+	if (!p2)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p2);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("R1 type=scalar expected=percpu_ptr_, percpu_rcu_ptr_, percpu_trusted_ptr_")
+int BPF_PROG(test_array_map_3)
+{
+	struct val_t __percpu_kptr *p, *p1;
+	struct val_t *v;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p1 = bpf_kptr_xchg(&e->pc, p);
+	if (p1)
+		bpf_percpu_obj_drop(p1);
+
+	v = bpf_this_cpu_ptr(p);
+	ret = v->b;
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("arg#0 expected for bpf_percpu_obj_drop_impl()")
+int BPF_PROG(test_array_map_4)
+{
+	struct val_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	bpf_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("arg#0 expected for bpf_obj_drop_impl()")
+int BPF_PROG(test_array_map_5)
+{
+	struct val_t *p;
+
+	p = bpf_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type ID argument must be of a struct of scalars")
+int BPF_PROG(test_array_map_6)
+{
+	struct val_with_ptr_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_with_ptr_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type ID argument must not contain special fields")
+int BPF_PROG(test_array_map_7)
+{
+	struct val_with_rb_root_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_with_rb_root_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 9bc95a95abbe91e9315c1fe27dc124019bd2592c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 27 Aug 2023 08:28:37 -0700
Subject: bpf: Mark BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE deprecated

Now 'BPF_MAP_TYPE_CGRP_STORAGE + local percpu ptr'
can cover all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE functionality
and more. So mark BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE deprecated.
Also make changes in selftests/bpf/test_bpftool_synctypes.py
and selftest libbpf_str to fix otherwise test errors.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20230827152837.2003563-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h                              | 9 ++++++++-
 tools/include/uapi/linux/bpf.h                        | 9 ++++++++-
 tools/testing/selftests/bpf/prog_tests/libbpf_str.c   | 6 +++++-
 tools/testing/selftests/bpf/test_bpftool_synctypes.py | 9 +++++++++
 4 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8790b3962e4b..73b155e52204 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -932,7 +932,14 @@ enum bpf_map_type {
 	 */
 	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+	/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
+	 * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
+	 * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * deprecated.
+	 */
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8790b3962e4b..73b155e52204 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -932,7 +932,14 @@ enum bpf_map_type {
 	 */
 	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+	/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
+	 * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
+	 * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * deprecated.
+	 */
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index efb8bd43653c..c440ea3311ed 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -142,10 +142,14 @@ static void test_libbpf_bpf_map_type_str(void)
 		/* Special case for map_type_name BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED
 		 * where it and BPF_MAP_TYPE_CGROUP_STORAGE have the same enum value
 		 * (map_type). For this enum value, libbpf_bpf_map_type_str() picks
-		 * BPF_MAP_TYPE_CGROUP_STORAGE.
+		 * BPF_MAP_TYPE_CGROUP_STORAGE. The same for
+		 * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and
+		 * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE.
 		 */
 		if (strcmp(map_type_name, "BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED") == 0)
 			continue;
+		if (strcmp(map_type_name, "BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED") == 0)
+			continue;
 
 		ASSERT_STREQ(buf, map_type_name, "exp_str_value");
 	}
diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index 0cfece7ff4f8..0ed67b6b31dd 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -509,6 +509,15 @@ def main():
     source_map_types.remove('cgroup_storage_deprecated')
     source_map_types.add('cgroup_storage')
 
+    # The same applied to BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and
+    # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE which share the same enum value
+    # and source_map_types picks
+    # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED/percpu_cgroup_storage_deprecated.
+    # Replace 'percpu_cgroup_storage_deprecated' with 'percpu_cgroup_storage'
+    # so it aligns with what `bpftool map help` shows.
+    source_map_types.remove('percpu_cgroup_storage_deprecated')
+    source_map_types.add('percpu_cgroup_storage')
+
     help_map_types = map_info.get_map_help()
     help_map_options = map_info.get_options()
     map_info.close()
-- 
cgit v1.2.3


From 29c11aa8082b6dbef2cffbcd5e81be27e9b50a5b Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Fri, 1 Sep 2023 19:19:54 +0800
Subject: selftests/bpf: Test preemption between bpf_obj_new() and
 bpf_obj_drop()

The test case creates 4 threads and then pins these 4 threads in CPU 0.
These 4 threads will run different bpf program through
bpf_prog_test_run_opts() and these bpf program will use bpf_obj_new()
and bpf_obj_drop() to allocate and free local kptrs concurrently.

Under preemptible kernel, bpf_obj_new() and bpf_obj_drop() may preempt
each other, bpf_obj_new() may return NULL and the test will fail before
applying these fixes as shown below:

  test_preempted_bpf_ma_op:PASS:open_and_load 0 nsec
  test_preempted_bpf_ma_op:PASS:attach 0 nsec
  test_preempted_bpf_ma_op:PASS:no test prog 0 nsec
  test_preempted_bpf_ma_op:PASS:no test prog 0 nsec
  test_preempted_bpf_ma_op:PASS:no test prog 0 nsec
  test_preempted_bpf_ma_op:PASS:no test prog 0 nsec
  test_preempted_bpf_ma_op:PASS:pthread_create 0 nsec
  test_preempted_bpf_ma_op:PASS:pthread_create 0 nsec
  test_preempted_bpf_ma_op:PASS:pthread_create 0 nsec
  test_preempted_bpf_ma_op:PASS:pthread_create 0 nsec
  test_preempted_bpf_ma_op:PASS:run prog err 0 nsec
  test_preempted_bpf_ma_op:PASS:run prog err 0 nsec
  test_preempted_bpf_ma_op:PASS:run prog err 0 nsec
  test_preempted_bpf_ma_op:PASS:run prog err 0 nsec
  test_preempted_bpf_ma_op:FAIL:ENOMEM unexpected ENOMEM: got TRUE
  #168     preempted_bpf_ma_op:FAIL
  Summary: 0/0 PASSED, 0 SKIPPED, 1 FAILED

Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230901111954.1804721-4-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/preempted_bpf_ma_op.c |  89 +++++++++++++++++
 .../selftests/bpf/progs/preempted_bpf_ma_op.c      | 106 +++++++++++++++++++++
 2 files changed, 195 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c
 create mode 100644 tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c b/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c
new file mode 100644
index 000000000000..3a2ec3923fca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <test_progs.h>
+
+#include "preempted_bpf_ma_op.skel.h"
+
+#define ALLOC_THREAD_NR 4
+#define ALLOC_LOOP_NR 512
+
+struct alloc_ctx {
+	/* output */
+	int run_err;
+	/* input */
+	int fd;
+	bool *nomem_err;
+};
+
+static void *run_alloc_prog(void *data)
+{
+	struct alloc_ctx *ctx = data;
+	cpu_set_t cpu_set;
+	int i;
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+
+	for (i = 0; i < ALLOC_LOOP_NR && !*ctx->nomem_err; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, topts);
+		int err;
+
+		err = bpf_prog_test_run_opts(ctx->fd, &topts);
+		ctx->run_err |= err | topts.retval;
+	}
+
+	return NULL;
+}
+
+void test_preempted_bpf_ma_op(void)
+{
+	struct alloc_ctx ctx[ALLOC_THREAD_NR];
+	struct preempted_bpf_ma_op *skel;
+	pthread_t tid[ALLOC_THREAD_NR];
+	int i, err;
+
+	skel = preempted_bpf_ma_op__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	err = preempted_bpf_ma_op__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(ctx); i++) {
+		struct bpf_program *prog;
+		char name[8];
+
+		snprintf(name, sizeof(name), "test%d", i);
+		prog = bpf_object__find_program_by_name(skel->obj, name);
+		if (!ASSERT_OK_PTR(prog, "no test prog"))
+			goto out;
+
+		ctx[i].run_err = 0;
+		ctx[i].fd = bpf_program__fd(prog);
+		ctx[i].nomem_err = &skel->bss->nomem_err;
+	}
+
+	memset(tid, 0, sizeof(tid));
+	for (i = 0; i < ARRAY_SIZE(tid); i++) {
+		err = pthread_create(&tid[i], NULL, run_alloc_prog, &ctx[i]);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tid); i++) {
+		if (!tid[i])
+			break;
+		pthread_join(tid[i], NULL);
+		ASSERT_EQ(ctx[i].run_err, 0, "run prog err");
+	}
+
+	ASSERT_FALSE(skel->bss->nomem_err, "ENOMEM");
+out:
+	preempted_bpf_ma_op__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c b/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c
new file mode 100644
index 000000000000..55907ef961bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+
+struct bin_data {
+	char data[256];
+	struct bpf_spin_lock lock;
+};
+
+struct map_value {
+	struct bin_data __kptr * data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2048);
+} array SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+bool nomem_err = false;
+
+static int del_array(unsigned int i, int *from)
+{
+	struct map_value *value;
+	struct bin_data *old;
+
+	value = bpf_map_lookup_elem(&array, from);
+	if (!value)
+		return 1;
+
+	old = bpf_kptr_xchg(&value->data, NULL);
+	if (old)
+		bpf_obj_drop(old);
+
+	(*from)++;
+	return 0;
+}
+
+static int add_array(unsigned int i, int *from)
+{
+	struct bin_data *old, *new;
+	struct map_value *value;
+
+	value = bpf_map_lookup_elem(&array, from);
+	if (!value)
+		return 1;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new) {
+		nomem_err = true;
+		return 1;
+	}
+
+	old = bpf_kptr_xchg(&value->data, new);
+	if (old)
+		bpf_obj_drop(old);
+
+	(*from)++;
+	return 0;
+}
+
+static void del_then_add_array(int from)
+{
+	int i;
+
+	i = from;
+	bpf_loop(512, del_array, &i, 0);
+
+	i = from;
+	bpf_loop(512, add_array, &i, 0);
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG2(test0, int, a)
+{
+	del_then_add_array(0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG2(test1, int, a, u64, b)
+{
+	del_then_add_array(512);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG2(test2, char, a, int, b, u64, c)
+{
+	del_then_add_array(1024);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG2(test3, void *, a, char, b, int, c, u64, d)
+{
+	del_then_add_array(1536);
+	return 0;
+}
-- 
cgit v1.2.3


From c698eaebdf4759d297343f20e00172610207b754 Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Thu, 7 Sep 2023 09:59:13 +0800
Subject: selftests/bpf: trace_helpers.c: Optimize kallsyms cache

Static ksyms often have problems because the number of symbols exceeds the
MAX_SYMS limit. Like changing the MAX_SYMS from 300000 to 400000 in
commit e76a014334a6("selftests/bpf: Bump and validate MAX_SYMS") solves
the problem somewhat, but it's not the perfect way.

This commit uses dynamic memory allocation, which completely solves the
problem caused by the limitation of the number of kallsyms. At the same
time, add APIs:

    load_kallsyms_local()
    ksym_search_local()
    ksym_get_addr_local()
    free_kallsyms_local()

There are used to solve the problem of selftests/bpf updating kallsyms
after attach new symbols during testmod testing.

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/tencent_C9BDA68F9221F21BE4081566A55D66A9700A@qq.com
---
 samples/bpf/Makefile                               |   4 +
 .../selftests/bpf/prog_tests/fill_link_info.c      |   2 +-
 .../bpf/prog_tests/kprobe_multi_testmod_test.c     |  20 ++--
 tools/testing/selftests/bpf/trace_helpers.c        | 130 +++++++++++++++------
 tools/testing/selftests/bpf/trace_helpers.h        |   8 +-
 5 files changed, 118 insertions(+), 46 deletions(-)

(limited to 'tools')

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4ccf4236031c..6c707ebcebb9 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -175,6 +175,7 @@ TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE)
 TPROGS_CFLAGS += -I$(srctree)/tools/include
 TPROGS_CFLAGS += -I$(srctree)/tools/perf
+TPROGS_CFLAGS += -I$(srctree)/tools/lib
 TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0
 
 ifdef SYSROOT
@@ -314,6 +315,9 @@ XDP_SAMPLE_CFLAGS += -Wall -O2 \
 
 $(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS)
 $(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h
+# Override includes for trace_helpers.o because __must_check won't be defined
+# in our include path.
+$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check=
 
 -include $(BPF_SAMPLES_PATH)/Makefile.target
 
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 9d768e083714..97142a4db374 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -308,7 +308,7 @@ void test_fill_link_info(void)
 		return;
 
 	/* load kallsyms to compare the addr */
-	if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+	if (!ASSERT_OK(load_kallsyms(), "load_kallsyms"))
 		goto cleanup;
 
 	kprobe_addr = ksym_get_addr(KPROBE_FUNC);
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
index 1fbe7e4ac00a..9d03528f05db 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
@@ -4,6 +4,8 @@
 #include "trace_helpers.h"
 #include "bpf/libbpf_internal.h"
 
+static struct ksyms *ksyms;
+
 static void kprobe_multi_testmod_check(struct kprobe_multi *skel)
 {
 	ASSERT_EQ(skel->bss->kprobe_testmod_test1_result, 1, "kprobe_test1_result");
@@ -50,12 +52,12 @@ static void test_testmod_attach_api_addrs(void)
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	unsigned long long addrs[3];
 
-	addrs[0] = ksym_get_addr("bpf_testmod_fentry_test1");
-	ASSERT_NEQ(addrs[0], 0, "ksym_get_addr");
-	addrs[1] = ksym_get_addr("bpf_testmod_fentry_test2");
-	ASSERT_NEQ(addrs[1], 0, "ksym_get_addr");
-	addrs[2] = ksym_get_addr("bpf_testmod_fentry_test3");
-	ASSERT_NEQ(addrs[2], 0, "ksym_get_addr");
+	addrs[0] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test1");
+	ASSERT_NEQ(addrs[0], 0, "ksym_get_addr_local");
+	addrs[1] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test2");
+	ASSERT_NEQ(addrs[1], 0, "ksym_get_addr_local");
+	addrs[2] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test3");
+	ASSERT_NEQ(addrs[2], 0, "ksym_get_addr_local");
 
 	opts.addrs = (const unsigned long *) addrs;
 	opts.cnt = ARRAY_SIZE(addrs);
@@ -79,11 +81,15 @@ static void test_testmod_attach_api_syms(void)
 
 void serial_test_kprobe_multi_testmod_test(void)
 {
-	if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+	ksyms = load_kallsyms_local();
+	if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_local"))
 		return;
 
 	if (test__start_subtest("testmod_attach_api_syms"))
 		test_testmod_attach_api_syms();
+
 	if (test__start_subtest("testmod_attach_api_addrs"))
 		test_testmod_attach_api_addrs();
+
+	free_kallsyms_local(ksyms);
 }
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index f83d9f65c65b..dc4efaf538ae 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -14,104 +14,162 @@
 #include <linux/limits.h>
 #include <libelf.h>
 #include <gelf.h>
+#include "bpf/libbpf_internal.h"
 
 #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
 #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
 
-#define MAX_SYMS 400000
-static struct ksym syms[MAX_SYMS];
-static int sym_cnt;
+struct ksyms {
+	struct ksym *syms;
+	size_t sym_cap;
+	size_t sym_cnt;
+};
+
+static struct ksyms *ksyms;
+
+static int ksyms__add_symbol(struct ksyms *ksyms, const char *name,
+			     unsigned long addr)
+{
+	void *tmp;
+
+	tmp = strdup(name);
+	if (!tmp)
+		return -ENOMEM;
+	ksyms->syms[ksyms->sym_cnt].addr = addr;
+	ksyms->syms[ksyms->sym_cnt].name = tmp;
+	ksyms->sym_cnt++;
+	return 0;
+}
+
+void free_kallsyms_local(struct ksyms *ksyms)
+{
+	unsigned int i;
+
+	if (!ksyms)
+		return;
+
+	if (!ksyms->syms) {
+		free(ksyms);
+		return;
+	}
+
+	for (i = 0; i < ksyms->sym_cnt; i++)
+		free(ksyms->syms[i].name);
+	free(ksyms->syms);
+	free(ksyms);
+}
 
 static int ksym_cmp(const void *p1, const void *p2)
 {
 	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
 }
 
-int load_kallsyms_refresh(void)
+struct ksyms *load_kallsyms_local(void)
 {
 	FILE *f;
 	char func[256], buf[256];
 	char symbol;
 	void *addr;
-	int i = 0;
-
-	sym_cnt = 0;
+	int ret;
+	struct ksyms *ksyms;
 
 	f = fopen("/proc/kallsyms", "r");
 	if (!f)
-		return -ENOENT;
+		return NULL;
+
+	ksyms = calloc(1, sizeof(struct ksyms));
+	if (!ksyms) {
+		fclose(f);
+		return NULL;
+	}
 
 	while (fgets(buf, sizeof(buf), f)) {
 		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
 			break;
 		if (!addr)
 			continue;
-		if (i >= MAX_SYMS)
-			return -EFBIG;
 
-		syms[i].addr = (long) addr;
-		syms[i].name = strdup(func);
-		i++;
+		ret = libbpf_ensure_mem((void **) &ksyms->syms, &ksyms->sym_cap,
+					sizeof(struct ksym), ksyms->sym_cnt + 1);
+		if (ret)
+			goto error;
+		ret = ksyms__add_symbol(ksyms, func, (unsigned long)addr);
+		if (ret)
+			goto error;
 	}
 	fclose(f);
-	sym_cnt = i;
-	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
-	return 0;
+	qsort(ksyms->syms, ksyms->sym_cnt, sizeof(struct ksym), ksym_cmp);
+	return ksyms;
+
+error:
+	fclose(f);
+	free_kallsyms_local(ksyms);
+	return NULL;
 }
 
 int load_kallsyms(void)
 {
-	/*
-	 * This is called/used from multiplace places,
-	 * load symbols just once.
-	 */
-	if (sym_cnt)
-		return 0;
-	return load_kallsyms_refresh();
+	if (!ksyms)
+		ksyms = load_kallsyms_local();
+	return ksyms ? 0 : 1;
 }
 
-struct ksym *ksym_search(long key)
+struct ksym *ksym_search_local(struct ksyms *ksyms, long key)
 {
-	int start = 0, end = sym_cnt;
+	int start = 0, end = ksyms->sym_cnt;
 	int result;
 
 	/* kallsyms not loaded. return NULL */
-	if (sym_cnt <= 0)
+	if (ksyms->sym_cnt <= 0)
 		return NULL;
 
 	while (start < end) {
 		size_t mid = start + (end - start) / 2;
 
-		result = key - syms[mid].addr;
+		result = key - ksyms->syms[mid].addr;
 		if (result < 0)
 			end = mid;
 		else if (result > 0)
 			start = mid + 1;
 		else
-			return &syms[mid];
+			return &ksyms->syms[mid];
 	}
 
-	if (start >= 1 && syms[start - 1].addr < key &&
-	    key < syms[start].addr)
+	if (start >= 1 && ksyms->syms[start - 1].addr < key &&
+	    key < ksyms->syms[start].addr)
 		/* valid ksym */
-		return &syms[start - 1];
+		return &ksyms->syms[start - 1];
 
 	/* out of range. return _stext */
-	return &syms[0];
+	return &ksyms->syms[0];
 }
 
-long ksym_get_addr(const char *name)
+struct ksym *ksym_search(long key)
+{
+	if (!ksyms)
+		return NULL;
+	return ksym_search_local(ksyms, key);
+}
+
+long ksym_get_addr_local(struct ksyms *ksyms, const char *name)
 {
 	int i;
 
-	for (i = 0; i < sym_cnt; i++) {
-		if (strcmp(syms[i].name, name) == 0)
-			return syms[i].addr;
+	for (i = 0; i < ksyms->sym_cnt; i++) {
+		if (strcmp(ksyms->syms[i].name, name) == 0)
+			return ksyms->syms[i].addr;
 	}
 
 	return 0;
 }
 
+long ksym_get_addr(const char *name)
+{
+	if (!ksyms)
+		return 0;
+	return ksym_get_addr_local(ksyms, name);
+}
+
 /* open kallsyms and read symbol addresses on the fly. Without caching all symbols,
  * this is faster than load + find.
  */
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 876f3e711df6..04fd1da7079d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -11,13 +11,17 @@ struct ksym {
 	long addr;
 	char *name;
 };
+struct ksyms;
 
 int load_kallsyms(void);
-int load_kallsyms_refresh(void);
-
 struct ksym *ksym_search(long key);
 long ksym_get_addr(const char *name);
 
+struct ksyms *load_kallsyms_local(void);
+struct ksym *ksym_search_local(struct ksyms *ksyms, long key);
+long ksym_get_addr_local(struct ksyms *ksyms, const char *name);
+void free_kallsyms_local(struct ksyms *ksyms);
+
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
-- 
cgit v1.2.3


From a28b1ba25934f24b9aabfc5cb86247150b7bb67d Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Thu, 7 Sep 2023 09:59:14 +0800
Subject: selftests/bpf: trace_helpers.c: Add a global ksyms initialization
 mutex

As Jirka said [0], we just need to make sure that global ksyms
initialization won't race.

[0] https://lore.kernel.org/lkml/ZPCbAs3ItjRd8XVh@krava/

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_5D0A837E219E2CFDCB0495DAD7D5D1204407@qq.com
---
 tools/testing/selftests/bpf/trace_helpers.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index dc4efaf538ae..4faa898ff7fc 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <poll.h>
+#include <pthread.h>
 #include <unistd.h>
 #include <linux/perf_event.h>
 #include <sys/mman.h>
@@ -26,6 +27,7 @@ struct ksyms {
 };
 
 static struct ksyms *ksyms;
+static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
 
 static int ksyms__add_symbol(struct ksyms *ksyms, const char *name,
 			     unsigned long addr)
@@ -109,8 +111,10 @@ error:
 
 int load_kallsyms(void)
 {
+	pthread_mutex_lock(&ksyms_mutex);
 	if (!ksyms)
 		ksyms = load_kallsyms_local();
+	pthread_mutex_unlock(&ksyms_mutex);
 	return ksyms ? 0 : 1;
 }
 
-- 
cgit v1.2.3


From ebc8484d0e6da9e6c9e8cfa1f40bf94e9c6fc512 Mon Sep 17 00:00:00 2001
From: Denys Zagorui <dzagorui@cisco.com>
Date: Thu, 7 Sep 2023 02:02:10 -0700
Subject: bpftool: Fix -Wcast-qual warning

This cast was made by purpose for older libbpf where the
bpf_object_skeleton field is void * instead of const void *
to eliminate a warning (as i understand
-Wincompatible-pointer-types-discards-qualifiers) but this
cast introduces another warning (-Wcast-qual) for libbpf
where data field is const void *

It makes sense for bpftool to be in sync with libbpf from
kernel sources

Signed-off-by: Denys Zagorui <dzagorui@cisco.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20230907090210.968612-1-dzagorui@cisco.com
---
 tools/bpf/bpftool/gen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 2883660d6b67..04c47745b3ea 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -1209,7 +1209,7 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
-			s->data = (void *)%2$s__elf_bytes(&s->data_sz);	    \n\
+			s->data = %2$s__elf_bytes(&s->data_sz);		    \n\
 									    \n\
 			obj->skeleton = s;				    \n\
 			return 0;					    \n\
-- 
cgit v1.2.3


From 96daa9874211d5497aa70fa409b67afc29f0cb86 Mon Sep 17 00:00:00 2001
From: Leon Hwang <hffilwlqm@gmail.com>
Date: Wed, 6 Sep 2023 23:42:56 +0800
Subject: selftests/bpf: Correct map_fd to data_fd in tailcalls

Get and check data_fd. It should not check map_fd again.

Meanwhile, correct some 'return' to 'goto out'.

Thank the suggestion from Maciej in "bpf, x64: Fix tailcall infinite
loop"[0] discussions.

[0] https://lore.kernel.org/bpf/e496aef8-1f80-0f8e-dcdd-25a8c300319a@gmail.com/T/#m7d3b601066ba66400d436b7e7579b2df4a101033

Fixes: 79d49ba048ec ("bpf, testing: Add various tail call test cases")
Fixes: 3b0379111197 ("selftests/bpf: Add tailcall_bpf2bpf tests")
Fixes: 5e0b0a4c52d3 ("selftests/bpf: Test tail call counting with bpf2bpf and data on stack")
Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230906154256.95461-1-hffilwlqm@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/tailcalls.c | 32 +++++++++++-----------
 1 file changed, 16 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 58fe2c586ed7..09c189761926 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -271,11 +271,11 @@ static void test_tailcall_count(const char *which)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	err = bpf_map_lookup_elem(data_fd, &i, &val);
@@ -352,11 +352,11 @@ static void test_tailcall_4(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
@@ -442,11 +442,11 @@ static void test_tailcall_5(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
@@ -631,11 +631,11 @@ static void test_tailcall_bpf2bpf_2(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	err = bpf_map_lookup_elem(data_fd, &i, &val);
@@ -805,11 +805,11 @@ static void test_tailcall_bpf2bpf_4(bool noise)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	val.noise = noise;
@@ -872,7 +872,7 @@ static void test_tailcall_bpf2bpf_6(void)
 	ASSERT_EQ(topts.retval, 0, "tailcall retval");
 
 	data_fd = bpf_map__fd(obj->maps.bss);
-	if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+	if (!ASSERT_GE(data_fd, 0, "bss map fd"))
 		goto out;
 
 	i = 0;
-- 
cgit v1.2.3


From e13b5f2f3ba3df1ca31824d2fdbd182250fa10c7 Mon Sep 17 00:00:00 2001
From: Leon Hwang <hffilwlqm@gmail.com>
Date: Tue, 12 Sep 2023 23:04:42 +0800
Subject: selftests/bpf: Add testcases for tailcall infinite loop fixing

Add 4 test cases to confirm the tailcall infinite loop bug has been fixed.

Like tailcall_bpf2bpf cases, do fentry/fexit on the bpf2bpf, and then
check the final count result.

tools/testing/selftests/bpf/test_progs -t tailcalls
226/13  tailcalls/tailcall_bpf2bpf_fentry:OK
226/14  tailcalls/tailcall_bpf2bpf_fexit:OK
226/15  tailcalls/tailcall_bpf2bpf_fentry_fexit:OK
226/16  tailcalls/tailcall_bpf2bpf_fentry_entry:OK
226     tailcalls:OK
Summary: 1/16 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Leon Hwang <hffilwlqm@gmail.com>
Link: https://lore.kernel.org/r/20230912150442.2009-4-hffilwlqm@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/tailcalls.c | 237 ++++++++++++++++++++-
 .../selftests/bpf/progs/tailcall_bpf2bpf_fentry.c  |  18 ++
 .../selftests/bpf/progs/tailcall_bpf2bpf_fexit.c   |  18 ++
 3 files changed, 269 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c
 create mode 100644 tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 09c189761926..fc6b2954e8f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -218,12 +218,14 @@ out:
 	bpf_object__close(obj);
 }
 
-static void test_tailcall_count(const char *which)
+static void test_tailcall_count(const char *which, bool test_fentry,
+				bool test_fexit)
 {
+	struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
+	struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
 	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
 	struct bpf_map *prog_array, *data_map;
 	struct bpf_program *prog;
-	struct bpf_object *obj;
 	char buff[128] = {};
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = buff,
@@ -265,6 +267,54 @@ static void test_tailcall_count(const char *which)
 	if (CHECK_FAIL(err))
 		goto out;
 
+	if (test_fentry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+	}
+
+	if (test_fexit) {
+		fexit_obj = bpf_object__open_file("tailcall_bpf2bpf_fexit.bpf.o",
+						  NULL);
+		if (!ASSERT_OK_PTR(fexit_obj, "open fexit_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fexit_obj, "fexit");
+		if (!ASSERT_OK_PTR(prog, "find fexit prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fexit_obj);
+		if (!ASSERT_OK(err, "load fexit_obj"))
+			goto out;
+
+		fexit_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fexit_link, "attach_trace"))
+			goto out;
+	}
+
 	err = bpf_prog_test_run_opts(main_fd, &topts);
 	ASSERT_OK(err, "tailcall");
 	ASSERT_EQ(topts.retval, 1, "tailcall retval");
@@ -282,6 +332,40 @@ static void test_tailcall_count(const char *which)
 	ASSERT_OK(err, "tailcall count");
 	ASSERT_EQ(val, 33, "tailcall count");
 
+	if (test_fentry) {
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fentry.bss map"))
+			goto out;
+
+		data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_FALSE(data_fd < 0,
+				  "find tailcall_bpf2bpf_fentry.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 33, "fentry count");
+	}
+
+	if (test_fexit) {
+		data_map = bpf_object__find_map_by_name(fexit_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fexit.bss map"))
+			goto out;
+
+		data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_FALSE(data_fd < 0,
+				  "find tailcall_bpf2bpf_fexit.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 33, "fexit count");
+	}
+
 	i = 0;
 	err = bpf_map_delete_elem(map_fd, &i);
 	if (CHECK_FAIL(err))
@@ -291,6 +375,10 @@ static void test_tailcall_count(const char *which)
 	ASSERT_OK(err, "tailcall");
 	ASSERT_OK(topts.retval, "tailcall retval");
 out:
+	bpf_link__destroy(fentry_link);
+	bpf_link__destroy(fexit_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(fexit_obj);
 	bpf_object__close(obj);
 }
 
@@ -299,7 +387,7 @@ out:
  */
 static void test_tailcall_3(void)
 {
-	test_tailcall_count("tailcall3.bpf.o");
+	test_tailcall_count("tailcall3.bpf.o", false, false);
 }
 
 /* test_tailcall_6 checks that the count value of the tail call limit
@@ -307,7 +395,7 @@ static void test_tailcall_3(void)
  */
 static void test_tailcall_6(void)
 {
-	test_tailcall_count("tailcall6.bpf.o");
+	test_tailcall_count("tailcall6.bpf.o", false, false);
 }
 
 /* test_tailcall_4 checks that the kernel properly selects indirect jump
@@ -884,6 +972,139 @@ out:
 	tailcall_bpf2bpf6__destroy(obj);
 }
 
+/* test_tailcall_bpf2bpf_fentry checks that the count value of the tail call
+ * limit enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call, and the bpf2bpf call is traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_fentry(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", true, false);
+}
+
+/* test_tailcall_bpf2bpf_fexit checks that the count value of the tail call
+ * limit enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call, and the bpf2bpf call is traced by fexit.
+ */
+static void test_tailcall_bpf2bpf_fexit(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", false, true);
+}
+
+/* test_tailcall_bpf2bpf_fentry_fexit checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcall is preceded
+ * with bpf2bpf call, and the bpf2bpf call is traced by both fentry and fexit.
+ */
+static void test_tailcall_bpf2bpf_fentry_fexit(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", true, true);
+}
+
+/* test_tailcall_bpf2bpf_fentry_entry checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcall is preceded
+ * with bpf2bpf call, and the bpf2bpf caller is traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_fentry_entry(void)
+{
+	struct bpf_object *tgt_obj = NULL, *fentry_obj = NULL;
+	int err, map_fd, prog_fd, data_fd, i, val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_link *fentry_link = NULL;
+	struct bpf_program *prog;
+	char buff[128] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf2.bpf.o",
+				 BPF_PROG_TYPE_SCHED_CLS,
+				 &tgt_obj, &prog_fd);
+	if (!ASSERT_OK(err, "load tgt_obj"))
+		return;
+
+	prog_array = bpf_object__find_map_by_name(tgt_obj, "jmp_table");
+	if (!ASSERT_OK_PTR(prog_array, "find jmp_table map"))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (!ASSERT_FALSE(map_fd < 0, "find jmp_table map fd"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(tgt_obj, "classifier_0");
+	if (!ASSERT_OK_PTR(prog, "find classifier_0 prog"))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_FALSE(prog_fd < 0, "find classifier_0 prog fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+					   NULL);
+	if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+	if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+		goto out;
+
+	err = bpf_program__set_attach_target(prog, prog_fd, "classifier_0");
+	if (!ASSERT_OK(err, "set_attach_target classifier_0"))
+		goto out;
+
+	err = bpf_object__load(fentry_obj);
+	if (!ASSERT_OK(err, "load fentry_obj"))
+		goto out;
+
+	fentry_link = bpf_program__attach_trace(prog);
+	if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	data_map = bpf_object__find_map_by_name(tgt_obj, "tailcall.bss");
+	if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+			  "find tailcall.bss map"))
+		goto out;
+
+	data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_FALSE(data_fd < 0, "find tailcall.bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 34, "tailcall count");
+
+	data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+	if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+			  "find tailcall_bpf2bpf_fentry.bss map"))
+		goto out;
+
+	data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_FALSE(data_fd < 0,
+			  "find tailcall_bpf2bpf_fentry.bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "fentry count");
+	ASSERT_EQ(val, 1, "fentry count");
+
+out:
+	bpf_link__destroy(fentry_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(tgt_obj);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -910,4 +1131,12 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_4(true);
 	if (test__start_subtest("tailcall_bpf2bpf_6"))
 		test_tailcall_bpf2bpf_6();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry"))
+		test_tailcall_bpf2bpf_fentry();
+	if (test__start_subtest("tailcall_bpf2bpf_fexit"))
+		test_tailcall_bpf2bpf_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry_fexit"))
+		test_tailcall_bpf2bpf_fentry_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry_entry"))
+		test_tailcall_bpf2bpf_fentry_entry();
 }
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c
new file mode 100644
index 000000000000..8436c6729167
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int count = 0;
+
+SEC("fentry/subprog_tail")
+int BPF_PROG(fentry, struct sk_buff *skb)
+{
+	count++;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c
new file mode 100644
index 000000000000..fe16412c6e6e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int count = 0;
+
+SEC("fexit/subprog_tail")
+int BPF_PROG(fexit, struct sk_buff *skb)
+{
+	count++;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 70ad43333cbeaaa173cce9825f3afa63ba7ce88d Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 11 Sep 2023 18:50:13 -0300
Subject: selftests/tc-testing: cls_fw: add tests for classid

As discussed in '76e42ae83199', cls_fw was handling the use of classid
incorrectly. Add a few tests to check if it's conforming to the correct
behaviour.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/tc-testing/tc-tests/filters/fw.json  | 49 ++++++++++++++++++++++
 1 file changed, 49 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
index 5272049566d6..a4a83fb3e96f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
@@ -1351,5 +1351,54 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "e470",
+        "name": "Try to delete class referenced by fw after a replace",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC class add dev $DEV1 parent root classid 1 drr",
+            "$TC filter add dev $DEV1 parent 10: handle 1 prio 1 fw classid 10:1 action ok",
+            "$TC filter replace dev $DEV1 parent 10: handle 1 prio 1 fw classid 10:1 action drop"
+        ],
+        "cmdUnderTest": "$TC class delete dev $DEV1 parent 10: classid 10:1",
+        "expExitCode": "2",
+        "verifyCmd": "$TC class show dev $DEV1",
+        "matchPattern": "class drr 10:1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
+    },
+    {
+        "id": "ec1a",
+        "name": "Replace fw classid with nil",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC class add dev $DEV1 parent root classid 1 drr",
+            "$TC filter add dev $DEV1 parent 10: handle 1 prio 1 fw classid 10:1 action ok"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent 10: handle 1 prio 1 fw action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent 10:",
+        "matchPattern": "fw chain 0 handle 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 7c339083616ce803fce1bfe322bf2e20d8d84ab0 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 11 Sep 2023 18:50:14 -0300
Subject: selftests/tc-testing: cls_route: add tests for classid

As discussed in 'b80b829e9e2c', cls_route was handling the use of classid
incorrectly. Add a test to check if it's conforming to the correct
behaviour.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/filters/route.json         | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
index 1f6f19f02997..8d8de8f65aef 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json
@@ -177,5 +177,30 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "b042",
+        "name": "Try to delete class referenced by route after a replace",
+        "category": [
+            "filter",
+            "route"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC class add dev $DEV1 parent root classid 1 drr",
+            "$TC filter add dev $DEV1 parent 10: prio 1 route from 10 classid 10:1 action ok",
+            "$TC filter replace dev $DEV1 parent 10: prio 1 route from 5 classid 10:1 action drop"
+        ],
+        "cmdUnderTest": "$TC class delete dev $DEV1 parent 10: classid 10:1",
+        "expExitCode": "2",
+        "verifyCmd": "$TC class show dev $DEV1",
+        "matchPattern": "class drr 10:1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
     }
 ]
-- 
cgit v1.2.3


From e2f2fb3c352da855da2b9e1b2fd43a07cc1cd009 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 11 Sep 2023 18:50:15 -0300
Subject: selftests/tc-testing: cls_u32: add tests for classid

As discussed in '3044b16e7c6f', cls_u32 was handling the use of classid
incorrectly. Add a test to check if it's conforming to the correct
behaviour.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/tc-testing/tc-tests/filters/u32.json | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
index bd64a4bf11ab..ddc7c355be0a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
@@ -247,5 +247,30 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "0c37",
+        "name": "Try to delete class referenced by u32 after a replace",
+        "category": [
+            "filter",
+            "u32"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 parent root handle 10: drr",
+            "$TC class add dev $DEV1 parent root classid 1 drr",
+            "$TC filter add dev $DEV1 parent 10: prio 1 u32 match icmp type 1 0xff classid 10:1 action ok",
+            "$TC filter replace dev $DEV1 parent 10: prio 1 u32 match icmp type 1 0xff classid 10:1 action drop"
+        ],
+        "cmdUnderTest": "$TC class delete dev $DEV1 parent 10: classid 10:1",
+        "expExitCode": "2",
+        "verifyCmd": "$TC class show dev $DEV1",
+        "matchPattern": "class drr 10:1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 parent root drr"
+        ]
     }
 ]
-- 
cgit v1.2.3


From b698bd97c571129cb642eb73ba6fc15bd4c23549 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Mon, 11 Sep 2023 23:20:27 +0300
Subject: test/vsock: shutdowned socket test

This adds two tests for 'shutdown()' call. It checks that SIGPIPE is
sent when MSG_NOSIGNAL is not set and vice versa. Both flags SHUT_WR
and SHUT_RD are tested.

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/vsock/vsock_test.c | 138 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 138 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 90718c2fd4ea..148fc9c47c50 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -19,6 +19,7 @@
 #include <time.h>
 #include <sys/mman.h>
 #include <poll.h>
+#include <signal.h>
 
 #include "timeout.h"
 #include "control.h"
@@ -1170,6 +1171,133 @@ static void test_seqpacket_msg_peek_server(const struct test_opts *opts)
 	return test_msg_peek_server(opts, true);
 }
 
+static sig_atomic_t have_sigpipe;
+
+static void sigpipe(int signo)
+{
+	have_sigpipe = 1;
+}
+
+static void test_stream_check_sigpipe(int fd)
+{
+	ssize_t res;
+
+	have_sigpipe = 0;
+
+	res = send(fd, "A", 1, 0);
+	if (res != -1) {
+		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!have_sigpipe) {
+		fprintf(stderr, "SIGPIPE expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	have_sigpipe = 0;
+
+	res = send(fd, "A", 1, MSG_NOSIGNAL);
+	if (res != -1) {
+		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
+		exit(EXIT_FAILURE);
+	}
+
+	if (have_sigpipe) {
+		fprintf(stderr, "SIGPIPE not expected\n");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void test_stream_shutwr_client(const struct test_opts *opts)
+{
+	int fd;
+
+	struct sigaction act = {
+		.sa_handler = sigpipe,
+	};
+
+	sigaction(SIGPIPE, &act, NULL);
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (shutdown(fd, SHUT_WR)) {
+		perror("shutdown");
+		exit(EXIT_FAILURE);
+	}
+
+	test_stream_check_sigpipe(fd);
+
+	control_writeln("CLIENTDONE");
+
+	close(fd);
+}
+
+static void test_stream_shutwr_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("CLIENTDONE");
+
+	close(fd);
+}
+
+static void test_stream_shutrd_client(const struct test_opts *opts)
+{
+	int fd;
+
+	struct sigaction act = {
+		.sa_handler = sigpipe,
+	};
+
+	sigaction(SIGPIPE, &act, NULL);
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("SHUTRDDONE");
+
+	test_stream_check_sigpipe(fd);
+
+	control_writeln("CLIENTDONE");
+
+	close(fd);
+}
+
+static void test_stream_shutrd_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	if (shutdown(fd, SHUT_RD)) {
+		perror("shutdown");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("SHUTRDDONE");
+	control_expectln("CLIENTDONE");
+
+	close(fd);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1250,6 +1378,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_seqpacket_msg_peek_client,
 		.run_server = test_seqpacket_msg_peek_server,
 	},
+	{
+		.name = "SOCK_STREAM SHUT_WR",
+		.run_client = test_stream_shutwr_client,
+		.run_server = test_stream_shutwr_server,
+	},
+	{
+		.name = "SOCK_STREAM SHUT_RD",
+		.run_client = test_stream_shutrd_client,
+		.run_server = test_stream_shutrd_server,
+	},
 	{},
 };
 
-- 
cgit v1.2.3


From 2d2712caf44b6cc0d571eed01ac13356667f0f8e Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:48 +0200
Subject: selftests/xsk: print per packet info in verbose mode

Print info about every packet in verbose mode, both for Tx and
Rx. This is useful to have when a test fails or to validate that a
test is really doing what it was designed to do. Info on what is
supposed to be received and sent is also printed for the custom packet
streams since they differ from the base line. Here is an example:

Tx addr: 37e0 len: 64 options: 0 pkt_nb: 8
Tx addr: 4000 len: 64 options: 0 pkt_nb: 9
Rx: addr: 100 len: 64 options: 0 pkt_nb: 0 valid: 1
Rx: addr: 1100 len: 64 options: 0 pkt_nb: 1 valid: 1
Rx: addr: 2100 len: 64 options: 0 pkt_nb: 4 valid: 1
Rx: addr: 3100 len: 64 options: 0 pkt_nb: 8 valid: 1
Rx: addr: 4100 len: 64 options: 0 pkt_nb: 9 valid: 1

One pointless verbose print statement is also deleted and another one
is made clearer.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-2-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 2827f2d7cf30..c595c0b65417 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -747,6 +747,9 @@ static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, s
 			len = 0;
 		}
 
+		print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n",
+			      pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb);
+
 		if (pkt->valid && pkt->len > pkt_stream->max_pkt_len)
 			pkt_stream->max_pkt_len = pkt->len;
 		pkt_nb++;
@@ -1042,6 +1045,9 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 				return TEST_FAILURE;
 			}
 
+			print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n",
+				      addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid);
+
 			if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
 			    !is_offset_correct(umem, pkt, addr) ||
 			    (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr)))
@@ -1165,6 +1171,9 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 					     bytes_written);
 			bytes_written += tx_desc->len;
 
+			print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n",
+				      tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb);
+
 			if (nb_frags_left) {
 				i++;
 				if (pkt_stream->verbatim)
@@ -1475,8 +1484,6 @@ static void *worker_testapp_validate_tx(void *arg)
 			thread_common_ops_tx(test, ifobject);
 	}
 
-	print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts,
-		      ifobject->ifname);
 	err = send_pkts(test, ifobject);
 
 	if (!err && ifobject->validation_func)
@@ -1715,7 +1722,7 @@ static int testapp_bidi(struct test_spec *test)
 	if (testapp_validate_traffic(test))
 		return TEST_FAILURE;
 
-	print_verbose("Switching Tx/Rx vectors\n");
+	print_verbose("Switching Tx/Rx direction\n");
 	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
 	res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx);
 
-- 
cgit v1.2.3


From 64370d7c8a91e65a08f6f5816f108a0485000481 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:49 +0200
Subject: selftests/xsk: add timeout for Tx thread

Add a timeout for the transmission thread. If packets are not
completed properly, for some reason, the test harness would previously
get stuck forever in a while loop. But with this patch, this timeout
will trigger, flag the test as a failure, and continue with the next
test.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-3-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index c595c0b65417..514fe994e02b 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1216,10 +1216,29 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 	return TEST_CONTINUE;
 }
 
-static void wait_for_tx_completion(struct xsk_socket_info *xsk)
+static int wait_for_tx_completion(struct xsk_socket_info *xsk)
 {
-	while (xsk->outstanding_tx)
+	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
+	int ret;
+
+	ret = gettimeofday(&tv_now, NULL);
+	if (ret)
+		exit_with_error(errno);
+	timeradd(&tv_now, &tv_timeout, &tv_end);
+
+	while (xsk->outstanding_tx) {
+		ret = gettimeofday(&tv_now, NULL);
+		if (ret)
+			exit_with_error(errno);
+		if (timercmp(&tv_now, &tv_end, >)) {
+			ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__);
+			return TEST_FAILURE;
+		}
+
 		complete_pkts(xsk, BATCH_SIZE);
+	}
+
+	return TEST_PASS;
 }
 
 static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
@@ -1242,8 +1261,7 @@ static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
 			return ret;
 	}
 
-	wait_for_tx_completion(ifobject->xsk);
-	return TEST_PASS;
+	return wait_for_tx_completion(ifobject->xsk);
 }
 
 static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats)
-- 
cgit v1.2.3


From 3956bc34b66c99217261def0a1058ebb9cc9b576 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:50 +0200
Subject: selftests/xsk: add option to only run tests in a single mode

Add an option -m on the command line that allows the user to run the
tests in a single mode instead of all of them. Valid modes are skb,
drv, and zc (zero-copy). An example:

To run test suite in drv mode only:

./test_xsk.sh -m drv

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-4-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_xsk.sh  | 10 +++++++-
 tools/testing/selftests/bpf/xskxceiver.c | 41 ++++++++++++++++++++++++++++----
 tools/testing/selftests/bpf/xskxceiver.h |  4 +---
 3 files changed, 47 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 2aa5a3445056..85e7a7e843f7 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -73,17 +73,21 @@
 #
 # Run test suite for physical device in loopback mode
 #   sudo ./test_xsk.sh -i IFACE
+#
+# Run test suite in a specific mode only [skb,drv,zc]
+#   sudo ./test_xsk.sh -m MODE
 
 . xsk_prereqs.sh
 
 ETH=""
 
-while getopts "vi:d" flag
+while getopts "vi:dm:" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
 		d) debug=1;;
 		i) ETH=${OPTARG};;
+		m) MODE=${OPTARG};;
 	esac
 done
 
@@ -153,6 +157,10 @@ if [[ $verbose -eq 1 ]]; then
 	ARGS+="-v "
 fi
 
+if [ -n "$MODE" ]; then
+	ARGS+="-m ${MODE} "
+fi
+
 retval=$?
 test_status $retval "${TEST_NAME}"
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 514fe994e02b..64a671fca54a 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -107,6 +107,9 @@
 static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
 static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
 
+static bool opt_verbose;
+static enum test_mode opt_mode = TEST_MODE_ALL;
+
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
 	ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error,
@@ -310,17 +313,19 @@ static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"busy-poll", no_argument, 0, 'b'},
 	{"verbose", no_argument, 0, 'v'},
+	{"mode", required_argument, 0, 'm'},
 	{0, 0, 0, 0}
 };
 
 static void usage(const char *prog)
 {
 	const char *str =
-		"  Usage: %s [OPTIONS]\n"
+		"  Usage: xskxceiver [OPTIONS]\n"
 		"  Options:\n"
 		"  -i, --interface      Use interface\n"
 		"  -v, --verbose        Verbose output\n"
-		"  -b, --busy-poll      Enable busy poll\n";
+		"  -b, --busy-poll      Enable busy poll\n"
+		"  -m, --mode           Run only mode skb, drv, or zc\n";
 
 	ksft_print_msg(str, prog);
 }
@@ -342,7 +347,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:vb", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:vbm:", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -371,6 +376,18 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			ifobj_tx->busy_poll = true;
 			ifobj_rx->busy_poll = true;
 			break;
+		case 'm':
+			if (!strncmp("skb", optarg, strlen(optarg))) {
+				opt_mode = TEST_MODE_SKB;
+			} else if (!strncmp("drv", optarg, strlen(optarg))) {
+				opt_mode = TEST_MODE_DRV;
+			} else if (!strncmp("zc", optarg, strlen(optarg))) {
+				opt_mode = TEST_MODE_ZC;
+			} else {
+				usage(basename(argv[0]));
+				ksft_exit_xfail();
+			}
+			break;
 		default:
 			usage(basename(argv[0]));
 			ksft_exit_xfail();
@@ -2365,9 +2382,25 @@ int main(int argc, char **argv)
 	test.tx_pkt_stream_default = tx_pkt_stream_default;
 	test.rx_pkt_stream_default = rx_pkt_stream_default;
 
-	ksft_set_plan(modes * TEST_TYPE_MAX);
+	if (opt_mode == TEST_MODE_ALL) {
+		ksft_set_plan(modes * TEST_TYPE_MAX);
+	} else {
+		if (opt_mode == TEST_MODE_DRV && modes <= TEST_MODE_DRV) {
+			ksft_print_msg("Error: XDP_DRV mode not supported.\n");
+			ksft_exit_xfail();
+		}
+		if (opt_mode == TEST_MODE_ZC && modes <= TEST_MODE_ZC) {
+			ksft_print_msg("Error: zero-copy mode not supported.\n");
+			ksft_exit_xfail();
+		}
+
+		ksft_set_plan(TEST_TYPE_MAX);
+	}
 
 	for (i = 0; i < modes; i++) {
+		if (opt_mode != TEST_MODE_ALL && i != opt_mode)
+			continue;
+
 		for (j = 0; j < TEST_TYPE_MAX; j++) {
 			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
 			run_pkt_test(&test, i, j);
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 233b66cef64a..1412492e9618 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -63,7 +63,7 @@ enum test_mode {
 	TEST_MODE_SKB,
 	TEST_MODE_DRV,
 	TEST_MODE_ZC,
-	TEST_MODE_MAX
+	TEST_MODE_ALL
 };
 
 enum test_type {
@@ -98,8 +98,6 @@ enum test_type {
 	TEST_TYPE_MAX
 };
 
-static bool opt_verbose;
-
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
 	struct xsk_ring_cons cq;
-- 
cgit v1.2.3


From 13c341c4508318f77f2c590b9971ac9efec925cc Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:51 +0200
Subject: selftests/xsk: move all tests to separate functions

Prepare for the capability to be able to run a single test by moving
all the tests to their own functions. This function can then be called
to execute that test in the next commit.

Also, the tests named RUN_TO_COMPLETION_* were not named well, so
change them to SEND_RECEIVE_* as it is just a basic send and receive
test of 4K packets.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-5-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 170 +++++++++++++++++++++----------
 1 file changed, 115 insertions(+), 55 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 64a671fca54a..e8425f758d79 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1872,13 +1872,14 @@ static int testapp_single_pkt(struct test_spec *test)
 {
 	struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}};
 
+	test_spec_set_name(test, "SEND_RECEIVE_SINGLE_PKT");
 	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
 	return testapp_validate_traffic(test);
 }
 
 static int testapp_multi_buffer(struct test_spec *test)
 {
-	test_spec_set_name(test, "RUN_TO_COMPLETION_9K_PACKETS");
+	test_spec_set_name(test, "SEND_RECEIVE_9K_PACKETS");
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 	pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE);
 
@@ -1983,7 +1984,7 @@ static int testapp_xdp_drop(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
-static int testapp_xdp_metadata_count(struct test_spec *test)
+static int testapp_xdp_metadata_copy(struct test_spec *test)
 {
 	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
 	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
@@ -2133,6 +2134,105 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	}
 }
 
+static int testapp_send_receive(struct test_spec *test)
+{
+	test_spec_set_name(test, "SEND_RECEIVE");
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_send_receive_2k_frame(struct test_spec *test)
+{
+	test_spec_set_name(test, "SEND_RECEIVE_2K_FRAME_SIZE");
+	test->ifobj_tx->umem->frame_size = 2048;
+	test->ifobj_rx->umem->frame_size = 2048;
+	pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_poll_rx(struct test_spec *test)
+{
+	test->ifobj_rx->use_poll = true;
+	test_spec_set_name(test, "POLL_RX");
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_poll_tx(struct test_spec *test)
+{
+	test->ifobj_tx->use_poll = true;
+	test_spec_set_name(test, "POLL_TX");
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_aligned_inv_desc(struct test_spec *test)
+{
+	test_spec_set_name(test, "ALIGNED_INV_DESC");
+	return testapp_invalid_desc(test);
+}
+
+static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
+{
+	test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE");
+	test->ifobj_tx->umem->frame_size = 2048;
+	test->ifobj_rx->umem->frame_size = 2048;
+	return testapp_invalid_desc(test);
+}
+
+static int testapp_unaligned_inv_desc(struct test_spec *test)
+{
+	test_spec_set_name(test, "UNALIGNED_INV_DESC");
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	return testapp_invalid_desc(test);
+}
+
+static int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test)
+{
+	u64 page_size, umem_size;
+
+	test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE");
+	/* Odd frame size so the UMEM doesn't end near a page boundary. */
+	test->ifobj_tx->umem->frame_size = 4001;
+	test->ifobj_rx->umem->frame_size = 4001;
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	/* This test exists to test descriptors that staddle the end of
+	 * the UMEM but not a page.
+	 */
+	page_size = sysconf(_SC_PAGESIZE);
+	umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size;
+	assert(umem_size % page_size > MIN_PKT_SIZE);
+	assert(umem_size % page_size < page_size - MIN_PKT_SIZE);
+
+	return testapp_invalid_desc(test);
+}
+
+static int testapp_aligned_inv_desc_mb(struct test_spec *test)
+{
+	test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF");
+	return testapp_invalid_desc_mb(test);
+}
+
+static int testapp_unaligned_inv_desc_mb(struct test_spec *test)
+{
+	test_spec_set_name(test, "UNALIGNED_INV_DESC_MULTI_BUFF");
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	return testapp_invalid_desc_mb(test);
+}
+
+static int testapp_xdp_metadata(struct test_spec *test)
+{
+	test_spec_set_name(test, "XDP_METADATA_COPY");
+	return testapp_xdp_metadata_copy(test);
+}
+
+static int testapp_xdp_metadata_mb(struct test_spec *test)
+{
+	test_spec_set_name(test, "XDP_METADATA_COPY_MULTI_BUFF");
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	return testapp_xdp_metadata_copy(test);
+}
+
 static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
 {
 	int ret = TEST_SKIP;
@@ -2160,32 +2260,22 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		ret = testapp_bpf_res(test);
 		break;
 	case TEST_TYPE_RUN_TO_COMPLETION:
-		test_spec_set_name(test, "RUN_TO_COMPLETION");
-		ret = testapp_validate_traffic(test);
+		ret = testapp_send_receive(test);
 		break;
 	case TEST_TYPE_RUN_TO_COMPLETION_MB:
 		ret = testapp_multi_buffer(test);
 		break;
 	case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT:
-		test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT");
 		ret = testapp_single_pkt(test);
 		break;
 	case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME:
-		test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE");
-		test->ifobj_tx->umem->frame_size = 2048;
-		test->ifobj_rx->umem->frame_size = 2048;
-		pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
-		ret = testapp_validate_traffic(test);
+		ret = testapp_send_receive_2k_frame(test);
 		break;
 	case TEST_TYPE_RX_POLL:
-		test->ifobj_rx->use_poll = true;
-		test_spec_set_name(test, "POLL_RX");
-		ret = testapp_validate_traffic(test);
+		ret = testapp_poll_rx(test);
 		break;
 	case TEST_TYPE_TX_POLL:
-		test->ifobj_tx->use_poll = true;
-		test_spec_set_name(test, "POLL_TX");
-		ret = testapp_validate_traffic(test);
+		ret = testapp_poll_tx(test);
 		break;
 	case TEST_TYPE_POLL_TXQ_TMOUT:
 		ret = testapp_poll_txq_tmout(test);
@@ -2194,49 +2284,22 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		ret = testapp_poll_rxq_tmout(test);
 		break;
 	case TEST_TYPE_ALIGNED_INV_DESC:
-		test_spec_set_name(test, "ALIGNED_INV_DESC");
-		ret = testapp_invalid_desc(test);
+		ret = testapp_aligned_inv_desc(test);
 		break;
 	case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME:
-		test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE");
-		test->ifobj_tx->umem->frame_size = 2048;
-		test->ifobj_rx->umem->frame_size = 2048;
-		ret = testapp_invalid_desc(test);
+		ret = testapp_aligned_inv_desc_2k_frame(test);
 		break;
 	case TEST_TYPE_UNALIGNED_INV_DESC:
-		test_spec_set_name(test, "UNALIGNED_INV_DESC");
-		test->ifobj_tx->umem->unaligned_mode = true;
-		test->ifobj_rx->umem->unaligned_mode = true;
-		ret = testapp_invalid_desc(test);
+		ret = testapp_unaligned_inv_desc(test);
 		break;
-	case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME: {
-		u64 page_size, umem_size;
-
-		test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE");
-		/* Odd frame size so the UMEM doesn't end near a page boundary. */
-		test->ifobj_tx->umem->frame_size = 4001;
-		test->ifobj_rx->umem->frame_size = 4001;
-		test->ifobj_tx->umem->unaligned_mode = true;
-		test->ifobj_rx->umem->unaligned_mode = true;
-		/* This test exists to test descriptors that staddle the end of
-		 * the UMEM but not a page.
-		 */
-		page_size = sysconf(_SC_PAGESIZE);
-		umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size;
-		assert(umem_size % page_size > MIN_PKT_SIZE);
-		assert(umem_size % page_size < page_size - MIN_PKT_SIZE);
-		ret = testapp_invalid_desc(test);
+	case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME:
+		ret = testapp_unaligned_inv_desc_4001_frame(test);
 		break;
-	}
 	case TEST_TYPE_ALIGNED_INV_DESC_MB:
-		test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF");
-		ret = testapp_invalid_desc_mb(test);
+		ret = testapp_aligned_inv_desc_mb(test);
 		break;
 	case TEST_TYPE_UNALIGNED_INV_DESC_MB:
-		test_spec_set_name(test, "UNALIGNED_INV_DESC_MULTI_BUFF");
-		test->ifobj_tx->umem->unaligned_mode = true;
-		test->ifobj_rx->umem->unaligned_mode = true;
-		ret = testapp_invalid_desc_mb(test);
+		ret = testapp_unaligned_inv_desc_mb(test);
 		break;
 	case TEST_TYPE_UNALIGNED:
 		ret = testapp_unaligned(test);
@@ -2251,13 +2314,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		ret = testapp_xdp_drop(test);
 		break;
 	case TEST_TYPE_XDP_METADATA_COUNT:
-		test_spec_set_name(test, "XDP_METADATA_COUNT");
-		ret = testapp_xdp_metadata_count(test);
+		ret = testapp_xdp_metadata(test);
 		break;
 	case TEST_TYPE_XDP_METADATA_COUNT_MB:
-		test_spec_set_name(test, "XDP_METADATA_COUNT_MULTI_BUFF");
-		test->mtu = MAX_ETH_JUMBO_SIZE;
-		ret = testapp_xdp_metadata_count(test);
+		ret = testapp_xdp_metadata_mb(test);
 		break;
 	case TEST_TYPE_TOO_MANY_FRAGS:
 		ret = testapp_too_many_frags(test);
-- 
cgit v1.2.3


From f20fbcd077eb8f46d6deee46e345fefb1130a181 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:52 +0200
Subject: selftests/xsk: declare test names in struct

Declare the test names statically in a struct so that we can refer to
them when adding the support to execute a single test in the next
commit. Before this patch, the names of them were not declared in a
single place which made it not possible to refer to them.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-6-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 191 +++++++++----------------------
 tools/testing/selftests/bpf/xskxceiver.h |  37 +-----
 2 files changed, 57 insertions(+), 171 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index e8425f758d79..38d4c036060d 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -444,7 +444,8 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 }
 
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
-			   struct ifobject *ifobj_rx, enum test_mode mode)
+			   struct ifobject *ifobj_rx, enum test_mode mode,
+			   const struct test_spec *test_to_run)
 {
 	struct pkt_stream *tx_pkt_stream;
 	struct pkt_stream *rx_pkt_stream;
@@ -466,6 +467,8 @@ static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 			ifobj->bind_flags |= XDP_COPY;
 	}
 
+	strncpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE);
+	test->test_func = test_to_run->test_func;
 	test->mode = mode;
 	__test_spec_init(test, ifobj_tx, ifobj_rx);
 }
@@ -475,11 +478,6 @@ static void test_spec_reset(struct test_spec *test)
 	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
 }
 
-static void test_spec_set_name(struct test_spec *test, const char *name)
-{
-	strncpy(test->name, name, MAX_TEST_NAME_SIZE);
-}
-
 static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx,
 				   struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx,
 				   struct bpf_map *xskmap_tx)
@@ -1724,7 +1722,6 @@ static int testapp_teardown(struct test_spec *test)
 {
 	int i;
 
-	test_spec_set_name(test, "TEARDOWN");
 	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
 		if (testapp_validate_traffic(test))
 			return TEST_FAILURE;
@@ -1746,11 +1743,10 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
 	*ifobj2 = tmp_ifobj;
 }
 
-static int testapp_bidi(struct test_spec *test)
+static int testapp_bidirectional(struct test_spec *test)
 {
 	int res;
 
-	test_spec_set_name(test, "BIDIRECTIONAL");
 	test->ifobj_tx->rx_on = true;
 	test->ifobj_rx->tx_on = true;
 	test->total_steps = 2;
@@ -1779,9 +1775,8 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj
 		exit_with_error(errno);
 }
 
-static int testapp_bpf_res(struct test_spec *test)
+static int testapp_xdp_prog_cleanup(struct test_spec *test)
 {
-	test_spec_set_name(test, "BPF_RES");
 	test->total_steps = 2;
 	test->nb_sockets = 2;
 	if (testapp_validate_traffic(test))
@@ -1793,14 +1788,12 @@ static int testapp_bpf_res(struct test_spec *test)
 
 static int testapp_headroom(struct test_spec *test)
 {
-	test_spec_set_name(test, "UMEM_HEADROOM");
 	test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE;
 	return testapp_validate_traffic(test);
 }
 
 static int testapp_stats_rx_dropped(struct test_spec *test)
 {
-	test_spec_set_name(test, "STAT_RX_DROPPED");
 	if (test->mode == TEST_MODE_ZC) {
 		ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n");
 		return TEST_SKIP;
@@ -1816,7 +1809,6 @@ static int testapp_stats_rx_dropped(struct test_spec *test)
 
 static int testapp_stats_tx_invalid_descs(struct test_spec *test)
 {
-	test_spec_set_name(test, "STAT_TX_INVALID");
 	pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0);
 	test->ifobj_tx->validation_func = validate_tx_invalid_descs;
 	return testapp_validate_traffic(test);
@@ -1824,7 +1816,6 @@ static int testapp_stats_tx_invalid_descs(struct test_spec *test)
 
 static int testapp_stats_rx_full(struct test_spec *test)
 {
-	test_spec_set_name(test, "STAT_RX_FULL");
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
 	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
 							 DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
@@ -1837,7 +1828,6 @@ static int testapp_stats_rx_full(struct test_spec *test)
 
 static int testapp_stats_fill_empty(struct test_spec *test)
 {
-	test_spec_set_name(test, "STAT_RX_FILL_EMPTY");
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
 	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
 							 DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
@@ -1847,9 +1837,8 @@ static int testapp_stats_fill_empty(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
-static int testapp_unaligned(struct test_spec *test)
+static int testapp_send_receive_unaligned(struct test_spec *test)
 {
-	test_spec_set_name(test, "UNALIGNED_MODE");
 	test->ifobj_tx->umem->unaligned_mode = true;
 	test->ifobj_rx->umem->unaligned_mode = true;
 	/* Let half of the packets straddle a 4K buffer boundary */
@@ -1858,9 +1847,8 @@ static int testapp_unaligned(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
-static int testapp_unaligned_mb(struct test_spec *test)
+static int testapp_send_receive_unaligned_mb(struct test_spec *test)
 {
-	test_spec_set_name(test, "UNALIGNED_MODE_9K");
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 	test->ifobj_tx->umem->unaligned_mode = true;
 	test->ifobj_rx->umem->unaligned_mode = true;
@@ -1872,14 +1860,12 @@ static int testapp_single_pkt(struct test_spec *test)
 {
 	struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}};
 
-	test_spec_set_name(test, "SEND_RECEIVE_SINGLE_PKT");
 	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
 	return testapp_validate_traffic(test);
 }
 
-static int testapp_multi_buffer(struct test_spec *test)
+static int testapp_send_receive_mb(struct test_spec *test)
 {
-	test_spec_set_name(test, "SEND_RECEIVE_9K_PACKETS");
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 	pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE);
 
@@ -1976,7 +1962,6 @@ static int testapp_xdp_drop(struct test_spec *test)
 	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
 	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
 
-	test_spec_set_name(test, "XDP_DROP_HALF");
 	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop,
 			       skel_rx->maps.xsk, skel_tx->maps.xsk);
 
@@ -2009,8 +1994,6 @@ static int testapp_xdp_metadata_copy(struct test_spec *test)
 
 static int testapp_poll_txq_tmout(struct test_spec *test)
 {
-	test_spec_set_name(test, "POLL_TXQ_FULL");
-
 	test->ifobj_tx->use_poll = true;
 	/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
 	test->ifobj_tx->umem->frame_size = 2048;
@@ -2020,7 +2003,6 @@ static int testapp_poll_txq_tmout(struct test_spec *test)
 
 static int testapp_poll_rxq_tmout(struct test_spec *test)
 {
-	test_spec_set_name(test, "POLL_RXQ_EMPTY");
 	test->ifobj_rx->use_poll = true;
 	return testapp_validate_traffic_single_thread(test, test->ifobj_rx);
 }
@@ -2030,7 +2012,6 @@ static int testapp_too_many_frags(struct test_spec *test)
 	struct pkt pkts[2 * XSK_DESC__MAX_SKB_FRAGS + 2] = {};
 	u32 max_frags, i;
 
-	test_spec_set_name(test, "TOO_MANY_FRAGS");
 	if (test->mode == TEST_MODE_ZC)
 		max_frags = test->ifobj_tx->xdp_zc_max_segs;
 	else
@@ -2136,13 +2117,11 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 
 static int testapp_send_receive(struct test_spec *test)
 {
-	test_spec_set_name(test, "SEND_RECEIVE");
 	return testapp_validate_traffic(test);
 }
 
 static int testapp_send_receive_2k_frame(struct test_spec *test)
 {
-	test_spec_set_name(test, "SEND_RECEIVE_2K_FRAME_SIZE");
 	test->ifobj_tx->umem->frame_size = 2048;
 	test->ifobj_rx->umem->frame_size = 2048;
 	pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
@@ -2152,26 +2131,22 @@ static int testapp_send_receive_2k_frame(struct test_spec *test)
 static int testapp_poll_rx(struct test_spec *test)
 {
 	test->ifobj_rx->use_poll = true;
-	test_spec_set_name(test, "POLL_RX");
 	return testapp_validate_traffic(test);
 }
 
 static int testapp_poll_tx(struct test_spec *test)
 {
 	test->ifobj_tx->use_poll = true;
-	test_spec_set_name(test, "POLL_TX");
 	return testapp_validate_traffic(test);
 }
 
 static int testapp_aligned_inv_desc(struct test_spec *test)
 {
-	test_spec_set_name(test, "ALIGNED_INV_DESC");
 	return testapp_invalid_desc(test);
 }
 
 static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
 {
-	test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE");
 	test->ifobj_tx->umem->frame_size = 2048;
 	test->ifobj_rx->umem->frame_size = 2048;
 	return testapp_invalid_desc(test);
@@ -2179,7 +2154,6 @@ static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
 
 static int testapp_unaligned_inv_desc(struct test_spec *test)
 {
-	test_spec_set_name(test, "UNALIGNED_INV_DESC");
 	test->ifobj_tx->umem->unaligned_mode = true;
 	test->ifobj_rx->umem->unaligned_mode = true;
 	return testapp_invalid_desc(test);
@@ -2189,7 +2163,6 @@ static int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test)
 {
 	u64 page_size, umem_size;
 
-	test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE");
 	/* Odd frame size so the UMEM doesn't end near a page boundary. */
 	test->ifobj_tx->umem->frame_size = 4001;
 	test->ifobj_rx->umem->frame_size = 4001;
@@ -2208,13 +2181,11 @@ static int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test)
 
 static int testapp_aligned_inv_desc_mb(struct test_spec *test)
 {
-	test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF");
 	return testapp_invalid_desc_mb(test);
 }
 
 static int testapp_unaligned_inv_desc_mb(struct test_spec *test)
 {
-	test_spec_set_name(test, "UNALIGNED_INV_DESC_MULTI_BUFF");
 	test->ifobj_tx->umem->unaligned_mode = true;
 	test->ifobj_rx->umem->unaligned_mode = true;
 	return testapp_invalid_desc_mb(test);
@@ -2222,109 +2193,20 @@ static int testapp_unaligned_inv_desc_mb(struct test_spec *test)
 
 static int testapp_xdp_metadata(struct test_spec *test)
 {
-	test_spec_set_name(test, "XDP_METADATA_COPY");
 	return testapp_xdp_metadata_copy(test);
 }
 
 static int testapp_xdp_metadata_mb(struct test_spec *test)
 {
-	test_spec_set_name(test, "XDP_METADATA_COPY_MULTI_BUFF");
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 	return testapp_xdp_metadata_copy(test);
 }
 
-static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
-{
-	int ret = TEST_SKIP;
-
-	switch (type) {
-	case TEST_TYPE_STATS_RX_DROPPED:
-		ret = testapp_stats_rx_dropped(test);
-		break;
-	case TEST_TYPE_STATS_TX_INVALID_DESCS:
-		ret = testapp_stats_tx_invalid_descs(test);
-		break;
-	case TEST_TYPE_STATS_RX_FULL:
-		ret = testapp_stats_rx_full(test);
-		break;
-	case TEST_TYPE_STATS_FILL_EMPTY:
-		ret = testapp_stats_fill_empty(test);
-		break;
-	case TEST_TYPE_TEARDOWN:
-		ret = testapp_teardown(test);
-		break;
-	case TEST_TYPE_BIDI:
-		ret = testapp_bidi(test);
-		break;
-	case TEST_TYPE_BPF_RES:
-		ret = testapp_bpf_res(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION:
-		ret = testapp_send_receive(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION_MB:
-		ret = testapp_multi_buffer(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT:
-		ret = testapp_single_pkt(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME:
-		ret = testapp_send_receive_2k_frame(test);
-		break;
-	case TEST_TYPE_RX_POLL:
-		ret = testapp_poll_rx(test);
-		break;
-	case TEST_TYPE_TX_POLL:
-		ret = testapp_poll_tx(test);
-		break;
-	case TEST_TYPE_POLL_TXQ_TMOUT:
-		ret = testapp_poll_txq_tmout(test);
-		break;
-	case TEST_TYPE_POLL_RXQ_TMOUT:
-		ret = testapp_poll_rxq_tmout(test);
-		break;
-	case TEST_TYPE_ALIGNED_INV_DESC:
-		ret = testapp_aligned_inv_desc(test);
-		break;
-	case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME:
-		ret = testapp_aligned_inv_desc_2k_frame(test);
-		break;
-	case TEST_TYPE_UNALIGNED_INV_DESC:
-		ret = testapp_unaligned_inv_desc(test);
-		break;
-	case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME:
-		ret = testapp_unaligned_inv_desc_4001_frame(test);
-		break;
-	case TEST_TYPE_ALIGNED_INV_DESC_MB:
-		ret = testapp_aligned_inv_desc_mb(test);
-		break;
-	case TEST_TYPE_UNALIGNED_INV_DESC_MB:
-		ret = testapp_unaligned_inv_desc_mb(test);
-		break;
-	case TEST_TYPE_UNALIGNED:
-		ret = testapp_unaligned(test);
-		break;
-	case TEST_TYPE_UNALIGNED_MB:
-		ret = testapp_unaligned_mb(test);
-		break;
-	case TEST_TYPE_HEADROOM:
-		ret = testapp_headroom(test);
-		break;
-	case TEST_TYPE_XDP_DROP_HALF:
-		ret = testapp_xdp_drop(test);
-		break;
-	case TEST_TYPE_XDP_METADATA_COUNT:
-		ret = testapp_xdp_metadata(test);
-		break;
-	case TEST_TYPE_XDP_METADATA_COUNT_MB:
-		ret = testapp_xdp_metadata_mb(test);
-		break;
-	case TEST_TYPE_TOO_MANY_FRAGS:
-		ret = testapp_too_many_frags(test);
-		break;
-	default:
-		break;
-	}
+static void run_pkt_test(struct test_spec *test)
+{
+	int ret;
+
+	ret = test->test_func(test);
 
 	if (ret == TEST_PASS)
 		ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test),
@@ -2392,6 +2274,39 @@ static bool is_xdp_supported(int ifindex)
 	return true;
 }
 
+static const struct test_spec tests[] = {
+	{.name = "SEND_RECEIVE", .test_func = testapp_send_receive},
+	{.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame},
+	{.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt},
+	{.name = "POLL_RX", .test_func = testapp_poll_rx},
+	{.name = "POLL_TX", .test_func = testapp_poll_tx},
+	{.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout},
+	{.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout},
+	{.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned},
+	{.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc},
+	{.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame},
+	{.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc},
+	{.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE",
+	 .test_func = testapp_unaligned_inv_desc_4001_frame},
+	{.name = "UMEM_HEADROOM", .test_func = testapp_headroom},
+	{.name = "TEARDOWN", .test_func = testapp_teardown},
+	{.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional},
+	{.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped},
+	{.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs},
+	{.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full},
+	{.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty},
+	{.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup},
+	{.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop},
+	{.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata},
+	{.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb},
+	{.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb},
+	{.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS",
+	 .test_func = testapp_send_receive_unaligned_mb},
+	{.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb},
+	{.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb},
+	{.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags},
+};
+
 int main(int argc, char **argv)
 {
 	struct pkt_stream *rx_pkt_stream_default;
@@ -2434,7 +2349,7 @@ int main(int argc, char **argv)
 	init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx);
 	init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx);
 
-	test_spec_init(&test, ifobj_tx, ifobj_rx, 0);
+	test_spec_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]);
 	tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
 	rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
 	if (!tx_pkt_stream_default || !rx_pkt_stream_default)
@@ -2443,7 +2358,7 @@ int main(int argc, char **argv)
 	test.rx_pkt_stream_default = rx_pkt_stream_default;
 
 	if (opt_mode == TEST_MODE_ALL) {
-		ksft_set_plan(modes * TEST_TYPE_MAX);
+		ksft_set_plan(modes * ARRAY_SIZE(tests));
 	} else {
 		if (opt_mode == TEST_MODE_DRV && modes <= TEST_MODE_DRV) {
 			ksft_print_msg("Error: XDP_DRV mode not supported.\n");
@@ -2454,16 +2369,16 @@ int main(int argc, char **argv)
 			ksft_exit_xfail();
 		}
 
-		ksft_set_plan(TEST_TYPE_MAX);
+		ksft_set_plan(ARRAY_SIZE(tests));
 	}
 
 	for (i = 0; i < modes; i++) {
 		if (opt_mode != TEST_MODE_ALL && i != opt_mode)
 			continue;
 
-		for (j = 0; j < TEST_TYPE_MAX; j++) {
-			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
-			run_pkt_test(&test, i, j);
+		for (j = 0; j < ARRAY_SIZE(tests); j++) {
+			test_spec_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]);
+			run_pkt_test(&test);
 			usleep(USLEEP_MAX);
 
 			if (test.fail)
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 1412492e9618..3a71d490db3e 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -34,7 +34,7 @@
 #define MAX_INTERFACES 2
 #define MAX_INTERFACE_NAME_CHARS 16
 #define MAX_SOCKETS 2
-#define MAX_TEST_NAME_SIZE 32
+#define MAX_TEST_NAME_SIZE 48
 #define MAX_TEARDOWN_ITER 10
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
 #define MIN_PKT_SIZE 64
@@ -66,38 +66,6 @@ enum test_mode {
 	TEST_MODE_ALL
 };
 
-enum test_type {
-	TEST_TYPE_RUN_TO_COMPLETION,
-	TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME,
-	TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT,
-	TEST_TYPE_RX_POLL,
-	TEST_TYPE_TX_POLL,
-	TEST_TYPE_POLL_RXQ_TMOUT,
-	TEST_TYPE_POLL_TXQ_TMOUT,
-	TEST_TYPE_UNALIGNED,
-	TEST_TYPE_ALIGNED_INV_DESC,
-	TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME,
-	TEST_TYPE_UNALIGNED_INV_DESC,
-	TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME,
-	TEST_TYPE_HEADROOM,
-	TEST_TYPE_TEARDOWN,
-	TEST_TYPE_BIDI,
-	TEST_TYPE_STATS_RX_DROPPED,
-	TEST_TYPE_STATS_TX_INVALID_DESCS,
-	TEST_TYPE_STATS_RX_FULL,
-	TEST_TYPE_STATS_FILL_EMPTY,
-	TEST_TYPE_BPF_RES,
-	TEST_TYPE_XDP_DROP_HALF,
-	TEST_TYPE_XDP_METADATA_COUNT,
-	TEST_TYPE_XDP_METADATA_COUNT_MB,
-	TEST_TYPE_RUN_TO_COMPLETION_MB,
-	TEST_TYPE_UNALIGNED_MB,
-	TEST_TYPE_ALIGNED_INV_DESC_MB,
-	TEST_TYPE_UNALIGNED_INV_DESC_MB,
-	TEST_TYPE_TOO_MANY_FRAGS,
-	TEST_TYPE_MAX
-};
-
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
 	struct xsk_ring_cons cq;
@@ -137,8 +105,10 @@ struct pkt_stream {
 };
 
 struct ifobject;
+struct test_spec;
 typedef int (*validation_func_t)(struct ifobject *ifobj);
 typedef void *(*thread_func_t)(void *arg);
+typedef int (*test_func_t)(struct test_spec *test);
 
 struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
@@ -180,6 +150,7 @@ struct test_spec {
 	struct bpf_program *xdp_prog_tx;
 	struct bpf_map *xskmap_rx;
 	struct bpf_map *xskmap_tx;
+	test_func_t test_func;
 	int mtu;
 	u16 total_steps;
 	u16 current_step;
-- 
cgit v1.2.3


From c53dab7d39abd46901122fa47d3dce3b482d9c54 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:53 +0200
Subject: selftests/xsk: add option that lists all tests

Add a command line option (-l) that lists all the tests. The number
before the test will be used in the next commit for specifying a
single test to run. Here is an example of the output:

Tests:
0: SEND_RECEIVE
1: SEND_RECEIVE_2K_FRAME
2: SEND_RECEIVE_SINGLE_PKT
3: POLL_RX
4: POLL_TX
5: POLL_RXQ_FULL
6: POLL_TXQ_FULL
7: SEND_RECEIVE_UNALIGNED
:
:

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-7-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_xsk.sh    | 15 ++++++++++++++-
 tools/testing/selftests/bpf/xsk_prereqs.sh | 10 ++++++----
 tools/testing/selftests/bpf/xskxceiver.c   | 24 ++++++++++++++++++++++--
 3 files changed, 42 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 85e7a7e843f7..cb215a83b622 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -76,18 +76,22 @@
 #
 # Run test suite in a specific mode only [skb,drv,zc]
 #   sudo ./test_xsk.sh -m MODE
+#
+# List available tests
+#   ./test_xsk.sh -l
 
 . xsk_prereqs.sh
 
 ETH=""
 
-while getopts "vi:dm:" flag
+while getopts "vi:dm:l" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
 		d) debug=1;;
 		i) ETH=${OPTARG};;
 		m) MODE=${OPTARG};;
+		l) list=1;;
 	esac
 done
 
@@ -135,6 +139,11 @@ setup_vethPairs() {
 	ip link set ${VETH0} up
 }
 
+if [[ $list -eq 1 ]]; then
+        ./${XSKOBJ} -l
+        exit
+fi
+
 if [ ! -z $ETH ]; then
 	VETH0=${ETH}
 	VETH1=${ETH}
@@ -183,6 +192,10 @@ else
 	cleanup_iface ${ETH} ${MTU}
 fi
 
+if [[ $list -eq 1 ]]; then
+    exit
+fi
+
 TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL"
 busy_poll=1
 
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index 29175682c44d..47c7b8064f38 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -83,9 +83,11 @@ exec_xskxceiver()
 	fi
 
 	./${XSKOBJ} -i ${VETH0} -i ${VETH1} ${ARGS}
-
 	retval=$?
-	test_status $retval "${TEST_NAME}"
-	statusList+=($retval)
-	nameList+=(${TEST_NAME})
+
+	if [[ $list -ne 1 ]]; then
+	    test_status $retval "${TEST_NAME}"
+	    statusList+=($retval)
+	    nameList+=(${TEST_NAME})
+	fi
 }
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 38d4c036060d..289fae654bab 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -108,6 +108,7 @@ static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
 static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
 
 static bool opt_verbose;
+static bool opt_print_tests;
 static enum test_mode opt_mode = TEST_MODE_ALL;
 
 static void __exit_with_error(int error, const char *file, const char *func, int line)
@@ -314,6 +315,7 @@ static struct option long_options[] = {
 	{"busy-poll", no_argument, 0, 'b'},
 	{"verbose", no_argument, 0, 'v'},
 	{"mode", required_argument, 0, 'm'},
+	{"list", no_argument, 0, 'l'},
 	{0, 0, 0, 0}
 };
 
@@ -325,7 +327,8 @@ static void usage(const char *prog)
 		"  -i, --interface      Use interface\n"
 		"  -v, --verbose        Verbose output\n"
 		"  -b, --busy-poll      Enable busy poll\n"
-		"  -m, --mode           Run only mode skb, drv, or zc\n";
+		"  -m, --mode           Run only mode skb, drv, or zc\n"
+		"  -l, --list           List all available tests\n";
 
 	ksft_print_msg(str, prog);
 }
@@ -347,7 +350,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:vbm:", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:vbm:l", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -388,6 +391,9 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 				ksft_exit_xfail();
 			}
 			break;
+		case 'l':
+			opt_print_tests = true;
+			break;
 		default:
 			usage(basename(argv[0]));
 			ksft_exit_xfail();
@@ -2307,6 +2313,15 @@ static const struct test_spec tests[] = {
 	{.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags},
 };
 
+static void print_tests(void)
+{
+	u32 i;
+
+	printf("Tests:\n");
+	for (i = 0; i < ARRAY_SIZE(tests); i++)
+		printf("%u: %s\n", i, tests[i].name);
+}
+
 int main(int argc, char **argv)
 {
 	struct pkt_stream *rx_pkt_stream_default;
@@ -2331,6 +2346,11 @@ int main(int argc, char **argv)
 
 	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
 
+	if (opt_print_tests) {
+		print_tests();
+		ksft_exit_xpass();
+	}
+
 	shared_netdev = (ifobj_tx->ifindex == ifobj_rx->ifindex);
 	ifobj_tx->shared_umem = shared_netdev;
 	ifobj_rx->shared_umem = shared_netdev;
-- 
cgit v1.2.3


From 146e30554a5309b183164b385019b0357ab144dc Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:54 +0200
Subject: selftests/xsk: add option to run single test

Add a command line option to be able to run a single test. This option
(-t) takes a number from the list of tests available with the "-l"
option. Here are two examples:

Run test number 2, the "receive single packet" test in all available modes:

./test_xsk.sh -t 2

Run test number 21, the metadata copy test in skb mode only

./test_xsh.sh -t 21 -m skb

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-8-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_xsk.sh  | 10 +++++-
 tools/testing/selftests/bpf/xskxceiver.c | 56 ++++++++++++++++++++------------
 tools/testing/selftests/bpf/xskxceiver.h |  3 ++
 3 files changed, 48 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index cb215a83b622..296006ea6e9c 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -79,12 +79,15 @@
 #
 # List available tests
 #   ./test_xsk.sh -l
+#
+# Run a specific test from the test suite
+#   sudo ./test_xsk.sh -t TEST_NAME
 
 . xsk_prereqs.sh
 
 ETH=""
 
-while getopts "vi:dm:l" flag
+while getopts "vi:dm:lt:" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
@@ -92,6 +95,7 @@ do
 		i) ETH=${OPTARG};;
 		m) MODE=${OPTARG};;
 		l) list=1;;
+		t) TEST=${OPTARG};;
 	esac
 done
 
@@ -170,6 +174,10 @@ if [ -n "$MODE" ]; then
 	ARGS+="-m ${MODE} "
 fi
 
+if [ -n "$TEST" ]; then
+	ARGS+="-t ${TEST} "
+fi
+
 retval=$?
 test_status $retval "${TEST_NAME}"
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 289fae654bab..fba42edc3961 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -110,6 +110,7 @@ static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
 static bool opt_verbose;
 static bool opt_print_tests;
 static enum test_mode opt_mode = TEST_MODE_ALL;
+static u32 opt_run_test = RUN_ALL_TESTS;
 
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
@@ -316,10 +317,11 @@ static struct option long_options[] = {
 	{"verbose", no_argument, 0, 'v'},
 	{"mode", required_argument, 0, 'm'},
 	{"list", no_argument, 0, 'l'},
+	{"test", required_argument, 0, 't'},
 	{0, 0, 0, 0}
 };
 
-static void usage(const char *prog)
+static void print_usage(char **argv)
 {
 	const char *str =
 		"  Usage: xskxceiver [OPTIONS]\n"
@@ -328,9 +330,11 @@ static void usage(const char *prog)
 		"  -v, --verbose        Verbose output\n"
 		"  -b, --busy-poll      Enable busy poll\n"
 		"  -m, --mode           Run only mode skb, drv, or zc\n"
-		"  -l, --list           List all available tests\n";
+		"  -l, --list           List all available tests\n"
+		"  -t, --test           Run a specific test. Enter number from -l option.\n";
 
-	ksft_print_msg(str, prog);
+	ksft_print_msg(str, basename(argv[0]));
+	ksft_exit_xfail();
 }
 
 static bool validate_interface(struct ifobject *ifobj)
@@ -350,7 +354,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:vbm:l", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:vbm:lt:", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -380,23 +384,26 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			ifobj_rx->busy_poll = true;
 			break;
 		case 'm':
-			if (!strncmp("skb", optarg, strlen(optarg))) {
+			if (!strncmp("skb", optarg, strlen(optarg)))
 				opt_mode = TEST_MODE_SKB;
-			} else if (!strncmp("drv", optarg, strlen(optarg))) {
+			else if (!strncmp("drv", optarg, strlen(optarg)))
 				opt_mode = TEST_MODE_DRV;
-			} else if (!strncmp("zc", optarg, strlen(optarg))) {
+			else if (!strncmp("zc", optarg, strlen(optarg)))
 				opt_mode = TEST_MODE_ZC;
-			} else {
-				usage(basename(argv[0]));
-				ksft_exit_xfail();
-			}
+			else
+				print_usage(argv);
 			break;
 		case 'l':
 			opt_print_tests = true;
 			break;
+		case 't':
+			errno = 0;
+			opt_run_test = strtol(optarg, NULL, 0);
+			if (errno)
+				print_usage(argv);
+			break;
 		default:
-			usage(basename(argv[0]));
-			ksft_exit_xfail();
+			print_usage(argv);
 		}
 	}
 }
@@ -2327,8 +2334,8 @@ int main(int argc, char **argv)
 	struct pkt_stream *rx_pkt_stream_default;
 	struct pkt_stream *tx_pkt_stream_default;
 	struct ifobject *ifobj_tx, *ifobj_rx;
+	u32 i, j, failed_tests = 0, nb_tests;
 	int modes = TEST_MODE_SKB + 1;
-	u32 i, j, failed_tests = 0;
 	struct test_spec test;
 	bool shared_netdev;
 
@@ -2350,15 +2357,17 @@ int main(int argc, char **argv)
 		print_tests();
 		ksft_exit_xpass();
 	}
+	if (opt_run_test != RUN_ALL_TESTS && opt_run_test >= ARRAY_SIZE(tests)) {
+		ksft_print_msg("Error: test %u does not exist.\n", opt_run_test);
+		ksft_exit_xfail();
+	}
 
 	shared_netdev = (ifobj_tx->ifindex == ifobj_rx->ifindex);
 	ifobj_tx->shared_umem = shared_netdev;
 	ifobj_rx->shared_umem = shared_netdev;
 
-	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) {
-		usage(basename(argv[0]));
-		ksft_exit_xfail();
-	}
+	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx))
+		print_usage(argv);
 
 	if (is_xdp_supported(ifobj_tx->ifindex)) {
 		modes++;
@@ -2377,8 +2386,12 @@ int main(int argc, char **argv)
 	test.tx_pkt_stream_default = tx_pkt_stream_default;
 	test.rx_pkt_stream_default = rx_pkt_stream_default;
 
+	if (opt_run_test == RUN_ALL_TESTS)
+		nb_tests = ARRAY_SIZE(tests);
+	else
+		nb_tests = 1;
 	if (opt_mode == TEST_MODE_ALL) {
-		ksft_set_plan(modes * ARRAY_SIZE(tests));
+		ksft_set_plan(modes * nb_tests);
 	} else {
 		if (opt_mode == TEST_MODE_DRV && modes <= TEST_MODE_DRV) {
 			ksft_print_msg("Error: XDP_DRV mode not supported.\n");
@@ -2389,7 +2402,7 @@ int main(int argc, char **argv)
 			ksft_exit_xfail();
 		}
 
-		ksft_set_plan(ARRAY_SIZE(tests));
+		ksft_set_plan(nb_tests);
 	}
 
 	for (i = 0; i < modes; i++) {
@@ -2397,6 +2410,9 @@ int main(int argc, char **argv)
 			continue;
 
 		for (j = 0; j < ARRAY_SIZE(tests); j++) {
+			if (opt_run_test != RUN_ALL_TESTS && j != opt_run_test)
+				continue;
+
 			test_spec_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]);
 			run_pkt_test(&test);
 			usleep(USLEEP_MAX);
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 3a71d490db3e..8015aeea839d 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -5,6 +5,8 @@
 #ifndef XSKXCEIVER_H_
 #define XSKXCEIVER_H_
 
+#include <limits.h>
+
 #include "xsk_xdp_progs.skel.h"
 
 #ifndef SOL_XDP
@@ -56,6 +58,7 @@
 #define XSK_DESC__MAX_SKB_FRAGS 18
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
+#define RUN_ALL_TESTS UINT_MAX
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
-- 
cgit v1.2.3


From 7c3fcf088ba329292d94c03536a8add6c5a84327 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:55 +0200
Subject: selftests/xsk: use ksft_print_msg uniformly

Use ksft_print_msg() instead of printf() and fprintf() in all places
as the ksefltests framework is being used. There is only one exception
and that is for the list-of-tests print out option, since no tests are
run in that case.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-9-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index fba42edc3961..cc39a20951ff 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -808,7 +808,7 @@ static void pkt_print_data(u32 *data, u32 cnt)
 
 		seqnum = ntohl(*data) & 0xffff;
 		pkt_nb = ntohl(*data) >> 16;
-		fprintf(stdout, "%u:%u ", pkt_nb, seqnum);
+		ksft_print_msg("%u:%u ", pkt_nb, seqnum);
 		data++;
 	}
 }
@@ -820,13 +820,13 @@ static void pkt_dump(void *pkt, u32 len, bool eth_header)
 
 	if (eth_header) {
 		/*extract L2 frame */
-		fprintf(stdout, "DEBUG>> L2: dst mac: ");
+		ksft_print_msg("DEBUG>> L2: dst mac: ");
 		for (i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ethhdr->h_dest[i]);
+			ksft_print_msg("%02X", ethhdr->h_dest[i]);
 
-		fprintf(stdout, "\nDEBUG>> L2: src mac: ");
+		ksft_print_msg("\nDEBUG>> L2: src mac: ");
 		for (i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ethhdr->h_source[i]);
+			ksft_print_msg("%02X", ethhdr->h_source[i]);
 
 		data = pkt + PKT_HDR_SIZE;
 	} else {
@@ -834,15 +834,15 @@ static void pkt_dump(void *pkt, u32 len, bool eth_header)
 	}
 
 	/*extract L5 frame */
-	fprintf(stdout, "\nDEBUG>> L5: seqnum: ");
+	ksft_print_msg("\nDEBUG>> L5: seqnum: ");
 	pkt_print_data(data, PKT_DUMP_NB_TO_PRINT);
-	fprintf(stdout, "....");
+	ksft_print_msg("....");
 	if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) {
-		fprintf(stdout, "\n.... ");
+		ksft_print_msg("\n.... ");
 		pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT,
 			       PKT_DUMP_NB_TO_PRINT);
 	}
-	fprintf(stdout, "\n---------------------------------------\n");
+	ksft_print_msg("\n---------------------------------------\n");
 }
 
 static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr)
@@ -1553,7 +1553,8 @@ static void *worker_testapp_validate_rx(void *arg)
 		xsk_clear_xskmap(ifobject->xskmap);
 		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
 		if (err) {
-			printf("Error: Failed to update xskmap, error %s\n", strerror(-err));
+			ksft_print_msg("Error: Failed to update xskmap, error %s\n",
+				       strerror(-err));
 			exit_with_error(-err);
 		}
 	}
@@ -1617,7 +1618,7 @@ static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_pro
 	xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode));
 	err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode));
 	if (err) {
-		printf("Error attaching XDP program\n");
+		ksft_print_msg("Error attaching XDP program\n");
 		exit_with_error(-err);
 	}
 
@@ -2104,7 +2105,7 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 
 	err = xsk_load_xdp_programs(ifobj);
 	if (err) {
-		printf("Error loading XDP program\n");
+		ksft_print_msg("Error loading XDP program\n");
 		exit_with_error(err);
 	}
 
-- 
cgit v1.2.3


From 5fc494d5ab4119967aa967aab0b70bab8bb8b970 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:56 +0200
Subject: selftests/xsk: fail single test instead of all tests

In a number of places at en error, exit_with_error() is called that
terminates the whole test suite. This is not always desirable as it
would be more logical to only fail that test and then go along with
the other ones. So change this in a number of places in which I
thought it would be more logical to just fail the test in
question. Examples of this are in code that is only used by a single
test.

Also delete a pointless if-statement in receive_pkts() that has an
exit_with_error() in it. It can never occur since the return value is
an unsigned and the test is for less than zero.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-10-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/xskxceiver.c | 70 +++++++++++++++++++++-----------
 1 file changed, 46 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index cc39a20951ff..d64061d647ae 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -947,36 +947,42 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 	return true;
 }
 
-static void kick_tx(struct xsk_socket_info *xsk)
+static int kick_tx(struct xsk_socket_info *xsk)
 {
 	int ret;
 
 	ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
 	if (ret >= 0)
-		return;
+		return TEST_PASS;
 	if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) {
 		usleep(100);
-		return;
+		return TEST_PASS;
 	}
-	exit_with_error(errno);
+	return TEST_FAILURE;
 }
 
-static void kick_rx(struct xsk_socket_info *xsk)
+static int kick_rx(struct xsk_socket_info *xsk)
 {
 	int ret;
 
 	ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL);
 	if (ret < 0)
-		exit_with_error(errno);
+		return TEST_FAILURE;
+
+	return TEST_PASS;
 }
 
 static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 {
 	unsigned int rcvd;
 	u32 idx;
+	int ret;
 
-	if (xsk_ring_prod__needs_wakeup(&xsk->tx))
-		kick_tx(xsk);
+	if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
+		ret = kick_tx(xsk);
+		if (ret)
+			return TEST_FAILURE;
+	}
 
 	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
 	if (rcvd) {
@@ -1024,11 +1030,14 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 			return TEST_FAILURE;
 		}
 
-		kick_rx(xsk);
+		ret = kick_rx(xsk);
+		if (ret)
+			return TEST_FAILURE;
+
 		if (ifobj->use_poll) {
 			ret = poll(fds, 1, POLL_TMOUT);
 			if (ret < 0)
-				exit_with_error(errno);
+				return TEST_FAILURE;
 
 			if (!ret) {
 				if (!is_umem_valid(test->ifobj_tx))
@@ -1049,12 +1058,10 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 		if (ifobj->use_fill_ring) {
 			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 			while (ret != rcvd) {
-				if (ret < 0)
-					exit_with_error(-ret);
 				if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
 					ret = poll(fds, 1, POLL_TMOUT);
 					if (ret < 0)
-						exit_with_error(errno);
+						return TEST_FAILURE;
 				}
 				ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 			}
@@ -1138,7 +1145,9 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 	buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len);
 	/* pkts_in_flight might be negative if many invalid packets are sent */
 	if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) {
-		kick_tx(xsk);
+		ret = kick_tx(xsk);
+		if (ret)
+			return TEST_FAILURE;
 		return TEST_CONTINUE;
 	}
 
@@ -1321,7 +1330,9 @@ static int validate_rx_dropped(struct ifobject *ifobject)
 	struct xdp_statistics stats;
 	int err;
 
-	kick_rx(ifobject->xsk);
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
 
 	err = get_xsk_stats(xsk, &stats);
 	if (err)
@@ -1347,7 +1358,9 @@ static int validate_rx_full(struct ifobject *ifobject)
 	int err;
 
 	usleep(1000);
-	kick_rx(ifobject->xsk);
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
 
 	err = get_xsk_stats(xsk, &stats);
 	if (err)
@@ -1366,7 +1379,9 @@ static int validate_fill_empty(struct ifobject *ifobject)
 	int err;
 
 	usleep(1000);
-	kick_rx(ifobject->xsk);
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
 
 	err = get_xsk_stats(xsk, &stats);
 	if (err)
@@ -1775,7 +1790,7 @@ static int testapp_bidirectional(struct test_spec *test)
 	return res;
 }
 
-static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
+static int swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
 {
 	int ret;
 
@@ -1786,7 +1801,9 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj
 
 	ret = xsk_update_xskmap(ifobj_rx->xskmap, ifobj_rx->xsk->xsk);
 	if (ret)
-		exit_with_error(errno);
+		return TEST_FAILURE;
+
+	return TEST_PASS;
 }
 
 static int testapp_xdp_prog_cleanup(struct test_spec *test)
@@ -1796,7 +1813,8 @@ static int testapp_xdp_prog_cleanup(struct test_spec *test)
 	if (testapp_validate_traffic(test))
 		return TEST_FAILURE;
 
-	swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
+	if (swap_xsk_resources(test->ifobj_tx, test->ifobj_rx))
+		return TEST_FAILURE;
 	return testapp_validate_traffic(test);
 }
 
@@ -1997,11 +2015,15 @@ static int testapp_xdp_metadata_copy(struct test_spec *test)
 	test->ifobj_rx->use_metadata = true;
 
 	data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
-	if (!data_map || !bpf_map__is_internal(data_map))
-		exit_with_error(ENOMEM);
+	if (!data_map || !bpf_map__is_internal(data_map)) {
+		ksft_print_msg("Error: could not find bss section of XDP program\n");
+		return TEST_FAILURE;
+	}
 
-	if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY))
-		exit_with_error(errno);
+	if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) {
+		ksft_print_msg("Error: could not update count element\n");
+		return TEST_FAILURE;
+	}
 
 	return testapp_validate_traffic(test);
 }
-- 
cgit v1.2.3


From 4a5f0ba55f4621aed4b22d28e496793e438555e1 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 14 Sep 2023 10:48:57 +0200
Subject: selftests/xsk: display command line options with -h

Add the -h option to display all available command line options
available for test_xsk.sh and xskxceiver.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20230914084900.492-11-magnus.karlsson@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_xsk.sh  | 11 ++++++++++-
 tools/testing/selftests/bpf/xskxceiver.c |  5 ++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 296006ea6e9c..65aafe0003db 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -82,12 +82,15 @@
 #
 # Run a specific test from the test suite
 #   sudo ./test_xsk.sh -t TEST_NAME
+#
+# Display the available command line options
+#   ./test_xsk.sh -h
 
 . xsk_prereqs.sh
 
 ETH=""
 
-while getopts "vi:dm:lt:" flag
+while getopts "vi:dm:lt:h" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
@@ -96,6 +99,7 @@ do
 		m) MODE=${OPTARG};;
 		l) list=1;;
 		t) TEST=${OPTARG};;
+		h) help=1;;
 	esac
 done
 
@@ -148,6 +152,11 @@ if [[ $list -eq 1 ]]; then
         exit
 fi
 
+if [[ $help -eq 1 ]]; then
+	./${XSKOBJ}
+        exit
+fi
+
 if [ ! -z $ETH ]; then
 	VETH0=${ETH}
 	VETH1=${ETH}
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index d64061d647ae..43e0a5796929 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -318,6 +318,7 @@ static struct option long_options[] = {
 	{"mode", required_argument, 0, 'm'},
 	{"list", no_argument, 0, 'l'},
 	{"test", required_argument, 0, 't'},
+	{"help", no_argument, 0, 'h'},
 	{0, 0, 0, 0}
 };
 
@@ -331,7 +332,8 @@ static void print_usage(char **argv)
 		"  -b, --busy-poll      Enable busy poll\n"
 		"  -m, --mode           Run only mode skb, drv, or zc\n"
 		"  -l, --list           List all available tests\n"
-		"  -t, --test           Run a specific test. Enter number from -l option.\n";
+		"  -t, --test           Run a specific test. Enter number from -l option.\n"
+		"  -h, --help           Display this help and exit\n";
 
 	ksft_print_msg(str, basename(argv[0]));
 	ksft_exit_xfail();
@@ -402,6 +404,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			if (errno)
 				print_usage(argv);
 			break;
+		case 'h':
 		default:
 			print_usage(argv);
 		}
-- 
cgit v1.2.3


From 971f7c32147f2d0953a815a109b22b8ed45949d4 Mon Sep 17 00:00:00 2001
From: Artem Savkov <asavkov@redhat.com>
Date: Thu, 14 Sep 2023 14:49:28 +0200
Subject: selftests/bpf: Skip module_fentry_shadow test when bpf_testmod is not
 available

This test relies on bpf_testmod, so skip it if the module is not available.

Fixes: aa3d65de4b900 ("bpf/selftests: Test fentry attachment to shadowed functions")
Signed-off-by: Artem Savkov <asavkov@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230914124928.340701-1-asavkov@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
index c7636e18b1eb..aa9f67eb1c95 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
@@ -61,6 +61,11 @@ void test_module_fentry_shadow(void)
 	int link_fd[2] = {};
 	__s32 btf_id[2] = {};
 
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
 	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
 		.expected_attach_type = BPF_TRACE_FENTRY,
 	);
-- 
cgit v1.2.3


From a9c2a608549bb1a2363d289d63907640afcf22af Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 13 Sep 2023 10:13:49 -0700
Subject: bpf: expose information about supported xdp metadata kfunc

Add new xdp-rx-metadata-features member to netdev netlink
which exports a bitmask of supported kfuncs. Most of the patch
is autogenerated (headers), the only relevant part is netdev.yaml
and the changes in netdev-genl.c to marshal into netlink.

Example output on veth:

$ ip link add veth0 type veth peer name veth1 # ifndex == 12
$ ./tools/net/ynl/samples/netdev 12

Select ifc ($ifindex; or 0 = dump; or -2 ntf check): 12
   veth1[12]    xdp-features (23): basic redirect rx-sg xdp-rx-metadata-features (3): timestamp hash xdp-zc-max-segs=0

Cc: netdev@vger.kernel.org
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230913171350.369987-3-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      | 21 +++++++++++++++++++++
 Documentation/networking/xdp-rx-metadata.rst |  7 +++++++
 include/net/xdp.h                            |  5 ++++-
 include/uapi/linux/netdev.h                  | 16 ++++++++++++++++
 kernel/bpf/offload.c                         |  2 +-
 net/core/netdev-genl.c                       | 12 +++++++++++-
 net/core/xdp.c                               |  4 ++--
 tools/include/uapi/linux/netdev.h            | 16 ++++++++++++++++
 8 files changed, 78 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 1c7284fd535b..c46fcc78fc04 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -42,6 +42,19 @@ definitions:
         doc:
           This feature informs if netdev implements non-linear XDP buffer
           support in ndo_xdp_xmit callback.
+  -
+    type: flags
+    name: xdp-rx-metadata
+    render-max: true
+    entries:
+      -
+        name: timestamp
+        doc:
+          Device is capable of exposing receive HW timestamp via bpf_xdp_metadata_rx_timestamp().
+      -
+        name: hash
+        doc:
+          Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
 
 attribute-sets:
   -
@@ -68,6 +81,13 @@ attribute-sets:
         type: u32
         checks:
           min: 1
+      -
+        name: xdp-rx-metadata-features
+        doc: Bitmask of supported XDP receive metadata features.
+             See Documentation/networking/xdp-rx-metadata.rst for more details.
+        type: u64
+        enum: xdp-rx-metadata
+        enum-as-flags: true
 
 operations:
   list:
@@ -84,6 +104,7 @@ operations:
             - ifindex
             - xdp-features
             - xdp-zc-max-segs
+            - xdp-rx-metadata-features
       dump:
         reply: *dev-all
     -
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 25ce72af81c2..205696780b78 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -105,6 +105,13 @@ bpf_tail_call
 Adding programs that access metadata kfuncs to the ``BPF_MAP_TYPE_PROG_ARRAY``
 is currently not supported.
 
+Supported Devices
+=================
+
+It is possible to query which kfunc the particular netdev implements via
+netlink. See ``xdp-rx-metadata-features`` attribute set in
+``Documentation/netlink/specs/netdev.yaml``.
+
 Example
 =======
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d59e12f8f311..349c36fb5fd8 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -386,19 +386,22 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 /* Define the relationship between xdp-rx-metadata kfunc and
  * various other entities:
  * - xdp_rx_metadata enum
+ * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml)
  * - kfunc name
  * - xdp_metadata_ops field
  */
 #define XDP_METADATA_KFUNC_xxx	\
 	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \
+			   NETDEV_XDP_RX_METADATA_TIMESTAMP, \
 			   bpf_xdp_metadata_rx_timestamp, \
 			   xmo_rx_timestamp) \
 	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \
+			   NETDEV_XDP_RX_METADATA_HASH, \
 			   bpf_xdp_metadata_rx_hash, \
 			   xmo_rx_hash) \
 
 enum xdp_rx_metadata {
-#define XDP_METADATA_KFUNC(name, _, __) name,
+#define XDP_METADATA_KFUNC(name, _, __, ___) name,
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 MAX_XDP_METADATA_KFUNC,
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index c1634b95c223..2943a151d4f1 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -38,11 +38,27 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
+/**
+ * enum netdev_xdp_rx_metadata
+ * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
+ *   timestamp via bpf_xdp_metadata_rx_timestamp().
+ * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
+ *   hash via bpf_xdp_metadata_rx_hash().
+ */
+enum netdev_xdp_rx_metadata {
+	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
+	NETDEV_XDP_RX_METADATA_HASH = 2,
+
+	/* private: */
+	NETDEV_XDP_RX_METADATA_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 6aa6de8d715d..e7a1752b5a09 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -845,7 +845,7 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
 	if (!ops)
 		goto out;
 
-#define XDP_METADATA_KFUNC(name, _, xmo) \
+#define XDP_METADATA_KFUNC(name, _, __, xmo) \
 	if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo;
 	XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index c1aea8b756b6..fe61f85bcf33 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -5,6 +5,7 @@
 #include <linux/rtnetlink.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
+#include <net/xdp.h>
 
 #include "netdev-genl-gen.h"
 
@@ -12,15 +13,24 @@ static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		   const struct genl_info *info)
 {
+	u64 xdp_rx_meta = 0;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
 	if (!hdr)
 		return -EMSGSIZE;
 
+#define XDP_METADATA_KFUNC(_, flag, __, xmo) \
+	if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo) \
+		xdp_rx_meta |= flag;
+XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
-			      netdev->xdp_features, NETDEV_A_DEV_PAD)) {
+			      netdev->xdp_features, NETDEV_A_DEV_PAD) ||
+	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+			      xdp_rx_meta, NETDEV_A_DEV_PAD)) {
 		genlmsg_cancel(rsp, hdr);
 		return -EINVAL;
 	}
diff --git a/net/core/xdp.c b/net/core/xdp.c
index bab563b2f812..df4789ab512d 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -741,7 +741,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 __diag_pop();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
-#define XDP_METADATA_KFUNC(_, name, __) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
+#define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 BTF_SET8_END(xdp_metadata_kfunc_ids)
@@ -752,7 +752,7 @@ static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = {
 };
 
 BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted)
-#define XDP_METADATA_KFUNC(name, str, _) BTF_ID(func, str)
+#define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str)
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index c1634b95c223..2943a151d4f1 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -38,11 +38,27 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
+/**
+ * enum netdev_xdp_rx_metadata
+ * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
+ *   timestamp via bpf_xdp_metadata_rx_timestamp().
+ * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
+ *   hash via bpf_xdp_metadata_rx_hash().
+ */
+enum netdev_xdp_rx_metadata {
+	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
+	NETDEV_XDP_RX_METADATA_HASH = 2,
+
+	/* private: */
+	NETDEV_XDP_RX_METADATA_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
-- 
cgit v1.2.3


From 0c6c9b105ee90d7415dc796bcf632147b3d267ce Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 13 Sep 2023 10:13:50 -0700
Subject: tools: ynl: extend netdev sample to dump xdp-rx-metadata-features

The tool can be used to verify that everything works end to end.

Unrelated updates:
- include tools/include/uapi to pick the latest kernel uapi headers
- print "xdp-features" and "xdp-rx-metadata-features" so it's clear
  which bitmask is being dumped

Cc: netdev@vger.kernel.org
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230913171350.369987-4-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/net/ynl/generated/netdev-user.c | 19 +++++++++++++++++++
 tools/net/ynl/generated/netdev-user.h |  3 +++
 tools/net/ynl/samples/Makefile        |  2 +-
 tools/net/ynl/samples/netdev.c        |  8 +++++++-
 4 files changed, 30 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 68b408ca0f7f..b5ffe8cd1144 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -45,12 +45,26 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value)
 	return netdev_xdp_act_strmap[value];
 }
 
+static const char * const netdev_xdp_rx_metadata_strmap[] = {
+	[0] = "timestamp",
+	[1] = "hash",
+};
+
+const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
+{
+	value = ffs(value) - 1;
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_rx_metadata_strmap))
+		return NULL;
+	return netdev_xdp_rx_metadata_strmap[value];
+}
+
 /* Policies */
 struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
 	[NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
 	[NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, },
 	[NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, },
+	[NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, },
 };
 
 struct ynl_policy_nest netdev_dev_nest = {
@@ -97,6 +111,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.xdp_zc_max_segs = 1;
 			dst->xdp_zc_max_segs = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_DEV_XDP_RX_METADATA_FEATURES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.xdp_rx_metadata_features = 1;
+			dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr);
 		}
 	}
 
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 0952d3261f4d..b4351ff34595 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -18,6 +18,7 @@ extern const struct ynl_family ynl_netdev_family;
 /* Enums */
 const char *netdev_op_str(int op);
 const char *netdev_xdp_act_str(enum netdev_xdp_act value);
+const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
 
 /* Common nested types */
 /* ============== NETDEV_CMD_DEV_GET ============== */
@@ -48,11 +49,13 @@ struct netdev_dev_get_rsp {
 		__u32 ifindex:1;
 		__u32 xdp_features:1;
 		__u32 xdp_zc_max_segs:1;
+		__u32 xdp_rx_metadata_features:1;
 	} _present;
 
 	__u32 ifindex;
 	__u64 xdp_features;
 	__u32 xdp_zc_max_segs;
+	__u64 xdp_rx_metadata_features;
 };
 
 void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp);
diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile
index f2db8bb78309..32abbc0af39e 100644
--- a/tools/net/ynl/samples/Makefile
+++ b/tools/net/ynl/samples/Makefile
@@ -4,7 +4,7 @@ include ../Makefile.deps
 
 CC=gcc
 CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \
-	-I../lib/ -I../generated/ -idirafter $(UAPI_PATH)
+	-I../../../include/uapi -I../lib/ -I../generated/ -idirafter $(UAPI_PATH)
 ifeq ("$(DEBUG)","1")
   CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan
 endif
diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c
index 06433400dddd..b828225daad0 100644
--- a/tools/net/ynl/samples/netdev.c
+++ b/tools/net/ynl/samples/netdev.c
@@ -32,12 +32,18 @@ static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op)
 	if (!d->_present.xdp_features)
 		return;
 
-	printf("%llx:", d->xdp_features);
+	printf("xdp-features (%llx):", d->xdp_features);
 	for (int i = 0; d->xdp_features > 1U << i; i++) {
 		if (d->xdp_features & (1U << i))
 			printf(" %s", netdev_xdp_act_str(1 << i));
 	}
 
+	printf(" xdp-rx-metadata-features (%llx):", d->xdp_rx_metadata_features);
+	for (int i = 0; d->xdp_rx_metadata_features > 1U << i; i++) {
+		if (d->xdp_rx_metadata_features & (1U << i))
+			printf(" %s", netdev_xdp_rx_metadata_str(1 << i));
+	}
+
 	printf(" xdp-zc-max-segs=%u", d->xdp_zc_max_segs);
 
 	name = netdev_op_str(op);
-- 
cgit v1.2.3


From 59ff6d63b7307be4dbfbecceea9aedca047c7ffe Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Thu, 7 Sep 2023 23:05:48 +0000
Subject: selftest, bpf: enable cpu v4 tests for arm32

Now that all the cpuv4 instructions are supported by the arm32 JIT,
enable the selftests for arm32.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Link: https://lore.kernel.org/r/20230907230550.1417590-8-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/verifier_bswap.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_gotol.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_movsx.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_sdiv.c  | 3 ++-
 5 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 8893094725f0..5d54f8eae6a1 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("BSWAP, 16")
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index 2dae5322a18e..aa54ecd5829e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("gotol, small_imm")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 0c638f45aaf1..1e1bc379c44f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("LDSX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index 3c8ac2c57b1b..ca11fd5dafd1 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("MOV32SX, S8")
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index 0990f8825675..fb039722b639 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("SDIV32, non-zero imm divisor, check 1")
-- 
cgit v1.2.3


From f18b03fabaa9b7c80e80b72a621f481f0d706ae0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:01 +0200
Subject: bpf: Implement BPF exceptions

This patch implements BPF exceptions, and introduces a bpf_throw kfunc
to allow programs to throw exceptions during their execution at runtime.
A bpf_throw invocation is treated as an immediate termination of the
program, returning back to its caller within the kernel, unwinding all
stack frames.

This allows the program to simplify its implementation, by testing for
runtime conditions which the verifier has no visibility into, and assert
that they are true. In case they are not, the program can simply throw
an exception from the other branch.

BPF exceptions are explicitly *NOT* an unlikely slowpath error handling
primitive, and this objective has guided design choices of the
implementation of the them within the kernel (with the bulk of the cost
for unwinding the stack offloaded to the bpf_throw kfunc).

The implementation of this mechanism requires use of add_hidden_subprog
mechanism introduced in the previous patch, which generates a couple of
instructions to move R1 to R0 and exit. The JIT then rewrites the
prologue of this subprog to take the stack pointer and frame pointer as
inputs and reset the stack frame, popping all callee-saved registers
saved by the main subprog. The bpf_throw function then walks the stack
at runtime, and invokes this exception subprog with the stack and frame
pointers as parameters.

Reviewers must take note that currently the main program is made to save
all callee-saved registers on x86_64 during entry into the program. This
is because we must do an equivalent of a lightweight context switch when
unwinding the stack, therefore we need the callee-saved registers of the
caller of the BPF program to be able to return with a sane state.

Note that we have to additionally handle r12, even though it is not used
by the program, because when throwing the exception the program makes an
entry into the kernel which could clobber r12 after saving it on the
stack. To be able to preserve the value we received on program entry, we
push r12 and restore it from the generated subprogram when unwinding the
stack.

For now, bpf_throw invocation fails when lingering resources or locks
exist in that path of the program. In a future followup, bpf_throw will
be extended to perform frame-by-frame unwinding to release lingering
resources for each stack frame, removing this limitation.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c                    |  89 ++++++++++++++++---
 include/linux/bpf.h                            |   3 +
 include/linux/bpf_verifier.h                   |   4 +
 include/linux/filter.h                         |   6 ++
 kernel/bpf/core.c                              |   2 +-
 kernel/bpf/helpers.c                           |  38 ++++++++
 kernel/bpf/verifier.c                          | 116 ++++++++++++++++++++++---
 tools/testing/selftests/bpf/bpf_experimental.h |  16 ++++
 8 files changed, 247 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d0c24b5a6abb..84005f2114e0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -18,6 +18,8 @@
 #include <asm/text-patching.h>
 #include <asm/unwind.h>
 
+static bool all_callee_regs_used[4] = {true, true, true, true};
+
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
 	if (len == 1)
@@ -256,6 +258,14 @@ struct jit_context {
 /* Number of bytes that will be skipped on tailcall */
 #define X86_TAIL_CALL_OFFSET	(11 + ENDBR_INSN_SIZE)
 
+static void push_r12(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x54);   /* push r12 */
+	*pprog = prog;
+}
+
 static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
 	u8 *prog = *pprog;
@@ -271,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+static void pop_r12(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x5C);   /* pop r12 */
+	*pprog = prog;
+}
+
 static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
 	u8 *prog = *pprog;
@@ -292,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
  * while jumping to another program
  */
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
-			  bool tail_call_reachable, bool is_subprog)
+			  bool tail_call_reachable, bool is_subprog,
+			  bool is_exception_cb)
 {
 	u8 *prog = *pprog;
 
@@ -312,8 +331,22 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 			/* Keep the same instruction layout. */
 			EMIT2(0x66, 0x90); /* nop2 */
 	}
-	EMIT1(0x55);             /* push rbp */
-	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	/* Exception callback receives FP as third parameter */
+	if (is_exception_cb) {
+		EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */
+		EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */
+		/* The main frame must have exception_boundary as true, so we
+		 * first restore those callee-saved regs from stack, before
+		 * reusing the stack frame.
+		 */
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+		/* Reset the stack frame. */
+		EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */
+	} else {
+		EMIT1(0x55);             /* push rbp */
+		EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	}
 
 	/* X86_TAIL_CALL_OFFSET is here */
 	EMIT_ENDBR();
@@ -472,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip)
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+					u8 **pprog, bool *callee_regs_used,
 					u32 stack_depth, u8 *ip,
 					struct jit_context *ctx)
 {
@@ -522,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
 	EMIT2(X86_JE, offset);                    /* je out */
 
-	pop_callee_regs(&prog, callee_regs_used);
+	if (bpf_prog->aux->exception_boundary) {
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+	} else {
+		pop_callee_regs(&prog, callee_regs_used);
+	}
 
 	EMIT1(0x58);                              /* pop rax */
 	if (stack_depth)
@@ -546,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	*pprog = prog;
 }
 
-static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
+static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+				      struct bpf_jit_poke_descriptor *poke,
 				      u8 **pprog, u8 *ip,
 				      bool *callee_regs_used, u32 stack_depth,
 				      struct jit_context *ctx)
@@ -575,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
 		  poke->tailcall_bypass);
 
-	pop_callee_regs(&prog, callee_regs_used);
+	if (bpf_prog->aux->exception_boundary) {
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+	} else {
+		pop_callee_regs(&prog, callee_regs_used);
+	}
+
 	EMIT1(0x58);                                  /* pop rax */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
@@ -1050,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
-		      bpf_is_subprog(bpf_prog));
-	push_callee_regs(&prog, callee_regs_used);
+		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
+	/* Exception callback will clobber callee regs for its own use, and
+	 * restore the original callee regs from main prog's stack frame.
+	 */
+	if (bpf_prog->aux->exception_boundary) {
+		/* We also need to save r12, which is not mapped to any BPF
+		 * register, as we throw after entry into the kernel, which may
+		 * overwrite r12.
+		 */
+		push_r12(&prog);
+		push_callee_regs(&prog, all_callee_regs_used);
+	} else {
+		push_callee_regs(&prog, callee_regs_used);
+	}
 
 	ilen = prog - temp;
 	if (rw_image)
@@ -1648,13 +1706,15 @@ st:			if (is_imm8(insn->off))
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
-				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
+				emit_bpf_tail_call_direct(bpf_prog,
+							  &bpf_prog->aux->poke_tab[imm32 - 1],
 							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
 							  bpf_prog->aux->stack_depth,
 							  ctx);
 			else
-				emit_bpf_tail_call_indirect(&prog,
+				emit_bpf_tail_call_indirect(bpf_prog,
+							    &prog,
 							    callee_regs_used,
 							    bpf_prog->aux->stack_depth,
 							    image + addrs[i - 1],
@@ -1907,7 +1967,12 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			pop_callee_regs(&prog, callee_regs_used);
+			if (bpf_prog->aux->exception_boundary) {
+				pop_callee_regs(&prog, all_callee_regs_used);
+				pop_r12(&prog);
+			} else {
+				pop_callee_regs(&prog, callee_regs_used);
+			}
 			EMIT1(0xC9);         /* leave */
 			emit_return(&prog, image + addrs[i - 1] + (prog - temp));
 			break;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c3667e95af59..16740ee82082 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1410,6 +1410,8 @@ struct bpf_prog_aux {
 	bool sleepable;
 	bool tail_call_reachable;
 	bool xdp_has_frags;
+	bool exception_cb;
+	bool exception_boundary;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -1432,6 +1434,7 @@ struct bpf_prog_aux {
 	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
+	unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp);
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3c2a8636ab29..da21a3ec5027 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -541,7 +541,9 @@ struct bpf_subprog_info {
 	bool has_tail_call;
 	bool tail_call_reachable;
 	bool has_ld_abs;
+	bool is_cb;
 	bool is_async_cb;
+	bool is_exception_cb;
 };
 
 struct bpf_verifier_env;
@@ -589,6 +591,7 @@ struct bpf_verifier_env {
 	u32 used_btf_cnt;		/* number of used BTF objects */
 	u32 id_gen;			/* used to generate unique reg IDs */
 	u32 hidden_subprog_cnt;		/* number of hidden subprogs */
+	int exception_callback_subprog;
 	bool explore_alu_limits;
 	bool allow_ptr_leaks;
 	bool allow_uninit_stack;
@@ -596,6 +599,7 @@ struct bpf_verifier_env {
 	bool bypass_spec_v1;
 	bool bypass_spec_v4;
 	bool seen_direct_write;
+	bool seen_exception;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 88874de974cb..27406aee2d40 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1171,6 +1171,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
 bool is_bpf_text_address(unsigned long addr);
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym);
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr);
 
 static inline const char *
 bpf_address_lookup(unsigned long addr, unsigned long *size,
@@ -1238,6 +1239,11 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value,
 	return -ERANGE;
 }
 
+static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+{
+	return NULL;
+}
+
 static inline const char *
 bpf_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 840ba952702d..7849b9cca749 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -733,7 +733,7 @@ bool is_bpf_text_address(unsigned long addr)
 	return ret;
 }
 
-static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
 {
 	struct bpf_ksym *ksym = bpf_ksym_find(addr);
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b0a9834f1051..78e8f4de6750 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2449,6 +2449,43 @@ __bpf_kfunc void bpf_rcu_read_unlock(void)
 	rcu_read_unlock();
 }
 
+struct bpf_throw_ctx {
+	struct bpf_prog_aux *aux;
+	u64 sp;
+	u64 bp;
+	int cnt;
+};
+
+static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+	struct bpf_throw_ctx *ctx = cookie;
+	struct bpf_prog *prog;
+
+	if (!is_bpf_text_address(ip))
+		return !ctx->cnt;
+	prog = bpf_prog_ksym_find(ip);
+	ctx->cnt++;
+	if (bpf_is_subprog(prog))
+		return true;
+	ctx->aux = prog->aux;
+	ctx->sp = sp;
+	ctx->bp = bp;
+	return false;
+}
+
+__bpf_kfunc void bpf_throw(u64 cookie)
+{
+	struct bpf_throw_ctx ctx = {};
+
+	arch_bpf_stack_walk(bpf_stack_walker, &ctx);
+	WARN_ON_ONCE(!ctx.aux);
+	if (ctx.aux)
+		WARN_ON_ONCE(!ctx.aux->exception_boundary);
+	WARN_ON_ONCE(!ctx.bp);
+	WARN_ON_ONCE(!ctx.cnt);
+	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+}
+
 __diag_pop();
 
 BTF_SET8_START(generic_btf_ids)
@@ -2478,6 +2515,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
 #endif
 BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_throw)
 BTF_SET8_END(generic_btf_ids)
 
 static const struct btf_kfunc_id_set generic_kfunc_set = {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 39548e326d53..9baa6f187b38 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -543,6 +543,7 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 }
 
 static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
 
 static bool is_callback_calling_function(enum bpf_func_id func_id)
 {
@@ -1748,7 +1749,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 		return -ENOMEM;
 	dst_state->jmp_history_cnt = src->jmp_history_cnt;
 
-	/* if dst has more stack frames then src frame, free them */
+	/* if dst has more stack frames then src frame, free them, this is also
+	 * necessary in case of exceptional exits using bpf_throw.
+	 */
 	for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
 		free_func_state(dst_state->frame[i]);
 		dst_state->frame[i] = NULL;
@@ -2868,7 +2871,7 @@ next:
 		if (i == subprog_end - 1) {
 			/* to avoid fall-through from one subprog into another
 			 * the last insn of the subprog should be either exit
-			 * or unconditional jump back
+			 * or unconditional jump back or bpf_throw call
 			 */
 			if (code != (BPF_JMP | BPF_EXIT) &&
 			    code != (BPF_JMP32 | BPF_JA) &&
@@ -5661,6 +5664,27 @@ continue_func:
 	for (; i < subprog_end; i++) {
 		int next_insn, sidx;
 
+		if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) {
+			bool err = false;
+
+			if (!is_bpf_throw_kfunc(insn + i))
+				continue;
+			if (subprog[idx].is_cb)
+				err = true;
+			for (int c = 0; c < frame && !err; c++) {
+				if (subprog[ret_prog[c]].is_cb) {
+					err = true;
+					break;
+				}
+			}
+			if (!err)
+				continue;
+			verbose(env,
+				"bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n",
+				i, idx);
+			return -EINVAL;
+		}
+
 		if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
 			continue;
 		/* remember insn and function to return to */
@@ -8919,6 +8943,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	 * callbacks
 	 */
 	if (set_callee_state_cb != set_callee_state) {
+		env->subprog_info[subprog].is_cb = true;
 		if (bpf_pseudo_kfunc_call(insn) &&
 		    !is_callback_calling_kfunc(insn->imm)) {
 			verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
@@ -9308,7 +9333,8 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		verbose(env, "to caller at %d:\n", *insn_idx);
 		print_verifier_state(env, caller, true);
 	}
-	/* clear everything in the callee */
+	/* clear everything in the callee. In case of exceptional exits using
+	 * bpf_throw, this will be done by copy_verifier_state for extra frames. */
 	free_func_state(callee);
 	state->frame[state->curframe--] = NULL;
 	return 0;
@@ -9432,17 +9458,17 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	return 0;
 }
 
-static int check_reference_leak(struct bpf_verifier_env *env)
+static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit)
 {
 	struct bpf_func_state *state = cur_func(env);
 	bool refs_lingering = false;
 	int i;
 
-	if (state->frameno && !state->in_callback_fn)
+	if (!exception_exit && state->frameno && !state->in_callback_fn)
 		return 0;
 
 	for (i = 0; i < state->acquired_refs; i++) {
-		if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+		if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
 			continue;
 		verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
 			state->refs[i].id, state->refs[i].insn_idx);
@@ -9697,7 +9723,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	switch (func_id) {
 	case BPF_FUNC_tail_call:
-		err = check_reference_leak(env);
+		err = check_reference_leak(env, false);
 		if (err) {
 			verbose(env, "tail_call would lead to reference leak\n");
 			return err;
@@ -10332,6 +10358,7 @@ enum special_kfunc_type {
 	KF_bpf_dynptr_clone,
 	KF_bpf_percpu_obj_new_impl,
 	KF_bpf_percpu_obj_drop_impl,
+	KF_bpf_throw,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -10354,6 +10381,7 @@ BTF_ID(func, bpf_dynptr_slice_rdwr)
 BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10378,6 +10406,7 @@ BTF_ID(func, bpf_dynptr_slice_rdwr)
 BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -10695,6 +10724,12 @@ static bool is_callback_calling_kfunc(u32 btf_id)
 	return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
 }
 
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn)
+{
+	return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+	       insn->imm == special_kfunc_list[KF_bpf_throw];
+}
+
 static bool is_rbtree_lock_required_kfunc(u32 btf_id)
 {
 	return is_bpf_rbtree_api_kfunc(btf_id);
@@ -11480,6 +11515,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
+	if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
+		if (!bpf_jit_supports_exceptions()) {
+			verbose(env, "JIT does not support calling kfunc %s#%d\n",
+				func_name, meta.func_id);
+			return -ENOTSUPP;
+		}
+		env->seen_exception = true;
+	}
+
 	for (i = 0; i < CALLER_SAVED_REGS; i++)
 		mark_reg_not_init(env, regs, caller_saved[i]);
 
@@ -14525,7 +14569,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	 * gen_ld_abs() may terminate the program at runtime, leading to
 	 * reference leak.
 	 */
-	err = check_reference_leak(env);
+	err = check_reference_leak(env, false);
 	if (err) {
 		verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
 		return err;
@@ -16539,6 +16583,7 @@ static int do_check(struct bpf_verifier_env *env)
 	int prev_insn_idx = -1;
 
 	for (;;) {
+		bool exception_exit = false;
 		struct bpf_insn *insn;
 		u8 class;
 		int err;
@@ -16753,12 +16798,17 @@ static int do_check(struct bpf_verifier_env *env)
 						return -EINVAL;
 					}
 				}
-				if (insn->src_reg == BPF_PSEUDO_CALL)
+				if (insn->src_reg == BPF_PSEUDO_CALL) {
 					err = check_func_call(env, insn, &env->insn_idx);
-				else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+				} else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 					err = check_kfunc_call(env, insn, &env->insn_idx);
-				else
+					if (!err && is_bpf_throw_kfunc(insn)) {
+						exception_exit = true;
+						goto process_bpf_exit_full;
+					}
+				} else {
 					err = check_helper_call(env, insn, &env->insn_idx);
+				}
 				if (err)
 					return err;
 
@@ -16788,7 +16838,7 @@ static int do_check(struct bpf_verifier_env *env)
 					verbose(env, "BPF_EXIT uses reserved fields\n");
 					return -EINVAL;
 				}
-
+process_bpf_exit_full:
 				if (env->cur_state->active_lock.ptr &&
 				    !in_rbtree_lock_required_cb(env)) {
 					verbose(env, "bpf_spin_unlock is missing\n");
@@ -16807,10 +16857,23 @@ static int do_check(struct bpf_verifier_env *env)
 				 * function, for which reference_state must
 				 * match caller reference state when it exits.
 				 */
-				err = check_reference_leak(env);
+				err = check_reference_leak(env, exception_exit);
 				if (err)
 					return err;
 
+				/* The side effect of the prepare_func_exit
+				 * which is being skipped is that it frees
+				 * bpf_func_state. Typically, process_bpf_exit
+				 * will only be hit with outermost exit.
+				 * copy_verifier_state in pop_stack will handle
+				 * freeing of any extra bpf_func_state left over
+				 * from not processing all nested function
+				 * exits. We also skip return code checks as
+				 * they are not needed for exceptional exits.
+				 */
+				if (exception_exit)
+					goto process_bpf_exit;
+
 				if (state->curframe) {
 					/* exit from nested function */
 					err = prepare_func_exit(env, &env->insn_idx);
@@ -18113,6 +18176,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		func[i]->aux->num_exentries = num_exentries;
 		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
+		func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb;
+		if (!i)
+			func[i]->aux->exception_boundary = env->seen_exception;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -18201,6 +18267,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	prog->aux->func = func;
 	prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
 	prog->aux->real_func_cnt = env->subprog_cnt;
+	prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func;
+	prog->aux->exception_boundary = func[0]->aux->exception_boundary;
 	bpf_prog_jit_attempt_done(prog);
 	return 0;
 out_free:
@@ -18437,7 +18505,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 }
 
 /* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */
-static __maybe_unused int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
+static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
 {
 	struct bpf_subprog_info *info = env->subprog_info;
 	int cnt = env->subprog_cnt;
@@ -18481,6 +18549,26 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 	struct bpf_map *map_ptr;
 	int i, ret, cnt, delta = 0;
 
+	if (env->seen_exception && !env->exception_callback_subprog) {
+		struct bpf_insn patch[] = {
+			env->prog->insnsi[insn_cnt - 1],
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		};
+
+		ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch));
+		if (ret < 0)
+			return ret;
+		prog = env->prog;
+		insn = prog->insnsi;
+
+		env->exception_callback_subprog = env->subprog_cnt - 1;
+		/* Don't update insn_cnt, as add_hidden_subprog always appends insns */
+		env->subprog_info[env->exception_callback_subprog].is_cb = true;
+		env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
+		env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+	}
+
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		/* Make divide-by-zero exceptions impossible. */
 		if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 4494eaa9937e..333b54a86e3a 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -162,4 +162,20 @@ extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
 /* Convenience macro to wrap over bpf_obj_drop_impl */
 #define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL)
 
+/* Description
+ *	Throw a BPF exception from the program, immediately terminating its
+ *	execution and unwinding the stack. The supplied 'cookie' parameter
+ *	will be the return value of the program when an exception is thrown.
+ *
+ *	Note that throwing an exception with lingering resources (locks,
+ *	references, etc.) will lead to a verification error.
+ *
+ *	Note that callbacks *cannot* call this helper.
+ * Returns
+ *	Never.
+ * Throws
+ *	An exception with the specified 'cookie' value.
+ */
+extern void bpf_throw(u64 cookie) __ksym;
+
 #endif
-- 
cgit v1.2.3


From b9ae0c9dd0aca79bffc17be51c2dc148d1f72708 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:03 +0200
Subject: bpf: Add support for custom exception callbacks

By default, the subprog generated by the verifier to handle a thrown
exception hardcodes a return value of 0. To allow user-defined logic
and modification of the return value when an exception is thrown,
introduce the 'exception_callback:' declaration tag, which marks a
callback as the default exception handler for the program.

The format of the declaration tag is 'exception_callback:<value>', where
<value> is the name of the exception callback. Each main program can be
tagged using this BTF declaratiion tag to associate it with an exception
callback. In case the tag is absent, the default callback is used.

As such, the exception callback cannot be modified at runtime, only set
during verification.

Allowing modification of the callback for the current program execution
at runtime leads to issues when the programs begin to nest, as any
per-CPU state maintaing this information will have to be saved and
restored. We don't want it to stay in bpf_prog_aux as this takes a
global effect for all programs. An alternative solution is spilling
the callback pointer at a known location on the program stack on entry,
and then passing this location to bpf_throw as a parameter.

However, since exceptions are geared more towards a use case where they
are ideally never invoked, optimizing for this use case and adding to
the complexity has diminishing returns.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                            |   4 +-
 include/linux/bpf_verifier.h                   |   1 +
 kernel/bpf/btf.c                               |  29 +++++--
 kernel/bpf/verifier.c                          | 113 +++++++++++++++++++++++--
 tools/testing/selftests/bpf/bpf_experimental.h |  31 ++++++-
 5 files changed, 160 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 16740ee82082..30063a760b5a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2422,9 +2422,11 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg);
+			  struct bpf_reg_state *reg, bool is_ex_cb);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+				    int comp_idx, const char *tag_key);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
 struct bpf_link *bpf_link_by_id(u32 id);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index da21a3ec5027..94ec766432f5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -300,6 +300,7 @@ struct bpf_func_state {
 	bool in_callback_fn;
 	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
+	bool in_exception_callback_fn;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 187b57276fec..f93e835d90af 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3310,10 +3310,10 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 	return BTF_FIELD_FOUND;
 }
 
-static const char *btf_find_decl_tag_value(const struct btf *btf,
-					   const struct btf_type *pt,
-					   int comp_idx, const char *tag_key)
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+				    int comp_idx, const char *tag_key)
 {
+	const char *value = NULL;
 	int i;
 
 	for (i = 1; i < btf_nr_types(btf); i++) {
@@ -3327,9 +3327,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf,
 			continue;
 		if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len))
 			continue;
-		return __btf_name_by_offset(btf, t->name_off) + len;
+		/* Prevent duplicate entries for same type */
+		if (value)
+			return ERR_PTR(-EEXIST);
+		value = __btf_name_by_offset(btf, t->name_off) + len;
 	}
-	return NULL;
+	if (!value)
+		return ERR_PTR(-ENOENT);
+	return value;
 }
 
 static int
@@ -3347,7 +3352,7 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
 	if (t->size != sz)
 		return BTF_FIELD_IGNORE;
 	value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:");
-	if (!value_type)
+	if (IS_ERR(value_type))
 		return -EINVAL;
 	node_field_name = strstr(value_type, ":");
 	if (!node_field_name)
@@ -6954,7 +6959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
  * (either PTR_TO_CTX or SCALAR_VALUE).
  */
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *regs)
+			  struct bpf_reg_state *regs, bool is_ex_cb)
 {
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
@@ -7011,7 +7016,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			tname, nargs, MAX_BPF_FUNC_REG_ARGS);
 		return -EINVAL;
 	}
-	/* check that function returns int */
+	/* check that function returns int, exception cb also requires this */
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
@@ -7060,6 +7065,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			i, btf_type_str(t), tname);
 		return -EINVAL;
 	}
+	/* We have already ensured that the callback returns an integer, just
+	 * like all global subprogs. We need to determine it only has a single
+	 * scalar argument.
+	 */
+	if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
+		bpf_log(log, "exception cb only supports single integer argument\n");
+		return -EINVAL;
+	}
 	return 0;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ec767ae08c2b..ec3f22312516 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2457,6 +2457,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
 	return env->subprog_cnt - 1;
 }
 
+static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env)
+{
+	struct bpf_prog_aux *aux = env->prog->aux;
+	struct btf *btf = aux->btf;
+	const struct btf_type *t;
+	u32 main_btf_id, id;
+	const char *name;
+	int ret, i;
+
+	/* Non-zero func_info_cnt implies valid btf */
+	if (!aux->func_info_cnt)
+		return 0;
+	main_btf_id = aux->func_info[0].type_id;
+
+	t = btf_type_by_id(btf, main_btf_id);
+	if (!t) {
+		verbose(env, "invalid btf id for main subprog in func_info\n");
+		return -EINVAL;
+	}
+
+	name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:");
+	if (IS_ERR(name)) {
+		ret = PTR_ERR(name);
+		/* If there is no tag present, there is no exception callback */
+		if (ret == -ENOENT)
+			ret = 0;
+		else if (ret == -EEXIST)
+			verbose(env, "multiple exception callback tags for main subprog\n");
+		return ret;
+	}
+
+	ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC);
+	if (ret < 0) {
+		verbose(env, "exception callback '%s' could not be found in BTF\n", name);
+		return ret;
+	}
+	id = ret;
+	t = btf_type_by_id(btf, id);
+	if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+		verbose(env, "exception callback '%s' must have global linkage\n", name);
+		return -EINVAL;
+	}
+	ret = 0;
+	for (i = 0; i < aux->func_info_cnt; i++) {
+		if (aux->func_info[i].type_id != id)
+			continue;
+		ret = aux->func_info[i].insn_off;
+		/* Further func_info and subprog checks will also happen
+		 * later, so assume this is the right insn_off for now.
+		 */
+		if (!ret) {
+			verbose(env, "invalid exception callback insn_off in func_info: 0\n");
+			ret = -EINVAL;
+		}
+	}
+	if (!ret) {
+		verbose(env, "exception callback type id not found in func_info\n");
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
 #define MAX_KFUNC_DESCS 256
 #define MAX_KFUNC_BTFS	256
 
@@ -2796,8 +2858,8 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
 static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 {
 	struct bpf_subprog_info *subprog = env->subprog_info;
+	int i, ret, insn_cnt = env->prog->len, ex_cb_insn;
 	struct bpf_insn *insn = env->prog->insnsi;
-	int i, ret, insn_cnt = env->prog->len;
 
 	/* Add entry function. */
 	ret = add_subprog(env, 0);
@@ -2823,6 +2885,26 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			return ret;
 	}
 
+	ret = bpf_find_exception_callback_insn_off(env);
+	if (ret < 0)
+		return ret;
+	ex_cb_insn = ret;
+
+	/* If ex_cb_insn > 0, this means that the main program has a subprog
+	 * marked using BTF decl tag to serve as the exception callback.
+	 */
+	if (ex_cb_insn) {
+		ret = add_subprog(env, ex_cb_insn);
+		if (ret < 0)
+			return ret;
+		for (i = 1; i < env->subprog_cnt; i++) {
+			if (env->subprog_info[i].start != ex_cb_insn)
+				continue;
+			env->exception_callback_subprog = i;
+			break;
+		}
+	}
+
 	/* Add a fake 'exit' subprog which could simplify subprog iteration
 	 * logic. 'subprog_cnt' should not be increased.
 	 */
@@ -5707,6 +5789,10 @@ continue_func:
 			/* async callbacks don't increase bpf prog stack size unless called directly */
 			if (!bpf_pseudo_call(insn + i))
 				continue;
+			if (subprog[sidx].is_exception_cb) {
+				verbose(env, "insn %d cannot call exception cb directly\n", i);
+				return -EINVAL;
+			}
 		}
 		i = next_insn;
 		idx = sidx;
@@ -5728,8 +5814,13 @@ continue_func:
 	 * tail call counter throughout bpf2bpf calls combined with tailcalls
 	 */
 	if (tail_call_reachable)
-		for (j = 0; j < frame; j++)
+		for (j = 0; j < frame; j++) {
+			if (subprog[ret_prog[j]].is_exception_cb) {
+				verbose(env, "cannot tail call within exception cb\n");
+				return -EINVAL;
+			}
 			subprog[ret_prog[j]].tail_call_reachable = true;
+		}
 	if (subprog[0].tail_call_reachable)
 		env->prog->aux->tail_call_reachable = true;
 
@@ -14630,7 +14721,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	const bool is_subprog = frame->subprogno;
 
 	/* LSM and struct_ops func-ptr's return type could be "void" */
-	if (!is_subprog) {
+	if (!is_subprog || frame->in_exception_callback_fn) {
 		switch (prog_type) {
 		case BPF_PROG_TYPE_LSM:
 			if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -14678,7 +14769,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 		return 0;
 	}
 
-	if (is_subprog) {
+	if (is_subprog && !frame->in_exception_callback_fn) {
 		if (reg->type != SCALAR_VALUE) {
 			verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
 				reg_type_str(env, reg->type));
@@ -19334,7 +19425,7 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_verifier_state *state;
@@ -19365,7 +19456,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		ret = btf_prepare_func_args(env, subprog, regs);
+		ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
 		if (ret)
 			goto out;
 		for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
@@ -19381,6 +19472,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 				regs[i].id = ++env->id_gen;
 			}
 		}
+		if (is_ex_cb) {
+			state->frame[0]->in_exception_callback_fn = true;
+			env->subprog_info[subprog].is_cb = true;
+			env->subprog_info[subprog].is_async_cb = true;
+			env->subprog_info[subprog].is_exception_cb = true;
+		}
 	} else {
 		/* 1st arg to a function */
 		regs[BPF_REG_1].type = PTR_TO_CTX;
@@ -19445,7 +19542,7 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 			continue;
 		env->insn_idx = env->subprog_info[i].start;
 		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i);
+		ret = do_check_common(env, i, env->exception_callback_subprog == i);
 		if (ret) {
 			return ret;
 		} else if (env->log.level & BPF_LOG_LEVEL) {
@@ -19462,7 +19559,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0);
+	ret = do_check_common(env, 0, false);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 333b54a86e3a..9a87170524ce 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -165,7 +165,16 @@ extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
 /* Description
  *	Throw a BPF exception from the program, immediately terminating its
  *	execution and unwinding the stack. The supplied 'cookie' parameter
- *	will be the return value of the program when an exception is thrown.
+ *	will be the return value of the program when an exception is thrown,
+ *	and the default exception callback is used. Otherwise, if an exception
+ *	callback is set using the '__exception_cb(callback)' declaration tag
+ *	on the main program, the 'cookie' parameter will be the callback's only
+ *	input argument.
+ *
+ *	Thus, in case of default exception callback, 'cookie' is subjected to
+ *	constraints on the program's return value (as with R0 on exit).
+ *	Otherwise, the return value of the marked exception callback will be
+ *	subjected to the same checks.
  *
  *	Note that throwing an exception with lingering resources (locks,
  *	references, etc.) will lead to a verification error.
@@ -178,4 +187,24 @@ extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
  */
 extern void bpf_throw(u64 cookie) __ksym;
 
+/* This macro must be used to mark the exception callback corresponding to the
+ * main program. For example:
+ *
+ * int exception_cb(u64 cookie) {
+ *	return cookie;
+ * }
+ *
+ * SEC("tc")
+ * __exception_cb(exception_cb)
+ * int main_prog(struct __sk_buff *ctx) {
+ *	...
+ *	return TC_ACT_OK;
+ * }
+ *
+ * Here, exception callback for the main program will be 'exception_cb'. Note
+ * that this attribute can only be used once, and multiple exception callbacks
+ * specified for the main program will lead to verification error.
+ */
+#define __exception_cb(name) __attribute__((btf_decl_tag("exception_callback:" #name)))
+
 #endif
-- 
cgit v1.2.3


From 6c918709bd30852258e66b3f566c9614e3f29e35 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:11 +0200
Subject: libbpf: Refactor bpf_object__reloc_code

Refactor bpf_object__append_subprog_code out of bpf_object__reloc_code
to be able to reuse it to append subprog related code for the exception
callback to the main program.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-15-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 52 ++++++++++++++++++++++++++++++++------------------
 1 file changed, 33 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 96ff1aa4bf6a..afc07a8f7dc7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6234,6 +6234,38 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 	return 0;
 }
 
+static int
+bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog,
+				struct bpf_program *subprog)
+{
+       struct bpf_insn *insns;
+       size_t new_cnt;
+       int err;
+
+       subprog->sub_insn_off = main_prog->insns_cnt;
+
+       new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
+       insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
+       if (!insns) {
+               pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
+               return -ENOMEM;
+       }
+       main_prog->insns = insns;
+       main_prog->insns_cnt = new_cnt;
+
+       memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
+              subprog->insns_cnt * sizeof(*insns));
+
+       pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
+                main_prog->name, subprog->insns_cnt, subprog->name);
+
+       /* The subprog insns are now appended. Append its relos too. */
+       err = append_subprog_relos(main_prog, subprog);
+       if (err)
+               return err;
+       return 0;
+}
+
 static int
 bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		       struct bpf_program *prog)
@@ -6316,25 +6348,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		 *   and relocate.
 		 */
 		if (subprog->sub_insn_off == 0) {
-			subprog->sub_insn_off = main_prog->insns_cnt;
-
-			new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
-			insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
-			if (!insns) {
-				pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
-				return -ENOMEM;
-			}
-			main_prog->insns = insns;
-			main_prog->insns_cnt = new_cnt;
-
-			memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
-			       subprog->insns_cnt * sizeof(*insns));
-
-			pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
-				 main_prog->name, subprog->insns_cnt, subprog->name);
-
-			/* The subprog insns are now appended. Append its relos too. */
-			err = append_subprog_relos(main_prog, subprog);
+			err = bpf_object__append_subprog_code(obj, main_prog, subprog);
 			if (err)
 				return err;
 			err = bpf_object__reloc_code(obj, main_prog, subprog);
-- 
cgit v1.2.3


From 7e2925f6723702bcfcfdf8f73d5e85f7514d4b9f Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:12 +0200
Subject: libbpf: Add support for custom exception callbacks

Add support to libbpf to append exception callbacks when loading a
program. The exception callback is found by discovering the declaration
tag 'exception_callback:<value>' and finding the callback in the value
of the tag.

The process is done in two steps. First, for each main program, the
bpf_object__sanitize_and_load_btf function finds and marks its
corresponding exception callback as defined by the declaration tag on
it. Second, bpf_object__reloc_code is modified to append the indicated
exception callback at the end of the instruction iteration (since
exception callback will never be appended in that loop, as it is not
directly referenced).

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-16-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 109 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index afc07a8f7dc7..3a6108e3238b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -436,9 +436,11 @@ struct bpf_program {
 	int fd;
 	bool autoload;
 	bool autoattach;
+	bool sym_global;
 	bool mark_btf_static;
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
+	int exception_cb_idx;
 
 	int prog_ifindex;
 	__u32 attach_btf_obj_fd;
@@ -765,6 +767,7 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
 
 	prog->type = BPF_PROG_TYPE_UNSPEC;
 	prog->fd = -1;
+	prog->exception_cb_idx = -1;
 
 	/* libbpf's convention for SEC("?abc...") is that it's just like
 	 * SEC("abc...") but the corresponding bpf_program starts out with
@@ -871,14 +874,16 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		if (err)
 			return err;
 
+		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL)
+			prog->sym_global = true;
+
 		/* if function is a global/weak symbol, but has restricted
 		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC
 		 * as static to enable more permissive BPF verification mode
 		 * with more outside context available to BPF verifier
 		 */
-		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL
-		    && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
-			|| ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
+		if (prog->sym_global && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+		    || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -3142,6 +3147,86 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		}
 	}
 
+	if (!kernel_supports(obj, FEAT_BTF_DECL_TAG))
+		goto skip_exception_cb;
+	for (i = 0; i < obj->nr_programs; i++) {
+		struct bpf_program *prog = &obj->programs[i];
+		int j, k, n;
+
+		if (prog_is_subprog(obj, prog))
+			continue;
+		n = btf__type_cnt(obj->btf);
+		for (j = 1; j < n; j++) {
+			const char *str = "exception_callback:", *name;
+			size_t len = strlen(str);
+			struct btf_type *t;
+
+			t = btf_type_by_id(obj->btf, j);
+			if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
+				continue;
+
+			name = btf__str_by_offset(obj->btf, t->name_off);
+			if (strncmp(name, str, len))
+				continue;
+
+			t = btf_type_by_id(obj->btf, t->type);
+			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+				pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
+					prog->name);
+				return -EINVAL;
+			}
+			if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)))
+				continue;
+			/* Multiple callbacks are specified for the same prog,
+			 * the verifier will eventually return an error for this
+			 * case, hence simply skip appending a subprog.
+			 */
+			if (prog->exception_cb_idx >= 0) {
+				prog->exception_cb_idx = -1;
+				break;
+			}
+
+			name += len;
+			if (str_is_empty(name)) {
+				pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
+					prog->name);
+				return -EINVAL;
+			}
+
+			for (k = 0; k < obj->nr_programs; k++) {
+				struct bpf_program *subprog = &obj->programs[k];
+
+				if (!prog_is_subprog(obj, subprog))
+					continue;
+				if (strcmp(name, subprog->name))
+					continue;
+				/* Enforce non-hidden, as from verifier point of
+				 * view it expects global functions, whereas the
+				 * mark_btf_static fixes up linkage as static.
+				 */
+				if (!subprog->sym_global || subprog->mark_btf_static) {
+					pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
+						prog->name, subprog->name);
+					return -EINVAL;
+				}
+				/* Let's see if we already saw a static exception callback with the same name */
+				if (prog->exception_cb_idx >= 0) {
+					pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
+					        prog->name, subprog->name);
+					return -EINVAL;
+				}
+				prog->exception_cb_idx = k;
+				break;
+			}
+
+			if (prog->exception_cb_idx >= 0)
+				continue;
+			pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
+			return -ENOENT;
+		}
+	}
+skip_exception_cb:
+
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -6270,10 +6355,10 @@ static int
 bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		       struct bpf_program *prog)
 {
-	size_t sub_insn_idx, insn_idx, new_cnt;
+	size_t sub_insn_idx, insn_idx;
 	struct bpf_program *subprog;
-	struct bpf_insn *insns, *insn;
 	struct reloc_desc *relo;
+	struct bpf_insn *insn;
 	int err;
 
 	err = reloc_prog_func_and_line_info(obj, main_prog, prog);
@@ -6582,6 +6667,25 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 				prog->name, err);
 			return err;
 		}
+
+		/* Now, also append exception callback if it has not been done already. */
+		if (prog->exception_cb_idx >= 0) {
+			struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx];
+
+			/* Calling exception callback directly is disallowed, which the
+			 * verifier will reject later. In case it was processed already,
+			 * we can skip this step, otherwise for all other valid cases we
+			 * have to append exception callback now.
+			 */
+			if (subprog->sub_insn_off == 0) {
+				err = bpf_object__append_subprog_code(obj, prog, subprog);
+				if (err)
+					return err;
+				err = bpf_object__reloc_code(obj, prog, subprog);
+				if (err)
+					return err;
+			}
+		}
 	}
 	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
-- 
cgit v1.2.3


From d6ea06803212d992cbab24466f491ee0178bf9e0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:13 +0200
Subject: selftests/bpf: Add BPF assertion macros

Add macros implementing an 'assert' statement primitive using macros,
built on top of the BPF exceptions support introduced in previous
patches.

The bpf_assert_*_with variants allow supplying a value which can the be
inspected within the exception handler to signify the assert statement
that led to the program being terminated abruptly, or be returned by the
default exception handler.

Note that only 64-bit scalar values are supported with these assertion
macros, as during testing I found other cases quite unreliable in
presence of compiler shifts/manipulations extracting the value of the
right width from registers scrubbing the verifier's bounds information
and knowledge about the value in the register.

Thus, it is easier to reliably support this feature with only the full
register width, and support both signed and unsigned variants.

The bpf_assert_range is interesting in particular, which clamps the
value in the [begin, end] (both inclusive) range within verifier state,
and emits a check for the same at runtime.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-17-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_experimental.h | 243 +++++++++++++++++++++++++
 1 file changed, 243 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 9a87170524ce..9aa29564bd74 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -207,4 +207,247 @@ extern void bpf_throw(u64 cookie) __ksym;
  */
 #define __exception_cb(name) __attribute__((btf_decl_tag("exception_callback:" #name)))
 
+#define __bpf_assert_signed(x) _Generic((x), \
+    unsigned long: 0,       \
+    unsigned long long: 0,  \
+    signed long: 1,         \
+    signed long long: 1     \
+)
+
+#define __bpf_assert_check(LHS, op, RHS)								 \
+	_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");			 \
+	_Static_assert(sizeof(LHS) == 8, "Only 8-byte integers are supported\n");			 \
+	_Static_assert(__builtin_constant_p(__bpf_assert_signed(LHS)), "internal static assert");	 \
+	_Static_assert(__builtin_constant_p((RHS)), "2nd argument must be a constant expression")
+
+#define __bpf_assert(LHS, op, cons, RHS, VAL)							\
+	({											\
+		(void)bpf_throw;								\
+		asm volatile ("if %[lhs] " op " %[rhs] goto +2; r1 = %[value]; call bpf_throw"	\
+			       : : [lhs] "r"(LHS), [rhs] cons(RHS), [value] "ri"(VAL) : );	\
+	})
+
+#define __bpf_assert_op_sign(LHS, op, cons, RHS, VAL, supp_sign)			\
+	({										\
+		__bpf_assert_check(LHS, op, RHS);					\
+		if (__bpf_assert_signed(LHS) && !(supp_sign))				\
+			__bpf_assert(LHS, "s" #op, cons, RHS, VAL);			\
+		else									\
+			__bpf_assert(LHS, #op, cons, RHS, VAL);				\
+	 })
+
+#define __bpf_assert_op(LHS, op, RHS, VAL, supp_sign)					\
+	({										\
+		if (sizeof(typeof(RHS)) == 8) {						\
+			const typeof(RHS) rhs_var = (RHS);				\
+			__bpf_assert_op_sign(LHS, op, "r", rhs_var, VAL, supp_sign);	\
+		} else {								\
+			__bpf_assert_op_sign(LHS, op, "i", RHS, VAL, supp_sign);	\
+		}									\
+	 })
+
+/* Description
+ *	Assert that a conditional expression is true.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
+
+/* Description
+ *	Assert that a conditional expression is true.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
+
+/* Description
+ *	Assert that LHS is equal to RHS. This statement updates the known value
+ *	of LHS during verification. Note that RHS must be a constant value, and
+ *	must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_eq(LHS, RHS)						\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, ==, RHS, 0, true);			\
+	})
+
+/* Description
+ *	Assert that LHS is equal to RHS. This statement updates the known value
+ *	of LHS during verification. Note that RHS must be a constant value, and
+ *	must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_eq_with(LHS, RHS, value)				\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, ==, RHS, value, true);		\
+	})
+
+/* Description
+ *	Assert that LHS is less than RHS. This statement updates the known
+ *	bounds of LHS during verification. Note that RHS must be a constant
+ *	value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_lt(LHS, RHS)						\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, <, RHS, 0, false);			\
+	})
+
+/* Description
+ *	Assert that LHS is less than RHS. This statement updates the known
+ *	bounds of LHS during verification. Note that RHS must be a constant
+ *	value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_lt_with(LHS, RHS, value)				\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, <, RHS, value, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is greater than RHS. This statement updates the known
+ *	bounds of LHS during verification. Note that RHS must be a constant
+ *	value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_gt(LHS, RHS)						\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >, RHS, 0, false);			\
+	})
+
+/* Description
+ *	Assert that LHS is greater than RHS. This statement updates the known
+ *	bounds of LHS during verification. Note that RHS must be a constant
+ *	value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_gt_with(LHS, RHS, value)				\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >, RHS, value, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is less than or equal to RHS. This statement updates the
+ *	known bounds of LHS during verification. Note that RHS must be a
+ *	constant value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_le(LHS, RHS)						\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, <=, RHS, 0, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is less than or equal to RHS. This statement updates the
+ *	known bounds of LHS during verification. Note that RHS must be a
+ *	constant value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_le_with(LHS, RHS, value)				\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, <=, RHS, value, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is greater than or equal to RHS. This statement updates
+ *	the known bounds of LHS during verification. Note that RHS must be a
+ *	constant value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_ge(LHS, RHS)						\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, RHS, 0, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is greater than or equal to RHS. This statement updates
+ *	the known bounds of LHS during verification. Note that RHS must be a
+ *	constant value, and must fit within the data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_ge_with(LHS, RHS, value)				\
+	({								\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, RHS, value, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
+ *	statement updates the known bounds of LHS during verification. Note
+ *	that both BEG and END must be constant values, and must fit within the
+ *	data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_range(LHS, BEG, END)					\
+	({								\
+		_Static_assert(BEG <= END, "BEG must be <= END");	\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, BEG, 0, false);		\
+		__bpf_assert_op(LHS, <=, END, 0, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
+ *	statement updates the known bounds of LHS during verification. Note
+ *	that both BEG and END must be constant values, and must fit within the
+ *	data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_range_with(LHS, BEG, END, value)			\
+	({								\
+		_Static_assert(BEG <= END, "BEG must be <= END");	\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, BEG, value, false);		\
+		__bpf_assert_op(LHS, <=, END, value, false);		\
+	})
+
 #endif
-- 
cgit v1.2.3


From d2a93715bfb0655a63bb1687f43f48eb2e61717b Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Wed, 13 Sep 2023 01:32:14 +0200
Subject: selftests/bpf: Add tests for BPF exceptions

Add selftests to cover success and failure cases of API usage, runtime
behavior and invariants that need to be maintained for implementation
correctness.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-18-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/DENYLIST.aarch64       |   1 +
 tools/testing/selftests/bpf/DENYLIST.s390x         |   1 +
 .../testing/selftests/bpf/prog_tests/exceptions.c  | 408 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/exceptions.c     | 368 +++++++++++++++++++
 .../selftests/bpf/progs/exceptions_assert.c        | 135 +++++++
 tools/testing/selftests/bpf/progs/exceptions_ext.c |  72 ++++
 .../testing/selftests/bpf/progs/exceptions_fail.c  | 347 ++++++++++++++++++
 7 files changed, 1332 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/exceptions.c
 create mode 100644 tools/testing/selftests/bpf/progs/exceptions.c
 create mode 100644 tools/testing/selftests/bpf/progs/exceptions_assert.c
 create mode 100644 tools/testing/selftests/bpf/progs/exceptions_ext.c
 create mode 100644 tools/testing/selftests/bpf/progs/exceptions_fail.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 7f768d335698..f5065576cae9 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -1,5 +1,6 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
+exceptions					 # JIT does not support calling kfunc bpf_throw: -524
 fexit_sleep                                      # The test never returns. The remaining tests cannot start.
 kprobe_multi_bench_attach                        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
 kprobe_multi_test/attach_api_addrs               # bpf_program__attach_kprobe_multi_opts unexpected error: -95
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 5061d9e24c16..ce6f291665cf 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -6,6 +6,7 @@ bpf_loop                                 # attaches to __x64_sys_nanosleep
 cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
 dynptr/test_dynptr_skb_data
 dynptr/test_skb_readonly
+exceptions				 # JIT does not support calling kfunc bpf_throw				       (exceptions)
 fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
 iters/testmod_seq*                       # s390x doesn't support kfuncs in modules yet
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions.c b/tools/testing/selftests/bpf/prog_tests/exceptions.c
new file mode 100644
index 000000000000..5663e427dc00
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "exceptions.skel.h"
+#include "exceptions_ext.skel.h"
+#include "exceptions_fail.skel.h"
+#include "exceptions_assert.skel.h"
+
+static char log_buf[1024 * 1024];
+
+static void test_exceptions_failure(void)
+{
+	RUN_TESTS(exceptions_fail);
+}
+
+static void test_exceptions_success(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, ropts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct exceptions_ext *eskel = NULL;
+	struct exceptions *skel;
+	int ret;
+
+	skel = exceptions__open();
+	if (!ASSERT_OK_PTR(skel, "exceptions__open"))
+		return;
+
+	ret = exceptions__load(skel);
+	if (!ASSERT_OK(ret, "exceptions__load"))
+		goto done;
+
+	if (!ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.jmp_table), &(int){0},
+					   &(int){bpf_program__fd(skel->progs.exception_tail_call_target)}, BPF_ANY),
+		       "bpf_map_update_elem jmp_table"))
+		goto done;
+
+#define RUN_SUCCESS(_prog, return_val)						  \
+	if (!test__start_subtest(#_prog)) goto _prog##_##return_val;		  \
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs._prog), &ropts); \
+	ASSERT_OK(ret, #_prog " prog run ret");					  \
+	ASSERT_EQ(ropts.retval, return_val, #_prog " prog run retval");		  \
+	_prog##_##return_val:
+
+	RUN_SUCCESS(exception_throw_always_1, 64);
+	RUN_SUCCESS(exception_throw_always_2, 32);
+	RUN_SUCCESS(exception_throw_unwind_1, 16);
+	RUN_SUCCESS(exception_throw_unwind_2, 32);
+	RUN_SUCCESS(exception_throw_default, 0);
+	RUN_SUCCESS(exception_throw_default_value, 5);
+	RUN_SUCCESS(exception_tail_call, 24);
+	RUN_SUCCESS(exception_ext, 0);
+	RUN_SUCCESS(exception_ext_mod_cb_runtime, 35);
+	RUN_SUCCESS(exception_throw_subprog, 1);
+	RUN_SUCCESS(exception_assert_nz_gfunc, 1);
+	RUN_SUCCESS(exception_assert_zero_gfunc, 1);
+	RUN_SUCCESS(exception_assert_neg_gfunc, 1);
+	RUN_SUCCESS(exception_assert_pos_gfunc, 1);
+	RUN_SUCCESS(exception_assert_negeq_gfunc, 1);
+	RUN_SUCCESS(exception_assert_poseq_gfunc, 1);
+	RUN_SUCCESS(exception_assert_nz_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_zero_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_neg_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_pos_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_negeq_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_poseq_gfunc_with, 1);
+	RUN_SUCCESS(exception_bad_assert_nz_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_zero_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_neg_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_pos_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_negeq_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_poseq_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_nz_gfunc_with, 100);
+	RUN_SUCCESS(exception_bad_assert_zero_gfunc_with, 105);
+	RUN_SUCCESS(exception_bad_assert_neg_gfunc_with, 200);
+	RUN_SUCCESS(exception_bad_assert_pos_gfunc_with, 0);
+	RUN_SUCCESS(exception_bad_assert_negeq_gfunc_with, 101);
+	RUN_SUCCESS(exception_bad_assert_poseq_gfunc_with, 99);
+	RUN_SUCCESS(exception_assert_range, 1);
+	RUN_SUCCESS(exception_assert_range_with, 1);
+	RUN_SUCCESS(exception_bad_assert_range, 0);
+	RUN_SUCCESS(exception_bad_assert_range_with, 10);
+
+#define RUN_EXT(load_ret, attach_err, expr, msg, after_link)			  \
+	{									  \
+		LIBBPF_OPTS(bpf_object_open_opts, o, .kernel_log_buf = log_buf,		 \
+						     .kernel_log_size = sizeof(log_buf), \
+						     .kernel_log_level = 2);		 \
+		exceptions_ext__destroy(eskel);					  \
+		eskel = exceptions_ext__open_opts(&o);				  \
+		struct bpf_program *prog = NULL;				  \
+		struct bpf_link *link = NULL;					  \
+		if (!ASSERT_OK_PTR(eskel, "exceptions_ext__open"))		  \
+			goto done;						  \
+		(expr);								  \
+		ASSERT_OK_PTR(bpf_program__name(prog), bpf_program__name(prog));  \
+		if (!ASSERT_EQ(exceptions_ext__load(eskel), load_ret,		  \
+			       "exceptions_ext__load"))	{			  \
+			printf("%s\n", log_buf);				  \
+			goto done;						  \
+		}								  \
+		if (load_ret != 0) {						  \
+			printf("%s\n", log_buf);				  \
+			if (!ASSERT_OK_PTR(strstr(log_buf, msg), "strstr"))	  \
+				goto done;					  \
+		}								  \
+		if (!load_ret && attach_err) {					  \
+			if (!ASSERT_ERR_PTR(link = bpf_program__attach(prog), "attach err")) \
+				goto done;					  \
+		} else if (!load_ret) {						  \
+			if (!ASSERT_OK_PTR(link = bpf_program__attach(prog), "attach ok"))  \
+				goto done;					  \
+			(void)(after_link);					  \
+			bpf_link__destroy(link);				  \
+		}								  \
+	}
+
+	if (test__start_subtest("non-throwing fentry -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing fentry -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("non-throwing fexit -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing fexit -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing extension (with custom cb) -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_exception_cb_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "Extension programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing extension -> global func in exception_cb"))
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_exception_cb_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod_global"), "set_attach_target"))
+				goto done;
+		}), "", ({ RUN_SUCCESS(exception_ext_mod_cb_runtime, 131); }));
+
+	if (test__start_subtest("throwing extension (with custom cb) -> global func in exception_cb"))
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext),
+				       "exception_ext_global"), "set_attach_target"))
+				goto done;
+		}), "", ({ RUN_SUCCESS(exception_ext, 128); }));
+
+	if (test__start_subtest("non-throwing fentry -> non-throwing subprog"))
+		/* non-throwing fentry -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fentry -> non-throwing subprog"))
+		/* throwing fentry -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fentry -> throwing subprog"))
+		/* non-throwing fentry -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fentry -> throwing subprog"))
+		/* throwing fentry -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fexit -> non-throwing subprog"))
+		/* non-throwing fexit -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fexit -> non-throwing subprog"))
+		/* throwing fexit -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fexit -> throwing subprog"))
+		/* non-throwing fexit -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fexit -> throwing subprog"))
+		/* throwing fexit -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	/* fmod_ret not allowed for subprog - Check so we remember to handle its
+	 * throwing specification compatibility with target when supported.
+	 */
+	if (test__start_subtest("non-throwing fmod_ret -> non-throwing subprog"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfmod_ret;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "can't modify return codes of BPF program", 0);
+
+	/* fmod_ret not allowed for subprog - Check so we remember to handle its
+	 * throwing specification compatibility with target when supported.
+	 */
+	if (test__start_subtest("non-throwing fmod_ret -> non-throwing global subprog"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfmod_ret;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "can't modify return codes of BPF program", 0);
+
+	if (test__start_subtest("non-throwing extension -> non-throwing subprog"))
+		/* non-throwing extension -> non-throwing subprog : BAD (!global) */
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "subprog() is not a global function", 0);
+
+	if (test__start_subtest("non-throwing extension -> throwing subprog"))
+		/* non-throwing extension -> throwing subprog : BAD (!global) */
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "throwing_subprog() is not a global function", 0);
+
+	if (test__start_subtest("non-throwing extension -> non-throwing subprog"))
+		/* non-throwing extension -> non-throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing extension -> throwing global subprog"))
+		/* non-throwing extension -> throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> throwing global subprog"))
+		/* throwing extension -> throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> non-throwing global subprog"))
+		/* throwing extension -> non-throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing extension -> main subprog"))
+		/* non-throwing extension -> main subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "exception_throw_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> main subprog"))
+		/* throwing extension -> main subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "exception_throw_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+done:
+	exceptions_ext__destroy(eskel);
+	exceptions__destroy(skel);
+}
+
+static void test_exceptions_assertions(void)
+{
+	RUN_TESTS(exceptions_assert);
+}
+
+void test_exceptions(void)
+{
+	test_exceptions_success();
+	test_exceptions_failure();
+	test_exceptions_assertions();
+}
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
new file mode 100644
index 000000000000..2811ee842b01
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+#ifndef ETH_P_IP
+#define ETH_P_IP 0x0800
+#endif
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+static __noinline int static_func(u64 i)
+{
+	bpf_throw(32);
+	return i;
+}
+
+__noinline int global2static_simple(u64 i)
+{
+	static_func(i + 2);
+	return i - 1;
+}
+
+__noinline int global2static(u64 i)
+{
+	if (i == ETH_P_IP)
+		bpf_throw(16);
+	return static_func(i);
+}
+
+static __noinline int static2global(u64 i)
+{
+	return global2static(i) + i;
+}
+
+SEC("tc")
+int exception_throw_always_1(struct __sk_buff *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+/* In this case, the global func will never be seen executing after call to
+ * static subprog, hence verifier will DCE the remaining instructions. Ensure we
+ * are resilient to that.
+ */
+SEC("tc")
+int exception_throw_always_2(struct __sk_buff *ctx)
+{
+	return global2static_simple(ctx->protocol);
+}
+
+SEC("tc")
+int exception_throw_unwind_1(struct __sk_buff *ctx)
+{
+	return static2global(bpf_ntohs(ctx->protocol));
+}
+
+SEC("tc")
+int exception_throw_unwind_2(struct __sk_buff *ctx)
+{
+	return static2global(bpf_ntohs(ctx->protocol) - 1);
+}
+
+SEC("tc")
+int exception_throw_default(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 1;
+}
+
+SEC("tc")
+int exception_throw_default_value(struct __sk_buff *ctx)
+{
+	bpf_throw(5);
+	return 1;
+}
+
+SEC("tc")
+int exception_tail_call_target(struct __sk_buff *ctx)
+{
+	bpf_throw(16);
+	return 0;
+}
+
+static __noinline
+int exception_tail_call_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 10;
+
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return ret;
+}
+
+SEC("tc")
+int exception_tail_call(struct __sk_buff *ctx) {
+	volatile int ret = 0;
+
+	ret = exception_tail_call_subprog(ctx);
+	return ret + 8;
+}
+
+__noinline int exception_ext_global(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	return ret;
+}
+
+static __noinline int exception_ext_static(struct __sk_buff *ctx)
+{
+	return exception_ext_global(ctx);
+}
+
+SEC("tc")
+int exception_ext(struct __sk_buff *ctx)
+{
+	return exception_ext_static(ctx);
+}
+
+__noinline int exception_cb_mod_global(u64 cookie)
+{
+	volatile int ret = 0;
+
+	return ret;
+}
+
+/* Example of how the exception callback supplied during verification can still
+ * introduce extensions by calling to dummy global functions, and alter runtime
+ * behavior.
+ *
+ * Right now we don't allow freplace attachment to exception callback itself,
+ * but if the need arises this restriction is technically feasible to relax in
+ * the future.
+ */
+__noinline int exception_cb_mod(u64 cookie)
+{
+	return exception_cb_mod_global(cookie) + cookie + 10;
+}
+
+SEC("tc")
+__exception_cb(exception_cb_mod)
+int exception_ext_mod_cb_runtime(struct __sk_buff *ctx)
+{
+	bpf_throw(25);
+	return 0;
+}
+
+__noinline static int subprog(struct __sk_buff *ctx)
+{
+	return bpf_ktime_get_ns();
+}
+
+__noinline static int throwing_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->tstamp)
+		bpf_throw(0);
+	return bpf_ktime_get_ns();
+}
+
+__noinline int global_subprog(struct __sk_buff *ctx)
+{
+	return bpf_ktime_get_ns();
+}
+
+__noinline int throwing_global_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->tstamp)
+		bpf_throw(0);
+	return bpf_ktime_get_ns();
+}
+
+SEC("tc")
+int exception_throw_subprog(struct __sk_buff *ctx)
+{
+	switch (ctx->protocol) {
+	case 1:
+		return subprog(ctx);
+	case 2:
+		return global_subprog(ctx);
+	case 3:
+		return throwing_subprog(ctx);
+	case 4:
+		return throwing_global_subprog(ctx);
+	default:
+		break;
+	}
+	bpf_throw(1);
+	return 0;
+}
+
+__noinline int assert_nz_gfunc(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert(cookie != 0);
+	return 0;
+}
+
+__noinline int assert_zero_gfunc(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert_eq(cookie, 0);
+	return 0;
+}
+
+__noinline int assert_neg_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_lt(cookie, 0);
+	return 0;
+}
+
+__noinline int assert_pos_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_gt(cookie, 0);
+	return 0;
+}
+
+__noinline int assert_negeq_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_le(cookie, -1);
+	return 0;
+}
+
+__noinline int assert_poseq_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_ge(cookie, 1);
+	return 0;
+}
+
+__noinline int assert_nz_gfunc_with(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert_with(cookie != 0, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_zero_gfunc_with(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert_eq_with(cookie, 0, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_neg_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_lt_with(cookie, 0, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_pos_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_gt_with(cookie, 0, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_negeq_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_le_with(cookie, -1, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_poseq_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_ge_with(cookie, 1, cookie + 100);
+	return 0;
+}
+
+#define check_assert(name, cookie, tag)				\
+SEC("tc")							\
+int exception##tag##name(struct __sk_buff *ctx)			\
+{								\
+	return name(cookie) + 1;				\
+}
+
+check_assert(assert_nz_gfunc, 5, _);
+check_assert(assert_zero_gfunc, 0, _);
+check_assert(assert_neg_gfunc, -100, _);
+check_assert(assert_pos_gfunc, 100, _);
+check_assert(assert_negeq_gfunc, -1, _);
+check_assert(assert_poseq_gfunc, 1, _);
+
+check_assert(assert_nz_gfunc_with, 5, _);
+check_assert(assert_zero_gfunc_with, 0, _);
+check_assert(assert_neg_gfunc_with, -100, _);
+check_assert(assert_pos_gfunc_with, 100, _);
+check_assert(assert_negeq_gfunc_with, -1, _);
+check_assert(assert_poseq_gfunc_with, 1, _);
+
+check_assert(assert_nz_gfunc, 0, _bad_);
+check_assert(assert_zero_gfunc, 5, _bad_);
+check_assert(assert_neg_gfunc, 100, _bad_);
+check_assert(assert_pos_gfunc, -100, _bad_);
+check_assert(assert_negeq_gfunc, 1, _bad_);
+check_assert(assert_poseq_gfunc, -1, _bad_);
+
+check_assert(assert_nz_gfunc_with, 0, _bad_);
+check_assert(assert_zero_gfunc_with, 5, _bad_);
+check_assert(assert_neg_gfunc_with, 100, _bad_);
+check_assert(assert_pos_gfunc_with, -100, _bad_);
+check_assert(assert_negeq_gfunc_with, 1, _bad_);
+check_assert(assert_poseq_gfunc_with, -1, _bad_);
+
+SEC("tc")
+int exception_assert_range(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range(time, 0, ~0ULL);
+	return 1;
+}
+
+SEC("tc")
+int exception_assert_range_with(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range_with(time, 0, ~0ULL, 10);
+	return 1;
+}
+
+SEC("tc")
+int exception_bad_assert_range(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range(time, -100, 100);
+	return 1;
+}
+
+SEC("tc")
+int exception_bad_assert_range_with(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range_with(time, -1000, 1000, 10);
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
new file mode 100644
index 000000000000..fa35832e6748
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <limits.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+#define check_assert(type, op, name, value)				\
+	SEC("?tc")							\
+	__log_level(2) __failure					\
+	int check_assert_##op##_##name(void *ctx)			\
+	{								\
+		type num = bpf_ktime_get_ns();				\
+		bpf_assert_##op(num, value);				\
+		return *(u64 *)num;					\
+	}
+
+__msg(": R0_w=-2147483648 R10=fp0")
+check_assert(s64, eq, int_min, INT_MIN);
+__msg(": R0_w=2147483647 R10=fp0")
+check_assert(s64, eq, int_max, INT_MAX);
+__msg(": R0_w=0 R10=fp0")
+check_assert(s64, eq, zero, 0);
+__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0")
+check_assert(s64, eq, llong_min, LLONG_MIN);
+__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0")
+check_assert(s64, eq, llong_max, LLONG_MAX);
+
+__msg(": R0_w=scalar(smax=2147483646) R10=fp0")
+check_assert(s64, lt, pos, INT_MAX);
+__msg(": R0_w=scalar(umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, lt, zero, 0);
+__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, lt, neg, INT_MIN);
+
+__msg(": R0_w=scalar(smax=2147483647) R10=fp0")
+check_assert(s64, le, pos, INT_MAX);
+__msg(": R0_w=scalar(smax=0) R10=fp0")
+check_assert(s64, le, zero, 0);
+__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, le, neg, INT_MIN);
+
+__msg(": R0_w=scalar(umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, gt, pos, INT_MAX);
+__msg(": R0_w=scalar(umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, gt, zero, 0);
+__msg(": R0_w=scalar(smin=-2147483647) R10=fp0")
+check_assert(s64, gt, neg, INT_MIN);
+
+__msg(": R0_w=scalar(umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, ge, pos, INT_MAX);
+__msg(": R0_w=scalar(umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
+check_assert(s64, ge, zero, 0);
+__msg(": R0_w=scalar(smin=-2147483648) R10=fp0")
+check_assert(s64, ge, neg, INT_MIN);
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=-2147483646,smax=2147483645) R10=fp0")
+int check_assert_range_s64(struct __sk_buff *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	s64 num;
+
+	_Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match");
+	if (!sk)
+		return 0;
+	num = sk->rx_queue_mapping;
+	bpf_assert_range(num, INT_MIN + 2, INT_MAX - 2);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=ctx(off=0,imm=0) R2=scalar(umin=4096,umax=8192,var_off=(0x0; 0x3fff))")
+int check_assert_range_u64(struct __sk_buff *ctx)
+{
+	u64 num = ctx->len;
+
+	bpf_assert_range(num, 4096, 8192);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R0=0 R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+int check_assert_single_range_s64(struct __sk_buff *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	s64 num;
+
+	_Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match");
+	if (!sk)
+		return 0;
+	num = sk->rx_queue_mapping;
+
+	bpf_assert_range(num, 4096, 4096);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=ctx(off=0,imm=0) R2=4096 R10=fp0")
+int check_assert_single_range_u64(struct __sk_buff *ctx)
+{
+	u64 num = ctx->len;
+
+	bpf_assert_range(num, 4096, 4096);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=pkt(off=64,r=64,imm=0) R2=pkt_end(off=0,imm=0) R6=pkt(off=0,r=64,imm=0) R10=fp0")
+int check_assert_generic(struct __sk_buff *ctx)
+{
+	u8 *data_end = (void *)(long)ctx->data_end;
+	u8 *data = (void *)(long)ctx->data;
+
+	bpf_assert(data + 64 <= data_end);
+	return data[128];
+}
+
+SEC("?fentry/bpf_check")
+__failure __msg("At program exit the register R0 has value (0x40; 0x0)")
+int check_assert_with_return(void *ctx)
+{
+	bpf_assert_with(!ctx, 64);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_ext.c b/tools/testing/selftests/bpf/progs/exceptions_ext.c
new file mode 100644
index 000000000000..743c05185d9b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_ext.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+
+SEC("?fentry")
+int pfentry(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fentry")
+int throwing_fentry(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline int exception_cb(u64 cookie)
+{
+	return cookie + 64;
+}
+
+SEC("?freplace")
+int extension(struct __sk_buff *ctx)
+{
+	return 0;
+}
+
+SEC("?freplace")
+__exception_cb(exception_cb)
+int throwing_exception_cb_extension(u64 cookie)
+{
+	bpf_throw(32);
+	return 0;
+}
+
+SEC("?freplace")
+__exception_cb(exception_cb)
+int throwing_extension(struct __sk_buff *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+SEC("?fexit")
+int pfexit(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fexit")
+int throwing_fexit(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?fmod_ret")
+int pfmod_ret(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fmod_ret")
+int throwing_fmod_ret(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
new file mode 100644
index 000000000000..4c39e920dac2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+extern void bpf_rcu_read_lock(void) __ksym;
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+
+struct foo {
+	struct bpf_rb_node node;
+};
+
+struct hmap_elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 64);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap SEC(".maps");
+
+private(A) struct bpf_spin_lock lock;
+private(A) struct bpf_rb_root rbtree __contains(foo, node);
+
+__noinline void *exception_cb_bad_ret_type(u64 cookie)
+{
+	return NULL;
+}
+
+__noinline int exception_cb_bad_arg_0(void)
+{
+	return 0;
+}
+
+__noinline int exception_cb_bad_arg_2(int a, int b)
+{
+	return 0;
+}
+
+__noinline int exception_cb_ok_arg_small(int a)
+{
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_ret_type)
+__failure __msg("Global function exception_cb_bad_ret_type() doesn't return scalar.")
+int reject_exception_cb_type_1(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_arg_0)
+__failure __msg("exception cb only supports single integer argument")
+int reject_exception_cb_type_2(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_arg_2)
+__failure __msg("exception cb only supports single integer argument")
+int reject_exception_cb_type_3(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_ok_arg_small)
+__success
+int reject_exception_cb_type_4(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline
+static int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback subprog")
+int reject_async_callback_throw(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+	return bpf_timer_set_callback(&elem->timer, timer_cb);
+}
+
+__noinline static int subprog_lock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_spin_lock(&lock);
+	if (ctx->len)
+		bpf_throw(0);
+	return ret;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_with_lock(void *ctx)
+{
+	bpf_spin_lock(&lock);
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_subprog_with_lock(void *ctx)
+{
+	return subprog_lock(ctx);
+}
+
+SEC("?tc")
+__failure __msg("bpf_rcu_read_unlock is missing")
+int reject_with_rcu_read_lock(void *ctx)
+{
+	bpf_rcu_read_lock();
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int throwing_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->len)
+		bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_rcu_read_unlock is missing")
+int reject_subprog_with_rcu_read_lock(void *ctx)
+{
+	bpf_rcu_read_lock();
+	return throwing_subprog(ctx);
+}
+
+static bool rbless(struct bpf_rb_node *n1, const struct bpf_rb_node *n2)
+{
+	bpf_throw(0);
+	return true;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_with_rbtree_add_throw(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&rbtree, &f->node, rbless);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_reference(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int subprog_ref(struct __sk_buff *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int subprog_cb_ref(u32 i, void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_cb_reference(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_with_cb(void *ctx)
+{
+	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_subprog_reference(void *ctx)
+{
+	return subprog_ref(ctx) + 1;
+}
+
+__noinline int throwing_exception_cb(u64 c)
+{
+	bpf_throw(0);
+	return c;
+}
+
+__noinline int exception_cb1(u64 c)
+{
+	return c;
+}
+
+__noinline int exception_cb2(u64 c)
+{
+	return c;
+}
+
+static __noinline int static_func(struct __sk_buff *ctx)
+{
+	return exception_cb1(ctx->tstamp);
+}
+
+__noinline int global_func(struct __sk_buff *ctx)
+{
+	return exception_cb1(ctx->tstamp);
+}
+
+SEC("?tc")
+__exception_cb(throwing_exception_cb)
+__failure __msg("cannot be called from callback subprog")
+int reject_throwing_exception_cb(struct __sk_buff *ctx)
+{
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__failure __msg("cannot call exception cb directly")
+int reject_exception_cb_call_global_func(struct __sk_buff *ctx)
+{
+	return global_func(ctx);
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__failure __msg("cannot call exception cb directly")
+int reject_exception_cb_call_static_func(struct __sk_buff *ctx)
+{
+	return static_func(ctx);
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__exception_cb(exception_cb2)
+__failure __msg("multiple exception callback tags for main subprog")
+int reject_multiple_exception_cb(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 16;
+}
+
+__noinline int exception_cb_bad_ret(u64 c)
+{
+	return c;
+}
+
+SEC("?fentry/bpf_check")
+__exception_cb(exception_cb_bad_ret)
+__failure __msg("At program exit the register R0 has unknown scalar value should")
+int reject_set_exception_cb_bad_ret1(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fentry/bpf_check")
+__failure __msg("At program exit the register R0 has value (0x40; 0x0) should")
+int reject_set_exception_cb_bad_ret2(void *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+__noinline static int loop_cb1(u32 index, int *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int loop_cb2(u32 index, int *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_exception_throw_cb(struct __sk_buff *ctx)
+{
+	bpf_loop(5, loop_cb1, NULL, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_exception_throw_cb_diff(struct __sk_buff *ctx)
+{
+	if (ctx->protocol)
+		bpf_loop(5, loop_cb1, NULL, 0);
+	else
+		bpf_loop(5, loop_cb2, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From a8ed71a27ef524c808b518031feac811ed3e741c Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 15 Sep 2023 14:14:48 +0200
Subject: vsock/test: add recv_buf() utility function

Move the code of recv_byte() out in a new utility function that
can be used to receive a generic buffer.

This new function can be used when we need to receive a custom
buffer and not just a single 'A' byte.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/util.c | 88 ++++++++++++++++++++++++++++------------------
 tools/testing/vsock/util.h |  1 +
 2 files changed, 54 insertions(+), 35 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 01b636d3039a..2826902706e8 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -211,6 +211,58 @@ int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 	return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET);
 }
 
+/* Receive bytes in a buffer and check the return value.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *  >0 Success (bytes successfully read)
+ */
+void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret)
+{
+	ssize_t nread = 0;
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = recv(fd, buf + nread, len - nread, flags);
+		timeout_check("recv");
+
+		if (ret == 0 || (ret < 0 && errno != EINTR))
+			break;
+
+		nread += ret;
+	} while (nread < len);
+	timeout_end();
+
+	if (expected_ret < 0) {
+		if (ret != -1) {
+			fprintf(stderr, "bogus recv(2) return value %zd (expected %zd)\n",
+				ret, expected_ret);
+			exit(EXIT_FAILURE);
+		}
+		if (errno != -expected_ret) {
+			perror("recv");
+			exit(EXIT_FAILURE);
+		}
+		return;
+	}
+
+	if (ret < 0) {
+		perror("recv");
+		exit(EXIT_FAILURE);
+	}
+
+	if (nread != expected_ret) {
+		if (ret == 0)
+			fprintf(stderr, "unexpected EOF while receiving bytes\n");
+
+		fprintf(stderr, "bogus recv(2) bytes read %zd (expected %zd)\n",
+			nread, expected_ret);
+		exit(EXIT_FAILURE);
+	}
+}
+
 /* Transmit one byte and check the return value.
  *
  * expected_ret:
@@ -270,43 +322,9 @@ void send_byte(int fd, int expected_ret, int flags)
 void recv_byte(int fd, int expected_ret, int flags)
 {
 	uint8_t byte;
-	ssize_t nread;
-
-	timeout_begin(TIMEOUT);
-	do {
-		nread = recv(fd, &byte, sizeof(byte), flags);
-		timeout_check("read");
-	} while (nread < 0 && errno == EINTR);
-	timeout_end();
-
-	if (expected_ret < 0) {
-		if (nread != -1) {
-			fprintf(stderr, "bogus recv(2) return value %zd\n",
-				nread);
-			exit(EXIT_FAILURE);
-		}
-		if (errno != -expected_ret) {
-			perror("read");
-			exit(EXIT_FAILURE);
-		}
-		return;
-	}
 
-	if (nread < 0) {
-		perror("read");
-		exit(EXIT_FAILURE);
-	}
-	if (nread == 0) {
-		if (expected_ret == 0)
-			return;
+	recv_buf(fd, &byte, sizeof(byte), flags, expected_ret);
 
-		fprintf(stderr, "unexpected EOF while receiving byte\n");
-		exit(EXIT_FAILURE);
-	}
-	if (nread != sizeof(byte)) {
-		fprintf(stderr, "bogus recv(2) return value %zd\n", nread);
-		exit(EXIT_FAILURE);
-	}
 	if (byte != 'A') {
 		fprintf(stderr, "unexpected byte read %c\n", byte);
 		exit(EXIT_FAILURE);
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fb99208a95ea..fe31f267e67e 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -42,6 +42,7 @@ int vsock_stream_accept(unsigned int cid, unsigned int port,
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
+void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret);
 void send_byte(int fd, int expected_ret, int flags);
 void recv_byte(int fd, int expected_ret, int flags);
 void run_tests(const struct test_case *test_cases,
-- 
cgit v1.2.3


From a0bcb83577165b0d6fb948c8ab207a1dd7146f6f Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 15 Sep 2023 14:14:49 +0200
Subject: vsock/test: use recv_buf() in vsock_test.c

We have a very common pattern used in vsock_test that we can
now replace with the new recv_buf().

This allows us to reuse the code we already had to check the
actual return value and wait for all bytes to be received with
an appropriate timeout.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/vsock_test.c | 104 +++++++--------------------------------
 1 file changed, 17 insertions(+), 87 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 148fc9c47c50..ed0cca23ca55 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -302,7 +302,6 @@ static void test_msg_peek_server(const struct test_opts *opts,
 	unsigned char buf_half[MSG_PEEK_BUF_LEN / 2];
 	unsigned char buf_normal[MSG_PEEK_BUF_LEN];
 	unsigned char buf_peek[MSG_PEEK_BUF_LEN];
-	ssize_t res;
 	int fd;
 
 	if (seqpacket)
@@ -316,34 +315,16 @@ static void test_msg_peek_server(const struct test_opts *opts,
 	}
 
 	/* Peek from empty socket. */
-	res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT);
-	if (res != -1) {
-		fprintf(stderr, "expected recv(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
-
-	if (errno != EAGAIN) {
-		perror("EAGAIN expected");
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT,
+		 -EAGAIN);
 
 	control_writeln("SRVREADY");
 
 	/* Peek part of data. */
-	res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK);
-	if (res != sizeof(buf_half)) {
-		fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n",
-			sizeof(buf_half), res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf_half, sizeof(buf_half), MSG_PEEK, sizeof(buf_half));
 
 	/* Peek whole data. */
-	res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK);
-	if (res != sizeof(buf_peek)) {
-		fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n",
-			sizeof(buf_peek), res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf_peek, sizeof(buf_peek), MSG_PEEK, sizeof(buf_peek));
 
 	/* Compare partial and full peek. */
 	if (memcmp(buf_half, buf_peek, sizeof(buf_half))) {
@@ -356,22 +337,11 @@ static void test_msg_peek_server(const struct test_opts *opts,
 		 * so check it with MSG_PEEK. We must get length
 		 * of the message.
 		 */
-		res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK |
-			   MSG_TRUNC);
-		if (res != sizeof(buf_peek)) {
-			fprintf(stderr,
-				"recv(2) + MSG_PEEK | MSG_TRUNC, exp %zu, got %zi\n",
-				sizeof(buf_half), res);
-			exit(EXIT_FAILURE);
-		}
+		recv_buf(fd, buf_half, sizeof(buf_half), MSG_PEEK | MSG_TRUNC,
+			 sizeof(buf_peek));
 	}
 
-	res = recv(fd, buf_normal, sizeof(buf_normal), 0);
-	if (res != sizeof(buf_normal)) {
-		fprintf(stderr, "recv(2), expected %zu, got %zi\n",
-			sizeof(buf_normal), res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf_normal, sizeof(buf_normal), 0, sizeof(buf_normal));
 
 	/* Compare full peek and normal read. */
 	if (memcmp(buf_peek, buf_normal, sizeof(buf_peek))) {
@@ -901,7 +871,6 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts)
 	unsigned long lowat_val = RCVLOWAT_BUF_SIZE;
 	char buf[RCVLOWAT_BUF_SIZE];
 	struct pollfd fds;
-	ssize_t read_res;
 	short poll_flags;
 	int fd;
 
@@ -956,12 +925,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts)
 	/* Use MSG_DONTWAIT, if call is going to wait, EAGAIN
 	 * will be returned.
 	 */
-	read_res = recv(fd, buf, sizeof(buf), MSG_DONTWAIT);
-	if (read_res != RCVLOWAT_BUF_SIZE) {
-		fprintf(stderr, "Unexpected recv result %zi\n",
-			read_res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf, sizeof(buf), MSG_DONTWAIT, RCVLOWAT_BUF_SIZE);
 
 	control_writeln("POLLDONE");
 
@@ -973,7 +937,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts)
 static void test_inv_buf_client(const struct test_opts *opts, bool stream)
 {
 	unsigned char data[INV_BUF_TEST_DATA_LEN] = {0};
-	ssize_t ret;
+	ssize_t expected_ret;
 	int fd;
 
 	if (stream)
@@ -989,39 +953,18 @@ static void test_inv_buf_client(const struct test_opts *opts, bool stream)
 	control_expectln("SENDDONE");
 
 	/* Use invalid buffer here. */
-	ret = recv(fd, NULL, sizeof(data), 0);
-	if (ret != -1) {
-		fprintf(stderr, "expected recv(2) failure, got %zi\n", ret);
-		exit(EXIT_FAILURE);
-	}
-
-	if (errno != EFAULT) {
-		fprintf(stderr, "unexpected recv(2) errno %d\n", errno);
-		exit(EXIT_FAILURE);
-	}
-
-	ret = recv(fd, data, sizeof(data), MSG_DONTWAIT);
+	recv_buf(fd, NULL, sizeof(data), 0, -EFAULT);
 
 	if (stream) {
 		/* For SOCK_STREAM we must continue reading. */
-		if (ret != sizeof(data)) {
-			fprintf(stderr, "expected recv(2) success, got %zi\n", ret);
-			exit(EXIT_FAILURE);
-		}
-		/* Don't check errno in case of success. */
+		expected_ret = sizeof(data);
 	} else {
 		/* For SOCK_SEQPACKET socket's queue must be empty. */
-		if (ret != -1) {
-			fprintf(stderr, "expected recv(2) failure, got %zi\n", ret);
-			exit(EXIT_FAILURE);
-		}
-
-		if (errno != EAGAIN) {
-			fprintf(stderr, "unexpected recv(2) errno %d\n", errno);
-			exit(EXIT_FAILURE);
-		}
+		expected_ret = -EAGAIN;
 	}
 
+	recv_buf(fd, data, sizeof(data), MSG_DONTWAIT, expected_ret);
+
 	control_writeln("DONE");
 
 	close(fd);
@@ -1118,7 +1061,6 @@ static void test_stream_virtio_skb_merge_client(const struct test_opts *opts)
 static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
 {
 	unsigned char buf[64];
-	ssize_t res;
 	int fd;
 
 	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
@@ -1130,26 +1072,14 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
 	control_expectln("SEND0");
 
 	/* Read skbuff partially. */
-	res = recv(fd, buf, 2, 0);
-	if (res != 2) {
-		fprintf(stderr, "expected recv(2) returns 2 bytes, got %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf, 2, 0, 2);
 
 	control_writeln("REPLY0");
 	control_expectln("SEND1");
 
-	res = recv(fd, buf + 2, sizeof(buf) - 2, 0);
-	if (res != 8) {
-		fprintf(stderr, "expected recv(2) returns 8 bytes, got %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf + 2, 8, 0, 8);
 
-	res = recv(fd, buf, sizeof(buf) - 8 - 2, MSG_DONTWAIT);
-	if (res != -1) {
-		fprintf(stderr, "expected recv(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	recv_buf(fd, buf, sizeof(buf) - 8 - 2, MSG_DONTWAIT, -EAGAIN);
 
 	if (memcmp(buf, HELLO_STR WORLD_STR, strlen(HELLO_STR WORLD_STR))) {
 		fprintf(stderr, "pattern mismatch\n");
-- 
cgit v1.2.3


From 12329bd51fdcde211fd9c76015ded4db3458ba8a Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 15 Sep 2023 14:14:50 +0200
Subject: vsock/test: add send_buf() utility function

Move the code of send_byte() out in a new utility function that
can be used to send a generic buffer.

This new function can be used when we need to send a custom
buffer and not just a single 'A' byte.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/util.c | 90 +++++++++++++++++++++++++++-------------------
 tools/testing/vsock/util.h |  2 ++
 2 files changed, 56 insertions(+), 36 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 2826902706e8..6779d5008b27 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -211,6 +211,59 @@ int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 	return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET);
 }
 
+/* Transmit bytes from a buffer and check the return value.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *  >0 Success (bytes successfully written)
+ */
+void send_buf(int fd, const void *buf, size_t len, int flags,
+	      ssize_t expected_ret)
+{
+	ssize_t nwritten = 0;
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = send(fd, buf + nwritten, len - nwritten, flags);
+		timeout_check("send");
+
+		if (ret == 0 || (ret < 0 && errno != EINTR))
+			break;
+
+		nwritten += ret;
+	} while (nwritten < len);
+	timeout_end();
+
+	if (expected_ret < 0) {
+		if (ret != -1) {
+			fprintf(stderr, "bogus send(2) return value %zd (expected %zd)\n",
+				ret, expected_ret);
+			exit(EXIT_FAILURE);
+		}
+		if (errno != -expected_ret) {
+			perror("send");
+			exit(EXIT_FAILURE);
+		}
+		return;
+	}
+
+	if (ret < 0) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	if (nwritten != expected_ret) {
+		if (ret == 0)
+			fprintf(stderr, "unexpected EOF while sending bytes\n");
+
+		fprintf(stderr, "bogus send(2) bytes written %zd (expected %zd)\n",
+			nwritten, expected_ret);
+		exit(EXIT_FAILURE);
+	}
+}
+
 /* Receive bytes in a buffer and check the return value.
  *
  * expected_ret:
@@ -273,43 +326,8 @@ void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret)
 void send_byte(int fd, int expected_ret, int flags)
 {
 	const uint8_t byte = 'A';
-	ssize_t nwritten;
-
-	timeout_begin(TIMEOUT);
-	do {
-		nwritten = send(fd, &byte, sizeof(byte), flags);
-		timeout_check("write");
-	} while (nwritten < 0 && errno == EINTR);
-	timeout_end();
-
-	if (expected_ret < 0) {
-		if (nwritten != -1) {
-			fprintf(stderr, "bogus send(2) return value %zd\n",
-				nwritten);
-			exit(EXIT_FAILURE);
-		}
-		if (errno != -expected_ret) {
-			perror("write");
-			exit(EXIT_FAILURE);
-		}
-		return;
-	}
 
-	if (nwritten < 0) {
-		perror("write");
-		exit(EXIT_FAILURE);
-	}
-	if (nwritten == 0) {
-		if (expected_ret == 0)
-			return;
-
-		fprintf(stderr, "unexpected EOF while sending byte\n");
-		exit(EXIT_FAILURE);
-	}
-	if (nwritten != sizeof(byte)) {
-		fprintf(stderr, "bogus send(2) return value %zd\n", nwritten);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, &byte, sizeof(byte), flags, expected_ret);
 }
 
 /* Receive one byte and check the return value.
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fe31f267e67e..e5407677ce05 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -42,6 +42,8 @@ int vsock_stream_accept(unsigned int cid, unsigned int port,
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
+void send_buf(int fd, const void *buf, size_t len, int flags,
+	      ssize_t expected_ret);
 void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret);
 void send_byte(int fd, int expected_ret, int flags);
 void recv_byte(int fd, int expected_ret, int flags);
-- 
cgit v1.2.3


From 2a8548a9bb4c4ba14badd6be72f1d2b87a6bddc0 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 15 Sep 2023 14:14:51 +0200
Subject: vsock/test: use send_buf() in vsock_test.c

We have a very common pattern used in vsock_test that we can
now replace with the new send_buf().

This allows us to reuse the code we already had to check the
actual return value and wait for all the bytes to be sent with
an appropriate timeout.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/vsock_test.c | 75 +++++-----------------------------------
 1 file changed, 9 insertions(+), 66 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index ed0cca23ca55..89d2cfaf7581 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -262,7 +262,6 @@ static void test_msg_peek_client(const struct test_opts *opts,
 				 bool seqpacket)
 {
 	unsigned char buf[MSG_PEEK_BUF_LEN];
-	ssize_t send_size;
 	int fd;
 	int i;
 
@@ -281,17 +280,7 @@ static void test_msg_peek_client(const struct test_opts *opts,
 
 	control_expectln("SRVREADY");
 
-	send_size = send(fd, buf, sizeof(buf), 0);
-
-	if (send_size < 0) {
-		perror("send");
-		exit(EXIT_FAILURE);
-	}
-
-	if (send_size != sizeof(buf)) {
-		fprintf(stderr, "Invalid send size %zi\n", send_size);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
 
 	close(fd);
 }
@@ -386,7 +375,6 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 	msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE;
 
 	for (int i = 0; i < msg_count; i++) {
-		ssize_t send_size;
 		size_t buf_size;
 		int flags;
 		void *buf;
@@ -414,17 +402,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 			flags = 0;
 		}
 
-		send_size = send(fd, buf, buf_size, flags);
-
-		if (send_size < 0) {
-			perror("send");
-			exit(EXIT_FAILURE);
-		}
-
-		if (send_size != buf_size) {
-			fprintf(stderr, "Invalid send size\n");
-			exit(EXIT_FAILURE);
-		}
+		send_buf(fd, buf, buf_size, flags, buf_size);
 
 		/*
 		 * Hash sum is computed at both client and server in
@@ -525,10 +503,7 @@ static void test_seqpacket_msg_trunc_client(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	if (send(fd, buf, sizeof(buf), 0) != sizeof(buf)) {
-		perror("send failed");
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
 
 	control_writeln("SENDDONE");
 	close(fd);
@@ -650,7 +625,6 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts)
 static void test_seqpacket_bigmsg_client(const struct test_opts *opts)
 {
 	unsigned long sock_buf_size;
-	ssize_t send_size;
 	socklen_t len;
 	void *data;
 	int fd;
@@ -677,18 +651,7 @@ static void test_seqpacket_bigmsg_client(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	send_size = send(fd, data, sock_buf_size, 0);
-	if (send_size != -1) {
-		fprintf(stderr, "expected 'send(2)' failure, got %zi\n",
-			send_size);
-		exit(EXIT_FAILURE);
-	}
-
-	if (errno != EMSGSIZE) {
-		fprintf(stderr, "expected EMSGSIZE in 'errno', got %i\n",
-			errno);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, data, sock_buf_size, 0, -EMSGSIZE);
 
 	control_writeln("CLISENT");
 
@@ -742,15 +705,9 @@ static void test_seqpacket_invalid_rec_buffer_client(const struct test_opts *opt
 	memset(buf1, BUF_PATTERN_1, buf_size);
 	memset(buf2, BUF_PATTERN_2, buf_size);
 
-	if (send(fd, buf1, buf_size, 0) != buf_size) {
-		perror("send failed");
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, buf1, buf_size, 0, buf_size);
 
-	if (send(fd, buf2, buf_size, 0) != buf_size) {
-		perror("send failed");
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, buf2, buf_size, 0, buf_size);
 
 	close(fd);
 }
@@ -973,7 +930,6 @@ static void test_inv_buf_client(const struct test_opts *opts, bool stream)
 static void test_inv_buf_server(const struct test_opts *opts, bool stream)
 {
 	unsigned char data[INV_BUF_TEST_DATA_LEN] = {0};
-	ssize_t res;
 	int fd;
 
 	if (stream)
@@ -986,11 +942,7 @@ static void test_inv_buf_server(const struct test_opts *opts, bool stream)
 		exit(EXIT_FAILURE);
 	}
 
-	res = send(fd, data, sizeof(data), 0);
-	if (res != sizeof(data)) {
-		fprintf(stderr, "unexpected send(2) result %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, data, sizeof(data), 0, sizeof(data));
 
 	control_writeln("SENDDONE");
 
@@ -1024,7 +976,6 @@ static void test_seqpacket_inv_buf_server(const struct test_opts *opts)
 
 static void test_stream_virtio_skb_merge_client(const struct test_opts *opts)
 {
-	ssize_t res;
 	int fd;
 
 	fd = vsock_stream_connect(opts->peer_cid, 1234);
@@ -1034,22 +985,14 @@ static void test_stream_virtio_skb_merge_client(const struct test_opts *opts)
 	}
 
 	/* Send first skbuff. */
-	res = send(fd, HELLO_STR, strlen(HELLO_STR), 0);
-	if (res != strlen(HELLO_STR)) {
-		fprintf(stderr, "unexpected send(2) result %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, HELLO_STR, strlen(HELLO_STR), 0, strlen(HELLO_STR));
 
 	control_writeln("SEND0");
 	/* Peer reads part of first skbuff. */
 	control_expectln("REPLY0");
 
 	/* Send second skbuff, it will be appended to the first. */
-	res = send(fd, WORLD_STR, strlen(WORLD_STR), 0);
-	if (res != strlen(WORLD_STR)) {
-		fprintf(stderr, "unexpected send(2) result %zi\n", res);
-		exit(EXIT_FAILURE);
-	}
+	send_buf(fd, WORLD_STR, strlen(WORLD_STR), 0, strlen(WORLD_STR));
 
 	control_writeln("SEND1");
 	/* Peer reads merged skbuff packet. */
-- 
cgit v1.2.3


From bc7bea452d322b785d960fd20795babff664975c Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 15 Sep 2023 14:14:52 +0200
Subject: vsock/test: track bytes in sk_buff merging test for SOCK_SEQPACKET

The test was a bit complicated to read.
Added variables to keep track of the bytes read and to be read
in each step. Also some comments.

The test is unchanged.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/vsock_test.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 89d2cfaf7581..da4cb819a183 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -1003,6 +1003,7 @@ static void test_stream_virtio_skb_merge_client(const struct test_opts *opts)
 
 static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
 {
+	size_t read = 0, to_read;
 	unsigned char buf[64];
 	int fd;
 
@@ -1015,14 +1016,21 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
 	control_expectln("SEND0");
 
 	/* Read skbuff partially. */
-	recv_buf(fd, buf, 2, 0, 2);
+	to_read = 2;
+	recv_buf(fd, buf + read, to_read, 0, to_read);
+	read += to_read;
 
 	control_writeln("REPLY0");
 	control_expectln("SEND1");
 
-	recv_buf(fd, buf + 2, 8, 0, 8);
+	/* Read the rest of both buffers */
+	to_read = strlen(HELLO_STR WORLD_STR) - read;
+	recv_buf(fd, buf + read, to_read, 0, to_read);
+	read += to_read;
 
-	recv_buf(fd, buf, sizeof(buf) - 8 - 2, MSG_DONTWAIT, -EAGAIN);
+	/* No more bytes should be there */
+	to_read = sizeof(buf) - read;
+	recv_buf(fd, buf + read, to_read, MSG_DONTWAIT, -EAGAIN);
 
 	if (memcmp(buf, HELLO_STR WORLD_STR, strlen(HELLO_STR WORLD_STR))) {
 		fprintf(stderr, "pattern mismatch\n");
-- 
cgit v1.2.3


From 9c2a19f71515553a874e2bf31655ac2264a66e37 Mon Sep 17 00:00:00 2001
From: Daniel Mendes <dmendes@redhat.com>
Date: Tue, 12 Sep 2023 10:28:35 -0400
Subject: kselftest: rtnetlink.sh: add verbose flag

Uses a run_cmd helper function similar to other selftests to add
verbose functionality i.e. print executed commands and their outputs

Many commands silence or redirect output. This can be removed since
the verbose helper function captures output anyway and only outputs it
if VERBOSE is true. Similarly, the helper command for pipes to grep
searches stderr and stdout. This makes output redirection unnecessary
in those cases.

Signed-off-by: Daniel Mendes <dmendes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 962 ++++++++++++-------------------
 1 file changed, 381 insertions(+), 581 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 488f4964365e..daaf1bcc10ac 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -31,6 +31,7 @@ ALL_TESTS="
 "
 
 devdummy="test-dummy0"
+VERBOSE=0
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -51,35 +52,91 @@ check_fail()
 	fi
 }
 
+run_cmd_common()
+{
+	local cmd="$*"
+	local out
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: ${cmd}"
+	fi
+	out=$($cmd 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+	return $rc
+}
+
+run_cmd() {
+	run_cmd_common "$@"
+	rc=$?
+	check_err $rc
+	return $rc
+}
+run_cmd_fail()
+{
+	run_cmd_common "$@"
+	rc=$?
+	check_fail $rc
+	return $rc
+}
+
+run_cmd_grep_common()
+{
+	local find="$1"; shift
+	local cmd="$*"
+	local out
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: ${cmd} 2>&1 | grep -q '${find}'"
+	fi
+	out=$($cmd 2>&1 | grep -q "${find}" 2>&1)
+	return $?
+}
+
+run_cmd_grep() {
+	run_cmd_grep_common "$@"
+	rc=$?
+	check_err $rc
+	return $rc
+}
+
+run_cmd_grep_fail()
+{
+	run_cmd_grep_common "$@"
+	rc=$?
+	check_fail $rc
+	return $rc
+}
+
+end_test()
+{
+	echo "$*"
+	[ "${VERBOSE}" = "1" ] && echo
+}
+
+
 kci_add_dummy()
 {
-	ip link add name "$devdummy" type dummy
-	check_err $?
-	ip link set "$devdummy" up
-	check_err $?
+	run_cmd ip link add name "$devdummy" type dummy
+	run_cmd ip link set "$devdummy" up
 }
 
 kci_del_dummy()
 {
-	ip link del dev "$devdummy"
-	check_err $?
+	run_cmd ip link del dev "$devdummy"
 }
 
 kci_test_netconf()
 {
 	dev="$1"
 	r=$ret
-
-	ip netconf show dev "$dev" > /dev/null
-	check_err $?
-
+	run_cmd ip netconf show dev "$dev"
 	for f in 4 6; do
-		ip -$f netconf show dev "$dev" > /dev/null
-		check_err $?
+		run_cmd ip -$f netconf show dev "$dev"
 	done
 
 	if [ $ret -ne 0 ] ;then
-		echo "FAIL: ip netconf show $dev"
+		end_test "FAIL: ip netconf show $dev"
 		test $r -eq 0 && ret=0
 		return 1
 	fi
@@ -92,43 +149,27 @@ kci_test_bridge()
 	vlandev="testbr-vlan1"
 
 	local ret=0
-	ip link add name "$devbr" type bridge
-	check_err $?
-
-	ip link set dev "$devdummy" master "$devbr"
-	check_err $?
-
-	ip link set "$devbr" up
-	check_err $?
-
-	ip link add link "$devbr" name "$vlandev" type vlan id 1
-	check_err $?
-	ip addr add dev "$vlandev" 10.200.7.23/30
-	check_err $?
-	ip -6 addr add dev "$vlandev" dead:42::1234/64
-	check_err $?
-	ip -d link > /dev/null
-	check_err $?
-	ip r s t all > /dev/null
-	check_err $?
+	run_cmd ip link add name "$devbr" type bridge
+	run_cmd ip link set dev "$devdummy" master "$devbr"
+	run_cmd ip link set "$devbr" up
+	run_cmd ip link add link "$devbr" name "$vlandev" type vlan id 1
+	run_cmd ip addr add dev "$vlandev" 10.200.7.23/30
+	run_cmd ip -6 addr add dev "$vlandev" dead:42::1234/64
+	run_cmd ip -d link
+	run_cmd ip r s t all
 
 	for name in "$devbr" "$vlandev" "$devdummy" ; do
 		kci_test_netconf "$name"
 	done
-
-	ip -6 addr del dev "$vlandev" dead:42::1234/64
-	check_err $?
-
-	ip link del dev "$vlandev"
-	check_err $?
-	ip link del dev "$devbr"
-	check_err $?
+	run_cmd ip -6 addr del dev "$vlandev" dead:42::1234/64
+	run_cmd ip link del dev "$vlandev"
+	run_cmd ip link del dev "$devbr"
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: bridge setup"
+		end_test "FAIL: bridge setup"
 		return 1
 	fi
-	echo "PASS: bridge setup"
+	end_test "PASS: bridge setup"
 
 }
 
@@ -139,34 +180,23 @@ kci_test_gre()
 	loc=10.0.0.1
 
 	local ret=0
-	ip tunnel add $gredev mode gre remote $rem local $loc ttl 1
-	check_err $?
-	ip link set $gredev up
-	check_err $?
-	ip addr add 10.23.7.10 dev $gredev
-	check_err $?
-	ip route add 10.23.8.0/30 dev $gredev
-	check_err $?
-	ip addr add dev "$devdummy" 10.23.7.11/24
-	check_err $?
-	ip link > /dev/null
-	check_err $?
-	ip addr > /dev/null
-	check_err $?
+	run_cmd ip tunnel add $gredev mode gre remote $rem local $loc ttl 1
+	run_cmd ip link set $gredev up
+	run_cmd ip addr add 10.23.7.10 dev $gredev
+	run_cmd ip route add 10.23.8.0/30 dev $gredev
+	run_cmd ip addr add dev "$devdummy" 10.23.7.11/24
+	run_cmd ip link
+	run_cmd ip addr
 
 	kci_test_netconf "$gredev"
-
-	ip addr del dev "$devdummy" 10.23.7.11/24
-	check_err $?
-
-	ip link del $gredev
-	check_err $?
+	run_cmd ip addr del dev "$devdummy" 10.23.7.11/24
+	run_cmd ip link del $gredev
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: gre tunnel endpoint"
+		end_test "FAIL: gre tunnel endpoint"
 		return 1
 	fi
-	echo "PASS: gre tunnel endpoint"
+	end_test "PASS: gre tunnel endpoint"
 }
 
 # tc uses rtnetlink too, for full tc testing
@@ -176,56 +206,40 @@ kci_test_tc()
 	dev=lo
 	local ret=0
 
-	tc qdisc add dev "$dev" root handle 1: htb
-	check_err $?
-	tc class add dev "$dev" parent 1: classid 1:10 htb rate 1mbit
-	check_err $?
-	tc filter add dev "$dev" parent 1:0 prio 5 handle ffe: protocol ip u32 divisor 256
-	check_err $?
-	tc filter add dev "$dev" parent 1:0 prio 5 handle ffd: protocol ip u32 divisor 256
-	check_err $?
-	tc filter add dev "$dev" parent 1:0 prio 5 handle ffc: protocol ip u32 divisor 256
-	check_err $?
-	tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 ht ffe:2: match ip src 10.0.0.3 flowid 1:10
-	check_err $?
-	tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:2 u32 ht ffe:2: match ip src 10.0.0.2 flowid 1:10
-	check_err $?
-	tc filter show dev "$dev" parent  1:0 > /dev/null
-	check_err $?
-	tc filter del dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32
-	check_err $?
-	tc filter show dev "$dev" parent  1:0 > /dev/null
-	check_err $?
-	tc qdisc del dev "$dev" root handle 1: htb
-	check_err $?
+	run_cmd tc qdisc add dev "$dev" root handle 1: htb
+	run_cmd tc class add dev "$dev" parent 1: classid 1:10 htb rate 1mbit
+	run_cmd tc filter add dev "$dev" parent 1:0 prio 5 handle ffe: protocol ip u32 divisor 256
+	run_cmd tc filter add dev "$dev" parent 1:0 prio 5 handle ffd: protocol ip u32 divisor 256
+	run_cmd tc filter add dev "$dev" parent 1:0 prio 5 handle ffc: protocol ip u32 divisor 256
+	run_cmd tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 ht ffe:2: match ip src 10.0.0.3 flowid 1:10
+	run_cmd tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:2 u32 ht ffe:2: match ip src 10.0.0.2 flowid 1:10
+	run_cmd tc filter show dev "$dev" parent  1:0
+	run_cmd tc filter del dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32
+	run_cmd tc filter show dev "$dev" parent  1:0
+	run_cmd tc qdisc del dev "$dev" root handle 1: htb
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: tc htb hierarchy"
+		end_test "FAIL: tc htb hierarchy"
 		return 1
 	fi
-	echo "PASS: tc htb hierarchy"
+	end_test "PASS: tc htb hierarchy"
 
 }
 
 kci_test_polrouting()
 {
 	local ret=0
-	ip rule add fwmark 1 lookup 100
-	check_err $?
-	ip route add local 0.0.0.0/0 dev lo table 100
-	check_err $?
-	ip r s t all > /dev/null
-	check_err $?
-	ip rule del fwmark 1 lookup 100
-	check_err $?
-	ip route del local 0.0.0.0/0 dev lo table 100
-	check_err $?
+	run_cmd ip rule add fwmark 1 lookup 100
+	run_cmd ip route add local 0.0.0.0/0 dev lo table 100
+	run_cmd ip r s t all
+	run_cmd ip rule del fwmark 1 lookup 100
+	run_cmd ip route del local 0.0.0.0/0 dev lo table 100
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: policy route test"
+		end_test "FAIL: policy route test"
 		return 1
 	fi
-	echo "PASS: policy routing"
+	end_test "PASS: policy routing"
 }
 
 kci_test_route_get()
@@ -233,65 +247,51 @@ kci_test_route_get()
 	local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
 
 	local ret=0
-
-	ip route get 127.0.0.1 > /dev/null
-	check_err $?
-	ip route get 127.0.0.1 dev "$devdummy" > /dev/null
-	check_err $?
-	ip route get ::1 > /dev/null
-	check_err $?
-	ip route get fe80::1 dev "$devdummy" > /dev/null
-	check_err $?
-	ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1 > /dev/null
-	check_err $?
-	ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1 > /dev/null
-	check_err $?
-	ip addr add dev "$devdummy" 10.23.7.11/24
-	check_err $?
-	ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null
-	check_err $?
-	ip route add 10.23.8.0/24 \
+	run_cmd ip route get 127.0.0.1
+	run_cmd ip route get 127.0.0.1 dev "$devdummy"
+	run_cmd ip route get ::1
+	run_cmd ip route get fe80::1 dev "$devdummy"
+	run_cmd ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1
+	run_cmd ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1
+	run_cmd ip addr add dev "$devdummy" 10.23.7.11/24
+	run_cmd ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy"
+	run_cmd ip route add 10.23.8.0/24 \
 		nexthop via 10.23.7.13 dev "$devdummy" \
 		nexthop via 10.23.7.14 dev "$devdummy"
-	check_err $?
+
 	sysctl -wq net.ipv4.fib_multipath_hash_policy=0
-	ip route get 10.23.8.11 > /dev/null
-	check_err $?
+	run_cmd ip route get 10.23.8.11
 	sysctl -wq net.ipv4.fib_multipath_hash_policy=1
-	ip route get 10.23.8.11 > /dev/null
-	check_err $?
+	run_cmd ip route get 10.23.8.11
 	sysctl -wq net.ipv4.fib_multipath_hash_policy="$hash_policy"
-	ip route del 10.23.8.0/24
-	check_err $?
-	ip addr del dev "$devdummy" 10.23.7.11/24
-	check_err $?
+	run_cmd ip route del 10.23.8.0/24
+	run_cmd ip addr del dev "$devdummy" 10.23.7.11/24
+
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: route get"
+		end_test "FAIL: route get"
 		return 1
 	fi
 
-	echo "PASS: route get"
+	end_test "PASS: route get"
 }
 
 kci_test_addrlft()
 {
 	for i in $(seq 10 100) ;do
 		lft=$(((RANDOM%3) + 1))
-		ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1))
-		check_err $?
+		run_cmd ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1))
 	done
 
 	sleep 5
-
-	ip addr show dev "$devdummy" | grep "10.23.11."
+	run_cmd_grep "10.23.11." ip addr show dev "$devdummy"
 	if [ $? -eq 0 ]; then
-		echo "FAIL: preferred_lft addresses remaining"
+		end_test "FAIL: preferred_lft addresses remaining"
 		check_err 1
 		return
 	fi
 
-	echo "PASS: preferred_lft addresses have expired"
+	end_test "PASS: preferred_lft addresses have expired"
 }
 
 kci_test_promote_secondaries()
@@ -310,27 +310,17 @@ kci_test_promote_secondaries()
 
 	[ $promote -eq 0 ] && sysctl -q net.ipv4.conf.$devdummy.promote_secondaries=0
 
-	echo "PASS: promote_secondaries complete"
+	end_test "PASS: promote_secondaries complete"
 }
 
 kci_test_addrlabel()
 {
 	local ret=0
-
-	ip addrlabel add prefix dead::/64 dev lo label 1
-	check_err $?
-
-	ip addrlabel list |grep -q "prefix dead::/64 dev lo label 1"
-	check_err $?
-
-	ip addrlabel del prefix dead::/64 dev lo label 1 2> /dev/null
-	check_err $?
-
-	ip addrlabel add prefix dead::/64 label 1 2> /dev/null
-	check_err $?
-
-	ip addrlabel del prefix dead::/64 label 1 2> /dev/null
-	check_err $?
+	run_cmd ip addrlabel add prefix dead::/64 dev lo label 1
+	run_cmd_grep "prefix dead::/64 dev lo label 1" ip addrlabel list
+	run_cmd ip addrlabel del prefix dead::/64 dev lo label 1
+	run_cmd ip addrlabel add prefix dead::/64 label 1
+	run_cmd ip addrlabel del prefix dead::/64 label 1
 
 	# concurrent add/delete
 	for i in $(seq 1 1000); do
@@ -346,11 +336,11 @@ kci_test_addrlabel()
 	ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: ipv6 addrlabel"
+		end_test "FAIL: ipv6 addrlabel"
 		return 1
 	fi
 
-	echo "PASS: ipv6 addrlabel"
+	end_test "PASS: ipv6 addrlabel"
 }
 
 kci_test_ifalias()
@@ -358,35 +348,28 @@ kci_test_ifalias()
 	local ret=0
 	namewant=$(uuidgen)
 	syspathname="/sys/class/net/$devdummy/ifalias"
-
-	ip link set dev "$devdummy" alias "$namewant"
-	check_err $?
+	run_cmd ip link set dev "$devdummy" alias "$namewant"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: cannot set interface alias of $devdummy to $namewant"
+		end_test "FAIL: cannot set interface alias of $devdummy to $namewant"
 		return 1
 	fi
-
-	ip link show "$devdummy" | grep -q "alias $namewant"
-	check_err $?
+	run_cmd_grep "alias $namewant" ip link show "$devdummy"
 
 	if [ -r "$syspathname" ] ; then
 		read namehave < "$syspathname"
 		if [ "$namewant" != "$namehave" ]; then
-			echo "FAIL: did set ifalias $namewant but got $namehave"
+			end_test "FAIL: did set ifalias $namewant but got $namehave"
 			return 1
 		fi
 
 		namewant=$(uuidgen)
 		echo "$namewant" > "$syspathname"
-	        ip link show "$devdummy" | grep -q "alias $namewant"
-		check_err $?
+	        run_cmd_grep "alias $namewant" ip link show "$devdummy"
 
 		# sysfs interface allows to delete alias again
 		echo "" > "$syspathname"
-
-	        ip link show "$devdummy" | grep -q "alias $namewant"
-		check_fail $?
+	        run_cmd_grep_fail "alias $namewant" ip link show "$devdummy"
 
 		for i in $(seq 1 100); do
 			uuidgen > "$syspathname" &
@@ -395,57 +378,48 @@ kci_test_ifalias()
 		wait
 
 		# re-add the alias -- kernel should free mem when dummy dev is removed
-		ip link set dev "$devdummy" alias "$namewant"
-		check_err $?
+		run_cmd ip link set dev "$devdummy" alias "$namewant"
+
 	fi
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: set interface alias $devdummy to $namewant"
+		end_test "FAIL: set interface alias $devdummy to $namewant"
 		return 1
 	fi
 
-	echo "PASS: set ifalias $namewant for $devdummy"
+	end_test "PASS: set ifalias $namewant for $devdummy"
 }
 
 kci_test_vrf()
 {
 	vrfname="test-vrf"
 	local ret=0
-
-	ip link show type vrf 2>/dev/null
+	run_cmd ip link show type vrf
 	if [ $? -ne 0 ]; then
-		echo "SKIP: vrf: iproute2 too old"
+		end_test "SKIP: vrf: iproute2 too old"
 		return $ksft_skip
 	fi
-
-	ip link add "$vrfname" type vrf table 10
-	check_err $?
+	run_cmd ip link add "$vrfname" type vrf table 10
 	if [ $ret -ne 0 ];then
-		echo "FAIL: can't add vrf interface, skipping test"
+		end_test "FAIL: can't add vrf interface, skipping test"
 		return 0
 	fi
-
-	ip -br link show type vrf | grep -q "$vrfname"
-	check_err $?
+	run_cmd_grep "$vrfname" ip -br link show type vrf
 	if [ $ret -ne 0 ];then
-		echo "FAIL: created vrf device not found"
+		end_test "FAIL: created vrf device not found"
 		return 1
 	fi
 
-	ip link set dev "$vrfname" up
-	check_err $?
-
-	ip link set dev "$devdummy" master "$vrfname"
-	check_err $?
-	ip link del dev "$vrfname"
-	check_err $?
+	run_cmd ip link set dev "$vrfname" up
+	run_cmd ip link set dev "$devdummy" master "$vrfname"
+	run_cmd ip link del dev "$vrfname"
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: vrf"
+		end_test "FAIL: vrf"
 		return 1
 	fi
 
-	echo "PASS: vrf"
+	end_test "PASS: vrf"
 }
 
 kci_test_encap_vxlan()
@@ -454,84 +428,44 @@ kci_test_encap_vxlan()
 	vxlan="test-vxlan0"
 	vlan="test-vlan0"
 	testns="$1"
-
-	ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
-		dev "$devdummy" dstport 4789 2>/dev/null
+	run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
+		dev "$devdummy" dstport 4789
 	if [ $? -ne 0 ]; then
-		echo "FAIL: can't add vxlan interface, skipping test"
+		end_test "FAIL: can't add vxlan interface, skipping test"
 		return 0
 	fi
-	check_err $?
-
-	ip -netns "$testns" addr add 10.2.11.49/24 dev "$vxlan"
-	check_err $?
 
-	ip -netns "$testns" link set up dev "$vxlan"
-	check_err $?
-
-	ip -netns "$testns" link add link "$vxlan" name "$vlan" type vlan id 1
-	check_err $?
+	run_cmd ip -netns "$testns" addr add 10.2.11.49/24 dev "$vxlan"
+	run_cmd ip -netns "$testns" link set up dev "$vxlan"
+	run_cmd ip -netns "$testns" link add link "$vxlan" name "$vlan" type vlan id 1
 
 	# changelink testcases
-	ip -netns "$testns" link set dev "$vxlan" type vxlan vni 43 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan group ffe5::5 dev "$devdummy" 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan ttl inherit 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan ttl 64
-	check_err $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan nolearning
-	check_err $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan proxy 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan norsc 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan l2miss 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan l3miss 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan external 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan udpcsum 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumtx 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumrx 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumtx 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumrx 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan gbp 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link set dev "$vxlan" type vxlan gpe 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" link del "$vxlan"
-	check_err $?
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan vni 43
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan group ffe5::5 dev "$devdummy"
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan ttl inherit
+
+	run_cmd ip -netns "$testns" link set dev "$vxlan" type vxlan ttl 64
+	run_cmd ip -netns "$testns" link set dev "$vxlan" type vxlan nolearning
+
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan proxy
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan norsc
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan l2miss
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan l3miss
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan external
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan udpcsum
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumtx
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan udp6zerocsumrx
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumtx
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan remcsumrx
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan gbp
+	run_cmd_fail ip -netns "$testns" link set dev "$vxlan" type vxlan gpe
+	run_cmd ip -netns "$testns" link del "$vxlan"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: vxlan"
+		end_test "FAIL: vxlan"
 		return 1
 	fi
-	echo "PASS: vxlan"
+	end_test "PASS: vxlan"
 }
 
 kci_test_encap_fou()
@@ -539,39 +473,32 @@ kci_test_encap_fou()
 	local ret=0
 	name="test-fou"
 	testns="$1"
-
-	ip fou help 2>&1 |grep -q 'Usage: ip fou'
+	run_cmd_grep 'Usage: ip fou' ip fou help
 	if [ $? -ne 0 ];then
-		echo "SKIP: fou: iproute2 too old"
+		end_test "SKIP: fou: iproute2 too old"
 		return $ksft_skip
 	fi
 
 	if ! /sbin/modprobe -q -n fou; then
-		echo "SKIP: module fou is not found"
+		end_test "SKIP: module fou is not found"
 		return $ksft_skip
 	fi
 	/sbin/modprobe -q fou
-	ip -netns "$testns" fou add port 7777 ipproto 47 2>/dev/null
+
+	run_cmd ip -netns "$testns" fou add port 7777 ipproto 47
 	if [ $? -ne 0 ];then
-		echo "FAIL: can't add fou port 7777, skipping test"
+		end_test "FAIL: can't add fou port 7777, skipping test"
 		return 1
 	fi
-
-	ip -netns "$testns" fou add port 8888 ipproto 4
-	check_err $?
-
-	ip -netns "$testns" fou del port 9999 2>/dev/null
-	check_fail $?
-
-	ip -netns "$testns" fou del port 7777
-	check_err $?
-
+	run_cmd ip -netns "$testns" fou add port 8888 ipproto 4
+	run_cmd_fail ip -netns "$testns" fou del port 9999
+	run_cmd ip -netns "$testns" fou del port 7777
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: fou"
+		end_test "FAIL: fou"s
 		return 1
 	fi
 
-	echo "PASS: fou"
+	end_test "PASS: fou"
 }
 
 # test various encap methods, use netns to avoid unwanted interference
@@ -579,25 +506,16 @@ kci_test_encap()
 {
 	testns="testns"
 	local ret=0
-
-	ip netns add "$testns"
+	run_cmd ip netns add "$testns"
 	if [ $? -ne 0 ]; then
-		echo "SKIP encap tests: cannot add net namespace $testns"
+		end_test "SKIP encap tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
-
-	ip -netns "$testns" link set lo up
-	check_err $?
-
-	ip -netns "$testns" link add name "$devdummy" type dummy
-	check_err $?
-	ip -netns "$testns" link set "$devdummy" up
-	check_err $?
-
-	kci_test_encap_vxlan "$testns"
-	check_err $?
-	kci_test_encap_fou "$testns"
-	check_err $?
+	run_cmd ip -netns "$testns" link set lo up
+	run_cmd ip -netns "$testns" link add name "$devdummy" type dummy
+	run_cmd ip -netns "$testns" link set "$devdummy" up
+	run_cmd kci_test_encap_vxlan "$testns"
+	run_cmd kci_test_encap_fou "$testns"
 
 	ip netns del "$testns"
 	return $ret
@@ -607,41 +525,28 @@ kci_test_macsec()
 {
 	msname="test_macsec0"
 	local ret=0
-
-	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+	run_cmd_grep "^Usage: ip macsec" ip macsec help
 	if [ $? -ne 0 ]; then
-		echo "SKIP: macsec: iproute2 too old"
+		end_test "SKIP: macsec: iproute2 too old"
 		return $ksft_skip
 	fi
-
-	ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
-	check_err $?
+	run_cmd ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
 	if [ $ret -ne 0 ];then
-		echo "FAIL: can't add macsec interface, skipping test"
+		end_test "FAIL: can't add macsec interface, skipping test"
 		return 1
 	fi
-
-	ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
-	check_err $?
-
-	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
-	check_err $?
-
-	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef
-	check_err $?
-
-	ip macsec show > /dev/null
-	check_err $?
-
-	ip link del dev "$msname"
-	check_err $?
+	run_cmd ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef
+	run_cmd ip macsec show
+	run_cmd ip link del dev "$msname"
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: macsec"
+		end_test "FAIL: macsec"
 		return 1
 	fi
 
-	echo "PASS: macsec"
+	end_test "PASS: macsec"
 }
 
 kci_test_macsec_offload()
@@ -650,19 +555,18 @@ kci_test_macsec_offload()
 	sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/
 	probed=false
 	local ret=0
-
-	ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+	run_cmd_grep "^Usage: ip macsec" ip macsec help
 	if [ $? -ne 0 ]; then
-		echo "SKIP: macsec: iproute2 too old"
+		end_test "SKIP: macsec: iproute2 too old"
 		return $ksft_skip
 	fi
 
 	# setup netdevsim since dummydev doesn't have offload support
 	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
-		modprobe -q netdevsim
-		check_err $?
+		run_cmd modprobe -q netdevsim
+
 		if [ $ret -ne 0 ]; then
-			echo "SKIP: macsec_offload can't load netdevsim"
+			end_test "SKIP: macsec_offload can't load netdevsim"
 			return $ksft_skip
 		fi
 		probed=true
@@ -675,43 +579,25 @@ kci_test_macsec_offload()
 
 	ip link set $dev up
 	if [ ! -d $sysfsd ] ; then
-		echo "FAIL: macsec_offload can't create device $dev"
+		end_test "FAIL: macsec_offload can't create device $dev"
 		return 1
 	fi
-
-	ethtool -k $dev | grep -q 'macsec-hw-offload: on'
+	run_cmd_grep 'macsec-hw-offload: on' ethtool -k $dev
 	if [ $? -eq 1 ] ; then
-		echo "FAIL: macsec_offload netdevsim doesn't support MACsec offload"
+		end_test "FAIL: macsec_offload netdevsim doesn't support MACsec offload"
 		return 1
 	fi
-
-	ip link add link $dev kci_macsec1 type macsec port 4 offload mac
-	check_err $?
-
-	ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
-	check_err $?
-
-	ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac
-	check_err $?
-
-	ip link add link $dev kci_macsec4 type macsec port 8 offload mac 2> /dev/null
-	check_fail $?
+	run_cmd ip link add link $dev kci_macsec1 type macsec port 4 offload mac
+	run_cmd ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
+	run_cmd ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac
+	run_cmd_fail ip link add link $dev kci_macsec4 type macsec port 8 offload mac
 
 	msname=kci_macsec1
-
-	ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
-	check_err $?
-
-	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
-	check_err $?
-
-	ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
+	run_cmd ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+	run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
 		key 00 0123456789abcdef0123456789abcdef
-	check_err $?
-
-	ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null
-	check_fail $?
-
+	run_cmd_fail ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef"
 	# clean up any leftovers
 	for msdev in kci_macsec{1,2,3,4} ; do
 	    ip link del $msdev 2> /dev/null
@@ -720,10 +606,10 @@ kci_test_macsec_offload()
 	$probed && rmmod netdevsim
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: macsec_offload"
+		end_test "FAIL: macsec_offload"
 		return 1
 	fi
-	echo "PASS: macsec_offload"
+	end_test "PASS: macsec_offload"
 }
 
 #-------------------------------------------------------------------
@@ -755,8 +641,7 @@ kci_test_ipsec()
 	ip addr add $srcip dev $devdummy
 
 	# flush to be sure there's nothing configured
-	ip x s flush ; ip x p flush
-	check_err $?
+	run_cmd ip x s flush ; ip x p flush
 
 	# start the monitor in the background
 	tmpfile=`mktemp /var/run/ipsectestXXX`
@@ -764,72 +649,57 @@ kci_test_ipsec()
 	sleep 0.2
 
 	ipsecid="proto esp src $srcip dst $dstip spi 0x07"
-	ip x s add $ipsecid \
+	run_cmd ip x s add $ipsecid \
             mode transport reqid 0x07 replay-window 32 \
             $algo sel src $srcip/24 dst $dstip/24
-	check_err $?
 
-	lines=`ip x s list | grep $srcip | grep $dstip | wc -l`
-	test $lines -eq 2
-	check_err $?
 
-	ip x s count | grep -q "SAD count 1"
-	check_err $?
+	lines=`ip x s list | grep $srcip | grep $dstip | wc -l`
+	run_cmd test $lines -eq 2
+	run_cmd_grep "SAD count 1" ip x s count
 
 	lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l`
-	test $lines -eq 2
-	check_err $?
-
-	ip x s delete $ipsecid
-	check_err $?
+	run_cmd test $lines -eq 2
+	run_cmd ip x s delete $ipsecid
 
 	lines=`ip x s list | wc -l`
-	test $lines -eq 0
-	check_err $?
+	run_cmd test $lines -eq 0
 
 	ipsecsel="dir out src $srcip/24 dst $dstip/24"
-	ip x p add $ipsecsel \
+	run_cmd ip x p add $ipsecsel \
 		    tmpl proto esp src $srcip dst $dstip \
 		    spi 0x07 mode transport reqid 0x07
-	check_err $?
+
 
 	lines=`ip x p list | grep $srcip | grep $dstip | wc -l`
-	test $lines -eq 2
-	check_err $?
+	run_cmd test $lines -eq 2
 
-	ip x p count | grep -q "SPD IN  0 OUT 1 FWD 0"
-	check_err $?
+	run_cmd_grep "SPD IN  0 OUT 1 FWD 0" ip x p count
 
 	lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l`
-	test $lines -eq 2
-	check_err $?
+	run_cmd test $lines -eq 2
 
-	ip x p delete $ipsecsel
-	check_err $?
+	run_cmd ip x p delete $ipsecsel
 
 	lines=`ip x p list | wc -l`
-	test $lines -eq 0
-	check_err $?
+	run_cmd test $lines -eq 0
 
 	# check the monitor results
 	kill $mpid
 	lines=`wc -l $tmpfile | cut "-d " -f1`
-	test $lines -eq 20
-	check_err $?
+	run_cmd test $lines -eq 20
 	rm -rf $tmpfile
 
 	# clean up any leftovers
-	ip x s flush
-	check_err $?
-	ip x p flush
-	check_err $?
+	run_cmd ip x s flush
+	run_cmd ip x p flush
 	ip addr del $srcip/32 dev $devdummy
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: ipsec"
+		end_test "FAIL: ipsec"
 		return 1
 	fi
-	echo "PASS: ipsec"
+	end_test "PASS: ipsec"
 }
 
 #-------------------------------------------------------------------
@@ -857,10 +727,9 @@ kci_test_ipsec_offload()
 
 	# setup netdevsim since dummydev doesn't have offload support
 	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
-		modprobe -q netdevsim
-		check_err $?
+		run_cmd modprobe -q netdevsim
 		if [ $ret -ne 0 ]; then
-			echo "SKIP: ipsec_offload can't load netdevsim"
+			end_test "SKIP: ipsec_offload can't load netdevsim"
 			return $ksft_skip
 		fi
 		probed=true
@@ -874,11 +743,11 @@ kci_test_ipsec_offload()
 	ip addr add $srcip dev $dev
 	ip link set $dev up
 	if [ ! -d $sysfsd ] ; then
-		echo "FAIL: ipsec_offload can't create device $dev"
+		end_test "FAIL: ipsec_offload can't create device $dev"
 		return 1
 	fi
 	if [ ! -f $sysfsf ] ; then
-		echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload"
+		end_test "FAIL: ipsec_offload netdevsim doesn't support IPsec offload"
 		return 1
 	fi
 
@@ -886,32 +755,31 @@ kci_test_ipsec_offload()
 	ip x s flush ; ip x p flush
 
 	# create offloaded SAs, both in and out
-	ip x p add dir out src $srcip/24 dst $dstip/24 \
+	run_cmd ip x p add dir out src $srcip/24 dst $dstip/24 \
 	    tmpl proto esp src $srcip dst $dstip spi 9 \
 	    mode transport reqid 42
-	check_err $?
-	ip x p add dir in src $dstip/24 dst $srcip/24 \
+
+	run_cmd ip x p add dir in src $dstip/24 dst $srcip/24 \
 	    tmpl proto esp src $dstip dst $srcip spi 9 \
 	    mode transport reqid 42
-	check_err $?
 
-	ip x s add proto esp src $srcip dst $dstip spi 9 \
+	run_cmd ip x s add proto esp src $srcip dst $dstip spi 9 \
 	    mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \
 	    offload dev $dev dir out
-	check_err $?
-	ip x s add proto esp src $dstip dst $srcip spi 9 \
+
+	run_cmd ip x s add proto esp src $dstip dst $srcip spi 9 \
 	    mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \
 	    offload dev $dev dir in
-	check_err $?
+
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: ipsec_offload can't create SA"
+		end_test "FAIL: ipsec_offload can't create SA"
 		return 1
 	fi
 
 	# does offload show up in ip output
 	lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"`
 	if [ $lines -ne 2 ] ; then
-		echo "FAIL: ipsec_offload SA offload missing from list output"
+		end_test "FAIL: ipsec_offload SA offload missing from list output"
 		check_err 1
 	fi
 
@@ -919,7 +787,7 @@ kci_test_ipsec_offload()
 	ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null
 
 	# does driver have correct offload info
-	diff $sysfsf - << EOF
+	run_cmd diff $sysfsf - << EOF
 SA count=2 tx=3
 sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000
 sa[0]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
@@ -929,7 +797,7 @@ sa[1]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
 sa[1]    key=0x34333231 38373635 32313039 36353433
 EOF
 	if [ $? -ne 0 ] ; then
-		echo "FAIL: ipsec_offload incorrect driver data"
+		end_test "FAIL: ipsec_offload incorrect driver data"
 		check_err 1
 	fi
 
@@ -938,7 +806,7 @@ EOF
 	ip x p flush
 	lines=`grep -c "SA count=0" $sysfsf`
 	if [ $lines -ne 1 ] ; then
-		echo "FAIL: ipsec_offload SA not removed from driver"
+		end_test "FAIL: ipsec_offload SA not removed from driver"
 		check_err 1
 	fi
 
@@ -947,10 +815,10 @@ EOF
 	$probed && rmmod netdevsim
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: ipsec_offload"
+		end_test "FAIL: ipsec_offload"
 		return 1
 	fi
-	echo "PASS: ipsec_offload"
+	end_test "PASS: ipsec_offload"
 }
 
 kci_test_gretap()
@@ -959,46 +827,38 @@ kci_test_gretap()
 	DEV_NS=gretap00
 	local ret=0
 
-	ip netns add "$testns"
+	run_cmd ip netns add "$testns"
 	if [ $? -ne 0 ]; then
-		echo "SKIP gretap tests: cannot add net namespace $testns"
+		end_test "SKIP gretap tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
 
-	ip link help gretap 2>&1 | grep -q "^Usage:"
+	run_cmd_grep "^Usage:" ip link help gretap
 	if [ $? -ne 0 ];then
-		echo "SKIP: gretap: iproute2 too old"
+		end_test "SKIP: gretap: iproute2 too old"
 		ip netns del "$testns"
 		return $ksft_skip
 	fi
 
 	# test native tunnel
-	ip -netns "$testns" link add dev "$DEV_NS" type gretap seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type gretap seq \
 		key 102 local 172.16.1.100 remote 172.16.1.200
-	check_err $?
-
-	ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	check_err $?
 
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
 
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
+	run_cmd ip -netns "$testns" link set dev $DEV_NS ups
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
-	ip -netns "$testns" link add dev "$DEV_NS" type gretap external
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type gretap external
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: gretap"
+		end_test "FAIL: gretap"
 		ip netns del "$testns"
 		return 1
 	fi
-	echo "PASS: gretap"
+	end_test "PASS: gretap"
 
 	ip netns del "$testns"
 }
@@ -1009,46 +869,38 @@ kci_test_ip6gretap()
 	DEV_NS=ip6gretap00
 	local ret=0
 
-	ip netns add "$testns"
+	run_cmd ip netns add "$testns"
 	if [ $? -ne 0 ]; then
-		echo "SKIP ip6gretap tests: cannot add net namespace $testns"
+		end_test "SKIP ip6gretap tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
 
-	ip link help ip6gretap 2>&1 | grep -q "^Usage:"
+	run_cmd_grep "^Usage:" ip link help ip6gretap
 	if [ $? -ne 0 ];then
-		echo "SKIP: ip6gretap: iproute2 too old"
+		end_test "SKIP: ip6gretap: iproute2 too old"
 		ip netns del "$testns"
 		return $ksft_skip
 	fi
 
 	# test native tunnel
-	ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap seq \
 		key 102 local fc00:100::1 remote fc00:100::2
-	check_err $?
 
-	ip -netns "$testns" addr add dev "$DEV_NS" fc00:200::1/96
-	check_err $?
 
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" fc00:200::1/96
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
-	ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap external
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type ip6gretap external
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: ip6gretap"
+		end_test "FAIL: ip6gretap"
 		ip netns del "$testns"
 		return 1
 	fi
-	echo "PASS: ip6gretap"
+	end_test "PASS: ip6gretap"
 
 	ip netns del "$testns"
 }
@@ -1058,62 +910,47 @@ kci_test_erspan()
 	testns="testns"
 	DEV_NS=erspan00
 	local ret=0
-
-	ip link help erspan 2>&1 | grep -q "^Usage:"
+	run_cmd_grep "^Usage:" ip link help erspan
 	if [ $? -ne 0 ];then
-		echo "SKIP: erspan: iproute2 too old"
+		end_test "SKIP: erspan: iproute2 too old"
 		return $ksft_skip
 	fi
-
-	ip netns add "$testns"
+	run_cmd ip netns add "$testns"
 	if [ $? -ne 0 ]; then
-		echo "SKIP erspan tests: cannot add net namespace $testns"
+		end_test "SKIP erspan tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
 
 	# test native tunnel erspan v1
-	ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \
 		key 102 local 172.16.1.100 remote 172.16.1.200 \
 		erspan_ver 1 erspan 488
-	check_err $?
 
-	ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	check_err $?
 
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test native tunnel erspan v2
-	ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type erspan seq \
 		key 102 local 172.16.1.100 remote 172.16.1.200 \
 		erspan_ver 2 erspan_dir ingress erspan_hwid 7
-	check_err $?
-
-	ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	check_err $?
 
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
 
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
-	ip -netns "$testns" link add dev "$DEV_NS" type erspan external
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type erspan external
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: erspan"
+		end_test "FAIL: erspan"
 		ip netns del "$testns"
 		return 1
 	fi
-	echo "PASS: erspan"
+	end_test "PASS: erspan"
 
 	ip netns del "$testns"
 }
@@ -1123,63 +960,49 @@ kci_test_ip6erspan()
 	testns="testns"
 	DEV_NS=ip6erspan00
 	local ret=0
-
-	ip link help ip6erspan 2>&1 | grep -q "^Usage:"
+	run_cmd_grep "^Usage:" ip link help ip6erspan
 	if [ $? -ne 0 ];then
-		echo "SKIP: ip6erspan: iproute2 too old"
+		end_test "SKIP: ip6erspan: iproute2 too old"
 		return $ksft_skip
 	fi
-
-	ip netns add "$testns"
+	run_cmd ip netns add "$testns"
 	if [ $? -ne 0 ]; then
-		echo "SKIP ip6erspan tests: cannot add net namespace $testns"
+		end_test "SKIP ip6erspan tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
 
 	# test native tunnel ip6erspan v1
-	ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \
 		key 102 local fc00:100::1 remote fc00:100::2 \
 		erspan_ver 1 erspan 488
-	check_err $?
 
-	ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	check_err $?
 
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
-
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test native tunnel ip6erspan v2
-	ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" type ip6erspan seq \
 		key 102 local fc00:100::1 remote fc00:100::2 \
 		erspan_ver 2 erspan_dir ingress erspan_hwid 7
-	check_err $?
 
-	ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	check_err $?
-
-	ip -netns "$testns" link set dev $DEV_NS up
-	check_err $?
 
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
-	ip -netns "$testns" link add dev "$DEV_NS" \
+	run_cmd ip -netns "$testns" link add dev "$DEV_NS" \
 		type ip6erspan external
-	check_err $?
 
-	ip -netns "$testns" link del "$DEV_NS"
-	check_err $?
+	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: ip6erspan"
+		end_test "FAIL: ip6erspan"
 		ip netns del "$testns"
 		return 1
 	fi
-	echo "PASS: ip6erspan"
+	end_test "PASS: ip6erspan"
 
 	ip netns del "$testns"
 }
@@ -1195,45 +1018,35 @@ kci_test_fdb_get()
 	dstip="10.0.2.3"
 	local ret=0
 
-	bridge fdb help 2>&1 |grep -q 'bridge fdb get'
+	run_cmd_grep 'bridge fdb get' bridge fdb help
 	if [ $? -ne 0 ];then
-		echo "SKIP: fdb get tests: iproute2 too old"
+		end_test "SKIP: fdb get tests: iproute2 too old"
 		return $ksft_skip
 	fi
 
-	ip netns add testns
+	run_cmd ip netns add testns
 	if [ $? -ne 0 ]; then
-		echo "SKIP fdb get tests: cannot add net namespace $testns"
+		end_test "SKIP fdb get tests: cannot add net namespace $testns"
 		return $ksft_skip
 	fi
-
-	$IP link add "$vxlandev" type vxlan id 10 local $localip \
-                dstport 4789 2>/dev/null
-	check_err $?
-	$IP link add name "$brdev" type bridge &>/dev/null
-	check_err $?
-	$IP link set dev "$vxlandev" master "$brdev" &>/dev/null
-	check_err $?
-	$BRIDGE fdb add $test_mac dev "$vxlandev" master &>/dev/null
-	check_err $?
-	$BRIDGE fdb add $test_mac dev "$vxlandev" dst $dstip self &>/dev/null
-	check_err $?
-
-	$BRIDGE fdb get $test_mac brport "$vxlandev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
-	check_err $?
-	$BRIDGE fdb get $test_mac br "$brdev" 2>/dev/null | grep -q "dev $vxlandev master $brdev"
-	check_err $?
-	$BRIDGE fdb get $test_mac dev "$vxlandev" self 2>/dev/null | grep -q "dev $vxlandev dst $dstip"
-	check_err $?
+	run_cmd $IP link add "$vxlandev" type vxlan id 10 local $localip \
+                dstport 4789
+	run_cmd $IP link add name "$brdev" type bridge
+	run_cmd $IP link set dev "$vxlandev" master "$brdev"
+	run_cmd $BRIDGE fdb add $test_mac dev "$vxlandev" master
+	run_cmd $BRIDGE fdb add $test_mac dev "$vxlandev" dst $dstip self
+	run_cmd_grep "dev $vxlandev master $brdev" $BRIDGE fdb get $test_mac brport "$vxlandev"
+	run_cmd_grep "dev $vxlandev master $brdev" $BRIDGE fdb get $test_mac br "$brdev"
+	run_cmd_grep "dev $vxlandev dst $dstip" $BRIDGE fdb get $test_mac dev "$vxlandev" self
 
 	ip netns del testns &>/dev/null
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: bridge fdb get"
+		end_test "FAIL: bridge fdb get"
 		return 1
 	fi
 
-	echo "PASS: bridge fdb get"
+	end_test "PASS: bridge fdb get"
 }
 
 kci_test_neigh_get()
@@ -1243,50 +1056,38 @@ kci_test_neigh_get()
 	dstip6=dead::2
 	local ret=0
 
-	ip neigh help 2>&1 |grep -q 'ip neigh get'
+	run_cmd_grep 'ip neigh get' ip neigh help
 	if [ $? -ne 0 ];then
-		echo "SKIP: fdb get tests: iproute2 too old"
+		end_test "SKIP: fdb get tests: iproute2 too old"
 		return $ksft_skip
 	fi
 
 	# ipv4
-	ip neigh add $dstip lladdr $dstmac dev "$devdummy"  > /dev/null
-	check_err $?
-	ip neigh get $dstip dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
-	check_err $?
-	ip neigh del $dstip lladdr $dstmac dev "$devdummy"  > /dev/null
-	check_err $?
+	run_cmd ip neigh add $dstip lladdr $dstmac dev "$devdummy"
+	run_cmd_grep "$dstmac" ip neigh get $dstip dev "$devdummy"
+	run_cmd ip neigh del $dstip lladdr $dstmac dev "$devdummy"
 
 	# ipv4 proxy
-	ip neigh add proxy $dstip dev "$devdummy" > /dev/null
-	check_err $?
-	ip neigh get proxy $dstip dev "$devdummy" 2>/dev/null | grep -q "$dstip"
-	check_err $?
-	ip neigh del proxy $dstip dev "$devdummy" > /dev/null
-	check_err $?
+	run_cmd ip neigh add proxy $dstip dev "$devdummy"
+	run_cmd_grep "$dstip" ip neigh get proxy $dstip dev "$devdummy"
+	run_cmd ip neigh del proxy $dstip dev "$devdummy"
 
 	# ipv6
-	ip neigh add $dstip6 lladdr $dstmac dev "$devdummy"  > /dev/null
-	check_err $?
-	ip neigh get $dstip6 dev "$devdummy" 2> /dev/null | grep -q "$dstmac"
-	check_err $?
-	ip neigh del $dstip6 lladdr $dstmac dev "$devdummy"  > /dev/null
-	check_err $?
+	run_cmd ip neigh add $dstip6 lladdr $dstmac dev "$devdummy"
+	run_cmd_grep "$dstmac" ip neigh get $dstip6 dev "$devdummy"
+	run_cmd ip neigh del $dstip6 lladdr $dstmac dev "$devdummy"
 
 	# ipv6 proxy
-	ip neigh add proxy $dstip6 dev "$devdummy" > /dev/null
-	check_err $?
-	ip neigh get proxy $dstip6 dev "$devdummy" 2>/dev/null | grep -q "$dstip6"
-	check_err $?
-	ip neigh del proxy $dstip6 dev "$devdummy" > /dev/null
-	check_err $?
+	run_cmd ip neigh add proxy $dstip6 dev "$devdummy"
+	run_cmd_grep "$dstip6" ip neigh get proxy $dstip6 dev "$devdummy"
+	run_cmd ip neigh del proxy $dstip6 dev "$devdummy"
 
 	if [ $ret -ne 0 ];then
-		echo "FAIL: neigh get"
+		end_test "FAIL: neigh get"
 		return 1
 	fi
 
-	echo "PASS: neigh get"
+	end_test "PASS: neigh get"
 }
 
 kci_test_bridge_parent_id()
@@ -1296,10 +1097,9 @@ kci_test_bridge_parent_id()
 	probed=false
 
 	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
-		modprobe -q netdevsim
-		check_err $?
+		run_cmd modprobe -q netdevsim
 		if [ $ret -ne 0 ]; then
-			echo "SKIP: bridge_parent_id can't load netdevsim"
+			end_test "SKIP: bridge_parent_id can't load netdevsim"
 			return $ksft_skip
 		fi
 		probed=true
@@ -1312,13 +1112,11 @@ kci_test_bridge_parent_id()
 	udevadm settle
 	dev10=`ls ${sysfsnet}10/net/`
 	dev20=`ls ${sysfsnet}20/net/`
-
-	ip link add name test-bond0 type bond mode 802.3ad
-	ip link set dev $dev10 master test-bond0
-	ip link set dev $dev20 master test-bond0
-	ip link add name test-br0 type bridge
-	ip link set dev test-bond0 master test-br0
-	check_err $?
+	run_cmd ip link add name test-bond0 type bond mode 802.3ad
+	run_cmd ip link set dev $dev10 master test-bond0
+	run_cmd ip link set dev $dev20 master test-bond0
+	run_cmd ip link add name test-br0 type bridge
+	run_cmd ip link set dev test-bond0 master test-br0
 
 	# clean up any leftovers
 	ip link del dev test-br0
@@ -1328,10 +1126,10 @@ kci_test_bridge_parent_id()
 	$probed && rmmod netdevsim
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: bridge_parent_id"
+		end_test "FAIL: bridge_parent_id"
 		return 1
 	fi
-	echo "PASS: bridge_parent_id"
+	end_test "PASS: bridge_parent_id"
 }
 
 address_get_proto()
@@ -1409,10 +1207,10 @@ do_test_address_proto()
 	ip address del dev "$devdummy" "$addr3"
 
 	if [ $ret -ne 0 ]; then
-		echo "FAIL: address proto $what"
+		end_test "FAIL: address proto $what"
 		return 1
 	fi
-	echo "PASS: address proto $what"
+	end_test "PASS: address proto $what"
 }
 
 kci_test_address_proto()
@@ -1435,7 +1233,7 @@ kci_test_rtnl()
 
 	kci_add_dummy
 	if [ $ret -ne 0 ];then
-		echo "FAIL: cannot add dummy interface"
+		end_test "FAIL: cannot add dummy interface"
 		return 1
 	fi
 
@@ -1455,26 +1253,28 @@ usage: ${0##*/} OPTS
 
         -t <test>   Test(s) to run (default: all)
                     (options: $(echo $ALL_TESTS))
+        -v          Verbose mode (show commands and output)
 EOF
 }
 
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
-	echo "SKIP: Need root privileges"
+	end_test "SKIP: Need root privileges"
 	exit $ksft_skip
 fi
 
 for x in ip tc;do
 	$x -Version 2>/dev/null >/dev/null
 	if [ $? -ne 0 ];then
-		echo "SKIP: Could not run test without the $x tool"
+		end_test "SKIP: Could not run test without the $x tool"
 		exit $ksft_skip
 	fi
 done
 
-while getopts t:h o; do
+while getopts t:hv o; do
 	case $o in
 		t) TESTS=$OPTARG;;
+		v) VERBOSE=1;;
 		h) usage; exit 0;;
 		*) usage; exit 1;;
 	esac
-- 
cgit v1.2.3


From a68eed9f63eedfa762dc54be3834c0df0abe8cc4 Mon Sep 17 00:00:00 2001
From: Daniel Mendes <dmendes@redhat.com>
Date: Tue, 12 Sep 2023 10:28:36 -0400
Subject: kselftest: rtnetlink: add pause and pause on fail flag

'Pause' prompts the user to press Enter to continue running tests
once one test has finished. Pause on fail on prompts the user to press
enter only when a test fails.

Modifications to kci_test_addrlft() and kci_test_ipsec_offload()
ensure that whenever end_test is called, [$ret -ne 0] indicates
failure. This allows end_test to really easily implement pause on fail
functionality.

Signed-off-by: Daniel Mendes <dmendes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index daaf1bcc10ac..5f2b3f6c0d74 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -32,6 +32,8 @@ ALL_TESTS="
 
 devdummy="test-dummy0"
 VERBOSE=0
+PAUSE=no
+PAUSE_ON_FAIL=no
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -112,6 +114,17 @@ end_test()
 {
 	echo "$*"
 	[ "${VERBOSE}" = "1" ] && echo
+
+	if [[ $ret -ne 0 ]] && [[ "${PAUSE_ON_FAIL}" = "yes" ]]; then
+		echo "Hit enter to continue"
+		read a
+	fi;
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo "Hit enter to continue"
+		read a
+	fi
+
 }
 
 
@@ -286,8 +299,8 @@ kci_test_addrlft()
 	sleep 5
 	run_cmd_grep "10.23.11." ip addr show dev "$devdummy"
 	if [ $? -eq 0 ]; then
-		end_test "FAIL: preferred_lft addresses remaining"
 		check_err 1
+		end_test "FAIL: preferred_lft addresses remaining"
 		return
 	fi
 
@@ -779,8 +792,8 @@ kci_test_ipsec_offload()
 	# does offload show up in ip output
 	lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"`
 	if [ $lines -ne 2 ] ; then
-		end_test "FAIL: ipsec_offload SA offload missing from list output"
 		check_err 1
+		end_test "FAIL: ipsec_offload SA offload missing from list output"
 	fi
 
 	# use ping to exercise the Tx path
@@ -806,8 +819,8 @@ EOF
 	ip x p flush
 	lines=`grep -c "SA count=0" $sysfsf`
 	if [ $lines -ne 1 ] ; then
-		end_test "FAIL: ipsec_offload SA not removed from driver"
 		check_err 1
+		end_test "FAIL: ipsec_offload SA not removed from driver"
 	fi
 
 	# clean up any leftovers
@@ -1254,6 +1267,8 @@ usage: ${0##*/} OPTS
         -t <test>   Test(s) to run (default: all)
                     (options: $(echo $ALL_TESTS))
         -v          Verbose mode (show commands and output)
+        -P          Pause after every test
+        -p          Pause after every failing test before cleanup (for debugging)
 EOF
 }
 
@@ -1271,15 +1286,19 @@ for x in ip tc;do
 	fi
 done
 
-while getopts t:hv o; do
+while getopts t:hvpP o; do
 	case $o in
 		t) TESTS=$OPTARG;;
 		v) VERBOSE=1;;
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
 		h) usage; exit 0;;
 		*) usage; exit 1;;
 	esac
 done
 
+[ $PAUSE = "yes" ] && PAUSE_ON_FAIL="no"
+
 kci_test_rtnl
 
 exit $?
-- 
cgit v1.2.3


From 4d84dcc739d5b253096f9e47957c5964709f5772 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 18 Sep 2023 17:52:31 +0200
Subject: selftests/bpf: Print log buffer for exceptions test only on failure

Alexei reported seeing log messages for some test cases even though we
just wanted to match the error string from the verifier. Move the
printing of the log buffer to a guarded condition so that we only print
it when we fail to match on the expected string in the log buffer,
preventing unneeded output when running the test.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Fixes: d2a93715bfb0 ("selftests/bpf: Add tests for BPF exceptions")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230918155233.297024-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/exceptions.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions.c b/tools/testing/selftests/bpf/prog_tests/exceptions.c
index 5663e427dc00..516f4a13013c 100644
--- a/tools/testing/selftests/bpf/prog_tests/exceptions.c
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions.c
@@ -103,9 +103,10 @@ static void test_exceptions_success(void)
 			goto done;						  \
 		}								  \
 		if (load_ret != 0) {						  \
-			printf("%s\n", log_buf);				  \
-			if (!ASSERT_OK_PTR(strstr(log_buf, msg), "strstr"))	  \
+			if (!ASSERT_OK_PTR(strstr(log_buf, msg), "strstr")) {	  \
+				printf("%s\n", log_buf);			  \
 				goto done;					  \
+			}							  \
 		}								  \
 		if (!load_ret && attach_err) {					  \
 			if (!ASSERT_ERR_PTR(link = bpf_program__attach(prog), "attach err")) \
-- 
cgit v1.2.3


From 6cb66eca36f3c6b37447ca79c6d7fc6db339c23e Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 19 Sep 2023 12:09:04 +0200
Subject: selftests/bpf: Unmount the cgroup2 work directory

test_progs -t bind_perm,bpf_obj_pinning/mounted-str-rel fails when
the selftests directory is mounted under /mnt, which is a reasonable
thing to do when sharing the selftests residing on the host with a
virtual machine, e.g., using 9p.

The reason is that cgroup2 is mounted at /mnt and not unmounted,
causing subsequent tests that need to access the selftests directory
to fail.

Fix by unmounting it. The kernel maintains a mount stack, so this
reveals what was mounted there before. Introduce cgroup_workdir_mounted
in order to maintain idempotency. Make it thread-local in order to
support test_progs -j.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20230919101336.2223655-3-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/cgroup_helpers.c | 33 ++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 2caee8423ee0..24ba56d42f2d 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -49,6 +49,10 @@
 	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
 		 CGROUP_WORK_DIR)
 
+static __thread bool cgroup_workdir_mounted;
+
+static void __cleanup_cgroup_environment(void);
+
 static int __enable_controllers(const char *cgroup_path, const char *controllers)
 {
 	char path[PATH_MAX + 1];
@@ -209,9 +213,10 @@ int setup_cgroup_environment(void)
 		log_err("mount cgroup2");
 		return 1;
 	}
+	cgroup_workdir_mounted = true;
 
 	/* Cleanup existing failed runs, now that the environment is setup */
-	cleanup_cgroup_environment();
+	__cleanup_cgroup_environment();
 
 	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
 		log_err("mkdir cgroup work dir");
@@ -305,11 +310,26 @@ int join_parent_cgroup(const char *relative_path)
 	return join_cgroup_from_top(cgroup_path);
 }
 
+/**
+ * __cleanup_cgroup_environment() - Delete temporary cgroups
+ *
+ * This is a helper for cleanup_cgroup_environment() that is responsible for
+ * deletion of all temporary cgroups that have been created during the test.
+ */
+static void __cleanup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+	join_cgroup_from_top(CGROUP_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
 /**
  * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
  *
  * This is an idempotent function to delete all temporary cgroups that
- * have been created during the test, including the cgroup testing work
+ * have been created during the test and unmount the cgroup testing work
  * directory.
  *
  * At call time, it moves the calling process to the root cgroup, and then
@@ -320,11 +340,10 @@ int join_parent_cgroup(const char *relative_path)
  */
 void cleanup_cgroup_environment(void)
 {
-	char cgroup_workdir[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_workdir, "");
-	join_cgroup_from_top(CGROUP_MOUNT_PATH);
-	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+	__cleanup_cgroup_environment();
+	if (cgroup_workdir_mounted && umount(CGROUP_MOUNT_PATH))
+		log_err("umount cgroup2");
+	cgroup_workdir_mounted = false;
 }
 
 /**
-- 
cgit v1.2.3


From 9873ce2e9c68193371c111a1a9f06064e36b9814 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 19 Sep 2023 12:09:05 +0200
Subject: selftests/bpf: Add big-endian support to the ldsx test

Prepare the ldsx test to run on big-endian systems by adding the
necessary endianness checks around narrow memory accesses.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20230919101336.2223655-4-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_ldsx_insn.c |   6 +-
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  | 146 ++++++++++++---------
 2 files changed, 90 insertions(+), 62 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 67c14ba1e87b..3709e5eb7dd0 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -104,7 +104,11 @@ int _tc(volatile struct __sk_buff *skb)
 		      "%[tmp_mark] = r1"
 		      : [tmp_mark]"=r"(tmp_mark)
 		      : [ctx]"r"(skb),
-			[off_mark]"i"(offsetof(struct __sk_buff, mark))
+			[off_mark]"i"(offsetof(struct __sk_buff, mark)
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+			+ sizeof(skb->mark) - 1
+#endif
+			)
 		      : "r1");
 #else
 	tmp_mark = (char)skb->mark;
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 1e1bc379c44f..97d35bc1c943 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -13,12 +13,16 @@ __description("LDSX, S8")
 __success __success_unpriv __retval(-2)
 __naked void ldsx_s8(void)
 {
-	asm volatile ("					\
-	r1 = 0x3fe;					\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s8 *)(r10 - 8);				\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0x3fe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s8 *)(r10 - 8);"
+#else
+	"r0 = *(s8 *)(r10 - 1);"
+#endif
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -26,12 +30,16 @@ __description("LDSX, S16")
 __success __success_unpriv __retval(-2)
 __naked void ldsx_s16(void)
 {
-	asm volatile ("					\
-	r1 = 0x3fffe;					\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s16 *)(r10 - 8);				\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0x3fffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s16 *)(r10 - 8);"
+#else
+	"r0 = *(s16 *)(r10 - 2);"
+#endif
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -39,13 +47,17 @@ __description("LDSX, S32")
 __success __success_unpriv __retval(-1)
 __naked void ldsx_s32(void)
 {
-	asm volatile ("					\
-	r1 = 0xfffffffe;				\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s32 *)(r10 - 8);				\
-	r0 >>= 1;					\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0xfffffffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s32 *)(r10 - 8);"
+#else
+	"r0 = *(s32 *)(r10 - 4);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -54,20 +66,24 @@ __log_level(2) __success __retval(1)
 __msg("R1_w=scalar(smin=-128,smax=127)")
 __naked void ldsx_s8_range_priv(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s8 *)(r10 - 8);				\
-	/* r1 with s8 range */				\
-	if r1 s> 0x7f goto l0_%=;			\
-	if r1 s< -0x80 goto l0_%=;			\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s8 *)(r10 - 8);"
+#else
+	"r1 = *(s8 *)(r10 - 1);"
+#endif
+	/* r1 with s8 range */
+	"if r1 s> 0x7f goto l0_%=;"
+	"if r1 s< -0x80 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
@@ -77,20 +93,24 @@ __description("LDSX, S16 range checking")
 __success __success_unpriv __retval(1)
 __naked void ldsx_s16_range(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s16 *)(r10 - 8);				\
-	/* r1 with s16 range */				\
-	if r1 s> 0x7fff goto l0_%=;			\
-	if r1 s< -0x8000 goto l0_%=;			\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s16 *)(r10 - 8);"
+#else
+	"r1 = *(s16 *)(r10 - 2);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fff goto l0_%=;"
+	"if r1 s< -0x8000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
@@ -100,20 +120,24 @@ __description("LDSX, S32 range checking")
 __success __success_unpriv __retval(1)
 __naked void ldsx_s32_range(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s32 *)(r10 - 8);				\
-	/* r1 with s16 range */				\
-	if r1 s> 0x7fffFFFF goto l0_%=;			\
-	if r1 s< -0x80000000 goto l0_%=;		\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s32 *)(r10 - 8);"
+#else
+	"r1 = *(s32 *)(r10 - 4);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fffFFFF goto l0_%=;"
+	"if r1 s< -0x80000000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
-- 
cgit v1.2.3


From 48c432382dd44363f5110692a9b469a7b2e962ee Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 19 Sep 2023 12:09:11 +0200
Subject: selftests/bpf: Enable the cpuv4 tests for s390x

Now that all the cpuv4 support is in place, enable the tests.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20230919101336.2223655-10-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_ldsx_insn.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_bswap.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_gotol.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_movsx.c | 3 ++-
 tools/testing/selftests/bpf/progs/verifier_sdiv.c  | 3 ++-
 6 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 3709e5eb7dd0..3ddcb3777912 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -6,7 +6,8 @@
 #include <bpf/bpf_tracing.h>
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||       \
+     defined(__TARGET_ARCH_s390)) && __clang_major__ >= 18
 const volatile int skip = 0;
 #else
 const volatile int skip = 1;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 5d54f8eae6a1..107525fb4a6a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index aa54ecd5829e..9f202eda952f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 97d35bc1c943..f90016a57eec 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index ca11fd5dafd1..b2a04d1179d0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index fb039722b639..8fc5174808b2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
-- 
cgit v1.2.3


From c29913bbf4ec172da08157efc7b417f684c42dd6 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 19 Sep 2023 12:09:12 +0200
Subject: selftests/bpf: Trim DENYLIST.s390x

Enable all selftests, except the 2 that have to do with the userspace
unwinding, and the new exceptions test, in the s390x CI.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20230919101336.2223655-11-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/DENYLIST.s390x | 25 -------------------------
 1 file changed, 25 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index ce6f291665cf..1a63996c0304 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -1,30 +1,5 @@
 # TEMPORARY
 # Alphabetical order
-bloom_filter_map                         # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
-bpf_cookie                               # failed to open_and_load program: -524 (trampoline)
-bpf_loop                                 # attaches to __x64_sys_nanosleep
-cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
-dynptr/test_dynptr_skb_data
-dynptr/test_skb_readonly
 exceptions				 # JIT does not support calling kfunc bpf_throw				       (exceptions)
-fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
-iters/testmod_seq*                       # s390x doesn't support kfuncs in modules yet
-kprobe_multi_bench_attach                # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test                        # relies on fentry
-ksyms_btf/weak_ksyms*                    # test_ksyms_weak__open_and_load unexpected error: -22                        (kfunc)
-ksyms_module                             # test_ksyms_module__open_and_load unexpected error: -9                       (?)
-ksyms_module_libbpf                      # JIT does not support calling kernel function                                (kfunc)
-ksyms_module_lskel                       # test_ksyms_module_lskel__open_and_load unexpected error: -9                 (?)
-module_attach                            # skel_attach skeleton attach failed: -524                                    (trampoline)
-ringbuf                                  # skel_load skeleton load failed                                              (?)
 stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
-test_lsm                                 # attach unexpected error: -524                                               (trampoline)
-trace_printk                             # trace_printk__load unexpected error: -2 (errno 2)                           (?)
-trace_vprintk                            # trace_vprintk__open_and_load unexpected error: -9                           (?)
-unpriv_bpf_disabled                      # fentry
-user_ringbuf                             # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3                (?)
-verif_stats                              # trace_vprintk__open_and_load unexpected error: -9                           (?)
-xdp_bonding                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
-xdp_metadata                             # JIT does not support calling kernel function                                (kfunc)
-test_task_under_cgroup                   # JIT does not support calling kernel function                                (kfunc)
-- 
cgit v1.2.3


From 7257cee65269a066c242f4863b456275cb0218b5 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Mon, 18 Sep 2023 02:48:11 +0000
Subject: libbpf: Resolve symbol conflicts at the same offset for uprobe

Dynamic symbols in shared library may have the same name, for example:

    $ nm -D /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
    000000000009b1a0 T __pthread_rwlock_wrlock@GLIBC_2.2.5
    000000000009b1a0 T pthread_rwlock_wrlock@@GLIBC_2.34
    000000000009b1a0 T pthread_rwlock_wrlock@GLIBC_2.2.5

    $ readelf -W --dyn-syms /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
     706: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 __pthread_rwlock_wrlock@GLIBC_2.2.5
    2568: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@@GLIBC_2.34
    2571: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@GLIBC_2.2.5

Currently, users can't attach a uprobe to pthread_rwlock_wrlock because
there are two symbols named pthread_rwlock_wrlock and both are global
bind. And libbpf considers it as a conflict.

Since both of them are at the same offset we could accept one of them
harmlessly. Note that we already does this in elf_resolve_syms_offsets.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230918024813.237475-2-hengqi.chen@gmail.com
---
 tools/lib/bpf/elf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 9d0296c1726a..5c9e588b17da 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -214,7 +214,10 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 
 			if (ret > 0) {
 				/* handle multiple matches */
-				if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
+				if (elf_sym_offset(sym) == ret) {
+					/* same offset, no problem */
+					continue;
+				} else if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
 					/* Only accept one non-weak bind. */
 					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
 						sym->name, name, binary_path);
-- 
cgit v1.2.3


From bb7fa09399b937cdc4432ac99f9748f5a7f69389 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Mon, 18 Sep 2023 02:48:12 +0000
Subject: libbpf: Support symbol versioning for uprobe

In current implementation, we assume that symbol found in .dynsym section
would have a version suffix and use it to compare with symbol user supplied.
According to the spec ([0]), this assumption is incorrect, the version info
of dynamic symbols are stored in .gnu.version and .gnu.version_d sections
of ELF objects. For example:

    $ nm -D /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
    000000000009b1a0 T __pthread_rwlock_wrlock@GLIBC_2.2.5
    000000000009b1a0 T pthread_rwlock_wrlock@@GLIBC_2.34
    000000000009b1a0 T pthread_rwlock_wrlock@GLIBC_2.2.5

    $ readelf -W --dyn-syms /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
      706: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 __pthread_rwlock_wrlock@GLIBC_2.2.5
      2568: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@@GLIBC_2.34
      2571: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@GLIBC_2.2.5

In this case, specify pthread_rwlock_wrlock@@GLIBC_2.34 or
pthread_rwlock_wrlock@GLIBC_2.2.5 in bpf_uprobe_opts::func_name won't work.
Because the qualified name does NOT match `pthread_rwlock_wrlock` (without
version suffix) in .dynsym sections.

This commit implements the symbol versioning for dynsym and allows user to
specify symbol in the following forms:
  - func
  - func@LIB_VERSION
  - func@@LIB_VERSION

In case of symbol conflicts, error out and users should resolve it by
specifying a qualified name.

  [0]: https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/symversion.html

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230918024813.237475-3-hengqi.chen@gmail.com
---
 tools/lib/bpf/elf.c    | 134 +++++++++++++++++++++++++++++++++++++++++++++----
 tools/lib/bpf/libbpf.c |   2 +-
 2 files changed, 124 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 5c9e588b17da..2a158e8a8b7c 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
 #include <libelf.h>
 #include <gelf.h>
 #include <fcntl.h>
@@ -10,6 +13,17 @@
 
 #define STRERR_BUFSIZE  128
 
+/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
+ * the symbol is hidden and can only be seen when referenced using an
+ * explicit version number. This is a GNU extension.
+ */
+#define VERSYM_HIDDEN	0x8000
+
+/* This is the mask for the rest of the data in a word read from a
+ * SHT_GNU_versym section.
+ */
+#define VERSYM_VERSION	0x7fff
+
 int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -64,13 +78,18 @@ struct elf_sym {
 	const char *name;
 	GElf_Sym sym;
 	GElf_Shdr sh;
+	int ver;
+	bool hidden;
 };
 
 struct elf_sym_iter {
 	Elf *elf;
 	Elf_Data *syms;
+	Elf_Data *versyms;
+	Elf_Data *verdefs;
 	size_t nr_syms;
 	size_t strtabidx;
+	size_t verdef_strtabidx;
 	size_t next_sym_idx;
 	struct elf_sym sym;
 	int st_type;
@@ -111,6 +130,26 @@ static int elf_sym_iter_new(struct elf_sym_iter *iter,
 	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
 	iter->elf = elf;
 	iter->st_type = st_type;
+
+	/* Version symbol table is meaningful to dynsym only */
+	if (sh_type != SHT_DYNSYM)
+		return 0;
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL);
+	if (!scn)
+		return 0;
+	iter->versyms = elf_getdata(scn, 0);
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
+	if (!scn) {
+		pr_debug("elf: failed to find verdef ELF sections in '%s'\n", binary_path);
+		return -ENOENT;
+	}
+	if (!gelf_getshdr(scn, &sh))
+		return -EINVAL;
+	iter->verdef_strtabidx = sh.sh_link;
+	iter->verdefs = elf_getdata(scn, 0);
+
 	return 0;
 }
 
@@ -119,6 +158,7 @@ static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
 	struct elf_sym *ret = &iter->sym;
 	GElf_Sym *sym = &ret->sym;
 	const char *name = NULL;
+	GElf_Versym versym;
 	Elf_Scn *sym_scn;
 	size_t idx;
 
@@ -138,12 +178,80 @@ static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
 
 		iter->next_sym_idx = idx + 1;
 		ret->name = name;
+		ret->ver = 0;
+		ret->hidden = false;
+
+		if (iter->versyms) {
+			if (!gelf_getversym(iter->versyms, idx, &versym))
+				continue;
+			ret->ver = versym & VERSYM_VERSION;
+			ret->hidden = versym & VERSYM_HIDDEN;
+		}
 		return ret;
 	}
 
 	return NULL;
 }
 
+static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
+{
+	GElf_Verdaux verdaux;
+	GElf_Verdef verdef;
+	int offset;
+
+	offset = 0;
+	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
+		if (verdef.vd_ndx != ver) {
+			if (!verdef.vd_next)
+				break;
+
+			offset += verdef.vd_next;
+			continue;
+		}
+
+		if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux))
+			break;
+
+		return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name);
+
+	}
+	return NULL;
+}
+
+static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym,
+			 const char *name, size_t name_len, const char *lib_ver)
+{
+	const char *ver_name;
+
+	/* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER
+	 * make sure the func part matches the user specified name
+	 */
+	if (strncmp(sym->name, name, name_len) != 0)
+		return false;
+
+	/* ...but we don't want a search for "foo" to match 'foo2" also, so any
+	 * additional characters in sname should be of the form "@@LIB".
+	 */
+	if (sym->name[name_len] != '\0' && sym->name[name_len] != '@')
+		return false;
+
+	/* If user does not specify symbol version, then we got a match */
+	if (!lib_ver)
+		return true;
+
+	/* If user specifies symbol version, for dynamic symbols,
+	 * get version name from ELF verdef section for comparison.
+	 */
+	if (sh_type == SHT_DYNSYM) {
+		ver_name = elf_get_vername(iter, sym->ver);
+		if (!ver_name)
+			return false;
+		return strcmp(ver_name, lib_ver) == 0;
+	}
+
+	/* For normal symbols, it is already in form of func@LIB_VER */
+	return strcmp(sym->name, name) == 0;
+}
 
 /* Transform symbol's virtual address (absolute for binaries and relative
  * for shared libs) into file offset, which is what kernel is expecting
@@ -166,7 +274,8 @@ static unsigned long elf_sym_offset(struct elf_sym *sym)
 long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 {
 	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	bool is_shared_lib, is_name_qualified;
+	const char *at_symbol, *lib_ver;
+	bool is_shared_lib;
 	long ret = -ENOENT;
 	size_t name_len;
 	GElf_Ehdr ehdr;
@@ -179,9 +288,18 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 	/* for shared lib case, we do not need to calculate relative offset */
 	is_shared_lib = ehdr.e_type == ET_DYN;
 
-	name_len = strlen(name);
-	/* Does name specify "@@LIB"? */
-	is_name_qualified = strstr(name, "@@") != NULL;
+	/* Does name specify "@@LIB_VER" or "@LIB_VER" ? */
+	at_symbol = strchr(name, '@');
+	if (at_symbol) {
+		name_len = at_symbol - name;
+		/* skip second @ if it's @@LIB_VER case */
+		if (at_symbol[1] == '@')
+			at_symbol++;
+		lib_ver = at_symbol + 1;
+	} else {
+		name_len = strlen(name);
+		lib_ver = NULL;
+	}
 
 	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
 	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
@@ -201,13 +319,7 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 			goto out;
 
 		while ((sym = elf_sym_iter_next(&iter))) {
-			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
-			if (strncmp(sym->name, name, name_len) != 0)
-				continue;
-			/* ...but we don't want a search for "foo" to match 'foo2" also, so any
-			 * additional characters in sname should be of the form "@@LIB".
-			 */
-			if (!is_name_qualified && sym->name[name_len] != '\0' && sym->name[name_len] != '@')
+			if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver))
 				continue;
 
 			cur_bind = GELF_ST_BIND(sym->sym.st_info);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3a6108e3238b..b4758e54a815 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11630,7 +11630,7 @@ static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf
 
 	*link = NULL;
 
-	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li",
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.@]+%li",
 		   &probe_type, &binary_path, &func_name, &offset);
 	switch (n) {
 	case 1:
-- 
cgit v1.2.3


From 7089f85a9eb943716052bb91bd65ce939976ebfa Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Mon, 18 Sep 2023 02:48:13 +0000
Subject: selftests/bpf: Add tests for symbol versioning for uprobe

This exercises the newly added dynsym symbol versioning logics.
Now we accept symbols in form of func, func@LIB_VERSION or
func@@LIB_VERSION.

The test rely on liburandom_read.so. For liburandom_read.so, we have:

    $ nm -D liburandom_read.so
                     w __cxa_finalize@GLIBC_2.17
                     w __gmon_start__
                     w _ITM_deregisterTMCloneTable
                     w _ITM_registerTMCloneTable
    0000000000000000 A LIBURANDOM_READ_1.0.0
    0000000000000000 A LIBURANDOM_READ_2.0.0
    000000000000081c T urandlib_api@@LIBURANDOM_READ_2.0.0
    0000000000000814 T urandlib_api@LIBURANDOM_READ_1.0.0
    0000000000000824 T urandlib_api_sameoffset@LIBURANDOM_READ_1.0.0
    0000000000000824 T urandlib_api_sameoffset@@LIBURANDOM_READ_2.0.0
    000000000000082c T urandlib_read_without_sema@@LIBURANDOM_READ_1.0.0
    00000000000007c4 T urandlib_read_with_sema@@LIBURANDOM_READ_1.0.0
    0000000000011018 D urandlib_read_with_sema_semaphore@@LIBURANDOM_READ_1.0.0

For `urandlib_api`, specifying `urandlib_api` will cause a conflict because
there are two symbols named urandlib_api and both are global bind.
For `urandlib_api_sameoffset`, there are also two symbols in the .so, but
both are at the same offset and essentially they refer to the same function
so no conflict.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20230918024813.237475-4-hengqi.chen@gmail.com
---
 tools/testing/selftests/bpf/Makefile            |  5 +-
 tools/testing/selftests/bpf/liburandom_read.map | 15 ++++
 tools/testing/selftests/bpf/prog_tests/uprobe.c | 95 +++++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_uprobe.c | 61 ++++++++++++++++
 tools/testing/selftests/bpf/urandom_read.c      | 15 +++-
 tools/testing/selftests/bpf/urandom_read_lib1.c | 22 ++++++
 6 files changed, 209 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/liburandom_read.map
 create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_uprobe.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index caede9b574cb..47365161b6fc 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -196,11 +196,12 @@ endif
 
 # Filter out -static for liburandom_read.so and its dependent targets so that static builds
 # do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
-$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
+$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c liburandom_read.map
 	$(call msg,LIB,,$@)
 	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS))   \
-		     $^ $(filter-out -static,$(LDLIBS))	     \
+		     $(filter %.c,$^) $(filter-out -static,$(LDLIBS)) \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
+		     -Wl,--version-script=liburandom_read.map \
 		     -fPIC -shared -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
diff --git a/tools/testing/selftests/bpf/liburandom_read.map b/tools/testing/selftests/bpf/liburandom_read.map
new file mode 100644
index 000000000000..38a97a419a04
--- /dev/null
+++ b/tools/testing/selftests/bpf/liburandom_read.map
@@ -0,0 +1,15 @@
+LIBURANDOM_READ_1.0.0 {
+	global:
+		urandlib_api;
+		urandlib_api_sameoffset;
+		urandlib_read_without_sema;
+		urandlib_read_with_sema;
+		urandlib_read_with_sema_semaphore;
+	local:
+		*;
+};
+
+LIBURANDOM_READ_2.0.0 {
+	global:
+		urandlib_api;
+} LIBURANDOM_READ_1.0.0;
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe.c b/tools/testing/selftests/bpf/prog_tests/uprobe.c
new file mode 100644
index 000000000000..cf3e0e7a64fa
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include <test_progs.h>
+#include "test_uprobe.skel.h"
+
+static FILE *urand_spawn(int *pid)
+{
+	FILE *f;
+
+	/* urandom_read's stdout is wired into f */
+	f = popen("./urandom_read 1 report-pid", "r");
+	if (!f)
+		return NULL;
+
+	if (fscanf(f, "%d", pid) != 1) {
+		pclose(f);
+		errno = EINVAL;
+		return NULL;
+	}
+
+	return f;
+}
+
+static int urand_trigger(FILE **urand_pipe)
+{
+	int exit_code;
+
+	/* pclose() waits for child process to exit and returns their exit code */
+	exit_code = pclose(*urand_pipe);
+	*urand_pipe = NULL;
+
+	return exit_code;
+}
+
+void test_uprobe(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct test_uprobe *skel;
+	FILE *urand_pipe = NULL;
+	int urand_pid = 0, err;
+
+	skel = test_uprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	urand_pipe = urand_spawn(&urand_pid);
+	if (!ASSERT_OK_PTR(urand_pipe, "urand_spawn"))
+		goto cleanup;
+
+	skel->bss->my_pid = urand_pid;
+
+	/* Manual attach uprobe to urandlib_api
+	 * There are two `urandlib_api` symbols in .dynsym section:
+	 *   - urandlib_api@LIBURANDOM_READ_1.0.0
+	 *   - urandlib_api@@LIBURANDOM_READ_2.0.0
+	 * Both are global bind and would cause a conflict if user
+	 * specify the symbol name without a version suffix
+	 */
+	uprobe_opts.func_name = "urandlib_api";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_ERR_PTR(skel->links.test4, "urandlib_api_attach_conflict"))
+		goto cleanup;
+
+	uprobe_opts.func_name = "urandlib_api@LIBURANDOM_READ_1.0.0";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.test4, "urandlib_api_attach_ok"))
+		goto cleanup;
+
+	/* Auto attach 3 u[ret]probes to urandlib_api_sameoffset */
+	err = test_uprobe__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger urandom_read */
+	ASSERT_OK(urand_trigger(&urand_pipe), "urand_exit_code");
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "urandlib_api_sameoffset");
+	ASSERT_EQ(skel->bss->test2_result, 1, "urandlib_api_sameoffset@v1");
+	ASSERT_EQ(skel->bss->test3_result, 3, "urandlib_api_sameoffset@@v2");
+	ASSERT_EQ(skel->bss->test4_result, 1, "urandlib_api");
+
+cleanup:
+	if (urand_pipe)
+		pclose(urand_pipe);
+	test_uprobe__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe.c b/tools/testing/selftests/bpf/progs/test_uprobe.c
new file mode 100644
index 000000000000..896c88a4960d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_uprobe.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+pid_t my_pid = 0;
+
+int test1_result = 0;
+int test2_result = 0;
+int test3_result = 0;
+int test4_result = 0;
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset")
+int BPF_UPROBE(test1)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test1_result = 1;
+	return 0;
+}
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset@LIBURANDOM_READ_1.0.0")
+int BPF_UPROBE(test2)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test2_result = 1;
+	return 0;
+}
+
+SEC("uretprobe/./liburandom_read.so:urandlib_api_sameoffset@@LIBURANDOM_READ_2.0.0")
+int BPF_URETPROBE(test3, int ret)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test3_result = ret;
+	return 0;
+}
+
+SEC("uprobe")
+int BPF_UPROBE(test4)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test4_result = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c
index e92644d0fa75..4ed795655b9f 100644
--- a/tools/testing/selftests/bpf/urandom_read.c
+++ b/tools/testing/selftests/bpf/urandom_read.c
@@ -11,6 +11,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 #define BUF_SIZE 256
@@ -21,10 +24,14 @@ void urand_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 
+int urandlib_api(void);
+COMPAT_VERSION(urandlib_api_old, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_old(void);
+int urandlib_api_sameoffset(void);
+
 unsigned short urand_read_with_sema_semaphore SEC(".probes");
 
-static __attribute__((noinline))
-void urandom_read(int fd, int count)
+static noinline void urandom_read(int fd, int count)
 {
 	char buf[BUF_SIZE];
 	int i;
@@ -83,6 +90,10 @@ int main(int argc, char *argv[])
 
 	urandom_read(fd, count);
 
+	urandlib_api();
+	urandlib_api_old();
+	urandlib_api_sameoffset();
+
 	close(fd);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/urandom_read_lib1.c b/tools/testing/selftests/bpf/urandom_read_lib1.c
index 86186e24b740..8c1356d8b4ee 100644
--- a/tools/testing/selftests/bpf/urandom_read_lib1.c
+++ b/tools/testing/selftests/bpf/urandom_read_lib1.c
@@ -3,6 +3,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 unsigned short urandlib_read_with_sema_semaphore SEC(".probes");
@@ -11,3 +14,22 @@ void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz)
 {
 	STAP_PROBE3(urandlib, read_with_sema, iter_num, iter_cnt, read_sz);
 }
+
+COMPAT_VERSION(urandlib_api_v1, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_v1(void)
+{
+	return 1;
+}
+
+DEFAULT_VERSION(urandlib_api_v2, urandlib_api, LIBURANDOM_READ_2.0.0)
+int urandlib_api_v2(void)
+{
+	return 2;
+}
+
+COMPAT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_1.0.0)
+DEFAULT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_2.0.0)
+int urandlib_api_sameoffset(void)
+{
+	return 3;
+}
-- 
cgit v1.2.3


From 4448f64c549c28175dd9af4e8f9a2e0c62ef6d38 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:32 -0700
Subject: libbpf: Refactor cleanup in ring_buffer__add

Refactor the cleanup code in ring_buffer__add to use a unified err_out
label. This reduces code duplication, as well as plugging a potential
leak if mmap_sz != (__u64)(size_t)mmap_sz (currently this would miss
unmapping tmp because ringbuf_unmap_ring isn't called).

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-2-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/ringbuf.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 02199364db13..29b0d19d920f 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -121,7 +121,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
 			map_fd, err);
-		return libbpf_err(err);
+		goto err_out;
 	}
 	r->consumer_pos = tmp;
 
@@ -131,16 +131,16 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	 */
 	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
 	if (mmap_sz != (__u64)(size_t)mmap_sz) {
+		err = -E2BIG;
 		pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries);
-		return libbpf_err(-E2BIG);
+		goto err_out;
 	}
 	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
-		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
 			map_fd, err);
-		return libbpf_err(err);
+		goto err_out;
 	}
 	r->producer_pos = tmp;
 	r->data = tmp + rb->page_size;
@@ -152,14 +152,17 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	e->data.fd = rb->ring_cnt;
 	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
 		err = -errno;
-		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
 			map_fd, err);
-		return libbpf_err(err);
+		goto err_out;
 	}
 
 	rb->ring_cnt++;
 	return 0;
+
+err_out:
+	ringbuf_unmap_ring(rb, r);
+	return libbpf_err(err);
 }
 
 void ring_buffer__free(struct ring_buffer *rb)
-- 
cgit v1.2.3


From ef3b82003e6ca9554a144a9f42e7239ba39f0b97 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:33 -0700
Subject: libbpf: Switch rings to array of pointers

Switch rb->rings to be an array of pointers instead of a contiguous
block. This allows for each ring pointer to be stable after
ring_buffer__add is called, which allows us to expose struct ring * to
the user without gotchas. Without this change, the realloc in
ring_buffer__add could invalidate a struct ring *, making it unsafe to
give to the user.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-3-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/ringbuf.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 29b0d19d920f..94d11fb44a49 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -34,7 +34,7 @@ struct ring {
 
 struct ring_buffer {
 	struct epoll_event *events;
-	struct ring *rings;
+	struct ring **rings;
 	size_t page_size;
 	int epoll_fd;
 	int ring_cnt;
@@ -57,7 +57,7 @@ struct ringbuf_hdr {
 	__u32 pad;
 };
 
-static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
+static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r)
 {
 	if (r->consumer_pos) {
 		munmap(r->consumer_pos, rb->page_size);
@@ -67,6 +67,8 @@ static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
 		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
 		r->producer_pos = NULL;
 	}
+
+	free(r);
 }
 
 /* Add extra RINGBUF maps to this ring buffer manager */
@@ -107,8 +109,10 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		return libbpf_err(-ENOMEM);
 	rb->events = tmp;
 
-	r = &rb->rings[rb->ring_cnt];
-	memset(r, 0, sizeof(*r));
+	r = calloc(1, sizeof(*r));
+	if (!r)
+		return libbpf_err(-ENOMEM);
+	rb->rings[rb->ring_cnt] = r;
 
 	r->map_fd = map_fd;
 	r->sample_cb = sample_cb;
@@ -161,7 +165,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	return 0;
 
 err_out:
-	ringbuf_unmap_ring(rb, r);
+	ringbuf_free_ring(rb, r);
 	return libbpf_err(err);
 }
 
@@ -173,7 +177,7 @@ void ring_buffer__free(struct ring_buffer *rb)
 		return;
 
 	for (i = 0; i < rb->ring_cnt; ++i)
-		ringbuf_unmap_ring(rb, &rb->rings[i]);
+		ringbuf_free_ring(rb, rb->rings[i]);
 	if (rb->epoll_fd >= 0)
 		close(rb->epoll_fd);
 
@@ -281,7 +285,7 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	int i;
 
 	for (i = 0; i < rb->ring_cnt; i++) {
-		struct ring *ring = &rb->rings[i];
+		struct ring *ring = rb->rings[i];
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
@@ -308,7 +312,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 	for (i = 0; i < cnt; i++) {
 		__u32 ring_id = rb->events[i].data.fd;
-		struct ring *ring = &rb->rings[ring_id];
+		struct ring *ring = rb->rings[ring_id];
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
-- 
cgit v1.2.3


From 1c97f6afd73934881ae8514c51efc8e162b4b406 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:34 -0700
Subject: libbpf: Add ring_buffer__ring

Add a new function ring_buffer__ring, which exposes struct ring * to the
user, representing a single ringbuffer.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-4-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 15 +++++++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/ringbuf.c  |  8 ++++++++
 3 files changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 0e52621cba43..de3ef59b9641 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1229,6 +1229,7 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
 
 /* Ring buffer APIs */
 struct ring_buffer;
+struct ring;
 struct user_ring_buffer;
 
 typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
@@ -1249,6 +1250,20 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
+/**
+ * @brief **ring_buffer__ring()** returns the ringbuffer object inside a given
+ * ringbuffer manager representing a single BPF_MAP_TYPE_RINGBUF map instance.
+ *
+ * @param rb A ringbuffer manager object.
+ * @param idx An index into the ringbuffers contained within the ringbuffer
+ * manager object. The index is 0-based and corresponds to the order in which
+ * ring_buffer__add was called.
+ * @return A ringbuffer object on success; NULL and errno set if the index is
+ * invalid.
+ */
+LIBBPF_API struct ring *ring_buffer__ring(struct ring_buffer *rb,
+					  unsigned int idx);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 57712321490f..7a7370c2bc25 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -400,4 +400,5 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
+		ring_buffer__ring;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 94d11fb44a49..efde453395b0 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -330,6 +330,14 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
 	return rb->epoll_fd;
 }
 
+struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx)
+{
+	if (idx >= rb->ring_cnt)
+		return errno = ERANGE, NULL;
+
+	return rb->rings[idx];
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From c1ad2e47f97c6d95e52be0c2a68b23fc99214734 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:35 -0700
Subject: selftests/bpf: Add tests for ring_buffer__ring

Add tests for the new API ring_buffer__ring.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-5-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 1455911d9fcb..58522195081b 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -42,6 +42,8 @@ void test_ringbuf_multi(void)
 {
 	struct test_ringbuf_multi *skel;
 	struct ring_buffer *ringbuf = NULL;
+	struct ring *ring_old;
+	struct ring *ring;
 	int err;
 	int page_size = getpagesize();
 	int proto_fd = -1;
@@ -84,11 +86,24 @@ void test_ringbuf_multi(void)
 	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
 		goto cleanup;
 
+	/* verify ring_buffer__ring returns expected results */
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_idx_0"))
+		goto cleanup;
+	ring_old = ring;
+	ring = ring_buffer__ring(ringbuf, 1);
+	ASSERT_ERR_PTR(ring, "ring_buffer__ring_idx_1");
+
 	err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2),
 			      process_sample, (void *)(long)2);
 	if (CHECK(err, "ringbuf_add", "failed to add another ring\n"))
 		goto cleanup;
 
+	/* verify adding a new ring didn't invalidate our older pointer */
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_EQ(ring, ring_old, "ring_buffer__ring_again"))
+		goto cleanup;
+
 	err = test_ringbuf_multi__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
 		goto cleanup;
-- 
cgit v1.2.3


From 059a8c0c5acd37ecfa64f1832e8765d30f253ce8 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:36 -0700
Subject: libbpf: Add ring__producer_pos, ring__consumer_pos

Add APIs to get the producer and consumer position for a given
ringbuffer.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-6-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 18 ++++++++++++++++++
 tools/lib/bpf/libbpf.map |  2 ++
 tools/lib/bpf/ringbuf.c  | 14 ++++++++++++++
 3 files changed, 34 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index de3ef59b9641..ab470179b7fe 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1264,6 +1264,24 @@ LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 LIBBPF_API struct ring *ring_buffer__ring(struct ring_buffer *rb,
 					  unsigned int idx);
 
+/**
+ * @brief **ring__consumer_pos()** returns the current consumer position in the
+ * given ringbuffer.
+ *
+ * @param r A ringbuffer object.
+ * @return The current consumer position.
+ */
+LIBBPF_API unsigned long ring__consumer_pos(const struct ring *r);
+
+/**
+ * @brief **ring__producer_pos()** returns the current producer position in the
+ * given ringbuffer.
+ *
+ * @param r A ringbuffer object.
+ * @return The current producer position.
+ */
+LIBBPF_API unsigned long ring__producer_pos(const struct ring *r);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 7a7370c2bc25..3bec002449d5 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -400,5 +400,7 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
+		ring__consumer_pos;
+		ring__producer_pos;
 		ring_buffer__ring;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index efde453395b0..d14a607f6b66 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -338,6 +338,20 @@ struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx)
 	return rb->rings[idx];
 }
 
+unsigned long ring__consumer_pos(const struct ring *r)
+{
+	/* Synchronizes with smp_store_release() in ringbuf_process_ring(). */
+	return smp_load_acquire(r->consumer_pos);
+}
+
+unsigned long ring__producer_pos(const struct ring *r)
+{
+	/* Synchronizes with smp_store_release() in __bpf_ringbuf_reserve() in
+	 * the kernel.
+	 */
+	return smp_load_acquire(r->producer_pos);
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From b18db8712ecf5c880da222f6e0d7be53f0af4c4d Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:37 -0700
Subject: selftests/bpf: Add tests for ring__*_pos

Add tests for the new APIs ring__producer_pos and ring__consumer_pos.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-7-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index ac104dc652e3..994a36a2b589 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -91,6 +91,8 @@ static void ringbuf_subtest(void)
 	int err, cnt, rb_fd;
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
+	struct ring *ring;
+	unsigned long cons_pos, prod_pos;
 
 	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -162,6 +164,10 @@ static void ringbuf_subtest(void)
 
 	trigger_samples();
 
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_idx_0"))
+		goto cleanup;
+
 	/* 2 submitted + 1 discarded records */
 	CHECK(skel->bss->avail_data != 3 * rec_sz,
 	      "err_avail_size", "exp %ld, got %ld\n",
@@ -176,6 +182,14 @@ static void ringbuf_subtest(void)
 	      "err_prod_pos", "exp %ld, got %ld\n",
 	      3L * rec_sz, skel->bss->prod_pos);
 
+	/* verify getting this data directly via the ring object yields the same
+	 * results
+	 */
+	cons_pos = ring__consumer_pos(ring);
+	ASSERT_EQ(cons_pos, 0, "ring_cons_pos");
+	prod_pos = ring__producer_pos(ring);
+	ASSERT_EQ(prod_pos, 3 * rec_sz, "ring_prod_pos");
+
 	/* poll for samples */
 	err = ring_buffer__poll(ringbuf, -1);
 
-- 
cgit v1.2.3


From 3b34d2972612299fb38ad7f3c2bc62c2d03237f3 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:38 -0700
Subject: libbpf: Add ring__avail_data_size

Add ring__avail_data_size for querying the currently available data in
the ringbuffer, similar to the BPF_RB_AVAIL_DATA flag in
bpf_ringbuf_query. This is racy during ongoing operations but is still
useful for overall information on how a ringbuffer is behaving.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-8-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 11 +++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/ringbuf.c  |  9 +++++++++
 3 files changed, 21 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index ab470179b7fe..d60254c5edc6 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1282,6 +1282,17 @@ LIBBPF_API unsigned long ring__consumer_pos(const struct ring *r);
  */
 LIBBPF_API unsigned long ring__producer_pos(const struct ring *r);
 
+/**
+ * @brief **ring__avail_data_size()** returns the number of bytes in the
+ * ringbuffer not yet consumed. This has no locking associated with it, so it
+ * can be inaccurate if operations are ongoing while this is called. However, it
+ * should still show the correct trend over the long-term.
+ *
+ * @param r A ringbuffer object.
+ * @return The number of bytes not yet consumed.
+ */
+LIBBPF_API size_t ring__avail_data_size(const struct ring *r);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 3bec002449d5..5184c94c0502 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -400,6 +400,7 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_netfilter;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
+		ring__avail_data_size;
 		ring__consumer_pos;
 		ring__producer_pos;
 		ring_buffer__ring;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index d14a607f6b66..07fbc6adcdd9 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -352,6 +352,15 @@ unsigned long ring__producer_pos(const struct ring *r)
 	return smp_load_acquire(r->producer_pos);
 }
 
+size_t ring__avail_data_size(const struct ring *r)
+{
+	unsigned long cons_pos, prod_pos;
+
+	cons_pos = ring__consumer_pos(r);
+	prod_pos = ring__producer_pos(r);
+	return prod_pos - cons_pos;
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From f3a01d385fbb9c76abfad8d104d08453f289e2d3 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:39 -0700
Subject: selftests/bpf: Add tests for ring__avail_data_size

Add test for the new API ring__avail_data_size.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-9-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 994a36a2b589..254b25b8614c 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -92,7 +92,7 @@ static void ringbuf_subtest(void)
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
 	struct ring *ring;
-	unsigned long cons_pos, prod_pos;
+	unsigned long avail_data, cons_pos, prod_pos;
 
 	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -185,6 +185,8 @@ static void ringbuf_subtest(void)
 	/* verify getting this data directly via the ring object yields the same
 	 * results
 	 */
+	avail_data = ring__avail_data_size(ring);
+	ASSERT_EQ(avail_data, 3 * rec_sz, "ring_avail_size");
 	cons_pos = ring__consumer_pos(ring);
 	ASSERT_EQ(cons_pos, 0, "ring_cons_pos");
 	prod_pos = ring__producer_pos(ring);
-- 
cgit v1.2.3


From e79abf717fce6439022547124571dfe17f2ac15a Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:40 -0700
Subject: libbpf: Add ring__size

Add ring__size to get the total size of a given ringbuffer.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-10-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 10 ++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/ringbuf.c  |  5 +++++
 3 files changed, 16 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index d60254c5edc6..53e2a645c560 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1293,6 +1293,16 @@ LIBBPF_API unsigned long ring__producer_pos(const struct ring *r);
  */
 LIBBPF_API size_t ring__avail_data_size(const struct ring *r);
 
+/**
+ * @brief **ring__size()** returns the total size of the ringbuffer's map data
+ * area (excluding special producer/consumer pages). Effectively this gives the
+ * amount of usable bytes of data inside the ringbuffer.
+ *
+ * @param r A ringbuffer object.
+ * @return The total size of the ringbuffer map data area.
+ */
+LIBBPF_API size_t ring__size(const struct ring *r);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 5184c94c0502..a116d0bb3c5d 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -403,5 +403,6 @@ LIBBPF_1.3.0 {
 		ring__avail_data_size;
 		ring__consumer_pos;
 		ring__producer_pos;
+		ring__size;
 		ring_buffer__ring;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 07fbc6adcdd9..98d0767dbb50 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -361,6 +361,11 @@ size_t ring__avail_data_size(const struct ring *r)
 	return prod_pos - cons_pos;
 }
 
+size_t ring__size(const struct ring *r)
+{
+	return r->mask + 1;
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From bb32dd2c8fec71990bbc231aac934e1c73a17341 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:41 -0700
Subject: selftests/bpf: Add tests for ring__size

Add tests for the new API ring__size.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-11-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 254b25b8614c..c5be480a6ef6 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -92,7 +92,7 @@ static void ringbuf_subtest(void)
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
 	struct ring *ring;
-	unsigned long avail_data, cons_pos, prod_pos;
+	unsigned long avail_data, ring_size, cons_pos, prod_pos;
 
 	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -187,6 +187,8 @@ static void ringbuf_subtest(void)
 	 */
 	avail_data = ring__avail_data_size(ring);
 	ASSERT_EQ(avail_data, 3 * rec_sz, "ring_avail_size");
+	ring_size = ring__size(ring);
+	ASSERT_EQ(ring_size, page_size, "ring_ring_size");
 	cons_pos = ring__consumer_pos(ring);
 	ASSERT_EQ(cons_pos, 0, "ring_cons_pos");
 	prod_pos = ring__producer_pos(ring);
-- 
cgit v1.2.3


From ae769390377adaec2798bd1a69171f00d0a25be0 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:42 -0700
Subject: libbpf: Add ring__map_fd

Add ring__map_fd to get the file descriptor underlying a given
ringbuffer.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-12-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 9 +++++++++
 tools/lib/bpf/libbpf.map | 1 +
 tools/lib/bpf/ringbuf.c  | 5 +++++
 3 files changed, 15 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 53e2a645c560..114e306c6507 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1303,6 +1303,15 @@ LIBBPF_API size_t ring__avail_data_size(const struct ring *r);
  */
 LIBBPF_API size_t ring__size(const struct ring *r);
 
+/**
+ * @brief **ring__map_fd()** returns the file descriptor underlying the given
+ * ringbuffer.
+ *
+ * @param r A ringbuffer object.
+ * @return The underlying ringbuffer file descriptor
+ */
+LIBBPF_API int ring__map_fd(const struct ring *r);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index a116d0bb3c5d..1b4225327ab6 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -402,6 +402,7 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_uprobe_multi;
 		ring__avail_data_size;
 		ring__consumer_pos;
+		ring__map_fd;
 		ring__producer_pos;
 		ring__size;
 		ring_buffer__ring;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 98d0767dbb50..8aec20216b7b 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -366,6 +366,11 @@ size_t ring__size(const struct ring *r)
 	return r->mask + 1;
 }
 
+int ring__map_fd(const struct ring *r)
+{
+	return r->map_fd;
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From 6e38ba5291f9e082f9472a8ef682dc54cff0b3e4 Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:43 -0700
Subject: selftests/bpf: Add tests for ring__map_fd

Add tests for the new API ring__map_fd.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-13-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index c5be480a6ef6..c23f6c54b373 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -92,6 +92,7 @@ static void ringbuf_subtest(void)
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
 	struct ring *ring;
+	int map_fd;
 	unsigned long avail_data, ring_size, cons_pos, prod_pos;
 
 	skel = test_ringbuf_lskel__open();
@@ -168,6 +169,9 @@ static void ringbuf_subtest(void)
 	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_idx_0"))
 		goto cleanup;
 
+	map_fd = ring__map_fd(ring);
+	ASSERT_EQ(map_fd, skel->maps.ringbuf.map_fd, "ring_map_fd");
+
 	/* 2 submitted + 1 discarded records */
 	CHECK(skel->bss->avail_data != 3 * rec_sz,
 	      "err_avail_size", "exp %ld, got %ld\n",
-- 
cgit v1.2.3


From 16058ff28b7eedd62f1643beb841e3bd611674fe Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:44 -0700
Subject: libbpf: Add ring__consume

Add ring__consume to consume a single ringbuffer, analogous to
ring_buffer__consume.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-14-martin.kelly@crowdstrike.com
---
 tools/lib/bpf/libbpf.h   | 10 ++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 tools/lib/bpf/ringbuf.c  | 11 +++++++++++
 3 files changed, 22 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 114e306c6507..475378438545 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1312,6 +1312,16 @@ LIBBPF_API size_t ring__size(const struct ring *r);
  */
 LIBBPF_API int ring__map_fd(const struct ring *r);
 
+/**
+ * @brief **ring__consume()** consumes available ringbuffer data without event
+ * polling.
+ *
+ * @param r A ringbuffer object.
+ * @return The number of records consumed (or INT_MAX, whichever is less), or
+ * a negative number if any of the callbacks return an error.
+ */
+LIBBPF_API int ring__consume(struct ring *r);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 1b4225327ab6..cc973b678a39 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -401,6 +401,7 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
 		ring__avail_data_size;
+		ring__consume;
 		ring__consumer_pos;
 		ring__map_fd;
 		ring__producer_pos;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 8aec20216b7b..aacb64278a01 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -371,6 +371,17 @@ int ring__map_fd(const struct ring *r)
 	return r->map_fd;
 }
 
+int ring__consume(struct ring *r)
+{
+	int64_t res;
+
+	res = ringbuf_process_ring(r);
+	if (res < 0)
+		return libbpf_err(res);
+
+	return res > INT_MAX ? INT_MAX : res;
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
-- 
cgit v1.2.3


From cb3d7dd2d0dbe92ff3ebdd87fefc254f1c89aeeb Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Mon, 25 Sep 2023 14:50:45 -0700
Subject: selftests/bpf: Add tests for ring__consume

Add tests for new API ring__consume.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230925215045.2375758-15-martin.kelly@crowdstrike.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index c23f6c54b373..48c5695b7abf 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -304,6 +304,10 @@ static void ringbuf_subtest(void)
 	err = ring_buffer__consume(ringbuf);
 	CHECK(err < 0, "rb_consume", "failed: %d\b", err);
 
+	/* also consume using ring__consume to make sure it works the same */
+	err = ring__consume(ring);
+	ASSERT_GE(err, 0, "ring_consume");
+
 	/* 3 rounds, 2 samples each */
 	cnt = atomic_xchg(&sample_cnt, 0);
 	CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt);
-- 
cgit v1.2.3


From e2b2cd592adbd303bcc02451d32fedd511000fb0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:38 +0200
Subject: bpf: Add missed value to kprobe_multi link info

Add missed value to kprobe_multi link info to hold the stats of missed
kprobe_multi probe.

The missed counter gets incremented when fprobe fails the recursion
check or there's no rethook available for return probe. In either
case the attached bpf program is not executed.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Reviewed-by: Song Liu <song@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-3-jolsa@kernel.org
---
 include/uapi/linux/bpf.h       | 1 +
 kernel/trace/bpf_trace.c       | 1 +
 tools/include/uapi/linux/bpf.h | 1 +
 3 files changed, 3 insertions(+)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5f13db15a3c7..1da5b1bcce71 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6532,6 +6532,7 @@ struct bpf_link_info {
 			__aligned_u64 addrs;
 			__u32 count; /* in/out: kprobe_multi function count */
 			__u32 flags;
+			__u64 missed;
 		} kprobe_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 54827d04c9a6..6aec6e7d612a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2614,6 +2614,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
 	info->kprobe_multi.count = kmulti_link->cnt;
 	info->kprobe_multi.flags = kmulti_link->flags;
+	info->kprobe_multi.missed = kmulti_link->fp.nmissed;
 
 	if (!uaddrs)
 		return 0;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 5f13db15a3c7..1da5b1bcce71 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6532,6 +6532,7 @@ struct bpf_link_info {
 			__aligned_u64 addrs;
 			__u32 count; /* in/out: kprobe_multi function count */
 			__u32 flags;
+			__u64 missed;
 		} kprobe_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
-- 
cgit v1.2.3


From 3acf8ace68230e9558cf916847f1cc9f208abdf1 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:39 +0200
Subject: bpf: Add missed value to kprobe perf link info

Add missed value to kprobe attached through perf link info to
hold the stats of missed kprobe handler execution.

The kprobe's missed counter gets incremented when kprobe handler
is not executed due to another kprobe running on the same cpu.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-4-jolsa@kernel.org
---
 include/linux/trace_events.h   |  6 ++++--
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           | 14 ++++++++------
 kernel/trace/bpf_trace.c       |  5 +++--
 kernel/trace/trace_kprobe.c    | 14 +++++++++++---
 tools/include/uapi/linux/bpf.h |  1 +
 6 files changed, 28 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 21ae37e49319..5eb88a66eb68 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -761,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
 void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
-			    u64 *probe_offset, u64 *probe_addr);
+			    u64 *probe_offset, u64 *probe_addr,
+			    unsigned long *missed);
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 #else
@@ -801,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 static inline int bpf_get_perf_event_info(const struct perf_event *event,
 					  u32 *prog_id, u32 *fd_type,
 					  const char **buf, u64 *probe_offset,
-					  u64 *probe_addr)
+					  u64 *probe_addr, unsigned long *missed)
 {
 	return -EOPNOTSUPP;
 }
@@ -877,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event);
 extern int bpf_get_kprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **symbol,
 			       u64 *probe_offset, u64 *probe_addr,
+			       unsigned long *missed,
 			       bool perf_type_tracepoint);
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1da5b1bcce71..70bfa997e896 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6548,6 +6548,7 @@ struct bpf_link_info {
 					__u32 name_len;
 					__u32 offset; /* offset from func_name */
 					__u64 addr;
+					__u64 missed;
 				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
 				struct {
 					__aligned_u64 tp_name;   /* in/out */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 85c1d908f70f..6b5280f14a53 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3374,7 +3374,7 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
 static int bpf_perf_link_fill_common(const struct perf_event *event,
 				     char __user *uname, u32 ulen,
 				     u64 *probe_offset, u64 *probe_addr,
-				     u32 *fd_type)
+				     u32 *fd_type, unsigned long *missed)
 {
 	const char *buf;
 	u32 prog_id;
@@ -3385,7 +3385,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
 		return -EINVAL;
 
 	err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
-				      probe_offset, probe_addr);
+				      probe_offset, probe_addr, missed);
 	if (err)
 		return err;
 	if (!uname)
@@ -3408,6 +3408,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
 static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 				     struct bpf_link_info *info)
 {
+	unsigned long missed;
 	char __user *uname;
 	u64 addr, offset;
 	u32 ulen, type;
@@ -3416,7 +3417,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 	uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
 	ulen = info->perf_event.kprobe.name_len;
 	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
-					&type);
+					&type, &missed);
 	if (err)
 		return err;
 	if (type == BPF_FD_TYPE_KRETPROBE)
@@ -3425,6 +3426,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 		info->perf_event.type = BPF_PERF_EVENT_KPROBE;
 
 	info->perf_event.kprobe.offset = offset;
+	info->perf_event.kprobe.missed = missed;
 	if (!kallsyms_show_value(current_cred()))
 		addr = 0;
 	info->perf_event.kprobe.addr = addr;
@@ -3444,7 +3446,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
 	uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
 	ulen = info->perf_event.uprobe.name_len;
 	err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
-					&type);
+					&type, NULL);
 	if (err)
 		return err;
 
@@ -3480,7 +3482,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
 	uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
 	ulen = info->perf_event.tracepoint.name_len;
 	info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
-	return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL);
+	return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL);
 }
 
 static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
@@ -4813,7 +4815,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 
 		err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
 					      &buf, &probe_offset,
-					      &probe_addr);
+					      &probe_addr, NULL);
 		if (!err)
 			err = bpf_task_fd_query_copy(attr, uattr, prog_id,
 						     fd_type, buf,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6aec6e7d612a..f6a7d2524949 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2384,7 +2384,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
-			    u64 *probe_offset, u64 *probe_addr)
+			    u64 *probe_offset, u64 *probe_addr,
+			    unsigned long *missed)
 {
 	bool is_tracepoint, is_syscall_tp;
 	struct bpf_prog *prog;
@@ -2419,7 +2420,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 #ifdef CONFIG_KPROBE_EVENTS
 		if (flags & TRACE_EVENT_FL_KPROBE)
 			err = bpf_get_kprobe_info(event, fd_type, buf,
-						  probe_offset, probe_addr,
+						  probe_offset, probe_addr, missed,
 						  event->attr.type == PERF_TYPE_TRACEPOINT);
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 3d7a180a8427..961a78ffd6d2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1189,6 +1189,12 @@ static const struct file_operations kprobe_events_ops = {
 	.write		= probes_write,
 };
 
+static unsigned long trace_kprobe_missed(struct trace_kprobe *tk)
+{
+	return trace_kprobe_is_return(tk) ?
+		tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+}
+
 /* Probes profiling interfaces */
 static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
@@ -1200,8 +1206,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 		return 0;
 
 	tk = to_trace_kprobe(ev);
-	nmissed = trace_kprobe_is_return(tk) ?
-		tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+	nmissed = trace_kprobe_missed(tk);
 	seq_printf(m, "  %-44s %15lu %15lu\n",
 		   trace_probe_name(&tk->tp),
 		   trace_kprobe_nhit(tk),
@@ -1547,7 +1552,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func);
 
 int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 			const char **symbol, u64 *probe_offset,
-			u64 *probe_addr, bool perf_type_tracepoint)
+			u64 *probe_addr, unsigned long *missed,
+			bool perf_type_tracepoint)
 {
 	const char *pevent = trace_event_name(event->tp_event);
 	const char *group = event->tp_event->class->system;
@@ -1566,6 +1572,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 	*probe_addr = kallsyms_show_value(current_cred()) ?
 		      (unsigned long)tk->rp.kp.addr : 0;
 	*symbol = tk->symbol;
+	if (missed)
+		*missed = trace_kprobe_missed(tk);
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1da5b1bcce71..70bfa997e896 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6548,6 +6548,7 @@ struct bpf_link_info {
 					__u32 name_len;
 					__u32 offset; /* offset from func_name */
 					__u64 addr;
+					__u64 missed;
 				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
 				struct {
 					__aligned_u64 tp_name;   /* in/out */
-- 
cgit v1.2.3


From b24fc35521b09b5feaf5d06a75e8a43042592d0b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:41 +0200
Subject: bpftool: Display missed count for kprobe_multi link

Adding 'missed' field to display missed counts for kprobes
attached by kprobe multi link, like:

  # bpftool link
  5: kprobe_multi  prog 76
          kprobe.multi  func_cnt 1  missed 1
          addr             func [module]
          ffffffffa039c030 fp3_test [fprobe_test]

  # bpftool link -jp
  [{
          "id": 5,
          "type": "kprobe_multi",
          "prog_id": 76,
          "retprobe": false,
          "func_cnt": 1,
          "missed": 1,
          "funcs": [{
                  "addr": 18446744072102723632,
                  "func": "fp3_test",
                  "module": "fprobe_test"
              }
          ]
      }
  ]

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-6-jolsa@kernel.org
---
 tools/bpf/bpftool/link.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2e5c231e08ac..d15d74cd1bed 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -265,6 +265,7 @@ show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_bool_field(json_wtr, "retprobe",
 			 info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN);
 	jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count);
+	jsonw_uint_field(json_wtr, "missed", info->kprobe_multi.missed);
 	jsonw_name(json_wtr, "funcs");
 	jsonw_start_array(json_wtr);
 	addrs = u64_to_ptr(info->kprobe_multi.addrs);
@@ -641,6 +642,8 @@ static void show_kprobe_multi_plain(struct bpf_link_info *info)
 	else
 		printf("\n\tkprobe.multi  ");
 	printf("func_cnt %u  ", info->kprobe_multi.count);
+	if (info->kprobe_multi.missed)
+		printf("missed %llu  ", info->kprobe_multi.missed);
 	addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs);
 	qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64);
 
-- 
cgit v1.2.3


From b563b9bae8c3a6583e34820856dc6eafc2239aaf Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:42 +0200
Subject: bpftool: Display missed count for kprobe perf link

Adding 'missed' field to display missed counts for kprobes
attached by perf event link, like:

  # bpftool link
  5: perf_event  prog 82
          kprobe ffffffff815203e0 ksys_write
  6: perf_event  prog 83
          kprobe ffffffff811d1e50 scheduler_tick  missed 682217

  # bpftool link -jp
  [{
          "id": 5,
          "type": "perf_event",
          "prog_id": 82,
          "retprobe": false,
          "addr": 18446744071584220128,
          "func": "ksys_write",
          "offset": 0,
          "missed": 0
      },{
          "id": 6,
          "type": "perf_event",
          "prog_id": 83,
          "retprobe": false,
          "addr": 18446744071580753488,
          "func": "scheduler_tick",
          "offset": 0,
          "missed": 693469
      }
  ]

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-7-jolsa@kernel.org
---
 tools/bpf/bpftool/link.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index d15d74cd1bed..4b1407b05056 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -302,6 +302,7 @@ show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
 	jsonw_string_field(wtr, "func",
 			   u64_to_ptr(info->perf_event.kprobe.func_name));
 	jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset);
+	jsonw_uint_field(wtr, "missed", info->perf_event.kprobe.missed);
 }
 
 static void
@@ -686,6 +687,8 @@ static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
 	printf("%s", buf);
 	if (info->perf_event.kprobe.offset)
 		printf("+%#x", info->perf_event.kprobe.offset);
+	if (info->perf_event.kprobe.missed)
+		printf("  missed %llu", info->perf_event.kprobe.missed);
 	printf("  ");
 }
 
-- 
cgit v1.2.3


From 01e4ae474e39b855f911caec355bb79e722562b3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:43 +0200
Subject: selftests/bpf: Add test for missed counts of perf event link kprobe

Adding test that puts kprobe on bpf_fentry_test1 that calls
bpf_kfunc_common_test kfunc, which has also kprobe on.

The latter won't get triggered due to kprobe recursion check
and kprobe missed counter is incremented.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-8-jolsa@kernel.org
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        |  5 +++
 .../selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h  |  2 +
 tools/testing/selftests/bpf/prog_tests/missed.c    | 47 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/missed_kprobe.c  | 30 ++++++++++++++
 4 files changed, 84 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/missed.c
 create mode 100644 tools/testing/selftests/bpf/progs/missed_kprobe.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index cefc5dd72573..a5e246f7b202 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -138,6 +138,10 @@ __bpf_kfunc void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it)
 	it->cnt = 0;
 }
 
+__bpf_kfunc void bpf_kfunc_common_test(void)
+{
+}
+
 struct bpf_testmod_btf_type_tag_1 {
 	int a;
 };
@@ -343,6 +347,7 @@ BTF_SET8_START(bpf_testmod_common_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_kfunc_common_test)
 BTF_SET8_END(bpf_testmod_common_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = {
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
index f5c5b1375c24..7c664dd61059 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h
@@ -104,4 +104,6 @@ void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p);
 void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p);
 void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p);
 void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len);
+
+void bpf_kfunc_common_test(void) __ksym;
 #endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
new file mode 100644
index 000000000000..ca52be3d80f3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "missed_kprobe.skel.h"
+
+/*
+ * Putting kprobe on bpf_fentry_test1 that calls bpf_kfunc_common_test
+ * kfunc, which has also kprobe on. The latter won't get triggered due
+ * to kprobe recursion check and kprobe missed counter is incremented.
+ */
+static void test_missed_perf_kprobe(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_link_info info = {};
+	struct missed_kprobe *skel;
+	__u32 len = sizeof(info);
+	int err, prog_fd;
+
+	skel = missed_kprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_kprobe__open_and_load"))
+		goto cleanup;
+
+	err = missed_kprobe__attach(skel);
+	if (!ASSERT_OK(err, "missed_kprobe__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	err = bpf_link_get_info_by_fd(bpf_link__fd(skel->links.test2), &info, &len);
+	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+		goto cleanup;
+
+	ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "info.type");
+	ASSERT_EQ(info.perf_event.type, BPF_PERF_EVENT_KPROBE, "info.perf_event.type");
+	ASSERT_EQ(info.perf_event.kprobe.missed, 1, "info.perf_event.kprobe.missed");
+
+cleanup:
+	missed_kprobe__destroy(skel);
+}
+
+void test_missed(void)
+{
+	if (test__start_subtest("perf_kprobe"))
+		test_missed_perf_kprobe();
+}
diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe.c b/tools/testing/selftests/bpf/progs/missed_kprobe.c
new file mode 100644
index 000000000000..7f9ef701f5de
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_kprobe.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_kfunc_common_test();
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
-- 
cgit v1.2.3


From 59e83c0187c5eed648c28aea637a5cf3e246921b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:44 +0200
Subject: selftests/bpf: Add test for recursion counts of perf event link
 kprobe

Adding selftest that puts kprobe.multi on bpf_fentry_test1 that
calls bpf_kfunc_common_test kfunc which has 3 perf event kprobes
and 1 kprobe.multi attached.

Because fprobe (kprobe.multi attach layear) does not have strict
recursion check the kprobe's bpf_prog_active check is hit for test2-5.

Disabling this test for arm64, because there's no fprobe support yet.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Reviewed-by: Song Liu <song@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-9-jolsa@kernel.org
---
 tools/testing/selftests/bpf/DENYLIST.aarch64       |  1 +
 tools/testing/selftests/bpf/prog_tests/missed.c    | 51 ++++++++++++++++++++++
 .../selftests/bpf/progs/missed_kprobe_recursion.c  | 48 ++++++++++++++++++++
 3 files changed, 100 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 1e827c24761c..5c2cc7e8c5d0 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -10,3 +10,4 @@ fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_ma
 fill_link_info/kprobe_multi_link_info            # bpf_program__attach_kprobe_multi_opts unexpected error: -95
 fill_link_info/kretprobe_multi_link_info         # bpf_program__attach_kprobe_multi_opts unexpected error: -95
 fill_link_info/kprobe_multi_invalid_ubuff        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
+missed/kprobe_recursion                          # missed_kprobe_recursion__attach unexpected error: -95 (errno 95)
diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
index ca52be3d80f3..54aaf2f8ad8c 100644
--- a/tools/testing/selftests/bpf/prog_tests/missed.c
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "missed_kprobe.skel.h"
+#include "missed_kprobe_recursion.skel.h"
 
 /*
  * Putting kprobe on bpf_fentry_test1 that calls bpf_kfunc_common_test
@@ -40,8 +41,58 @@ cleanup:
 	missed_kprobe__destroy(skel);
 }
 
+static __u64 get_missed_count(int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+
+	err = bpf_prog_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		return (__u64) -1;
+	return info.recursion_misses;
+}
+
+/*
+ * Putting kprobe.multi on bpf_fentry_test1 that calls bpf_kfunc_common_test
+ * kfunc which has 3 perf event kprobes and 1 kprobe.multi attached.
+ *
+ * Because fprobe (kprobe.multi attach layear) does not have strict recursion
+ * check the kprobe's bpf_prog_active check is hit for test2-5.
+ */
+static void test_missed_kprobe_recursion(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct missed_kprobe_recursion *skel;
+	int err, prog_fd;
+
+	skel = missed_kprobe_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_kprobe_recursion__open_and_load"))
+		goto cleanup;
+
+	err = missed_kprobe_recursion__attach(skel);
+	if (!ASSERT_OK(err, "missed_kprobe_recursion__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test1)), 0, "test1_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses");
+
+cleanup:
+	missed_kprobe_recursion__destroy(skel);
+}
+
 void test_missed(void)
 {
 	if (test__start_subtest("perf_kprobe"))
 		test_missed_perf_kprobe();
+	if (test__start_subtest("kprobe_recursion"))
+		test_missed_kprobe_recursion();
 }
diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c
new file mode 100644
index 000000000000..8ea71cbd6c45
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe.multi/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_kfunc_common_test();
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test3(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test4(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe.multi/bpf_kfunc_common_test")
+int test5(struct pt_regs *ctx)
+{
+	return 0;
+}
-- 
cgit v1.2.3


From 85981e0f9e9fc882578f0ad7488d6c59193dd187 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Sep 2023 23:31:45 +0200
Subject: selftests/bpf: Add test for recursion counts of perf event link
 tracepoint

Adding selftest that puts kprobe on bpf_fentry_test1 that calls bpf_printk
and invokes bpf_trace_printk tracepoint. The bpf_trace_printk tracepoint
has test[234] programs attached to it.

Because kprobe execution goes through bpf_prog_active check, programs
attached to the tracepoint will fail the recursion check and increment the
recursion_misses stats.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Reviewed-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/bpf/20230920213145.1941596-10-jolsa@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/missed.c    | 40 +++++++++++++++++++++
 .../selftests/bpf/progs/missed_tp_recursion.c      | 41 ++++++++++++++++++++++
 2 files changed, 81 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/missed_tp_recursion.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
index 54aaf2f8ad8c..24ade11f5c05 100644
--- a/tools/testing/selftests/bpf/prog_tests/missed.c
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -2,6 +2,7 @@
 #include <test_progs.h>
 #include "missed_kprobe.skel.h"
 #include "missed_kprobe_recursion.skel.h"
+#include "missed_tp_recursion.skel.h"
 
 /*
  * Putting kprobe on bpf_fentry_test1 that calls bpf_kfunc_common_test
@@ -89,10 +90,49 @@ cleanup:
 	missed_kprobe_recursion__destroy(skel);
 }
 
+/*
+ * Putting kprobe on bpf_fentry_test1 that calls bpf_printk and invokes
+ * bpf_trace_printk tracepoint. The bpf_trace_printk tracepoint has test[234]
+ * programs attached to it.
+ *
+ * Because kprobe execution goes through bpf_prog_active check, programs
+ * attached to the tracepoint will fail the recursion check and increment
+ * the recursion_misses stats.
+ */
+static void test_missed_tp_recursion(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct missed_tp_recursion *skel;
+	int err, prog_fd;
+
+	skel = missed_tp_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_tp_recursion__open_and_load"))
+		goto cleanup;
+
+	err = missed_tp_recursion__attach(skel);
+	if (!ASSERT_OK(err, "missed_tp_recursion__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test1)), 0, "test1_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
+
+cleanup:
+	missed_tp_recursion__destroy(skel);
+}
+
 void test_missed(void)
 {
 	if (test__start_subtest("perf_kprobe"))
 		test_missed_perf_kprobe();
 	if (test__start_subtest("kprobe_recursion"))
 		test_missed_kprobe_recursion();
+	if (test__start_subtest("tp_recursion"))
+		test_missed_tp_recursion();
 }
diff --git a/tools/testing/selftests/bpf/progs/missed_tp_recursion.c b/tools/testing/selftests/bpf/progs/missed_tp_recursion.c
new file mode 100644
index 000000000000..762385f827c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_tp_recursion.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_printk("test");
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test3(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test4(struct pt_regs *ctx)
+{
+	return 0;
+}
-- 
cgit v1.2.3


From 98cfbe4234a41e4d7baf3f58b95cab5fc50d1492 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 19 Sep 2023 10:54:01 -0300
Subject: selftests/tc-testing: localize test resources

As of today, the current tdc architecture creates one netns and uses it
to run all tests. This assumption was embedded into the nsPlugin which
carried over as how the tests were written.

The tdc tests are by definition self contained and can,
theoretically, run in parallel. Even though in the kernel they will
serialize over the rtnl lock, we should expect a significant speedup of the
total wall time for the entire test suite, which is hitting close to
1100 tests at this point.

A first step to achieve this goal is to remove sharing of global resources like
veth/dummy interfaces and the netns. In this patch we 'localize' these
resources on a per test basis. Each test gets it's own netns, VETH/dummy interfaces.
The resources are spawned in the pre_suite phase, where tdc will prepare
all netns and interfaces for all tests. This is done in order to avoid
concurrency issues with netns / interfaces spawning and commands using
them. As tdc progresses, the resources are deleted after each test finishes
executing.

Tests that don't use the nsPlugin still run under the root namespace,
but are now required to manage any external resources like interfaces.
These cannot be parallelized as their definition doesn't allow it.
On the other hand, when using the nsPlugin, tests don't need to create
dummy/veth interfaces as these are handled already.

Tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/tc-testing/TdcPlugin.py    |   4 +-
 .../selftests/tc-testing/plugin-lib/nsPlugin.py    | 185 +++++++++++++++------
 .../selftests/tc-testing/plugin-lib/rootPlugin.py  |   4 +-
 .../tc-testing/plugin-lib/valgrindPlugin.py        |   5 +-
 tools/testing/selftests/tc-testing/tdc.py          | 129 +++++++++-----
 5 files changed, 229 insertions(+), 98 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py
index 79f3ca8617c9..aae85ce4f776 100644
--- a/tools/testing/selftests/tc-testing/TdcPlugin.py
+++ b/tools/testing/selftests/tc-testing/TdcPlugin.py
@@ -5,10 +5,10 @@ class TdcPlugin:
         super().__init__()
         print(' -- {}.__init__'.format(self.sub_class))
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         '''run commands before test_runner goes into a test loop'''
         self.testcount = testcount
-        self.testidlist = testidlist
+        self.testlist = testlist
         if self.args.verbose > 1:
             print(' -- {}.pre_suite'.format(self.sub_class))
 
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
index 9539cffa9e5e..78acbfa5af9d 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
@@ -3,6 +3,7 @@ import signal
 from string import Template
 import subprocess
 import time
+from functools import cached_property
 from TdcPlugin import TdcPlugin
 
 from tdc_config import *
@@ -12,26 +13,77 @@ class SubPlugin(TdcPlugin):
         self.sub_class = 'ns/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
-        '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+    def pre_suite(self, testcount, testlist):
+        super().pre_suite(testcount, testlist)
 
-        if self.args.namespace:
-            self._ns_create()
-        else:
-            self._ports_create()
+        print("Setting up namespaces and devices...")
 
-    def post_suite(self, index):
-        '''run commands after test_runner goes into a test loop'''
-        super().post_suite(index)
+        original = self.args.NAMES
+
+        for t in testlist:
+            if 'skip' in t and t['skip'] == 'yes':
+                continue
+
+            if 'nsPlugin' not in t['plugins']:
+                continue
+
+            shadow = {}
+            shadow['IP'] = original['IP']
+            shadow['TC'] = original['TC']
+            shadow['NS'] = '{}-{}'.format(original['NS'], t['random'])
+            shadow['DEV0'] = '{}id{}'.format(original['DEV0'], t['id'])
+            shadow['DEV1'] = '{}id{}'.format(original['DEV1'], t['id'])
+            shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], t['id'])
+            shadow['DEV2'] = original['DEV2']
+            self.args.NAMES = shadow
+
+            if self.args.namespace:
+                self._ns_create()
+            else:
+                self._ports_create()
+
+        self.args.NAMES = original
+
+    def pre_case(self, caseinfo, test_skip):
         if self.args.verbose:
-            print('{}.post_suite'.format(self.sub_class))
+            print('{}.pre_case'.format(self.sub_class))
+
+        if test_skip:
+            return
+
+        # Make sure the netns is visible in the fs
+        while True:
+            self._proc_check()
+            try:
+                ns = self.args.NAMES['NS']
+                f = open('/run/netns/{}'.format(ns))
+                f.close()
+                break
+            except:
+                continue
+
+    def post_case(self):
+        if self.args.verbose:
+            print('{}.post_case'.format(self.sub_class))
 
         if self.args.namespace:
             self._ns_destroy()
         else:
             self._ports_destroy()
 
+    def post_suite(self, index):
+        if self.args.verbose:
+            print('{}.post_suite'.format(self.sub_class))
+
+        # Make sure we don't leak resources
+        for f in os.listdir('/run/netns/'):
+            cmd = self._replace_keywords("$IP netns del {}".format(f))
+
+            if self.args.verbose > 3:
+                print('_exec_cmd:  command "{}"'.format(cmd))
+
+            subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+
     def add_args(self, parser):
         super().add_args(parser)
         self.argparser_group = self.argparser.add_argument_group(
@@ -77,18 +129,43 @@ class SubPlugin(TdcPlugin):
             print('adjust_command:  return command [{}]'.format(command))
         return command
 
-    def _ports_create(self):
-        cmd = '$IP link add $DEV0 type veth peer name $DEV1'
-        self._exec_cmd('pre', cmd)
-        cmd = '$IP link set $DEV0 up'
-        self._exec_cmd('pre', cmd)
+    def _ports_create_cmds(self):
+        cmds = []
+
+        cmds.append(self._replace_keywords('link add $DEV0 type veth peer name $DEV1'))
+        cmds.append(self._replace_keywords('link set $DEV0 up'))
+        cmds.append(self._replace_keywords('link add $DUMMY type dummy'))
         if not self.args.namespace:
-            cmd = '$IP link set $DEV1 up'
-            self._exec_cmd('pre', cmd)
+            cmds.append(self._replace_keywords('link set $DEV1 up'))
+
+        return cmds
+
+    def _ports_create(self):
+        self._exec_cmd_batched('pre', self._ports_create_cmds())
+
+    def _ports_destroy_cmd(self):
+        return self._replace_keywords('link del $DEV0')
 
     def _ports_destroy(self):
-        cmd = '$IP link del $DEV0'
-        self._exec_cmd('post', cmd)
+        self._exec_cmd('post', self._ports_destroy_cmd())
+
+    def _ns_create_cmds(self):
+        cmds = []
+
+        if self.args.namespace:
+            ns = self.args.NAMES['NS']
+
+            cmds.append(self._replace_keywords('netns add {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns)))
+
+            if self.args.device:
+                cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns)))
+                cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns)))
+
+        return cmds
 
     def _ns_create(self):
         '''
@@ -96,18 +173,10 @@ class SubPlugin(TdcPlugin):
         the required network devices for it.
         '''
         self._ports_create()
-        if self.args.namespace:
-            cmd = '$IP netns add {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            if self.args.device:
-                cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
-                cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
+        self._exec_cmd_batched('pre', self._ns_create_cmds())
+
+    def _ns_destroy_cmd(self):
+        return self._replace_keywords('netns delete {}'.format(self.args.NAMES['NS']))
 
     def _ns_destroy(self):
         '''
@@ -115,35 +184,49 @@ class SubPlugin(TdcPlugin):
         devices as well)
         '''
         if self.args.namespace:
-            cmd = '$IP netns delete {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('post', cmd)
+            self._exec_cmd('post', self._ns_destroy_cmd())
+            self._ports_destroy()
+
+    @cached_property
+    def _proc(self):
+        ip = self._replace_keywords("$IP -b -")
+        proc = subprocess.Popen(ip,
+            shell=True,
+            stdin=subprocess.PIPE,
+            env=ENVIR)
+
+        return proc
+
+    def _proc_check(self):
+        proc = self._proc
+
+        proc.poll()
+
+        if proc.returncode is not None and proc.returncode != 0:
+            raise RuntimeError("iproute2 exited with an error code")
 
     def _exec_cmd(self, stage, command):
         '''
         Perform any required modifications on an executable command, then run
         it in a subprocess and return the results.
         '''
-        if '$' in command:
-            command = self._replace_keywords(command)
 
-        self.adjust_command(stage, command)
-        if self.args.verbose:
+        if self.args.verbose > 3:
             print('_exec_cmd:  command "{}"'.format(command))
-        proc = subprocess.Popen(command,
-            shell=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=ENVIR)
-        (rawout, serr) = proc.communicate()
 
-        if proc.returncode != 0 and len(serr) > 0:
-            foutput = serr.decode("utf-8")
-        else:
-            foutput = rawout.decode("utf-8")
+        proc = self._proc
+
+        proc.stdin.write((command + '\n').encode())
+        proc.stdin.flush()
+
+        if self.args.verbose > 3:
+            print('_exec_cmd proc: {}'.format(proc))
+
+        self._proc_check()
 
-        proc.stdout.close()
-        proc.stderr.close()
-        return proc, foutput
+    def _exec_cmd_batched(self, stage, commands):
+        for cmd in commands:
+            self._exec_cmd(stage, cmd)
 
     def _replace_keywords(self, cmd):
         """
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
index e36775bd4d12..8762c0f4a095 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py
@@ -10,9 +10,9 @@ class SubPlugin(TdcPlugin):
         self.sub_class = 'root/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         # run commands before test_runner goes into a test loop
-        super().pre_suite(testcount, testidlist)
+        super().pre_suite(testcount, testlist)
 
         if os.geteuid():
             print('This script must be run with root privileges', file=sys.stderr)
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
index 4bb866575ea1..c6f61649c430 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py
@@ -25,9 +25,10 @@ class SubPlugin(TdcPlugin):
         self._tsr = TestSuiteReport()
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testist):
         '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+        self.testidlist = [tidx['id'] for tidx in testlist]
+        super().pre_suite(testcount, testlist)
         if self.args.verbose > 1:
             print('{}.pre_suite'.format(self.sub_class))
         if self.args.valgrind:
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index b98256f38447..3914caa14de1 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -16,6 +16,7 @@ import json
 import subprocess
 import time
 import traceback
+import random
 from collections import OrderedDict
 from string import Template
 
@@ -38,12 +39,11 @@ class PluginMgrTestFail(Exception):
 class PluginMgr:
     def __init__(self, argparser):
         super().__init__()
-        self.plugins = {}
+        self.plugins = set()
         self.plugin_instances = []
         self.failed_plugins = {}
         self.argparser = argparser
 
-        # TODO, put plugins in order
         plugindir = os.getenv('TDC_PLUGIN_DIR', './plugins')
         for dirpath, dirnames, filenames in os.walk(plugindir):
             for fn in filenames:
@@ -53,32 +53,43 @@ class PluginMgr:
                     not fn.startswith('.#')):
                     mn = fn[0:-3]
                     foo = importlib.import_module('plugins.' + mn)
-                    self.plugins[mn] = foo
-                    self.plugin_instances.append(foo.SubPlugin())
+                    self.plugins.add(mn)
+                    self.plugin_instances[mn] = foo.SubPlugin()
 
     def load_plugin(self, pgdir, pgname):
         pgname = pgname[0:-3]
+        self.plugins.add(pgname)
+
         foo = importlib.import_module('{}.{}'.format(pgdir, pgname))
-        self.plugins[pgname] = foo
-        self.plugin_instances.append(foo.SubPlugin())
-        self.plugin_instances[-1].check_args(self.args, None)
+
+        # nsPlugin must always be the first one
+        if pgname == "nsPlugin":
+            self.plugin_instances.insert(0, (pgname, foo.SubPlugin()))
+            self.plugin_instances[0][1].check_args(self.args, None)
+        else:
+            self.plugin_instances.append((pgname, foo.SubPlugin()))
+            self.plugin_instances[-1][1].check_args(self.args, None)
 
     def get_required_plugins(self, testlist):
         '''
         Get all required plugins from the list of test cases and return
         all unique items.
         '''
-        reqs = []
+        reqs = set()
         for t in testlist:
             try:
                 if 'requires' in t['plugins']:
                     if isinstance(t['plugins']['requires'], list):
-                        reqs.extend(t['plugins']['requires'])
+                        reqs.update(set(t['plugins']['requires']))
                     else:
-                        reqs.append(t['plugins']['requires'])
+                        reqs.add(t['plugins']['requires'])
+                    t['plugins'] = t['plugins']['requires']
+                else:
+                    t['plugins'] = []
             except KeyError:
+                t['plugins'] = []
                 continue
-        reqs = get_unique_item(reqs)
+
         return reqs
 
     def load_required_plugins(self, reqs, parser, args, remaining):
@@ -115,15 +126,17 @@ class PluginMgr:
         return args
 
     def call_pre_suite(self, testcount, testidlist):
-        for pgn_inst in self.plugin_instances:
+        for (_, pgn_inst) in self.plugin_instances:
             pgn_inst.pre_suite(testcount, testidlist)
 
     def call_post_suite(self, index):
-        for pgn_inst in reversed(self.plugin_instances):
+        for (_, pgn_inst) in reversed(self.plugin_instances):
             pgn_inst.post_suite(index)
 
     def call_pre_case(self, caseinfo, *, test_skip=False):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             try:
                 pgn_inst.pre_case(caseinfo, test_skip)
             except Exception as ee:
@@ -133,29 +146,37 @@ class PluginMgr:
                 print('testid is {}'.format(caseinfo['id']))
                 raise
 
-    def call_post_case(self):
-        for pgn_inst in reversed(self.plugin_instances):
+    def call_post_case(self, caseinfo):
+        for (pgn, pgn_inst) in reversed(self.plugin_instances):
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.post_case()
 
-    def call_pre_execute(self):
-        for pgn_inst in self.plugin_instances:
+    def call_pre_execute(self, caseinfo):
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.pre_execute()
 
-    def call_post_execute(self):
-        for pgn_inst in reversed(self.plugin_instances):
+    def call_post_execute(self, caseinfo):
+        for (pgn, pgn_inst) in reversed(self.plugin_instances):
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.post_execute()
 
     def call_add_args(self, parser):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
             parser = pgn_inst.add_args(parser)
         return parser
 
     def call_check_args(self, args, remaining):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
             pgn_inst.check_args(args, remaining)
 
-    def call_adjust_command(self, stage, command):
-        for pgn_inst in self.plugin_instances:
+    def call_adjust_command(self, caseinfo, stage, command):
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             command = pgn_inst.adjust_command(stage, command)
         return command
 
@@ -177,7 +198,7 @@ def replace_keywords(cmd):
     return subcmd
 
 
-def exec_cmd(args, pm, stage, command):
+def exec_cmd(caseinfo, args, pm, stage, command):
     """
     Perform any required modifications on an executable command, then run
     it in a subprocess and return the results.
@@ -187,9 +208,10 @@ def exec_cmd(args, pm, stage, command):
     if '$' in command:
         command = replace_keywords(command)
 
-    command = pm.call_adjust_command(stage, command)
+    command = pm.call_adjust_command(caseinfo, stage, command)
     if args.verbose > 0:
         print('command "{}"'.format(command))
+
     proc = subprocess.Popen(command,
         shell=True,
         stdout=subprocess.PIPE,
@@ -211,7 +233,7 @@ def exec_cmd(args, pm, stage, command):
     return proc, foutput
 
 
-def prepare_env(args, pm, stage, prefix, cmdlist, output = None):
+def prepare_env(caseinfo, args, pm, stage, prefix, cmdlist, output = None):
     """
     Execute the setup/teardown commands for a test case.
     Optionally terminate test execution if the command fails.
@@ -229,7 +251,7 @@ def prepare_env(args, pm, stage, prefix, cmdlist, output = None):
         if not cmd:
             continue
 
-        (proc, foutput) = exec_cmd(args, pm, stage, cmd)
+        (proc, foutput) = exec_cmd(caseinfo, args, pm, stage, cmd)
 
         if proc and (proc.returncode not in exit_codes):
             print('', file=sys.stderr)
@@ -352,6 +374,10 @@ def find_in_json_other(res, outputJSONVal, matchJSONVal, matchJSONKey=None):
 
 def run_one_test(pm, args, index, tidx):
     global NAMES
+    ns = NAMES['NS']
+    dev0 = NAMES['DEV0']
+    dev1 = NAMES['DEV1']
+    dummy = NAMES['DUMMY']
     result = True
     tresult = ""
     tap = ""
@@ -366,38 +392,42 @@ def run_one_test(pm, args, index, tidx):
             res.set_result(ResultState.skip)
             res.set_errormsg('Test case designated as skipped.')
             pm.call_pre_case(tidx, test_skip=True)
-            pm.call_post_execute()
+            pm.call_post_execute(tidx)
             return res
 
     if 'dependsOn' in tidx:
         if (args.verbose > 0):
             print('probe command for test skip')
-        (p, procout) = exec_cmd(args, pm, 'execute', tidx['dependsOn'])
+        (p, procout) = exec_cmd(tidx, args, pm, 'execute', tidx['dependsOn'])
         if p:
             if (p.returncode != 0):
                 res = TestResult(tidx['id'], tidx['name'])
                 res.set_result(ResultState.skip)
                 res.set_errormsg('probe command: test skipped.')
                 pm.call_pre_case(tidx, test_skip=True)
-                pm.call_post_execute()
+                pm.call_post_execute(tidx)
                 return res
 
     # populate NAMES with TESTID for this test
     NAMES['TESTID'] = tidx['id']
+    NAMES['NS'] = '{}-{}'.format(NAMES['NS'], tidx['random'])
+    NAMES['DEV0'] = '{}id{}'.format(NAMES['DEV0'], tidx['id'])
+    NAMES['DEV1'] = '{}id{}'.format(NAMES['DEV1'], tidx['id'])
+    NAMES['DUMMY'] = '{}id{}'.format(NAMES['DUMMY'], tidx['id'])
 
     pm.call_pre_case(tidx)
-    prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"])
+    prepare_env(tidx, args, pm, 'setup', "-----> prepare stage", tidx["setup"])
 
     if (args.verbose > 0):
         print('-----> execute stage')
-    pm.call_pre_execute()
-    (p, procout) = exec_cmd(args, pm, 'execute', tidx["cmdUnderTest"])
+    pm.call_pre_execute(tidx)
+    (p, procout) = exec_cmd(tidx, args, pm, 'execute', tidx["cmdUnderTest"])
     if p:
         exit_code = p.returncode
     else:
         exit_code = None
 
-    pm.call_post_execute()
+    pm.call_post_execute(tidx)
 
     if (exit_code is None or exit_code != int(tidx["expExitCode"])):
         print("exit: {!r}".format(exit_code))
@@ -409,7 +439,7 @@ def run_one_test(pm, args, index, tidx):
     else:
         if args.verbose > 0:
             print('-----> verify stage')
-        (p, procout) = exec_cmd(args, pm, 'verify', tidx["verifyCmd"])
+        (p, procout) = exec_cmd(tidx, args, pm, 'verify', tidx["verifyCmd"])
         if procout:
             if 'matchJSON' in tidx:
                 verify_by_json(procout, res, tidx, args, pm)
@@ -431,13 +461,20 @@ def run_one_test(pm, args, index, tidx):
         else:
             res.set_result(ResultState.success)
 
-    prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
-    pm.call_post_case()
+    prepare_env(tidx, args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
+    pm.call_post_case(tidx)
 
     index += 1
 
     # remove TESTID from NAMES
     del(NAMES['TESTID'])
+
+    # Restore names
+    NAMES['NS'] = ns
+    NAMES['DEV0'] = dev0
+    NAMES['DEV1'] = dev1
+    NAMES['DUMMY'] = dummy
+
     return res
 
 def test_runner(pm, args, filtered_tests):
@@ -461,7 +498,7 @@ def test_runner(pm, args, filtered_tests):
     tsr = TestSuiteReport()
 
     try:
-        pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
+        pm.call_pre_suite(tcount, testlist)
     except Exception as ee:
         ex_type, ex, ex_tb = sys.exc_info()
         print('Exception {} {} (caught in pre_suite).'.
@@ -661,7 +698,6 @@ def get_id_list(alltests):
     """
     return [x["id"] for x in alltests]
 
-
 def check_case_id(alltests):
     """
     Check for duplicate test case IDs.
@@ -683,7 +719,6 @@ def generate_case_ids(alltests):
     If a test case has a blank ID field, generate a random hex ID for it
     and then write the test cases back to disk.
     """
-    import random
     for c in alltests:
         if (c["id"] == ""):
             while True:
@@ -742,6 +777,9 @@ def filter_tests_by_category(args, testlist):
 
     return answer
 
+def set_random(alltests):
+    for tidx in alltests:
+        tidx['random'] = random.getrandbits(32)
 
 def get_test_cases(args):
     """
@@ -840,6 +878,8 @@ def set_operation_mode(pm, parser, args, remaining):
         list_test_cases(alltests)
         exit(0)
 
+    set_random(alltests)
+
     exit_code = 0 # KSFT_PASS
     if len(alltests):
         req_plugins = pm.get_required_plugins(alltests)
@@ -883,6 +923,13 @@ def main():
     Start of execution; set up argument parser and get the arguments,
     and start operations.
     """
+    import resource
+
+    if sys.version_info.major < 3 or sys.version_info.minor < 8:
+        sys.exit("tdc requires at least python 3.8")
+
+    resource.setrlimit(resource.RLIMIT_NOFILE, (1048576, 1048576))
+
     parser = args_parse()
     parser = set_args(parser)
     pm = PluginMgr(parser)
-- 
cgit v1.2.3


From d227cc0b1ee12560f7489239fc69ba6a10b14607 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 19 Sep 2023 10:54:02 -0300
Subject: selftests/tc-testing: update test definitions for local resources

With resources localized on a per test basis, some tests definitions
either contain redundant commands, were wrong or could be simplified.
Update all of them to match the new requirements.

Tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../tc-testing/tc-tests/actions/connmark.json      |  45 ++++
 .../tc-testing/tc-tests/actions/csum.json          |  69 +++++
 .../selftests/tc-testing/tc-tests/actions/ct.json  |  54 ++++
 .../tc-testing/tc-tests/actions/ctinfo.json        |  36 +++
 .../tc-testing/tc-tests/actions/gact.json          |  75 ++++++
 .../tc-testing/tc-tests/actions/gate.json          |  36 +++
 .../selftests/tc-testing/tc-tests/actions/ife.json | 144 +++++++++++
 .../tc-testing/tc-tests/actions/mirred.json        |  72 ++++++
 .../tc-testing/tc-tests/actions/mpls.json          | 159 ++++++++++++
 .../selftests/tc-testing/tc-tests/actions/nat.json |  81 ++++++
 .../tc-testing/tc-tests/actions/pedit.json         | 198 ++++++++++++++
 .../tc-testing/tc-tests/actions/police.json        | 102 ++++++++
 .../tc-testing/tc-tests/actions/sample.json        |  87 +++++++
 .../tc-testing/tc-tests/actions/simple.json        |  27 ++
 .../tc-testing/tc-tests/actions/skbedit.json       |  90 +++++++
 .../tc-testing/tc-tests/actions/skbmod.json        |  54 ++++
 .../tc-testing/tc-tests/actions/tunnel_key.json    | 117 +++++++++
 .../tc-testing/tc-tests/actions/vlan.json          | 108 ++++++++
 .../selftests/tc-testing/tc-tests/actions/xt.json  |  24 ++
 .../selftests/tc-testing/tc-tests/filters/bpf.json |  10 +-
 .../selftests/tc-testing/tc-tests/filters/fw.json  | 266 ++++++++++---------
 .../tc-testing/tc-tests/filters/matchall.json      | 141 +++++-----
 .../tc-testing/tc-tests/infra/actions.json         | 144 +++++------
 .../tc-testing/tc-tests/infra/filter.json          |   9 +-
 .../selftests/tc-testing/tc-tests/qdiscs/cake.json |  82 ++----
 .../selftests/tc-testing/tc-tests/qdiscs/cbs.json  |  38 +--
 .../tc-testing/tc-tests/qdiscs/choke.json          |  30 +--
 .../tc-testing/tc-tests/qdiscs/codel.json          |  34 +--
 .../selftests/tc-testing/tc-tests/qdiscs/drr.json  |  10 +-
 .../selftests/tc-testing/tc-tests/qdiscs/etf.json  |  18 +-
 .../selftests/tc-testing/tc-tests/qdiscs/ets.json  | 284 ++++++++++++---------
 .../selftests/tc-testing/tc-tests/qdiscs/fifo.json |  98 ++++---
 .../selftests/tc-testing/tc-tests/qdiscs/fq.json   |  68 ++---
 .../tc-testing/tc-tests/qdiscs/fq_codel.json       |  54 +---
 .../tc-testing/tc-tests/qdiscs/fq_pie.json         |   5 +-
 .../selftests/tc-testing/tc-tests/qdiscs/gred.json |  28 +-
 .../selftests/tc-testing/tc-tests/qdiscs/hfsc.json |  26 +-
 .../selftests/tc-testing/tc-tests/qdiscs/hhf.json  |  36 +--
 .../selftests/tc-testing/tc-tests/qdiscs/htb.json  |  46 +---
 .../tc-testing/tc-tests/qdiscs/ingress.json        |  36 +--
 .../tc-testing/tc-tests/qdiscs/netem.json          |  62 ++---
 .../tc-testing/tc-tests/qdiscs/pfifo_fast.json     |  18 +-
 .../selftests/tc-testing/tc-tests/qdiscs/plug.json |  30 +--
 .../selftests/tc-testing/tc-tests/qdiscs/prio.json |  85 +++---
 .../selftests/tc-testing/tc-tests/qdiscs/qfq.json  |  39 +--
 .../selftests/tc-testing/tc-tests/qdiscs/red.json  |  34 +--
 .../selftests/tc-testing/tc-tests/qdiscs/sfb.json  |  48 +---
 .../selftests/tc-testing/tc-tests/qdiscs/sfq.json  |  40 +--
 .../tc-testing/tc-tests/qdiscs/skbprio.json        |  16 +-
 .../selftests/tc-testing/tc-tests/qdiscs/tbf.json  |  36 +--
 .../selftests/tc-testing/tc-tests/qdiscs/teql.json |  34 +--
 51 files changed, 2369 insertions(+), 1114 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 0de2f79ea329..3d0f9310bde4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -6,6 +6,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -30,6 +33,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -54,6 +60,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -78,6 +87,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -102,6 +114,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -126,6 +141,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -150,6 +168,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -174,6 +195,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -198,6 +222,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -222,6 +249,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -246,6 +276,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -271,6 +304,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -295,6 +331,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -320,6 +359,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
@@ -345,6 +387,9 @@
             "actions",
             "connmark"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action connmark",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index 072febf25f55..56e11136d0f6 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -6,6 +6,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -30,6 +33,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -54,6 +60,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -78,6 +87,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -102,6 +114,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -126,6 +141,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -150,6 +168,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -174,6 +195,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -198,6 +222,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -222,6 +249,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -246,6 +276,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -270,6 +303,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -294,6 +330,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -318,6 +357,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -342,6 +384,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -366,6 +411,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -390,6 +438,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -414,6 +465,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -438,6 +492,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -461,6 +518,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -485,6 +545,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -508,6 +571,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
@@ -533,6 +599,9 @@
             "actions",
             "csum"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action csum",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
index bd843ab00a58..7d07c55bb668 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
@@ -6,6 +6,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -30,6 +33,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -54,6 +60,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -78,6 +87,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -102,6 +114,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -126,6 +141,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -150,6 +168,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -174,6 +195,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -198,6 +222,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -222,6 +249,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -246,6 +276,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -270,6 +303,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -294,6 +330,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -318,6 +357,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -342,6 +384,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -366,6 +411,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -390,6 +438,9 @@
             "actions",
             "ct"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ct",
@@ -415,6 +466,9 @@
             "ct",
 	    "scapy"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
 	"plugins": {
 		"requires": [
 			"nsPlugin",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ctinfo.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ctinfo.json
index d9710c067eb7..bb54d71241a0 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ctinfo.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ctinfo.json
@@ -6,6 +6,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action ctinfo",
@@ -30,6 +33,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -54,6 +60,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action ctinfo",
@@ -78,6 +87,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action ctinfo",
@@ -102,6 +114,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -132,6 +147,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -162,6 +180,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -192,6 +213,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action ctinfo",
@@ -219,6 +243,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -246,6 +273,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -271,6 +301,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
@@ -295,6 +328,9 @@
             "actions",
             "ctinfo"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ctinfo",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index c652e8c1157d..0fcd52742939 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -6,6 +6,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -30,6 +33,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -54,6 +60,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -78,6 +87,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -102,6 +114,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -126,6 +141,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -150,6 +168,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -175,6 +196,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -199,6 +223,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -223,6 +250,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -252,6 +282,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             "$TC actions add action reclassify index 101",
             "$TC actions add action reclassify index 102",
@@ -273,6 +306,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -298,6 +334,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -323,6 +362,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -348,6 +390,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -373,6 +418,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -398,6 +446,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -422,6 +473,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -448,6 +502,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -473,6 +530,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -497,6 +557,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -521,6 +584,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -544,6 +610,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -568,6 +637,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
@@ -593,6 +665,9 @@
             "actions",
             "gact"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gact",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gate.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gate.json
index e16a4963fdd2..db645c22ad7b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gate.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gate.json
@@ -6,6 +6,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action gate",
@@ -30,6 +33,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -54,6 +60,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action gate",
@@ -78,6 +87,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action gate",
@@ -102,6 +114,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -132,6 +147,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -162,6 +180,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -192,6 +213,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action gate",
@@ -219,6 +243,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -246,6 +273,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -271,6 +301,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
@@ -295,6 +328,9 @@
             "actions",
             "gate"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action gate",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index 459bcad35810..f587a32e44c4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -6,6 +6,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -30,6 +33,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -54,6 +60,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -78,6 +87,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -102,6 +114,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -126,6 +141,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -150,6 +168,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -174,6 +195,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -196,6 +220,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -220,6 +247,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -244,6 +274,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -268,6 +301,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -292,6 +328,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -316,6 +355,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -340,6 +382,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -364,6 +409,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -386,6 +434,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -410,6 +461,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -434,6 +488,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -458,6 +515,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -482,6 +542,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -506,6 +569,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -530,6 +596,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -554,6 +623,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -578,6 +650,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -600,6 +675,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -624,6 +702,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -648,6 +729,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -672,6 +756,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -696,6 +783,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -720,6 +810,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -744,6 +837,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -768,6 +864,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -792,6 +891,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -816,6 +918,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -840,6 +945,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -864,6 +972,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -888,6 +999,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -912,6 +1026,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -934,6 +1051,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -956,6 +1076,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -980,6 +1103,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1002,6 +1128,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1024,6 +1153,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1046,6 +1178,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1068,6 +1203,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1093,6 +1231,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
@@ -1118,6 +1259,9 @@
             "actions",
             "ife"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action ife",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index 12a2fe0e1472..b53d12909962 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -6,6 +6,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -30,6 +33,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -55,6 +61,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -81,6 +90,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -105,6 +117,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -129,6 +144,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -153,6 +171,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -178,6 +199,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -202,6 +226,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -226,6 +253,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -250,6 +280,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -274,6 +307,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -298,6 +334,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -322,6 +361,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -346,6 +388,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -370,6 +415,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -392,6 +440,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -417,6 +468,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -442,6 +496,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -467,6 +524,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -491,6 +551,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -514,6 +577,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -538,6 +604,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
@@ -561,6 +630,9 @@
             "actions",
             "mirred"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mirred",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mpls.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mpls.json
index 866f0efd0859..b1c5dd27a70d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mpls.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mpls.json
@@ -6,6 +6,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -30,6 +33,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -54,6 +60,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -78,6 +87,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -102,6 +114,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -126,6 +141,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -150,6 +168,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -174,6 +195,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -198,6 +222,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -222,6 +249,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -244,6 +274,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -266,6 +299,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -288,6 +324,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -310,6 +349,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -332,6 +374,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -356,6 +401,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -380,6 +428,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -404,6 +455,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -426,6 +480,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -448,6 +505,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -470,6 +530,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -492,6 +555,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -514,6 +580,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -538,6 +607,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -562,6 +634,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -586,6 +661,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -610,6 +688,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -634,6 +715,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -656,6 +740,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -678,6 +765,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -700,6 +790,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -722,6 +815,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -744,6 +840,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -768,6 +867,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -792,6 +894,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -814,6 +919,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -836,6 +944,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -860,6 +971,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -884,6 +998,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -906,6 +1023,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -930,6 +1050,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -954,6 +1077,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -978,6 +1104,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1002,6 +1131,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1024,6 +1156,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1046,6 +1181,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1070,6 +1208,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1094,6 +1235,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1116,6 +1260,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1138,6 +1285,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1163,6 +1313,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1188,6 +1341,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
@@ -1211,6 +1367,9 @@
             "actions",
             "mpls"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action mpls",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
index 0a3c491edbc5..ee2792998c89 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -6,6 +6,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -30,6 +33,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -54,6 +60,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -78,6 +87,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -102,6 +114,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -126,6 +141,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -150,6 +168,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -174,6 +195,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -203,6 +227,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -232,6 +259,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -261,6 +291,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -285,6 +318,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -309,6 +345,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -333,6 +372,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -357,6 +399,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -381,6 +426,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -405,6 +453,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -429,6 +480,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -453,6 +507,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -477,6 +534,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -501,6 +561,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -525,6 +588,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -549,6 +615,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -573,6 +642,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -597,6 +669,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -622,6 +697,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
@@ -647,6 +725,9 @@
             "actions",
             "nat"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action nat",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
index 72cdc3c800a5..37c410332174 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
@@ -6,6 +6,9 @@
             "actions",
             "pedit"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -30,6 +33,9 @@
             "actions",
             "pedit"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -56,6 +62,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -81,6 +90,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -106,6 +118,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -131,6 +146,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -156,6 +174,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -206,6 +227,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -231,6 +255,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -256,6 +283,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -281,6 +311,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -306,6 +339,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -331,6 +367,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -356,6 +395,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -381,6 +423,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -406,6 +451,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -431,6 +479,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -456,6 +507,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -481,6 +535,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -506,6 +563,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -531,6 +591,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -556,6 +619,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -581,6 +647,9 @@
             "pedit",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -606,6 +675,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -631,6 +703,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -656,6 +731,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -681,6 +759,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -706,6 +787,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -731,6 +815,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -756,6 +843,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -779,6 +869,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -804,6 +897,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -829,6 +925,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -854,6 +953,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -879,6 +981,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -904,6 +1009,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -929,6 +1037,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -954,6 +1065,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -979,6 +1093,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1004,6 +1121,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1029,6 +1149,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1054,6 +1177,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1079,6 +1205,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1104,6 +1233,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1129,6 +1261,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1154,6 +1289,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1179,6 +1317,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1204,6 +1345,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1229,6 +1373,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1254,6 +1401,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1279,6 +1429,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1304,6 +1457,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1329,6 +1485,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1354,6 +1513,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1379,6 +1541,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1404,6 +1569,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1429,6 +1597,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1454,6 +1625,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1479,6 +1653,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1504,6 +1681,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1554,6 +1734,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1579,6 +1762,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1629,6 +1815,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1654,6 +1843,9 @@
             "pedit",
             "layered_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1680,6 +1872,9 @@
             "layered_op",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
@@ -1706,6 +1901,9 @@
             "layered_op",
             "raw_op"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action pedit",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index b7205a069534..dd8109768f8f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -6,6 +6,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -30,6 +33,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -55,6 +61,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -79,6 +88,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -103,6 +115,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -127,6 +142,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -151,6 +169,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -175,6 +196,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -199,6 +223,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -223,6 +250,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -247,6 +277,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -271,6 +304,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -295,6 +331,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -319,6 +358,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -343,6 +385,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -367,6 +412,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -391,6 +439,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -415,6 +466,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -439,6 +493,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -463,6 +520,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -488,6 +548,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -520,6 +583,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -545,6 +611,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -577,6 +646,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             "$TC actions add action police rate 1mbit burst 100k index 1",
             "$TC actions add action police rate 2mbit burst 200k index 2",
@@ -603,6 +675,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -627,6 +702,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -651,6 +729,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -675,6 +756,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -699,6 +783,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -723,6 +810,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -747,6 +837,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -772,6 +865,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -796,6 +892,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
@@ -820,6 +919,9 @@
             "actions",
             "police"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action police",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 148d8bcb8606..af35e2f30a95 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -6,6 +6,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -30,6 +33,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -54,6 +60,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -78,6 +87,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -102,6 +114,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -126,6 +141,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -150,6 +168,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -174,6 +195,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -196,6 +220,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -218,6 +245,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -240,6 +270,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -262,6 +295,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -284,6 +320,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -308,6 +347,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -332,6 +374,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -356,6 +401,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -380,6 +428,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -402,6 +453,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -424,6 +478,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -446,6 +503,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -468,6 +528,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -492,6 +555,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -516,6 +582,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -541,6 +610,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -566,6 +638,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -591,6 +666,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -616,6 +694,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -641,6 +722,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
@@ -666,6 +750,9 @@
             "actions",
             "sample"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action sample",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index e0c5f060ccb9..ac960e70dc9b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -6,6 +6,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -30,6 +33,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -54,6 +60,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -79,6 +88,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -106,6 +118,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -131,6 +146,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -158,6 +176,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -183,6 +204,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
@@ -213,6 +237,9 @@
             "actions",
             "simple"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action simple",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 9cdd2e31ac2c..27ba0f72e904 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -6,6 +6,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -30,6 +33,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -54,6 +60,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -76,6 +85,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -100,6 +112,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -124,6 +139,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -146,6 +164,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -168,6 +189,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -193,6 +217,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -217,6 +244,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -241,6 +271,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -265,6 +298,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -289,6 +325,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -313,6 +352,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -337,6 +379,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -361,6 +406,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -385,6 +433,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -409,6 +460,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -433,6 +487,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -457,6 +514,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -481,6 +541,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -505,6 +568,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -529,6 +595,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -557,6 +626,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -581,6 +653,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -603,6 +678,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -628,6 +706,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             "$TC actions add action skbedit mark 500",
             "$TC actions add action skbedit mark 501",
@@ -653,6 +734,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -678,6 +762,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
@@ -702,6 +789,9 @@
             "actions",
             "skbedit"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbedit",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index 742f2290973e..33ed7a8099e2 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -6,6 +6,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -30,6 +33,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -54,6 +60,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -78,6 +87,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -102,6 +114,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -126,6 +141,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -150,6 +168,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -174,6 +195,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -198,6 +222,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -222,6 +249,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -246,6 +276,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -270,6 +303,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -294,6 +330,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -323,6 +362,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -352,6 +394,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -377,6 +422,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             "$TC actions add action skbmod set etype 0x0001",
             "$TC actions add action skbmod set etype 0x0011",
@@ -400,6 +448,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
@@ -425,6 +476,9 @@
             "actions",
             "skbmod"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action skbmod",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
index b5b47fbf6c00..0b6f0b5aeaad 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -6,6 +6,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -30,6 +33,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -59,6 +65,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -88,6 +97,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -117,6 +129,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -146,6 +161,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -175,6 +193,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -204,6 +225,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -228,6 +252,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -252,6 +279,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -281,6 +311,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -305,6 +338,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -334,6 +370,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -358,6 +397,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -387,6 +429,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -411,6 +456,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -435,6 +483,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -459,6 +510,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -488,6 +542,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -517,6 +574,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -541,6 +601,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -565,6 +628,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -594,6 +660,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -618,6 +687,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -642,6 +714,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -666,6 +741,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -690,6 +768,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -714,6 +795,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -738,6 +822,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -762,6 +849,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -786,6 +876,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -811,6 +904,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -836,6 +932,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -864,6 +963,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -892,6 +994,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -917,6 +1022,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -941,6 +1049,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -966,6 +1077,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action tunnel_key",
@@ -991,6 +1105,9 @@
             "actions",
             "tunnel_key"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "dependsOn": "$TC actions add action tunnel_key help 2>&1 | grep -q nofrag",
         "setup": [
             [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index 2aad4caa8581..e5fe8762978a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -6,6 +6,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -30,6 +33,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -54,6 +60,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -78,6 +87,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -102,6 +114,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -126,6 +141,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -150,6 +168,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -174,6 +195,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -196,6 +220,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -220,6 +247,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -242,6 +272,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -264,6 +297,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -286,6 +322,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -310,6 +349,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -334,6 +376,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -358,6 +403,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -382,6 +430,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -406,6 +457,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -430,6 +484,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -452,6 +509,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -476,6 +536,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -500,6 +563,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -524,6 +590,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -549,6 +618,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -574,6 +646,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -599,6 +674,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -624,6 +702,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -647,6 +728,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -670,6 +754,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -696,6 +783,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -720,6 +810,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -745,6 +838,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -769,6 +865,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -792,6 +891,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -816,6 +918,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
@@ -839,6 +944,9 @@
             "actions",
             "vlan"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action vlan",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json b/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json
index c9f002aea6d4..1a92e8898fec 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/xt.json
@@ -6,6 +6,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
@@ -30,6 +33,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
@@ -60,6 +66,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
@@ -90,6 +99,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
@@ -120,6 +132,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC action flush action xt",
@@ -147,6 +162,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
 		"$TC actions flush action xt",
@@ -174,6 +192,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
@@ -199,6 +220,9 @@
             "actions",
             "xt"
         ],
+        "plugins": {
+           "requires": "nsPlugin"
+        },
         "setup": [
             [
                 "$TC actions flush action xt",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
index 1f0cae474db2..013fb983bc3f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json
@@ -51,7 +51,10 @@
             "bpf-filter"
         ],
         "plugins": {
-            "requires": "buildebpfPlugin"
+            "requires": [
+               "buildebpfPlugin",
+               "nsPlugin"
+            ]
         },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
@@ -73,7 +76,10 @@
             "bpf-filter"
         ],
         "plugins": {
-            "requires": "buildebpfPlugin"
+            "requires": [
+               "buildebpfPlugin",
+               "nsPlugin"
+            ]
         },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
index a4a83fb3e96f..a9b071e1354b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
@@ -53,111 +53,6 @@
 	"plugins": {
 		"requires": "nsPlugin"
 	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
-	"plugins": {
-		"requires": "nsPlugin"
-	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -173,14 +68,15 @@
     {
         "id": "c591",
         "name": "Add fw filter with action ok by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet. Remove this when the behaviour is fixed.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact ok index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -189,9 +85,7 @@
         "matchPattern": "handle 0x1.*gact action pass.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -201,6 +95,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -216,14 +113,15 @@
     {
         "id": "38b3",
         "name": "Add fw filter with action continue by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet. Remove this when the behaviour is fixed.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact continue index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -232,9 +130,7 @@
         "matchPattern": "handle 0x1.*gact action continue.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -244,6 +140,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -259,14 +158,15 @@
     {
         "id": "6753",
         "name": "Add fw filter with action pipe by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact pipe index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -275,9 +175,7 @@
         "matchPattern": "handle 0x1.*gact action pipe.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -287,6 +185,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -302,14 +203,15 @@
     {
         "id": "6dc6",
         "name": "Add fw filter with action drop by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact drop index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -318,9 +220,7 @@
         "matchPattern": "handle 0x1.*gact action drop.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -330,6 +230,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -345,14 +248,15 @@
     {
         "id": "3bc2",
         "name": "Add fw filter with action reclassify by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact reclassify index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -361,9 +265,7 @@
         "matchPattern": "handle 0x1.*gact action reclassify.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -373,6 +275,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -388,14 +293,15 @@
     {
         "id": "36f7",
         "name": "Add fw filter with action jump 10 by reference",
-        "__comment": "We add sleep here because action might have not been deleted by workqueue just yet.",
         "category": [
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress",
-            "/bin/sleep 1",
             "$TC actions add action gact jump 10 index 1"
         ],
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action gact index 1",
@@ -404,9 +310,7 @@
         "matchPattern": "handle 0x1.*gact action jump 10.*index 1 ref 2 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DEV1 ingress",
-            "/bin/sleep 1",
-            "$TC actions del action gact index 1"
+            "$TC qdisc del dev $DEV1 ingress"
         ]
     },
     {
@@ -416,6 +320,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -435,6 +342,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -454,6 +364,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -473,6 +386,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -492,6 +408,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -511,6 +430,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -530,6 +452,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -549,6 +474,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -568,6 +496,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -587,6 +518,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -606,6 +540,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -625,6 +562,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -644,6 +584,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -663,6 +606,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -682,6 +628,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -701,6 +650,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -720,6 +672,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -739,6 +694,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -758,6 +716,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -777,6 +738,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -796,6 +760,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -815,6 +782,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -834,6 +804,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -853,6 +826,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -872,6 +848,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -891,6 +870,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -910,6 +892,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -929,6 +914,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -948,6 +936,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -967,6 +958,9 @@
             "filter",
             "fw"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -1096,7 +1090,6 @@
     {
         "id": "0e99",
         "name": "Del single fw filter x1",
-        "__comment__": "First of two tests to check that one filter is there and the other isn't",
         "category": [
             "filter",
             "fw"
@@ -1121,7 +1114,6 @@
     {
         "id": "f54c",
         "name": "Del single fw filter x2",
-        "__comment__": "Second of two tests to check that one filter is there and the other isn't",
         "category": [
             "filter",
             "fw"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
index 2df68017dfb8..afa1b9b0c856 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json
@@ -6,8 +6,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ip matchall action ok",
@@ -16,8 +18,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -27,8 +28,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol ip matchall action ok",
@@ -37,8 +40,7 @@
         "matchPattern": "^filter parent 1: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -48,8 +50,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall action drop",
@@ -58,8 +62,7 @@
         "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -69,8 +72,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol ipv6 matchall action drop",
@@ -79,8 +84,7 @@
         "matchPattern": "^filter parent 1: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -90,8 +94,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 65535 protocol ipv4 matchall action pass",
@@ -100,8 +106,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -111,8 +116,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 65535 protocol ipv4 matchall action pass",
@@ -121,8 +128,7 @@
         "matchPattern": "^filter parent 1: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -132,8 +138,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 655355 protocol ipv4 matchall action pass",
@@ -142,8 +150,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -153,8 +160,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 655355 protocol ipv4 matchall action pass",
@@ -163,8 +172,7 @@
         "matchPattern": "^filter parent 1: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -174,8 +182,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0xffffffff prio 1 protocol all matchall action continue",
@@ -184,8 +194,7 @@
         "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -195,8 +204,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0xffffffff prio 1 protocol all matchall action continue",
@@ -205,8 +216,7 @@
         "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -216,8 +226,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify",
@@ -226,8 +238,7 @@
         "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -237,8 +248,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent 1: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify",
@@ -247,8 +260,7 @@
         "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: prio"
         ]
     },
     {
@@ -258,8 +270,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:1 action pass",
@@ -268,8 +282,7 @@
         "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:1.*gact action pass.*ref 1 bind 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -279,8 +292,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 6789defg action pass",
@@ -289,8 +304,7 @@
         "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 6789defg.*gact action pass.*ref 1 bind 1",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -300,8 +314,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:2 action pass"
         ],
@@ -311,8 +327,7 @@
         "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:2.*gact action pass.*ref 1 bind 1",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -322,8 +337,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass",
             "$TC filter add dev $DUMMY parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass",
@@ -336,8 +353,7 @@
         "matchPattern": "^filter protocol all pref.*matchall.*handle.*flowid.*gact action pass",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -347,8 +363,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass",
             "$TC filter add dev $DUMMY parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass",
@@ -361,8 +379,7 @@
         "matchPattern": "^filter protocol all pref 2 matchall.*handle 0x2 flowid 1:2.*gact action pass",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -372,8 +389,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol all chain 1 matchall classid 1:1 action pass",
             "$TC filter add dev $DUMMY parent ffff: handle 0x1 prio 1 protocol ipv4 chain 2 matchall classid 1:3 action continue"
@@ -384,8 +403,7 @@
         "matchPattern": "^filter protocol all pref 1 matchall chain 1 handle 0x1 flowid 1:1.*gact action pass",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -395,8 +413,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions flush action police",
             "$TC actions add action police rate 1mbit burst 100k index 199 skip_hw"
@@ -408,7 +428,6 @@
         "matchCount": "0",
         "teardown": [
             "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
             "$TC actions del action police index 199"
         ]
     },
@@ -419,8 +438,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions flush action police",
             "$TC actions add action police rate 1mbit burst 100k index 199"
@@ -432,7 +453,6 @@
         "matchCount": "0",
         "teardown": [
             "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
             "$TC actions del action police index 199"
         ]
     },
@@ -443,8 +463,10 @@
             "filter",
             "matchall"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions flush action police",
             "$TC actions add action police rate 1mbit burst 100k index 199"
@@ -456,7 +478,6 @@
         "matchCount": "0",
         "teardown": [
             "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
             "$TC actions del action police index 199"
         ]
     }
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
index 16f3a83605e4..1ba96c467754 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
@@ -6,8 +6,10 @@
             "infra",
             "pedit"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC action add action pedit munge offset 0 u8 clear index 1"
         ],
@@ -17,9 +19,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action pedit"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -29,8 +29,10 @@
             "infra",
             "mpls"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC action add action mpls pop protocol ipv4 index 1"
         ],
@@ -40,9 +42,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action mpls"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -52,8 +52,10 @@
             "infra",
             "bpf"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC action add action bpf bytecode '4,40 0 0 12,21 0 1 2048,6 0 0 262144,6 0 0 0' index 1"
         ],
@@ -63,9 +65,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action bpf"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -75,8 +75,10 @@
             "infra",
             "connmark"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action connmark"
         ],
@@ -86,9 +88,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action connmark"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -98,8 +98,10 @@
             "infra",
             "csum"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action csum ip4h index 1"
         ],
@@ -109,9 +111,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action csum"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -121,8 +121,10 @@
             "infra",
             "ct"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action ct index 1"
         ],
@@ -132,9 +134,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action ct"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -144,8 +144,10 @@
             "infra",
             "ctinfo"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC action add action ctinfo index 1"
         ],
@@ -155,9 +157,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action ctinfo"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -167,8 +167,10 @@
             "infra",
             "gact"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action pass index 1"
         ],
@@ -178,9 +180,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action gact"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -190,8 +190,10 @@
             "infra",
             "gate"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC action add action gate priority 1 sched-entry close 100000000ns index 1"
         ],
@@ -201,9 +203,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action gate"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -213,8 +213,10 @@
             "infra",
             "ife"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action ife encode allow mark pass index 1"
         ],
@@ -224,9 +226,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action ife"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -236,8 +236,10 @@
             "infra",
             "mirred"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action mirred egress mirror index 1 dev lo"
         ],
@@ -247,9 +249,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action mirred"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -259,8 +259,10 @@
             "infra",
             "nat"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action nat ingress 192.168.1.1 200.200.200.1"
         ],
@@ -270,9 +272,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action nat"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -282,8 +282,10 @@
             "infra",
             "police"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action police rate 1kbit burst 10k index 1"
         ],
@@ -293,9 +295,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action police"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -305,8 +305,10 @@
             "infra",
             "sample"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action sample rate 10 group 1 index 1"
         ],
@@ -316,9 +318,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action sample"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -328,8 +328,10 @@
             "infra",
             "skbedit"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action skbedit mark 1"
         ],
@@ -339,9 +341,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action skbedit"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -351,8 +351,10 @@
             "infra",
             "skbmod"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 1"
         ],
@@ -362,9 +364,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action skbmod"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -374,8 +374,10 @@
             "infra",
             "tunnel_key"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1 index 1"
         ],
@@ -385,9 +387,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action tunnel_key"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -397,8 +397,10 @@
             "infra",
             "tunnel_key"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC actions add action vlan pop pipe index 1"
         ],
@@ -408,9 +410,7 @@
         "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy",
-            "$TC actions flush action vlan"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
index c4c778e83da2..8d10042b489b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
@@ -1,13 +1,15 @@
 [
     {
         "id": "c2b4",
-        "name": "soft lockup alarm will be not generated after delete the prio 0 filter of the chain",
+        "name": "Soft lockup alarm will be not generated after delete the prio 0 filter of the chain",
         "category": [
             "filter",
             "chain"
         ],
+	"plugins": {
+		"requires": "nsPlugin"
+	},
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: htb default 1",
             "$TC chain add dev $DUMMY",
             "$TC filter del dev $DUMMY chain 0 parent 1: prio 0"
@@ -18,8 +20,7 @@
         "matchPattern": "chain parent 1: chain 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY root handle 1: htb default 1",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY root handle 1: htb default 1"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cake.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cake.json
index 1134b72d281d..c4c5f7ba0e0f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cake.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cake.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake bandwidth 1000",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth 1Kbit diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake autorate-ingress",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited autorate-ingress diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake rtt 200",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 200us raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake besteffort",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited besteffort triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake diffserv8",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv8 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake diffserv4",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv4 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake flowblind",
         "expExitCode": "0",
@@ -179,8 +164,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 flowblind nonat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -194,7 +178,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake dsthost nat",
         "expExitCode": "0",
@@ -202,8 +185,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 dsthost nat nowash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -217,7 +199,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake hosts wash",
         "expExitCode": "0",
@@ -225,8 +206,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 hosts nonat wash no-ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -240,7 +220,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake flowblind no-split-gso",
         "expExitCode": "0",
@@ -248,8 +227,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 flowblind nonat nowash no-ack-filter no-split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -263,7 +241,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake dual-srchost ack-filter",
         "expExitCode": "0",
@@ -271,8 +248,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 dual-srchost nonat nowash ack-filter split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -286,7 +262,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake dual-dsthost ack-filter-aggressive",
         "expExitCode": "0",
@@ -294,8 +269,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 dual-dsthost nonat nowash ack-filter-aggressive split-gso rtt 100ms raw overhead",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -309,7 +283,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake memlimit 10000 ptm",
         "expExitCode": "0",
@@ -317,8 +290,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw ptm overhead 0 memlimit 10000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -332,7 +304,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake fwmark 8 atm",
         "expExitCode": "0",
@@ -340,8 +311,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms raw atm overhead 0 fwmark 0x8",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -355,7 +325,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake overhead 128 mpu 256",
         "expExitCode": "0",
@@ -363,8 +332,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms noatm overhead 128 mpu 256",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -378,7 +346,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake conservative ingress",
         "expExitCode": "0",
@@ -386,8 +353,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash ingress no-ack-filter split-gso rtt 100ms atm overhead 48",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -401,7 +367,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cake conservative ingress"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -410,7 +375,6 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash ingress no-ack-filter split-gso rtt 100ms atm overhead 48",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -424,7 +388,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cake overhead 128 mpu 256"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root cake mpu 128",
@@ -433,8 +396,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms noatm overhead 128 mpu 128",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -448,7 +410,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cake overhead 128 mpu 256"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root cake mpu 128",
@@ -457,8 +418,7 @@
         "matchPattern": "qdisc cake 1: root refcnt [0-9]+ bandwidth unlimited diffserv3 triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms noatm overhead 128 mpu 128",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -472,7 +432,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cake",
         "expExitCode": "0",
@@ -480,8 +439,7 @@
         "matchPattern": "class cake",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbs.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbs.json
index a46bf5ff8277..33ea986176d9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbs.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 0 idleslope 0 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs hicredit 64",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 64 locredit 0 sendslope 0 idleslope 0 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs locredit 10",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 10 sendslope 0 idleslope 0 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs sendslope 888",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 888 idleslope 0 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs idleslope 666",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 0 idleslope 666 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs hicredit 10 locredit 75 sendslope 2 idleslope 666",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 10 locredit 75 sendslope 2 idleslope 666 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cbs idleslope 666"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root cbs sendslope 10",
@@ -157,8 +144,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 10 idleslope 0 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -172,7 +158,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cbs idleslope 666"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root cbs idleslope 1",
@@ -181,8 +166,7 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 0 idleslope 1 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -196,7 +180,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root cbs idleslope 666"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -205,7 +188,6 @@
         "matchPattern": "qdisc cbs 1: root refcnt [0-9]+ hicredit 0 locredit 0 sendslope 0 idleslope 1 offload 0.*qdisc pfifo 0: parent 1: limit 1000p",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -219,7 +201,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbs",
         "expExitCode": "0",
@@ -227,8 +208,7 @@
         "matchPattern": "class cbs 1:[0-9]+ parent 1:",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/choke.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/choke.json
index 31b7775d25fc..d46e5e2c9430 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/choke.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/choke.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 83p max 250p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 min 100",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 100p max 250p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 max 900",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min.*max 900p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 ecn",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 83p max 250p ecn",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 burst 100",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 83p max 250p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -134,7 +123,6 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 83p max 250p",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 min 100",
@@ -157,8 +144,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 100p max 250p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -172,7 +158,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root choke limit 1000 bandwidth 10000 min 100",
@@ -181,8 +166,7 @@
         "matchPattern": "qdisc choke 1: root refcnt [0-9]+ limit 1000p min 100p max 250p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
index ea38099d48e5..e9469ee71e6f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 5ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel limit 1500",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1500p target 5ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel target 100ms",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 100ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel interval 20ms",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 5ms interval 20ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel ecn",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 5ms interval 100ms ecn",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root codel ce_threshold 20ms",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 5ms ce_threshold 20ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root codel"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -157,7 +144,6 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1000p target 5ms interval 100ms",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root codel"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root codel limit 5000",
@@ -180,8 +165,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 5000p target 5ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -195,7 +179,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root codel"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root codel limit 100",
@@ -204,8 +187,7 @@
         "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 100p target 5ms interval 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
index 486a425b3c1c..7126ec3485cb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root drr",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc drr 1: root refcnt [0-9]+",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root drr"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -42,7 +39,6 @@
         "matchPattern": "qdisc drr 1: root refcnt [0-9]+",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root drr",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "class drr 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/etf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/etf.json
index 0046d44bcd93..2c73ee47bf58 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/etf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/etf.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root etf clockid CLOCK_TAI",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc etf 1: root refcnt [0-9]+ clockid TAI delta 0 offload off deadline_mode off skip_sock_check off",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root etf delta 100 clockid CLOCK_TAI",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc etf 1: root refcnt [0-9]+ clockid TAI delta 100 offload off deadline_mode off skip_sock_check off",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root etf clockid CLOCK_TAI deadline_mode",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc etf 1: root refcnt [0-9]+ clockid TAI delta 0 offload off deadline_mode on skip_sock_check off",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root etf clockid CLOCK_TAI skip_sock_check",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc etf 1: root refcnt [0-9]+ clockid TAI delta 0 offload off deadline_mode off skip_sock_check on",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root etf clockid CLOCK_TAI"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -111,7 +102,6 @@
         "matchPattern": "qdisc etf 1: root refcnt [0-9]+ clockid TAI delta 0 offload off deadline_mode off skip_sock_check off",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json
index 180593010675..a5d94cdec605 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json
@@ -6,8 +6,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2",
         "expExitCode": "0",
@@ -15,8 +17,7 @@
         "matchPattern": "qdisc ets 1: root .* bands 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -26,8 +27,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 900 800 700",
         "expExitCode": "0",
@@ -35,8 +38,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -46,8 +48,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3",
         "expExitCode": "0",
@@ -55,8 +59,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 3 strict 3",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -66,8 +69,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 quanta 1000 900 800 700",
         "expExitCode": "0",
@@ -75,8 +80,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -86,8 +90,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 3",
         "expExitCode": "0",
@@ -95,8 +101,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 3 strict 3 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -106,8 +111,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3 quanta 1500 750",
         "expExitCode": "0",
@@ -115,8 +122,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 5 strict 3 quanta 1500 750 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -126,8 +132,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 0 quanta 1500 750",
         "expExitCode": "0",
@@ -135,8 +143,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 2 quanta 1500 750 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -146,8 +153,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 strict 3 quanta 1500 750",
         "expExitCode": "0",
@@ -155,8 +164,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 5 .*strict 3 quanta 1500 750 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -166,8 +174,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000",
         "expExitCode": "0",
@@ -175,8 +185,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 2 .*quanta 1000 [1-9][0-9]* priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -186,8 +195,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1",
         "expExitCode": "0",
@@ -195,8 +206,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta ([1-9][0-9]* ){2}priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -206,8 +216,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1 quanta 1000",
         "expExitCode": "0",
@@ -215,8 +227,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta 1000 [1-9][0-9]* priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -226,8 +237,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 16",
         "expExitCode": "0",
@@ -235,8 +248,7 @@
         "matchPattern": "qdisc ets 1: root .* bands 16",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -246,8 +258,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17",
         "expExitCode": "1",
@@ -255,7 +269,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -265,8 +278,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 17",
         "expExitCode": "1",
@@ -274,7 +289,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -284,8 +298,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16",
         "expExitCode": "0",
@@ -293,8 +309,7 @@
         "matchPattern": "qdisc ets 1: root .* bands 16",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -304,8 +319,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17",
         "expExitCode": "2",
@@ -313,7 +330,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -323,8 +339,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 8 quanta 1 2 3 4 5 6 7 8",
         "expExitCode": "0",
@@ -332,8 +350,7 @@
         "matchPattern": "qdisc ets 1: root .* bands 16",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -343,8 +360,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 9 quanta 1 2 3 4 5 6 7 8",
         "expExitCode": "2",
@@ -352,7 +371,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -362,8 +380,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "expExitCode": "0",
@@ -371,8 +391,7 @@
         "matchPattern": "qdisc ets 1: root .*priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -382,8 +401,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "expExitCode": "0",
@@ -391,8 +412,7 @@
         "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -402,8 +422,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "expExitCode": "0",
@@ -411,8 +433,7 @@
         "matchPattern": "qdisc ets 1: root .*bands 5 strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -422,8 +443,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "expExitCode": "0",
@@ -431,8 +454,7 @@
         "matchPattern": "qdisc ets 1: root .*strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -442,8 +464,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000",
         "expExitCode": "0",
@@ -451,8 +475,7 @@
         "matchPattern": "class ets 1:1 root quantum 4000",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -462,8 +485,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000",
         "expExitCode": "0",
@@ -471,8 +496,7 @@
         "matchPattern": "class ets 1:2 root quantum 3000",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -482,8 +506,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000",
         "expExitCode": "0",
@@ -491,8 +517,7 @@
         "matchPattern": "class ets 1:3 root quantum 2000",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -502,8 +527,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3",
         "expExitCode": "0",
@@ -511,8 +538,7 @@
         "matchPattern": "class ets 1:1 root $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -522,8 +548,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000 2000 3000",
         "expExitCode": "1",
@@ -531,7 +559,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -541,8 +568,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 3",
         "expExitCode": "1",
@@ -550,7 +579,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -560,8 +588,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 2 quanta 1000 2000 3000",
         "expExitCode": "1",
@@ -569,7 +599,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -579,8 +608,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0 1 2",
         "expExitCode": "1",
@@ -588,7 +619,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -598,8 +628,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 priomap 0 1 2",
         "expExitCode": "1",
@@ -607,7 +639,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -617,8 +648,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 500 priomap 0 1 2",
         "expExitCode": "1",
@@ -626,7 +659,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -636,8 +668,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 priomap 0 1 2",
         "expExitCode": "1",
@@ -645,7 +679,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -655,8 +688,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 1 quanta 1000 500 priomap 0 1 2 3",
         "expExitCode": "1",
@@ -664,7 +699,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -674,8 +708,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3",
         "expExitCode": "0",
@@ -683,7 +719,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -693,8 +728,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3 4",
         "expExitCode": "1",
@@ -702,7 +739,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -712,8 +748,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 priomap 0 0 0 0",
         "expExitCode": "0",
@@ -721,7 +759,6 @@
         "matchPattern": "qdisc ets .*priomap 0 0 0 0 3 3 3 3 3 3 3 3 3 3 3 3",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -731,8 +768,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4",
         "expExitCode": "0",
@@ -740,7 +779,6 @@
         "matchPattern": "qdisc ets .*priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -750,8 +788,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 0",
         "expExitCode": "1",
@@ -759,7 +799,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -769,8 +808,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17",
         "expExitCode": "1",
@@ -778,7 +819,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -788,8 +828,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets",
         "expExitCode": "1",
@@ -797,7 +839,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -807,8 +848,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 0 800 700",
         "expExitCode": "1",
@@ -816,7 +859,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -826,8 +868,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 0",
         "expExitCode": "1",
@@ -835,7 +879,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -845,8 +888,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta",
         "expExitCode": "255",
@@ -854,7 +899,6 @@
         "matchPattern": "qdisc ets",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -864,8 +908,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000"
         ],
         "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets quantum 1500",
@@ -874,7 +920,6 @@
         "matchPattern": "qdisc ets 1: root .*quanta 1500 2000 3000 priomap ",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -884,8 +929,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000"
         ],
         "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets",
@@ -894,7 +941,6 @@
         "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 priomap ",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -904,8 +950,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root ets strict 5"
         ],
         "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets quantum 1500",
@@ -914,7 +962,6 @@
         "matchPattern": "qdisc ets .*bands 5 .*strict 5",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -924,8 +971,10 @@
             "qdisc",
             "ets"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root ets strict 5"
         ],
         "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets",
@@ -934,7 +983,6 @@
         "matchPattern": "qdisc ets .*bands 5 .*strict 5",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
index 5ecd93b4c473..ae3d286a32b2 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
@@ -2,13 +2,14 @@
     {
         "id": "a519",
         "name": "Add bfifo qdisc with system default parameters on egress",
-        "__comment": "When omitted, queue size in bfifo is calculated as: txqueuelen * (MTU + LinkLayerHdrSize), where LinkLayerHdrSize=14 for Ethernet",
         "category": [
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo",
         "expExitCode": "0",
@@ -16,20 +17,20 @@
         "matchPattern": "qdisc bfifo 1: root.*limit [0-9]+b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root bfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root bfifo"
         ]
     },
     {
         "id": "585c",
         "name": "Add pfifo qdisc with system default parameters on egress",
-        "__comment": "When omitted, queue size in pfifo is defaulted to the interface's txqueuelen value.",
         "category": [
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo",
         "expExitCode": "0",
@@ -37,8 +38,7 @@
         "matchPattern": "qdisc pfifo 1: root.*limit [0-9]+p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root pfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root pfifo"
         ]
     },
     {
@@ -48,8 +48,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle ffff: bfifo",
         "expExitCode": "0",
@@ -57,8 +59,7 @@
         "matchPattern": "qdisc bfifo ffff: root.*limit [0-9]+b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle ffff: root bfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle ffff: root bfifo"
         ]
     },
     {
@@ -68,8 +69,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo limit 3000b",
         "expExitCode": "0",
@@ -77,8 +80,7 @@
         "matchPattern": "qdisc bfifo 1: root.*limit 3000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root bfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root bfifo"
         ]
     },
     {
@@ -88,8 +90,11 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY txqueuelen 3000 type dummy || /bin/true"
+            "$IP link set dev $DUMMY txqueuelen 3000"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo limit 3000",
         "expExitCode": "0",
@@ -97,8 +102,7 @@
         "matchPattern": "qdisc pfifo 1: root.*limit 3000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root pfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root pfifo"
         ]
     },
     {
@@ -108,8 +112,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 10000: bfifo",
         "expExitCode": "255",
@@ -117,7 +123,6 @@
         "matchPattern": "qdisc bfifo 10000: root.*limit [0-9]+b",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -127,8 +132,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo foorbar",
         "expExitCode": "1",
@@ -136,7 +143,6 @@
         "matchPattern": "qdisc bfifo 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -146,8 +152,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo foorbar",
         "expExitCode": "1",
@@ -155,7 +163,6 @@
         "matchPattern": "qdisc pfifo 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -165,9 +172,11 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link del dev $DUMMY type dummy || /bin/true",
-            "$IP link add dev $DUMMY txqueuelen 1000 type dummy",
+            "$IP link set dev $DUMMY txqueuelen 1000",
             "$TC qdisc add dev $DUMMY handle 1: root bfifo"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root bfifo limit 3000b",
@@ -176,8 +185,7 @@
         "matchPattern": "qdisc bfifo 1: root.*limit 3000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root bfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root bfifo"
         ]
     },
     {
@@ -187,9 +195,11 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link del dev $DUMMY type dummy || /bin/true",
-            "$IP link add dev $DUMMY txqueuelen 1000 type dummy",
+            "$IP link set dev $DUMMY txqueuelen 1000",
             "$TC qdisc add dev $DUMMY handle 1: root pfifo"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root pfifo limit 30",
@@ -198,8 +208,7 @@
         "matchPattern": "qdisc pfifo 1: root.*limit 30p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root pfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root pfifo"
         ]
     },
     {
@@ -209,8 +218,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo limit foo-bar",
         "expExitCode": "1",
@@ -218,7 +229,6 @@
         "matchPattern": "qdisc bfifo 1: root.*limit foo-bar",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -228,8 +238,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root bfifo"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root bfifo",
@@ -238,8 +250,7 @@
         "matchPattern": "qdisc bfifo 1: root",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root bfifo",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root bfifo"
         ]
     },
     {
@@ -249,8 +260,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY root handle 1: bfifo",
         "expExitCode": "2",
@@ -258,7 +271,6 @@
         "matchPattern": "qdisc bfifo 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -268,8 +280,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 123^ bfifo limit 100b",
         "expExitCode": "255",
@@ -277,7 +291,6 @@
         "matchPattern": "qdisc bfifo 123 root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -287,8 +300,10 @@
             "qdisc",
             "fifo"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: bfifo",
             "$TC qdisc del dev $DUMMY root handle 1: bfifo"
         ],
@@ -298,7 +313,6 @@
         "matchPattern": "qdisc bfifo 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
index 3593fb8f79ad..be293e7c6d18 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq limit 3000",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 3000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq flow_limit 300",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 300p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq quantum 9000",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p buckets.*orphan_mask 1023 quantum 9000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq initial_quantum 900000",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p buckets.*initial_quantum 900000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq initial_quantum 0x80000000",
         "expExitCode": "2",
@@ -133,7 +122,6 @@
         "matchPattern": "qdisc fq 1: root.*initial_quantum 2048Mb",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -147,7 +135,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq maxrate 100000",
         "expExitCode": "0",
@@ -155,8 +142,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p buckets.*maxrate 100Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -170,7 +156,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq nopacing",
         "expExitCode": "0",
@@ -178,8 +163,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*nopacing",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -193,7 +177,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq refill_delay 100ms",
         "expExitCode": "0",
@@ -201,8 +184,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*refill_delay 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -216,7 +198,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq low_rate_threshold 10000",
         "expExitCode": "0",
@@ -224,8 +205,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*low_rate_threshold 10Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -239,7 +219,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq orphan_mask 255",
         "expExitCode": "0",
@@ -247,8 +226,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*orphan_mask 255",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -262,7 +240,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq timer_slack 100",
         "expExitCode": "0",
@@ -270,8 +247,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*timer_slack 100ns",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -285,7 +261,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq ce_threshold 100",
         "expExitCode": "0",
@@ -293,8 +268,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -308,7 +282,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq horizon 100",
         "expExitCode": "0",
@@ -316,8 +289,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*horizon 100us",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -331,7 +303,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq horizon_cap",
         "expExitCode": "0",
@@ -339,8 +310,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p flow_limit 100p.*horizon_cap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -354,7 +324,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -363,7 +332,6 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 10000p",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -377,7 +345,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root fq limit 5000",
@@ -386,8 +353,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 5000p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -401,7 +367,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root fq limit 100",
@@ -410,8 +375,7 @@
         "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 100p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
index a65266357a9a..9774b1e8801b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel limit 1000",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1000p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel memory_limit 100000",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms interval 100ms memory_limit 100000b ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel target 2000",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 2ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel interval 5000",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms interval 5ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel quantum 9000",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum 9000 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel noecn",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel ce_threshold 1024000",
         "expExitCode": "0",
@@ -179,8 +164,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms ce_threshold 1.02s interval 100ms memory_limit 32Mb ecn drop_batch 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -194,7 +178,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel drop_batch 100",
         "expExitCode": "0",
@@ -202,8 +185,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 10240p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 100",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -217,7 +199,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel limit 1000 flows 256 drop_batch 100",
         "expExitCode": "0",
@@ -225,8 +206,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1000p flows 256 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 100",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -240,7 +220,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq_codel limit 1000 flows 256 drop_batch 100"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root fq_codel noecn",
@@ -249,8 +228,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1000p flows 256 quantum.*target 5ms interval 100ms memory_limit 32Mb drop_batch 100",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -264,7 +242,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq_codel limit 1000 flows 256 drop_batch 100"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root fq_codel limit 2000",
@@ -273,8 +250,7 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 2000p flows 256 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 100",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -288,7 +264,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root fq_codel limit 1000 flows 256 drop_batch 100"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -297,7 +272,6 @@
         "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1000p flows 256 quantum.*target 5ms interval 100ms memory_limit 32Mb noecn drop_batch 100",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -311,7 +285,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_codel",
         "expExitCode": "0",
@@ -319,8 +292,7 @@
         "matchPattern": "class fq_codel 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index 773c5027553d..d012d88d67fe 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -6,8 +6,10 @@
             "qdisc",
             "fq_pie"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root fq_pie flows 65536",
         "expExitCode": "0",
@@ -15,7 +17,6 @@
         "matchPattern": "qdisc fq_pie 1: root refcnt 2 limit 10240p flows 65536",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/gred.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/gred.json
index 013c8ee037a4..df07fe318de9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/gred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/gred.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 1",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 1 grio",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 1.*grio",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 1 limit 1000",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 1 limit 1000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 2 ecn",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 2.*ecn",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 2 harddrop",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 2.*harddrop",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 1"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root gred limit 60KB min 15K max 25K burst 64 avpkt 1500 bandwidth 10Mbit DP 1 probability 0.1",
@@ -134,8 +123,7 @@
         "matchPattern": "qdisc gred 1: root refcnt [0-9]+ vqs 10 default 1 limit.*vq 1 prio [0-9]+ limit 60Kb min 15Kb max 25Kb",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -149,7 +137,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root gred setup vqs 10 default 1",
         "expExitCode": "0",
@@ -157,8 +144,7 @@
         "matchPattern": "class gred 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
index af27b2c20e17..0ddb8e1b4369 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc hfsc 1: root refcnt [0-9]+",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hfsc default 11"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc sc rate 20000 ul rate 10000",
@@ -42,8 +39,7 @@
         "matchPattern": "class hfsc 1:1 parent 1: sc m1 0bit d 0us m2 20Kbit ul m1 0bit d 0us m2 10Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -57,7 +53,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hfsc default 11"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc sc umax 1540 dmax 5ms rate 10000 ul rate 10000",
@@ -66,8 +61,7 @@
         "matchPattern": "class hfsc 1:1 parent 1: sc m1 2464Kbit d 5ms m2 10Kbit ul m1 0bit d 0us m2 10Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -81,7 +75,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hfsc default 11"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc rt rate 20000 ls rate 10000",
@@ -90,8 +83,7 @@
         "matchPattern": "class hfsc 1:1 parent 1: rt m1 0bit d 0us m2 20Kbit ls m1 0bit d 0us m2 10Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -105,7 +97,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hfsc default 11"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc rt umax 1540 dmax 5ms rate 10000 ls rate 10000",
@@ -114,8 +105,7 @@
         "matchPattern": "class hfsc 1:1 parent 1: rt m1 2464Kbit d 5ms m2 10Kbit ls m1 0bit d 0us m2 10Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -129,7 +119,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hfsc default 11"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -138,7 +127,6 @@
         "matchPattern": "qdisc hfsc 1: root refcnt [0-9]+",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -152,7 +140,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc",
         "expExitCode": "0",
@@ -160,8 +147,7 @@
         "matchPattern": "class hfsc 1: root",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
index 949f6e5de902..dbef5474b26b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf limit 1500",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1500p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf quantum 9000",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*quantum 9000b hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf reset_timeout 100ms",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*hh_limit 2048 reset_timeout 100ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf admit_bytes 100000",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*hh_limit 2048 reset_timeout 40ms admit_bytes 100000b evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf evict_timeout 0.5s",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 500ms non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf non_hh_weight 10",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 10",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root hhf"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root hhf limit 1500",
@@ -180,8 +165,7 @@
         "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1500p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -195,7 +179,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hhf",
         "expExitCode": "0",
@@ -203,8 +186,7 @@
         "matchPattern": "class hhf 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/htb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/htb.json
index 9529899482e0..cab745f9a83c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/htb.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/htb.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root htb",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc htb 1: root refcnt [0-9]+ r2q 10 default 0 direct_packets_stat.*direct_qlen",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root htb default 10",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc htb 1: root refcnt [0-9]+ r2q 10 default 0x10 direct_packets_stat.* direct_qlen",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root htb r2q 5",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc htb 1: root refcnt [0-9]+ r2q 5 default 0 direct_packets_stat.*direct_qlen",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root htb direct_qlen 1024",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc htb 1: root refcnt [0-9]+ r2q 10 default 0 direct_packets_stat.*direct_qlen 1024",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20kbit burst 1000",
@@ -111,8 +102,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 20Kbit burst 1000b cburst 1600b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -126,7 +116,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit mpu 64",
@@ -135,8 +124,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 20Kbit burst 1600b cburst 1600b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -150,7 +138,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit prio 1",
@@ -159,8 +146,7 @@
         "matchPattern": "class htb 1:1 root prio 1 rate 20Kbit ceil 20Kbit burst 1600b cburst 1600b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -174,7 +160,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit ceil 10Kbit",
@@ -183,8 +168,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 10Kbit burst 1600b cburst 1600b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -198,7 +182,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit cburst 2000",
@@ -207,8 +190,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 20Kbit burst 1600b cburst 2000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -222,7 +204,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit mtu 2048",
@@ -231,8 +212,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 20Kbit burst 2Kb cburst 2Kb",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -246,7 +226,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 20Kbit quantum 2048",
@@ -255,8 +234,7 @@
         "matchPattern": "class htb 1:1 root prio 0 rate 20Kbit ceil 20Kbit burst 1600b cburst 1600b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -270,7 +248,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root htb r2q 5"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -279,7 +256,6 @@
         "matchPattern": "qdisc htb 1: root refcnt [0-9]+",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
index 11d33362408c..57bddc1212d8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
@@ -7,16 +7,17 @@
             "ingress"
         ],
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress",
         "expExitCode": "0",
         "verifyCmd": "$TC qdisc show dev $DUMMY",
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -26,8 +27,10 @@
             "qdisc",
             "ingress"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress foorbar",
         "expExitCode": "1",
@@ -35,7 +38,6 @@
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -45,8 +47,10 @@
             "qdisc",
             "ingress"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress",
@@ -55,8 +59,7 @@
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     },
     {
@@ -66,8 +69,10 @@
             "qdisc",
             "ingress"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY ingress",
         "expExitCode": "2",
@@ -75,7 +80,6 @@
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -85,8 +89,10 @@
             "qdisc",
             "ingress"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY ingress",
             "$TC qdisc del dev $DUMMY ingress"
         ],
@@ -96,7 +102,6 @@
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -106,8 +111,10 @@
             "qdisc",
             "ingress"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY ingress",
         "expExitCode": "0",
@@ -115,8 +122,7 @@
         "matchPattern": "class ingress",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY ingress",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY ingress"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json
index 7e41f548f8e8..3c4444961488 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ limit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem limit 200",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ limit 200",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal corrupt 1%",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms  10ms corrupt 1%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal duplicate 1%",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms  10ms duplicate 1%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution pareto loss 1%",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms  10ms loss 1%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution paretonormal loss state 1",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms  10ms loss state p13 1% p31 99% p32 0% p23 100% p14 0%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem loss gemodel 1%",
         "expExitCode": "0",
@@ -179,8 +164,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*loss gemodel p 1%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -194,7 +178,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms reorder 2% gap 100",
         "expExitCode": "0",
@@ -202,8 +185,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*reorder 2%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -217,7 +199,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem rate 20000",
         "expExitCode": "0",
@@ -225,8 +206,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*rate 20Kbit",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -240,7 +220,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem slot 10 200 packets 2000 bytes 9000",
         "expExitCode": "0",
@@ -248,8 +227,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*slot 10ns 200ns packets 2000 bytes 9000",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -263,7 +241,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem slot distribution pareto 1ms 0.1ms",
         "expExitCode": "0",
@@ -271,8 +248,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*slot distribution 1ms 100us",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -286,7 +262,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal loss 1%"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal loss 2%",
@@ -295,8 +270,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*loss 2%",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -310,7 +284,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal loss 1%"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root netem delay 200ms 10ms",
@@ -319,8 +292,7 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 200ms  10ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -334,7 +306,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root netem delay 100ms 10ms distribution normal"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -343,7 +314,6 @@
         "matchPattern": "qdisc netem 1: root refcnt [0-9]+ .*delay 100ms  10ms",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -357,7 +327,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root netem",
         "expExitCode": "0",
@@ -365,8 +334,7 @@
         "matchPattern": "class netem 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json
index ab53238f4c5a..30da27fe8806 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pfifo_fast.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo_fast",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc pfifo_fast 1: root refcnt [0-9]+ bands 3 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root pfifo_fast",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "Sent.*bytes.*pkt \\(dropped.*overlimits.*requeues .*\\)",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root pfifo_fast"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 2: root pfifo_fast",
@@ -65,8 +60,7 @@
         "matchPattern": "qdisc pfifo_fast 2: root refcnt [0-9]+ bands 3 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 2: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 2: root"
         ]
     },
     {
@@ -80,7 +74,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root pfifo_fast"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -89,7 +82,6 @@
         "matchPattern": "qdisc pfifo_fast 1: root refcnt [0-9]+ bands 3 priomap",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -103,7 +95,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root pfifo_fast"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: root",
@@ -112,8 +103,7 @@
         "matchPattern": "qdisc pfifo_fast 1: root refcnt [0-9]+ bands 3 priomap",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/plug.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/plug.json
index 6454518af178..6ec7e0a01265 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/plug.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/plug.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root plug",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root plug block",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root plug release",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root plug release_indefinite",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root plug limit 100",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root plug"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -134,7 +123,6 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root plug"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root plug limit 1000",
@@ -157,8 +144,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -172,7 +158,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root plug"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root plug limit 1000",
@@ -181,8 +166,7 @@
         "matchPattern": "qdisc plug 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json
index 8186de2f0dcf..69abf041c799 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/prio.json
@@ -6,8 +6,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio",
         "expExitCode": "0",
@@ -15,8 +17,7 @@
         "matchPattern": "qdisc prio 1: root",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root prio"
         ]
     },
     {
@@ -26,8 +27,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle ffff: prio",
         "expExitCode": "0",
@@ -35,7 +38,6 @@
         "matchPattern": "qdisc prio ffff: root",
         "matchCount": "1",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -45,8 +47,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 10000: prio",
         "expExitCode": "255",
@@ -54,7 +58,6 @@
         "matchPattern": "qdisc prio 10000: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -64,8 +67,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio foorbar",
         "expExitCode": "1",
@@ -73,7 +78,6 @@
         "matchPattern": "qdisc prio 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -83,8 +87,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0",
         "expExitCode": "0",
@@ -92,8 +98,7 @@
         "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root prio"
         ]
     },
     {
@@ -103,8 +108,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0 1 1",
         "expExitCode": "1",
@@ -112,7 +119,6 @@
         "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 3 3 0 0 1 2 3 0 0 0 0 0 1 1",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -122,8 +128,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 4 priomap 1 1 2 2 7 5 0 0 1 2 3 0 0 0 0 0",
         "expExitCode": "1",
@@ -131,7 +139,6 @@
         "matchPattern": "qdisc prio 1: root.*bands 4 priomap.*1 1 2 2 7 5 0 0 1 2 3 0 0 0 0 0",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -141,8 +148,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 1 priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0",
         "expExitCode": "2",
@@ -150,7 +159,6 @@
         "matchPattern": "qdisc prio 1: root.*bands 1 priomap.*0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -160,8 +168,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio bands 1024 priomap 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16",
         "expExitCode": "2",
@@ -169,7 +179,6 @@
         "matchPattern": "qdisc prio 1: root.*bands 1024 priomap.*1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -179,8 +188,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root prio"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root prio bands 8 priomap 1 1 2 2 3 3 4 4 5 5 6 6 7 7 0 0",
@@ -189,8 +200,7 @@
         "matchPattern": "qdisc prio 1: root.*bands 8 priomap.*1 1 2 2 3 3 4 4 5 5 6 6 7 7 0 0",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root prio"
         ]
     },
     {
@@ -200,8 +210,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root prio"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio",
@@ -210,8 +222,7 @@
         "matchPattern": "qdisc prio 1: root",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root prio"
         ]
     },
     {
@@ -221,8 +232,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY root handle 1: prio",
         "expExitCode": "2",
@@ -230,7 +243,6 @@
         "matchPattern": "qdisc prio 1: root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -240,8 +252,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY root handle 123^ prio",
         "expExitCode": "255",
@@ -249,7 +263,6 @@
         "matchPattern": "qdisc prio 123 root",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -259,8 +272,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY root handle 1: prio",
             "$TC qdisc del dev $DUMMY root handle 1: prio"
         ],
@@ -270,7 +285,6 @@
         "matchPattern": "qdisc ingress ffff:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -280,8 +294,10 @@
             "qdisc",
             "prio"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root prio",
         "expExitCode": "0",
@@ -289,8 +305,7 @@
         "matchPattern": "class prio 1:[0-9]+ parent 1:",
         "matchCount": "3",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root prio",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root prio"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json
index 976dffda4654..c95643929841 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/qfq.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root qfq",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc qfq 1: root refcnt [0-9]+",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100",
@@ -42,8 +39,7 @@
         "matchPattern": "class qfq 1:1 root weight 100 maxpkt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -57,7 +53,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 9999",
@@ -66,8 +61,7 @@
         "matchPattern": "class qfq 1:1 root weight 9999 maxpkt",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -81,7 +75,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq maxpkt 2000",
@@ -90,8 +83,7 @@
         "matchPattern": "class qfq 1:1 root weight 1 maxpkt 2000",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -105,7 +97,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq maxpkt 128",
@@ -114,8 +105,7 @@
         "matchPattern": "class qfq 1:1 root weight 1 maxpkt 128",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -129,7 +119,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
         "cmdUnderTest": "$TC class add dev $DUMMY parent 1: classid 1:1 qfq maxpkt 99999",
@@ -138,8 +127,7 @@
         "matchPattern": "class qfq 1:1 root weight 1 maxpkt 99999",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -153,7 +141,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq",
             "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100"
         ],
@@ -163,8 +150,7 @@
         "matchPattern": "class qfq 1:[0-9]+ root weight [0-9]+00 maxpkt",
         "matchCount": "2",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -178,7 +164,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq",
             "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100"
         ],
@@ -188,7 +173,6 @@
         "matchPattern": "qdisc qfq 1: root refcnt [0-9]+",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -202,7 +186,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root qfq",
         "expExitCode": "0",
@@ -210,8 +193,7 @@
         "matchPattern": "class qfq 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -225,7 +207,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$IP link set dev $DUMMY mtu 2147483647 || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
@@ -235,7 +216,6 @@
         "matchPattern": "class qfq 1:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -249,7 +229,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$IP link set dev $DUMMY mtu 256 || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root qfq"
         ],
@@ -259,7 +238,6 @@
         "matchPattern": "class qfq 1:",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -277,7 +255,6 @@
             ]
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$IP link set dev $DUMMY up || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: stab mtu 2048 tsize 512 mpu 0 overhead 999999999 linklayer ethernet root qfq",
             "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 100",
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json
index 4b3e449857f2..eec73fda6c80 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/red.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red adaptive limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb adaptive $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn adaptive limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn adaptive $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn harddrop limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn harddrop $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn nodrop limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn nodrop $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red nodrop limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "2",
@@ -156,7 +143,6 @@
         "matchPattern": "qdisc red",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
         ]
     },
     {
@@ -170,7 +156,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red ecn harddrop nodrop limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -178,8 +163,7 @@
         "matchPattern": "qdisc red 1: root .* limit 1Mb min 100Kb max 300Kb ecn harddrop nodrop $",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -193,7 +177,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root red limit 1M avpkt 1500 min 100K max 300K",
         "expExitCode": "0",
@@ -201,8 +184,7 @@
         "matchPattern": "class red 1:[0-9]+ parent 1:",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json
index e21c7f22c6d4..aa7914c441ea 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 60s",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb rehash 60",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 60ms db 60s",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 100",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb limit 100",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 60s limit 100p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb max 100",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*max 100p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb target 100",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*target 100p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb increment 0.1",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*increment 0.1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb decrement 0.1",
         "expExitCode": "0",
@@ -179,8 +164,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*decrement 0.1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -194,7 +178,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb penalty_rate 4000",
         "expExitCode": "0",
@@ -202,8 +185,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*penalty_rate 4000pps",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -217,7 +199,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb penalty_burst 64",
         "expExitCode": "0",
@@ -225,8 +206,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 600s db 60s.*penalty_burst 64p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -240,7 +220,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root sfb penalty_burst 64"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root sfb rehash 100",
@@ -249,8 +228,7 @@
         "matchPattern": "qdisc sfb 1: root refcnt 2 rehash 100ms db 60s",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -264,7 +242,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb",
         "expExitCode": "0",
@@ -272,8 +249,7 @@
         "matchPattern": "class sfb 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
index b6be718a174a..16d51936b385 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum.*depth 127 divisor 1024",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq limit 8",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 8p",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq perturb 10",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "depth 127 divisor 1024 perturb 10sec",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq quantum 9000",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum 9000b depth 127 divisor 1024",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq divisor 512",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum 1514b depth 127 divisor 512",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq flows 20",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq depth 64",
         "expExitCode": "0",
@@ -156,8 +143,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum 1514b depth 64 divisor 1024",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -171,7 +157,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq headdrop",
         "expExitCode": "0",
@@ -179,8 +164,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum 1514b depth 127 headdrop divisor 1024",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -194,7 +178,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq redflowlimit 100000 min 8000 max 60000 probability 0.20 ecn headdrop",
         "expExitCode": "0",
@@ -202,8 +185,7 @@
         "matchPattern": "qdisc sfq 1: root refcnt [0-9]+ limit 127p quantum 1514b depth 127 headdrop divisor 1024 ewma 6 min 8000b max 60000b probability 0.2 ecn",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -217,7 +199,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq",
         "expExitCode": "0",
@@ -225,8 +206,7 @@
         "matchPattern": "class sfq 1:",
         "matchCount": "0",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/skbprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/skbprio.json
index 5766045c9d33..076d1d69a3a4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/skbprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/skbprio.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root skbprio",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc skbprio 1: root refcnt [0-9]+ limit 64",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root skbprio limit 1",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc skbprio 1: root refcnt [0-9]+ limit 1",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root skbprio"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root skbprio limit 32",
@@ -65,8 +60,7 @@
         "matchPattern": "qdisc skbprio 1: root refcnt [0-9]+ limit 32",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -80,7 +74,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root skbprio",
         "expExitCode": "0",
@@ -88,8 +81,7 @@
         "matchPattern": "class skbprio 1:",
         "matchCount": "64",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/tbf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/tbf.json
index a4b3dfe51ff5..547a44910041 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/tbf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/tbf.json
@@ -10,7 +10,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 10000",
         "expExitCode": "0",
@@ -18,8 +17,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 10Kbit burst 1500b limit 1000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -33,7 +31,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 mtu 2048",
         "expExitCode": "0",
@@ -41,8 +38,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1500b limit 1000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -56,7 +52,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 mtu 1510 peakrate 30000",
         "expExitCode": "0",
@@ -64,8 +59,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1500b peakrate 30Kbit minburst.*limit 1000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -79,7 +73,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf burst 1500 rate 20000 latency 100ms",
         "expExitCode": "0",
@@ -87,8 +80,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1500b lat 100ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -102,7 +94,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 overhead 300",
         "expExitCode": "0",
@@ -110,8 +101,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1800b limit 1000b overhead 300",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -125,7 +115,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 linklayer atm",
         "expExitCode": "0",
@@ -133,8 +122,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1696b limit 1000b linklayer atm",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -148,7 +136,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 linklayer atm"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 20000 linklayer ethernet",
@@ -157,8 +144,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1500b limit 1000b",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -172,7 +158,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
             "$TC qdisc add dev $DUMMY handle 1: root tbf burst 1500 rate 20000 latency 10ms"
         ],
         "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: root tbf burst 1500 rate 20000 latency 200ms",
@@ -181,8 +166,7 @@
         "matchPattern": "qdisc tbf 1: root refcnt [0-9]+ rate 20Kbit burst 1500b lat 200ms",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     },
     {
@@ -196,7 +180,6 @@
             "requires": "nsPlugin"
         },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root tbf limit 1000 burst 1500 rate 10000",
         "expExitCode": "0",
@@ -204,8 +187,7 @@
         "matchPattern": "class tbf.*parent 1:",
         "matchCount": "1",
         "teardown": [
-            "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$TC qdisc del dev $DUMMY handle 1: root"
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json
index 0082be0e93ac..e5cc31f265f8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json
@@ -6,11 +6,8 @@
             "qdisc",
             "teql"
         ],
-        "plugins": {
-            "requires": "nsPlugin"
-        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
+            "$IP link add dev $DUMMY type dummy"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root teql0",
         "expExitCode": "0",
@@ -19,7 +16,7 @@
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$IP link del dev $DUMMY"
         ]
     },
     {
@@ -29,13 +26,10 @@
             "qdisc",
             "teql"
         ],
-        "plugins": {
-            "requires": "nsPlugin"
-        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
-            "echo \"1 1 4\" > /sys/bus/netdevsim/new_device",
-            "$TC qdisc add dev $ETH root handle 1: teql0"
+            "$IP link add dev $DUMMY type dummy",
+            "$IP link add dev $ETH type dummy",
+            "$TC qdisc add dev $ETH handle 1: root teql0"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root teql0",
         "expExitCode": "0",
@@ -44,8 +38,8 @@
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root",
-            "echo \"1\" > /sys/bus/netdevsim/del_device",
-            "$IP link del dev $DUMMY type dummy"
+            "$IP link del dev $DUMMY",
+            "$IP link del dev $ETH"
         ]
     },
     {
@@ -55,11 +49,8 @@
             "qdisc",
             "teql"
         ],
-        "plugins": {
-            "requires": "nsPlugin"
-        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true",
+            "$IP link add dev $DUMMY type dummy",
             "$TC qdisc add dev $DUMMY handle 1: root teql0"
         ],
         "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root",
@@ -68,7 +59,7 @@
         "matchPattern": "qdisc teql0 1: root refcnt",
         "matchCount": "0",
         "teardown": [
-            "$IP link del dev $DUMMY type dummy"
+            "$IP link del dev $DUMMY"
         ]
     },
     {
@@ -78,11 +69,8 @@
             "qdisc",
             "teql"
         ],
-        "plugins": {
-            "requires": "nsPlugin"
-        },
         "setup": [
-            "$IP link add dev $DUMMY type dummy || /bin/true"
+            "$IP link add dev $DUMMY type dummy"
         ],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root teql0",
         "expExitCode": "0",
@@ -91,7 +79,7 @@
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root",
-            "$IP link del dev $DUMMY type dummy"
+            "$IP link del dev $DUMMY"
         ]
     }
 ]
-- 
cgit v1.2.3


From ac9b8293096465914c1a0b778e759333ceac5cd1 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 19 Sep 2023 10:54:03 -0300
Subject: selftests/tc-testing: implement tdc parallel test run

Use a Python process pool to run the tests in parallel.
Not all tests can run in parallel, for instance tests that are not
namespaced and tests that use netdevsim, as they can conflict with one
another.

The code logic will split the tests into serial and parallel.
For the parallel tests, we build batches of 32 tests and queue each
batch on the process pool. For the serial tests, they are queued as a
whole into the process pool, which in turn executes them concurrently
with the parallel tests.

Even though the tests serialize on rtnl_lock in the kernel, this feature
showed results with a ~3x speedup on the wall time for the entire test suite
running in a VM:
   Before - 4m32.502s
   After - 1m19.202s

Examples:
   In order to run tdc using 4 processes:
      ./tdc.py -J4 <...>
   In order to run tdc using 1 process:
      ./tdc.py -J1 <...> || ./tdc.py <...>

Note that the kernel configuration will affect the speed of the tests,
especially if such configuration slows down process creation and/or
fork().

Tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/tc-testing/TdcResults.py   |   3 +-
 .../selftests/tc-testing/plugin-lib/nsPlugin.py    |  79 +++++++------
 tools/testing/selftests/tc-testing/tdc.py          | 123 +++++++++++++++++----
 3 files changed, 148 insertions(+), 57 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/TdcResults.py b/tools/testing/selftests/tc-testing/TdcResults.py
index 1e4d95fdf8d0..e56817b97f08 100644
--- a/tools/testing/selftests/tc-testing/TdcResults.py
+++ b/tools/testing/selftests/tc-testing/TdcResults.py
@@ -59,7 +59,8 @@ class TestResult:
         return self.steps
 
 class TestSuiteReport():
-    _testsuite = []
+    def __init__(self):
+        self._testsuite = []
 
     def add_resultdata(self, result_data):
         if isinstance(result_data, TestResult):
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
index 78acbfa5af9d..b62429b0fcdb 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py
@@ -3,46 +3,65 @@ import signal
 from string import Template
 import subprocess
 import time
+from multiprocessing import Pool
 from functools import cached_property
 from TdcPlugin import TdcPlugin
 
 from tdc_config import *
 
+def prepare_suite(obj, test):
+    original = obj.args.NAMES
+
+    if 'skip' in test and test['skip'] == 'yes':
+        return
+
+    if 'nsPlugin' not in test['plugins']:
+        return
+
+    shadow = {}
+    shadow['IP'] = original['IP']
+    shadow['TC'] = original['TC']
+    shadow['NS'] = '{}-{}'.format(original['NS'], test['random'])
+    shadow['DEV0'] = '{}id{}'.format(original['DEV0'], test['id'])
+    shadow['DEV1'] = '{}id{}'.format(original['DEV1'], test['id'])
+    shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], test['id'])
+    shadow['DEV2'] = original['DEV2']
+    obj.args.NAMES = shadow
+
+    if obj.args.namespace:
+        obj._ns_create()
+    else:
+        obj._ports_create()
+
+    # Make sure the netns is visible in the fs
+    while True:
+        obj._proc_check()
+        try:
+            ns = obj.args.NAMES['NS']
+            f = open('/run/netns/{}'.format(ns))
+            f.close()
+            break
+        except:
+            time.sleep(0.1)
+            continue
+
+    obj.args.NAMES = original
+
 class SubPlugin(TdcPlugin):
     def __init__(self):
         self.sub_class = 'ns/SubPlugin'
         super().__init__()
 
     def pre_suite(self, testcount, testlist):
+        from itertools import cycle
+
         super().pre_suite(testcount, testlist)
 
         print("Setting up namespaces and devices...")
 
-        original = self.args.NAMES
-
-        for t in testlist:
-            if 'skip' in t and t['skip'] == 'yes':
-                continue
-
-            if 'nsPlugin' not in t['plugins']:
-                continue
-
-            shadow = {}
-            shadow['IP'] = original['IP']
-            shadow['TC'] = original['TC']
-            shadow['NS'] = '{}-{}'.format(original['NS'], t['random'])
-            shadow['DEV0'] = '{}id{}'.format(original['DEV0'], t['id'])
-            shadow['DEV1'] = '{}id{}'.format(original['DEV1'], t['id'])
-            shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], t['id'])
-            shadow['DEV2'] = original['DEV2']
-            self.args.NAMES = shadow
-
-            if self.args.namespace:
-                self._ns_create()
-            else:
-                self._ports_create()
-
-        self.args.NAMES = original
+        with Pool(self.args.mp) as p:
+            it = zip(cycle([self]), testlist)
+            p.starmap(prepare_suite, it)
 
     def pre_case(self, caseinfo, test_skip):
         if self.args.verbose:
@@ -51,16 +70,6 @@ class SubPlugin(TdcPlugin):
         if test_skip:
             return
 
-        # Make sure the netns is visible in the fs
-        while True:
-            self._proc_check()
-            try:
-                ns = self.args.NAMES['NS']
-                f = open('/run/netns/{}'.format(ns))
-                f.close()
-                break
-            except:
-                continue
 
     def post_case(self):
         if self.args.verbose:
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index 3914caa14de1..a6718192aff3 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -17,6 +17,7 @@ import subprocess
 import time
 import traceback
 import random
+from multiprocessing import Pool
 from collections import OrderedDict
 from string import Template
 
@@ -477,26 +478,11 @@ def run_one_test(pm, args, index, tidx):
 
     return res
 
-def test_runner(pm, args, filtered_tests):
-    """
-    Driver function for the unit tests.
-
-    Prints information about the tests being run, executes the setup and
-    teardown commands and the command under test itself. Also determines
-    success/failure based on the information in the test case and generates
-    TAP output accordingly.
-    """
-    testlist = filtered_tests
+def prepare_run(pm, args, testlist):
     tcount = len(testlist)
-    index = 1
-    tap = ''
-    badtest = None
-    stage = None
     emergency_exit = False
     emergency_exit_message = ''
 
-    tsr = TestSuiteReport()
-
     try:
         pm.call_pre_suite(tcount, testlist)
     except Exception as ee:
@@ -506,14 +492,37 @@ def test_runner(pm, args, filtered_tests):
         traceback.print_tb(ex_tb)
         emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex)
         emergency_exit = True
-        stage = 'pre-SUITE'
 
     if emergency_exit:
-        pm.call_post_suite(index)
+        pm.call_post_suite(1)
         return emergency_exit_message
-    if args.verbose > 1:
+
+    if args.verbose:
         print('give test rig 2 seconds to stabilize')
+
     time.sleep(2)
+
+def purge_run(pm, index):
+    pm.call_post_suite(index)
+
+def test_runner(pm, args, filtered_tests):
+    """
+    Driver function for the unit tests.
+
+    Prints information about the tests being run, executes the setup and
+    teardown commands and the command under test itself. Also determines
+    success/failure based on the information in the test case and generates
+    TAP output accordingly.
+    """
+    testlist = filtered_tests
+    tcount = len(testlist)
+    index = 1
+    tap = ''
+    badtest = None
+    stage = None
+
+    tsr = TestSuiteReport()
+
     for tidx in testlist:
         if "flower" in tidx["category"] and args.device == None:
             errmsg = "Tests using the DEV2 variable must define the name of a "
@@ -576,7 +585,68 @@ def test_runner(pm, args, filtered_tests):
         if input(sys.stdin):
             print('got something on stdin')
 
-    pm.call_post_suite(index)
+    return (index, tsr)
+
+def mp_bins(alltests):
+    serial = []
+    parallel = []
+
+    for test in alltests:
+        if 'nsPlugin' not in test['plugins']:
+            serial.append(test)
+        else:
+            # We can only create one netdevsim device at a time
+            if 'netdevsim/new_device' in str(test['setup']):
+                serial.append(test)
+            else:
+                parallel.append(test)
+
+    return (serial, parallel)
+
+def __mp_runner(tests):
+    (_, tsr) = test_runner(mp_pm, mp_args, tests)
+    return tsr._testsuite
+
+def test_runner_mp(pm, args, alltests):
+    prepare_run(pm, args, alltests)
+
+    (serial, parallel) = mp_bins(alltests)
+
+    batches = [parallel[n : n + 32] for n in range(0, len(parallel), 32)]
+    batches.insert(0, serial)
+
+    print("Executing {} tests in parallel and {} in serial".format(len(parallel), len(serial)))
+    print("Using {} batches".format(len(batches)))
+
+    # We can't pickle these objects so workaround them
+    global mp_pm
+    mp_pm = pm
+
+    global mp_args
+    mp_args = args
+
+    with Pool(args.mp) as p:
+        pres = p.map(__mp_runner, batches)
+
+    tsr = TestSuiteReport()
+    for trs in pres:
+        for res in trs:
+            tsr.add_resultdata(res)
+
+    # Passing an index is not useful in MP
+    purge_run(pm, None)
+
+    return tsr
+
+def test_runner_serial(pm, args, alltests):
+    prepare_run(pm, args, alltests)
+
+    if args.verbose:
+        print("Executing {} tests in serial".format(len(alltests)))
+
+    (index, tsr) = test_runner(pm, args, alltests)
+
+    purge_run(pm, index)
 
     return tsr
 
@@ -605,12 +675,15 @@ def load_from_file(filename):
                 k['filename'] = filename
     return testlist
 
+def identity(string):
+    return string
 
 def args_parse():
     """
     Create the argument parser.
     """
     parser = argparse.ArgumentParser(description='Linux TC unit tests')
+    parser.register('type', None, identity)
     return parser
 
 
@@ -668,6 +741,9 @@ def set_args(parser):
     parser.add_argument(
         '-P', '--pause', action='store_true',
         help='Pause execution just before post-suite stage')
+    parser.add_argument(
+        '-J', '--multiprocess', type=int, default=1, dest='mp',
+        help='Run tests in parallel whenever possible')
     return parser
 
 
@@ -888,7 +964,12 @@ def set_operation_mode(pm, parser, args, remaining):
         except PluginDependencyException as pde:
             print('The following plugins were not found:')
             print('{}'.format(pde.missing_pg))
-        catresults = test_runner(pm, args, alltests)
+
+        if args.mp > 1:
+            catresults = test_runner_mp(pm, args, alltests)
+        else:
+            catresults = test_runner_serial(pm, args, alltests)
+
         if catresults.count_failures() != 0:
             exit_code = 1 # KSFT_FAIL
         if args.format == 'none':
-- 
cgit v1.2.3


From d3fc4eea9742b89ba9b1609463cf62bba4b9be82 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 19 Sep 2023 10:54:04 -0300
Subject: selftests/tc-testing: update tdc documentation

Update the documentation to reflect the changes made to tdc with regards
to minimal requirements and test definitions expectations.

Tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/tc-testing/README | 65 +++++--------------------------
 1 file changed, 10 insertions(+), 55 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index b0954c873e2f..be7b00799b3e 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -9,8 +9,7 @@ execute them inside a network namespace dedicated to the task.
 REQUIREMENTS
 ------------
 
-*  Minimum Python version of 3.4. Earlier 3.X versions may work but are not
-   guaranteed.
+*  Minimum Python version of 3.8.
 
 *  The kernel must have network namespace support if using nsPlugin
 
@@ -96,6 +95,15 @@ the stdout with a regular expression.
 
 Each of the commands in any stage will run in a shell instance.
 
+Each test is an atomic unit. A test that for whatever reason spans multiple test
+definitions is a bug.
+
+A test that runs inside a namespace (requires "nsPlugin") will run in parallel
+with other tests.
+
+Tests that use netdevsim or don't run inside a namespace run serially with regards
+to each other.
+
 
 USER-DEFINED CONSTANTS
 ----------------------
@@ -116,59 +124,6 @@ COMMAND LINE ARGUMENTS
 
 Run tdc.py -h to see the full list of available arguments.
 
-usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]]
-              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] [-N]
-              [-d DEVICE] [-P] [-n] [-V]
-
-Linux TC unit tests
-
-optional arguments:
-  -h, --help            show this help message and exit
-  -p PATH, --path PATH  The full path to the tc executable to use
-  -v, --verbose         Show the commands that are being run
-  -N, --notap           Suppress tap results for command under test
-  -d DEVICE, --device DEVICE
-                        Execute test cases that use a physical device, where
-                        DEVICE is its name. (If not defined, tests that require
-                        a physical device will be skipped)
-  -P, --pause           Pause execution just before post-suite stage
-
-selection:
-  select which test cases: files plus directories; filtered by categories
-  plus testids
-
-  -D DIR [DIR ...], --directory DIR [DIR ...]
-                        Collect tests from the specified directory(ies)
-                        (default [tc-tests])
-  -f FILE [FILE ...], --file FILE [FILE ...]
-                        Run tests from the specified file(s)
-  -c [CATG [CATG ...]], --category [CATG [CATG ...]]
-                        Run tests only from the specified category/ies, or if
-                        no category/ies is/are specified, list known
-                        categories.
-  -e ID [ID ...], --execute ID [ID ...]
-                        Execute the specified test cases with specified IDs
-
-action:
-  select action to perform on selected test cases
-
-  -l, --list            List all test cases, or those only within the
-                        specified category
-  -s, --show            Display the selected test cases
-  -i, --id              Generate ID numbers for new test cases
-
-netns:
-  options for nsPlugin (run commands in net namespace)
-
-  -N, --no-namespace
-                        Do not run commands in a network namespace.
-
-valgrind:
-  options for valgrindPlugin (run command under test under Valgrind)
-
-  -V, --valgrind        Run commands under valgrind
-
-
 PLUGIN ARCHITECTURE
 -------------------
 
-- 
cgit v1.2.3


From 117e149e26d193467a3a136aa4393d32a3e7046f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 15 Aug 2023 11:52:41 +0200
Subject: selftests: netfilter: test nat source port clash resolution
 interaction with tcp early demux

Test that nat engine resolves the source port clash and tcp packet
is passed to the correct socket.

While at it, get rid of the iperf3 dependency, just use socat for
listener side too.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 tools/testing/selftests/netfilter/nf_nat_edemux.sh | 46 +++++++++++++++++-----
 1 file changed, 37 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nf_nat_edemux.sh b/tools/testing/selftests/netfilter/nf_nat_edemux.sh
index 1092bbcb1fba..a1aa8f4a5828 100755
--- a/tools/testing/selftests/netfilter/nf_nat_edemux.sh
+++ b/tools/testing/selftests/netfilter/nf_nat_edemux.sh
@@ -11,16 +11,18 @@ ret=0
 sfx=$(mktemp -u "XXXXXXXX")
 ns1="ns1-$sfx"
 ns2="ns2-$sfx"
+socatpid=0
 
 cleanup()
 {
+	[ $socatpid -gt 0 ] && kill $socatpid
 	ip netns del $ns1
 	ip netns del $ns2
 }
 
-iperf3 -v > /dev/null 2>&1
+socat -h > /dev/null 2>&1
 if [ $? -ne 0 ];then
-	echo "SKIP: Could not run test without iperf3"
+	echo "SKIP: Could not run test without socat"
 	exit $ksft_skip
 fi
 
@@ -60,8 +62,8 @@ ip netns exec $ns2 ip link set up dev veth2
 ip netns exec $ns2 ip addr add 192.168.1.2/24 dev veth2
 
 # Create a server in one namespace
-ip netns exec $ns1 iperf3 -s > /dev/null 2>&1 &
-iperfs=$!
+ip netns exec $ns1 socat -u TCP-LISTEN:5201,fork OPEN:/dev/null,wronly=1 &
+socatpid=$!
 
 # Restrict source port to just one so we don't have to exhaust
 # all others.
@@ -83,17 +85,43 @@ sleep 1
 # ip daddr:dport will be rewritten to 192.168.1.1 5201
 # NAT must reallocate source port 10000 because
 # 192.168.1.2:10000 -> 192.168.1.1:5201 is already in use
-echo test | ip netns exec $ns2 socat -t 3 -u STDIN TCP:10.96.0.1:443 >/dev/null
+echo test | ip netns exec $ns2 socat -t 3 -u STDIN TCP:10.96.0.1:443,connect-timeout=3 >/dev/null
 ret=$?
 
-kill $iperfs
-
 # Check socat can connect to 10.96.0.1:443 (aka 192.168.1.1:5201).
 if [ $ret -eq 0 ]; then
 	echo "PASS: socat can connect via NAT'd address"
 else
 	echo "FAIL: socat cannot connect via NAT'd address"
-	exit 1
 fi
 
-exit 0
+# check sport clashres.
+ip netns exec $ns1 iptables -t nat -A PREROUTING -p tcp --dport 5202 -j REDIRECT --to-ports 5201
+ip netns exec $ns1 iptables -t nat -A PREROUTING -p tcp --dport 5203 -j REDIRECT --to-ports 5201
+
+sleep 5 | ip netns exec $ns2 socat -t 5 -u STDIN TCP:192.168.1.1:5202,connect-timeout=5 >/dev/null &
+cpid1=$!
+sleep 1
+
+# if connect succeeds, client closes instantly due to EOF on stdin.
+# if connect hangs, it will time out after 5s.
+echo | ip netns exec $ns2 socat -t 3 -u STDIN TCP:192.168.1.1:5203,connect-timeout=5 >/dev/null &
+cpid2=$!
+
+time_then=$(date +%s)
+wait $cpid2
+rv=$?
+time_now=$(date +%s)
+
+# Check how much time has elapsed, expectation is for
+# 'cpid2' to connect and then exit (and no connect delay).
+delta=$((time_now - time_then))
+
+if [ $delta -lt 2 -a $rv -eq 0 ]; then
+	echo "PASS: could connect to service via redirected ports"
+else
+	echo "FAIL: socat cannot connect to service via redirect ($delta seconds elapsed, returned $rv)"
+	ret=1
+fi
+
+exit $ret
-- 
cgit v1.2.3


From 2147c8d07e1abc8dfc3433ca18eed5295e230ede Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 29 Sep 2023 15:59:54 +0000
Subject: libbpf: Allow Golang symbols in uprobe secdef

Golang symbols in ELF files are different from C/C++
which contains special characters like '*', '(' and ')'.
With generics, things get more complicated, there are
symbols like:

  github.com/cilium/ebpf/internal.(*Deque[go.shape.interface { Format(fmt.State, int32); TypeName() string;github.com/cilium/ebpf/btf.copy() github.com/cilium/ebpf/btf.Type}]).Grow

Matching such symbols using `%m[^\n]` in sscanf, this
excludes newline which typically does not appear in ELF
symbols. This should work in most use-cases and also
work for unicode letters in identifiers. If newline do
show up in ELF symbols, users can still attach to such
symbol by specifying bpf_uprobe_opts::func_name.

A working example can be found at this repo ([0]).

  [0]: https://github.com/chenhengqi/libbpf-go-symbols

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230929155954.92448-1-hengqi.chen@gmail.com
---
 tools/lib/bpf/libbpf.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b4758e54a815..31b8b252e614 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11114,7 +11114,7 @@ static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, stru
 
 	*link = NULL;
 
-	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%ms",
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[^\n]",
 		   &probe_type, &binary_path, &func_name);
 	switch (n) {
 	case 1:
@@ -11624,14 +11624,14 @@ err_out:
 static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
-	char *probe_type = NULL, *binary_path = NULL, *func_name = NULL;
-	int n, ret = -EINVAL;
+	char *probe_type = NULL, *binary_path = NULL, *func_name = NULL, *func_off;
+	int n, c, ret = -EINVAL;
 	long offset = 0;
 
 	*link = NULL;
 
-	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.@]+%li",
-		   &probe_type, &binary_path, &func_name, &offset);
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[^\n]",
+		   &probe_type, &binary_path, &func_name);
 	switch (n) {
 	case 1:
 		/* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */
@@ -11642,7 +11642,17 @@ static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf
 			prog->name, prog->sec_name);
 		break;
 	case 3:
-	case 4:
+		/* check if user specifies `+offset`, if yes, this should be
+		 * the last part of the string, make sure sscanf read to EOL
+		 */
+		func_off = strrchr(func_name, '+');
+		if (func_off) {
+			n = sscanf(func_off, "+%li%n", &offset, &c);
+			if (n == 1 && *(func_off + c) == '\0')
+				func_off[0] = '\0';
+			else
+				offset = 0;
+		}
 		opts.retprobe = strcmp(probe_type, "uretprobe") == 0 ||
 				strcmp(probe_type, "uretprobe.s") == 0;
 		if (opts.retprobe && offset != 0) {
-- 
cgit v1.2.3


From e08d0b3d172311e2bb500865c0d0038533d0ff11 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Sep 2023 03:42:16 +0000
Subject: inet: implement lockless IP_TOS

Some reads of inet->tos are racy.

Add needed READ_ONCE() annotations and convert IP_TOS option lockless.

v2: missing changes in include/net/route.h (David Ahern)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h                                   |  3 +--
 include/net/route.h                                |  4 +--
 net/dccp/ipv4.c                                    |  2 +-
 net/ipv4/inet_diag.c                               |  2 +-
 net/ipv4/ip_output.c                               |  4 +--
 net/ipv4/ip_sockglue.c                             | 29 +++++++++-------------
 net/ipv4/tcp_ipv4.c                                |  9 ++++---
 net/mptcp/sockopt.c                                |  8 +++---
 net/sctp/protocol.c                                |  4 +--
 tools/testing/selftests/net/mptcp/mptcp_connect.sh |  2 +-
 10 files changed, 31 insertions(+), 36 deletions(-)

(limited to 'tools')

diff --git a/include/net/ip.h b/include/net/ip.h
index 46933a0d98ea..6fbc0dcf4b97 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -258,7 +258,7 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
 
 static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
 {
-	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
+	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos));
 }
 
 /* datagram.c */
@@ -810,6 +810,5 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val);
 void ip_sock_set_pktinfo(struct sock *sk);
 void ip_sock_set_recverr(struct sock *sk);
 void ip_sock_set_tos(struct sock *sk, int val);
-void  __ip_sock_set_tos(struct sock *sk, int val);
 
 #endif	/* _IP_H */
diff --git a/include/net/route.h b/include/net/route.h
index 51a45b1887b5..5c248a8e3d0e 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -37,7 +37,7 @@
 
 #define RTO_ONLINK	0x01
 
-#define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
+#define RT_CONN_FLAGS(sk)   (RT_TOS(READ_ONCE(inet_sk(sk)->tos)) | sock_flag(sk, SOCK_LOCALROUTE))
 #define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
 static inline __u8 ip_sock_rt_scope(const struct sock *sk)
@@ -50,7 +50,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk)
 
 static inline __u8 ip_sock_rt_tos(const struct sock *sk)
 {
-	return RT_TOS(inet_sk(sk)->tos);
+	return RT_TOS(READ_ONCE(inet_sk(sk)->tos));
 }
 
 struct ip_tunnel_info;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 69453b936bd5..1b8cbfda6e5d 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -511,7 +511,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
 					    rcu_dereference(ireq->ireq_opt),
-					    inet_sk(sk)->tos);
+					    READ_ONCE(inet_sk(sk)->tos));
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 9f0bd518901a..f01aee832aab 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -134,7 +134,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	 * hence this needs to be included regardless of socket family.
 	 */
 	if (ext & (1 << (INET_DIAG_TOS - 1)))
-		if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
+		if (nla_put_u8(skb, INET_DIAG_TOS, READ_ONCE(inet->tos)) < 0)
 			goto errout;
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9fc7be2c2033..89e62ed08dad 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -544,7 +544,7 @@ EXPORT_SYMBOL(__ip_queue_xmit);
 
 int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 {
-	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+	return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos));
 }
 EXPORT_SYMBOL(ip_queue_xmit);
 
@@ -1438,7 +1438,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
-	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
+	iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos);
 	iph->frag_off = df;
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6d874cc03c8b..50c008efbb6d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -585,25 +585,20 @@ out:
 	return err;
 }
 
-void __ip_sock_set_tos(struct sock *sk, int val)
+void ip_sock_set_tos(struct sock *sk, int val)
 {
+	u8 old_tos = READ_ONCE(inet_sk(sk)->tos);
+
 	if (sk->sk_type == SOCK_STREAM) {
 		val &= ~INET_ECN_MASK;
-		val |= inet_sk(sk)->tos & INET_ECN_MASK;
+		val |= old_tos & INET_ECN_MASK;
 	}
-	if (inet_sk(sk)->tos != val) {
-		inet_sk(sk)->tos = val;
+	if (old_tos != val) {
+		WRITE_ONCE(inet_sk(sk)->tos, val);
 		WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
 		sk_dst_reset(sk);
 	}
 }
-
-void ip_sock_set_tos(struct sock *sk, int val)
-{
-	lock_sock(sk);
-	__ip_sock_set_tos(sk, val);
-	release_sock(sk);
-}
 EXPORT_SYMBOL(ip_sock_set_tos);
 
 void ip_sock_set_freebind(struct sock *sk)
@@ -1050,6 +1045,9 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		return 0;
 	case IP_MTU_DISCOVER:
 		return ip_sock_set_mtu_discover(sk, val);
+	case IP_TOS:	/* This sets both TOS and Precedence */
+		ip_sock_set_tos(sk, val);
+		return 0;
 	}
 
 	err = 0;
@@ -1104,9 +1102,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		break;
-	case IP_TOS:	/* This sets both TOS and Precedence */
-		__ip_sock_set_tos(sk, val);
-		break;
 	case IP_UNICAST_IF:
 	{
 		struct net_device *dev = NULL;
@@ -1593,6 +1588,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_MTU_DISCOVER:
 		val = READ_ONCE(inet->pmtudisc);
 		goto copyval;
+	case IP_TOS:
+		val = READ_ONCE(inet->tos);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1629,9 +1627,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		return 0;
 	}
-	case IP_TOS:
-		val = inet->tos;
-		break;
 	case IP_MTU:
 	{
 		struct dst_entry *dst;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 95e972be0c05..a441740616d7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1024,10 +1024,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
-		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
-				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
-				(inet_sk(sk)->tos & INET_ECN_MASK) :
-				inet_sk(sk)->tos;
+		tos = READ_ONCE(inet_sk(sk)->tos);
+
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
+			tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+			      (tos & INET_ECN_MASK);
 
 		if (!INET_ECN_is_capable(tos) &&
 		    tcp_bpf_ca_needs_ecn((struct sock *)req))
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index f3485a6b35e7..18ce624bfde2 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -734,11 +734,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 
 	lock_sock(sk);
 	sockopt_seq_inc(msk);
-	val = inet_sk(sk)->tos;
+	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
-		__ip_sock_set_tos(ssk, val);
+		ip_sock_set_tos(ssk, val);
 	}
 	release_sock(sk);
 
@@ -1343,7 +1343,7 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case IP_TOS:
-		return mptcp_put_int_option(msk, optval, optlen, inet_sk(sk)->tos);
+		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
 	}
 
 	return -EOPNOTSUPP;
@@ -1411,7 +1411,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	ssk->sk_incoming_cpu = sk->sk_incoming_cpu;
 	ssk->sk_ipv6only = sk->sk_ipv6only;
-	__ip_sock_set_tos(ssk, inet_sk(sk)->tos);
+	ip_sock_set_tos(ssk, inet_sk(sk)->tos);
 
 	if (sk->sk_userlocks & tx_rx_locks) {
 		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 2185f44198de..94c6dd53cd62 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -426,7 +426,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct dst_entry *dst = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
-	__u8 tos = inet_sk(sk)->tos;
+	u8 tos = READ_ONCE(inet_sk(sk)->tos);
 
 	if (t->dscp & SCTP_DSCP_SET_MASK)
 		tos = t->dscp & SCTP_DSCP_VAL_MASK;
@@ -1057,7 +1057,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
 	struct flowi4 *fl4 = &t->fl.u.ip4;
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
-	__u8 dscp = inet->tos;
+	__u8 dscp = READ_ONCE(inet->tos);
 	__be16 df = 0;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index b1fc8afd072d..61a2a1988ce6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -716,7 +716,7 @@ run_test_transparent()
 	# the required infrastructure in MPTCP sockopt code. To support TOS, the
 	# following function has been exported (T). Not great but better than
 	# checking for a specific kernel version.
-	if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then
+	if ! mptcp_lib_kallsyms_has "T ip_sock_set_tos$"; then
 		echo "INFO: ${msg} not supported by the kernel: SKIP"
 		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
-- 
cgit v1.2.3


From a6b07a51b161ba1ad3d81919955fe77b697f9d48 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 21 Sep 2023 09:07:40 -0400
Subject: handshake: Fix sign of socket file descriptor fields

Socket file descriptors are signed integers. Use nla_get/put_s32 for
those to avoid implicit signed conversion in the netlink protocol.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/169530165057.8905.8650469415145814828.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/handshake.yaml | 4 ++--
 net/handshake/genl.c                       | 2 +-
 net/handshake/netlink.c                    | 2 +-
 net/handshake/tlshd.c                      | 2 +-
 tools/net/ynl/generated/handshake-user.h   | 6 +++---
 5 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml
index 6d89e30f5fd5..a49b46b80e16 100644
--- a/Documentation/netlink/specs/handshake.yaml
+++ b/Documentation/netlink/specs/handshake.yaml
@@ -43,7 +43,7 @@ attribute-sets:
     attributes:
       -
         name: sockfd
-        type: u32
+        type: s32
       -
         name: handler-class
         type: u32
@@ -79,7 +79,7 @@ attribute-sets:
         type: u32
       -
         name: sockfd
-        type: u32
+        type: s32
       -
         name: remote-auth
         type: u32
diff --git a/net/handshake/genl.c b/net/handshake/genl.c
index 233be5cbfec9..f55d14d7b726 100644
--- a/net/handshake/genl.c
+++ b/net/handshake/genl.c
@@ -18,7 +18,7 @@ static const struct nla_policy handshake_accept_nl_policy[HANDSHAKE_A_ACCEPT_HAN
 /* HANDSHAKE_CMD_DONE - do */
 static const struct nla_policy handshake_done_nl_policy[HANDSHAKE_A_DONE_REMOTE_AUTH + 1] = {
 	[HANDSHAKE_A_DONE_STATUS] = { .type = NLA_U32, },
-	[HANDSHAKE_A_DONE_SOCKFD] = { .type = NLA_U32, },
+	[HANDSHAKE_A_DONE_SOCKFD] = { .type = NLA_S32, },
 	[HANDSHAKE_A_DONE_REMOTE_AUTH] = { .type = NLA_U32, },
 };
 
diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c
index d0bc1dd8e65a..64a0046dd611 100644
--- a/net/handshake/netlink.c
+++ b/net/handshake/netlink.c
@@ -163,7 +163,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
 
 	if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD))
 		return -EINVAL;
-	fd = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_SOCKFD]);
+	fd = nla_get_s32(info->attrs[HANDSHAKE_A_DONE_SOCKFD]);
 
 	sock = sockfd_lookup(fd, &err);
 	if (!sock)
diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c
index bbfb4095ddd6..7ac80201aa1f 100644
--- a/net/handshake/tlshd.c
+++ b/net/handshake/tlshd.c
@@ -214,7 +214,7 @@ static int tls_handshake_accept(struct handshake_req *req,
 		goto out_cancel;
 
 	ret = -EMSGSIZE;
-	ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_SOCKFD, fd);
+	ret = nla_put_s32(msg, HANDSHAKE_A_ACCEPT_SOCKFD, fd);
 	if (ret < 0)
 		goto out_cancel;
 	ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_MESSAGE_TYPE, treq->th_type);
diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h
index 47646bb91cea..f8e481fa9e09 100644
--- a/tools/net/ynl/generated/handshake-user.h
+++ b/tools/net/ynl/generated/handshake-user.h
@@ -65,7 +65,7 @@ struct handshake_accept_rsp {
 		__u32 peername_len;
 	} _present;
 
-	__u32 sockfd;
+	__s32 sockfd;
 	enum handshake_msg_type message_type;
 	__u32 timeout;
 	enum handshake_auth auth_mode;
@@ -104,7 +104,7 @@ struct handshake_done_req {
 	} _present;
 
 	__u32 status;
-	__u32 sockfd;
+	__s32 sockfd;
 	unsigned int n_remote_auth;
 	__u32 *remote_auth;
 };
@@ -122,7 +122,7 @@ handshake_done_req_set_status(struct handshake_done_req *req, __u32 status)
 	req->status = status;
 }
 static inline void
-handshake_done_req_set_sockfd(struct handshake_done_req *req, __u32 sockfd)
+handshake_done_req_set_sockfd(struct handshake_done_req *req, __s32 sockfd)
 {
 	req->_present.sockfd = 1;
 	req->sockfd = sockfd;
-- 
cgit v1.2.3


From 160f404495aa9282cac99b518d1b379e31ef1bdd Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 21 Sep 2023 09:08:07 -0400
Subject: handshake: Fix sign of key_serial_t fields

key_serial_t fields are signed integers. Use nla_get/put_s32 for
those to avoid implicit signed conversion in the netlink protocol.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/169530167716.8905.645746457741372879.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/handshake.yaml | 4 ++--
 net/handshake/tlshd.c                      | 4 ++--
 tools/net/ynl/generated/handshake-user.h   | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml
index a49b46b80e16..b934cc513e3d 100644
--- a/Documentation/netlink/specs/handshake.yaml
+++ b/Documentation/netlink/specs/handshake.yaml
@@ -34,10 +34,10 @@ attribute-sets:
     attributes:
       -
         name: cert
-        type: u32
+        type: s32
       -
         name: privkey
-        type: u32
+        type: s32
   -
     name: accept
     attributes:
diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c
index 7ac80201aa1f..d697f68c598c 100644
--- a/net/handshake/tlshd.c
+++ b/net/handshake/tlshd.c
@@ -173,9 +173,9 @@ static int tls_handshake_put_certificate(struct sk_buff *msg,
 	if (!entry_attr)
 		return -EMSGSIZE;
 
-	if (nla_put_u32(msg, HANDSHAKE_A_X509_CERT,
+	if (nla_put_s32(msg, HANDSHAKE_A_X509_CERT,
 			treq->th_certificate) ||
-	    nla_put_u32(msg, HANDSHAKE_A_X509_PRIVKEY,
+	    nla_put_s32(msg, HANDSHAKE_A_X509_PRIVKEY,
 			treq->th_privkey)) {
 		nla_nest_cancel(msg, entry_attr);
 		return -EMSGSIZE;
diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h
index f8e481fa9e09..2b34acc608de 100644
--- a/tools/net/ynl/generated/handshake-user.h
+++ b/tools/net/ynl/generated/handshake-user.h
@@ -28,8 +28,8 @@ struct handshake_x509 {
 		__u32 privkey:1;
 	} _present;
 
-	__u32 cert;
-	__u32 privkey;
+	__s32 cert;
+	__s32 privkey;
 };
 
 /* ============== HANDSHAKE_CMD_ACCEPT ============== */
-- 
cgit v1.2.3


From 8367eb954e24f0842e42c0b21ddb4513e0e9a235 Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:34 +0530
Subject: selftests/xsk: Move pkt_stream to the xsk_socket_info

Move the packet stream from the ifobject struct to the xsk_socket_info
struct to enable the use of different streams for different sockets. This
will facilitate the sending and receiving of data from multiple sockets
simultaneously using the SHARED_XDP_UMEM feature.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-2-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/xskxceiver.c | 71 +++++++++++++++++---------------
 tools/testing/selftests/bpf/xskxceiver.h |  2 +-
 2 files changed, 38 insertions(+), 35 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 43e0a5796929..16a09751b093 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -260,7 +260,7 @@ static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_i
 	cfg.bind_flags = ifobject->bind_flags;
 	if (shared)
 		cfg.bind_flags |= XDP_SHARED_UMEM;
-	if (ifobject->pkt_stream && ifobject->mtu > MAX_ETH_PKT_SIZE)
+	if (ifobject->mtu > MAX_ETH_PKT_SIZE)
 		cfg.bind_flags |= XDP_USE_SG;
 
 	txr = ifobject->tx_on ? &xsk->tx : NULL;
@@ -429,11 +429,9 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		if (i == 0) {
 			ifobj->rx_on = false;
 			ifobj->tx_on = true;
-			ifobj->pkt_stream = test->tx_pkt_stream_default;
 		} else {
 			ifobj->rx_on = true;
 			ifobj->tx_on = false;
-			ifobj->pkt_stream = test->rx_pkt_stream_default;
 		}
 
 		memset(ifobj->umem, 0, sizeof(*ifobj->umem));
@@ -443,6 +441,10 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		for (j = 0; j < MAX_SOCKETS; j++) {
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
 			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+			if (i == 0)
+				ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default;
+			else
+				ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default;
 		}
 	}
 
@@ -557,17 +559,17 @@ static void pkt_stream_delete(struct pkt_stream *pkt_stream)
 
 static void pkt_stream_restore_default(struct test_spec *test)
 {
-	struct pkt_stream *tx_pkt_stream = test->ifobj_tx->pkt_stream;
-	struct pkt_stream *rx_pkt_stream = test->ifobj_rx->pkt_stream;
+	struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream;
+	struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream;
 
 	if (tx_pkt_stream != test->tx_pkt_stream_default) {
-		pkt_stream_delete(test->ifobj_tx->pkt_stream);
-		test->ifobj_tx->pkt_stream = test->tx_pkt_stream_default;
+		pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream);
+		test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default;
 	}
 
 	if (rx_pkt_stream != test->rx_pkt_stream_default) {
-		pkt_stream_delete(test->ifobj_rx->pkt_stream);
-		test->ifobj_rx->pkt_stream = test->rx_pkt_stream_default;
+		pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream);
+		test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default;
 	}
 }
 
@@ -674,9 +676,9 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 	struct pkt_stream *pkt_stream;
 
 	pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len);
-	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
 	pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, nb_pkts, pkt_len);
-	test->ifobj_rx->pkt_stream = pkt_stream;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
 }
 
 static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
@@ -686,11 +688,11 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
 	struct pkt_stream *pkt_stream;
 	u32 i;
 
-	pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream);
-	for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2)
+	pkt_stream = pkt_stream_clone(umem, ifobj->xsk->pkt_stream);
+	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
 		pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len);
 
-	ifobj->pkt_stream = pkt_stream;
+	ifobj->xsk->pkt_stream = pkt_stream;
 }
 
 static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
@@ -702,12 +704,12 @@ static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int off
 static void pkt_stream_receive_half(struct test_spec *test)
 {
 	struct xsk_umem_info *umem = test->ifobj_rx->umem;
-	struct pkt_stream *pkt_stream = test->ifobj_tx->pkt_stream;
+	struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream;
 	u32 i;
 
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(umem, pkt_stream->nb_pkts,
-							 pkt_stream->pkts[0].len);
-	pkt_stream = test->ifobj_rx->pkt_stream;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(umem, pkt_stream->nb_pkts,
+							      pkt_stream->pkts[0].len);
+	pkt_stream = test->ifobj_rx->xsk->pkt_stream;
 	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
 		pkt_stream->pkts[i].valid = false;
 }
@@ -796,10 +798,10 @@ static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts,
 	struct pkt_stream *pkt_stream;
 
 	pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true);
-	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
 
 	pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false);
-	test->ifobj_rx->pkt_stream = pkt_stream;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
 }
 
 static void pkt_print_data(u32 *data, u32 cnt)
@@ -1007,7 +1009,7 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 {
 	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
-	struct pkt_stream *pkt_stream = test->ifobj_rx->pkt_stream;
+	struct pkt_stream *pkt_stream = test->ifobj_rx->xsk->pkt_stream;
 	struct xsk_socket_info *xsk = test->ifobj_rx->xsk;
 	u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0;
 	struct ifobject *ifobj = test->ifobj_rx;
@@ -1139,7 +1141,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout)
 {
 	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
-	struct pkt_stream *pkt_stream = ifobject->pkt_stream;
+	struct pkt_stream *pkt_stream = ifobject->xsk->pkt_stream;
 	struct xsk_socket_info *xsk = ifobject->xsk;
 	struct xsk_umem_info *umem = ifobject->umem;
 	bool use_poll = ifobject->use_poll;
@@ -1283,7 +1285,7 @@ static int wait_for_tx_completion(struct xsk_socket_info *xsk)
 
 static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
 {
-	struct pkt_stream *pkt_stream = ifobject->pkt_stream;
+	struct pkt_stream *pkt_stream = ifobject->xsk->pkt_stream;
 	bool timeout = !is_umem_valid(test->ifobj_rx);
 	struct pollfd fds = { };
 	u32 ret;
@@ -1347,8 +1349,8 @@ static int validate_rx_dropped(struct ifobject *ifobject)
 	 * packet being invalid). Since the last packet may or may not have
 	 * been dropped already, both outcomes must be allowed.
 	 */
-	if (stats.rx_dropped == ifobject->pkt_stream->nb_pkts / 2 ||
-	    stats.rx_dropped == ifobject->pkt_stream->nb_pkts / 2 - 1)
+	if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 ||
+	    stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1)
 		return TEST_PASS;
 
 	return TEST_FAILURE;
@@ -1412,9 +1414,10 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
 		return TEST_FAILURE;
 	}
 
-	if (stats.tx_invalid_descs != ifobject->pkt_stream->nb_pkts / 2) {
+	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
 		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
-			       __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts);
+			       __func__, stats.tx_invalid_descs,
+			       ifobject->xsk->pkt_stream->nb_pkts);
 		return TEST_FAILURE;
 	}
 
@@ -1528,7 +1531,7 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	if (!ifobject->rx_on)
 		return;
 
-	xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream, ifobject->use_fill_ring);
+	xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring);
 
 	ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
 	if (ret)
@@ -1691,11 +1694,11 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i
 	if (ifobj2) {
 		if (pthread_barrier_init(&barr, NULL, 2))
 			exit_with_error(errno);
-		pkt_stream_reset(ifobj2->pkt_stream);
+		pkt_stream_reset(ifobj2->xsk->pkt_stream);
 	}
 
 	test->current_step++;
-	pkt_stream_reset(ifobj1->pkt_stream);
+	pkt_stream_reset(ifobj1->xsk->pkt_stream);
 	pkts_in_flight = 0;
 
 	signal(SIGUSR1, handler);
@@ -1852,8 +1855,8 @@ static int testapp_stats_tx_invalid_descs(struct test_spec *test)
 static int testapp_stats_rx_full(struct test_spec *test)
 {
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							 DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
+							      DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
 
 	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
 	test->ifobj_rx->release_rx = false;
@@ -1864,8 +1867,8 @@ static int testapp_stats_rx_full(struct test_spec *test)
 static int testapp_stats_fill_empty(struct test_spec *test)
 {
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							 DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
+							      DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
 
 	test->ifobj_rx->use_fill_ring = false;
 	test->ifobj_rx->validation_func = validate_fill_empty;
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 8015aeea839d..06b82b39c59c 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -87,6 +87,7 @@ struct xsk_socket_info {
 	struct xsk_ring_prod tx;
 	struct xsk_umem_info *umem;
 	struct xsk_socket *xsk;
+	struct pkt_stream *pkt_stream;
 	u32 outstanding_tx;
 	u32 rxqsize;
 };
@@ -120,7 +121,6 @@ struct ifobject {
 	struct xsk_umem_info *umem;
 	thread_func_t func_ptr;
 	validation_func_t validation_func;
-	struct pkt_stream *pkt_stream;
 	struct xsk_xdp_progs *xdp_progs;
 	struct bpf_map *xskmap;
 	struct bpf_program *xdp_prog;
-- 
cgit v1.2.3


From 93ba112479070d9cd2445640b60f414178c3914c Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:35 +0530
Subject: selftests/xsk: Rename xsk_xdp_metadata.h to xsk_xdp_common.h

Rename the header file to a generic name so that it can be used by all
future XDP programs. Ensure that the xsk_xdp_common.h header file includes
include guards.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-3-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/progs/xsk_xdp_progs.c |  2 +-
 tools/testing/selftests/bpf/xsk_xdp_common.h      | 10 ++++++++++
 tools/testing/selftests/bpf/xsk_xdp_metadata.h    |  5 -----
 tools/testing/selftests/bpf/xskxceiver.c          |  2 +-
 4 files changed, 12 insertions(+), 7 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/xsk_xdp_common.h
 delete mode 100644 tools/testing/selftests/bpf/xsk_xdp_metadata.h

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index 24369f242853..734f231a8534 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -3,7 +3,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "xsk_xdp_metadata.h"
+#include "xsk_xdp_common.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_XSKMAP);
diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h
new file mode 100644
index 000000000000..f55d61625336
--- /dev/null
+++ b/tools/testing/selftests/bpf/xsk_xdp_common.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef XSK_XDP_COMMON_H_
+#define XSK_XDP_COMMON_H_
+
+struct xdp_info {
+	__u64 count;
+} __attribute__((aligned(32)));
+
+#endif /* XSK_XDP_COMMON_H_ */
diff --git a/tools/testing/selftests/bpf/xsk_xdp_metadata.h b/tools/testing/selftests/bpf/xsk_xdp_metadata.h
deleted file mode 100644
index 943133da378a..000000000000
--- a/tools/testing/selftests/bpf/xsk_xdp_metadata.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-struct xdp_info {
-	__u64 count;
-} __attribute__((aligned(32)));
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 16a09751b093..ad1f7f078f5f 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -102,7 +102,7 @@
 #include <bpf/bpf.h>
 #include <linux/filter.h>
 #include "../kselftest.h"
-#include "xsk_xdp_metadata.h"
+#include "xsk_xdp_common.h"
 
 static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
 static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
-- 
cgit v1.2.3


From 985fd2145a2932c9d7bda219271e3f453d4607ef Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:36 +0530
Subject: selftests/xsk: Move src_mac and dst_mac to the xsk_socket_info

Move the src_mac and dst_mac fields from the ifobject structure to the
xsk_socket_info structure to achieve per-socket MAC address assignment.

Require this in order to steer traffic to various sockets in subsequent
patches.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-4-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/xskxceiver.c | 34 +++++++++++++++-----------------
 tools/testing/selftests/bpf/xskxceiver.h |  7 +++++--
 2 files changed, 21 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index ad1f7f078f5f..e26f942a7b9e 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -104,9 +104,6 @@
 #include "../kselftest.h"
 #include "xsk_xdp_common.h"
 
-static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
-static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
-
 static bool opt_verbose;
 static bool opt_print_tests;
 static enum test_mode opt_mode = TEST_MODE_ALL;
@@ -159,10 +156,10 @@ static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size)
 		ptr[i] = htonl(pkt_nb << 16 | (i + start));
 }
 
-static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr)
+static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr)
 {
-	memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN);
-	memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN);
+	memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN);
+	memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN);
 	eth_hdr->h_proto = htons(ETH_P_LOOPBACK);
 }
 
@@ -445,6 +442,11 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 				ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default;
 			else
 				ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default;
+
+			memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN);
+			memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN);
+			ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0);
+			ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1);
 		}
 	}
 
@@ -726,16 +728,16 @@ static void pkt_stream_cancel(struct pkt_stream *pkt_stream)
 	pkt_stream->current_pkt_nb--;
 }
 
-static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb,
-			 u32 bytes_written)
+static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len,
+			 u32 pkt_nb, u32 bytes_written)
 {
-	void *data = xsk_umem__get_data(ifobject->umem->buffer, addr);
+	void *data = xsk_umem__get_data(umem->buffer, addr);
 
 	if (len < MIN_PKT_SIZE)
 		return;
 
 	if (!bytes_written) {
-		gen_eth_hdr(ifobject, data);
+		gen_eth_hdr(xsk, data);
 
 		len -= PKT_HDR_SIZE;
 		data += PKT_HDR_SIZE;
@@ -1209,7 +1211,7 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 				tx_desc->options = 0;
 			}
 			if (pkt->valid)
-				pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
+				pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
 					     bytes_written);
 			bytes_written += tx_desc->len;
 
@@ -2120,15 +2122,11 @@ static bool hugepages_present(void)
 	return true;
 }
 
-static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
-		       thread_func_t func_ptr)
+static void init_iface(struct ifobject *ifobj, thread_func_t func_ptr)
 {
 	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
 	int err;
 
-	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
-	memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
-
 	ifobj->func_ptr = func_ptr;
 
 	err = xsk_load_xdp_programs(ifobj);
@@ -2404,8 +2402,8 @@ int main(int argc, char **argv)
 			modes++;
 	}
 
-	init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx);
-	init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx);
+	init_iface(ifobj_rx, worker_testapp_validate_rx);
+	init_iface(ifobj_tx, worker_testapp_validate_tx);
 
 	test_spec_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]);
 	tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 06b82b39c59c..3d494adef792 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -59,6 +59,7 @@
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 #define RUN_ALL_TESTS UINT_MAX
+#define NUM_MAC_ADDRESSES 4
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
@@ -90,6 +91,8 @@ struct xsk_socket_info {
 	struct pkt_stream *pkt_stream;
 	u32 outstanding_tx;
 	u32 rxqsize;
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
 };
 
 struct pkt {
@@ -140,8 +143,6 @@ struct ifobject {
 	bool unaligned_supp;
 	bool multi_buff_supp;
 	bool multi_buff_zc_supp;
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
 };
 
 struct test_spec {
@@ -168,4 +169,6 @@ pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER;
 
 int pkts_in_flight;
 
+static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00};
+
 #endif				/* XSKXCEIVER_H_ */
-- 
cgit v1.2.3


From 8913e653e9b8e08f15c2c25d1b7a6d897350985b Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:37 +0530
Subject: selftests/xsk: Iterate over all the sockets in the receive pkts
 function

Improve the receive_pkt() function to enable it to receive packets from
multiple sockets. Define a sock_num variable to iterate through all the
sockets in the Rx path. Add nb_valid_entries to check that all the
expected number of packets are received.

Revise the function __receive_pkts() to only inspect the receive ring
once, handle any received packets, and promptly return. Implement a bitmap
to store the value of number of sockets. Update Makefile to include
find_bit.c for compiling xskxceiver.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-5-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/Makefile     |   4 +-
 tools/testing/selftests/bpf/xskxceiver.c | 285 +++++++++++++++++++------------
 tools/testing/selftests/bpf/xskxceiver.h |   2 +
 3 files changed, 178 insertions(+), 113 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 47365161b6fc..db01ef82d6b1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -641,7 +641,9 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
-$(OUTPUT)/xskxceiver: xskxceiver.c xskxceiver.h $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT)
+# Include find_bit.c to compile xskxceiver.
+EXTRA_SRC := $(TOOLSDIR)/lib/find_bit.c
+$(OUTPUT)/xskxceiver: $(EXTRA_SRC) xskxceiver.c xskxceiver.h $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index e26f942a7b9e..6d0cd0cc7b5f 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -80,6 +80,7 @@
 #include <linux/if_ether.h>
 #include <linux/mman.h>
 #include <linux/netdev.h>
+#include <linux/bitmap.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <locale.h>
@@ -530,8 +531,10 @@ static int test_spec_set_mtu(struct test_spec *test, int mtu)
 
 static void pkt_stream_reset(struct pkt_stream *pkt_stream)
 {
-	if (pkt_stream)
+	if (pkt_stream) {
 		pkt_stream->current_pkt_nb = 0;
+		pkt_stream->nb_rx_pkts = 0;
+	}
 }
 
 static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream)
@@ -631,14 +634,16 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk
 	return nb_frags;
 }
 
-static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len)
+static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
 {
 	pkt->offset = offset;
 	pkt->len = len;
-	if (len > MAX_ETH_JUMBO_SIZE)
+	if (len > MAX_ETH_JUMBO_SIZE) {
 		pkt->valid = false;
-	else
+	} else {
 		pkt->valid = true;
+		pkt_stream->nb_valid_entries++;
+	}
 }
 
 static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
@@ -660,7 +665,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	for (i = 0; i < nb_pkts; i++) {
 		struct pkt *pkt = &pkt_stream->pkts[i];
 
-		pkt_set(umem, pkt, 0, pkt_len);
+		pkt_set(pkt_stream, pkt, 0, pkt_len);
 		pkt->pkt_nb = i;
 	}
 
@@ -692,9 +697,10 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
 
 	pkt_stream = pkt_stream_clone(umem, ifobj->xsk->pkt_stream);
 	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
-		pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len);
+		pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);
 
 	ifobj->xsk->pkt_stream = pkt_stream;
+	pkt_stream->nb_valid_entries /= 2;
 }
 
 static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
@@ -714,6 +720,8 @@ static void pkt_stream_receive_half(struct test_spec *test)
 	pkt_stream = test->ifobj_rx->xsk->pkt_stream;
 	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
 		pkt_stream->pkts[i].valid = false;
+
+	pkt_stream->nb_valid_entries /= 2;
 }
 
 static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem)
@@ -787,6 +795,10 @@ static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, s
 
 		if (pkt->valid && pkt->len > pkt_stream->max_pkt_len)
 			pkt_stream->max_pkt_len = pkt->len;
+
+		if (pkt->valid)
+			pkt_stream->nb_valid_entries++;
+
 		pkt_nb++;
 	}
 
@@ -1008,133 +1020,178 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 	return TEST_PASS;
 }
 
-static int receive_pkts(struct test_spec *test, struct pollfd *fds)
+static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk)
 {
-	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
-	struct pkt_stream *pkt_stream = test->ifobj_rx->xsk->pkt_stream;
-	struct xsk_socket_info *xsk = test->ifobj_rx->xsk;
+	u32 frags_processed = 0, nb_frags = 0, pkt_len = 0;
 	u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0;
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
 	struct ifobject *ifobj = test->ifobj_rx;
 	struct xsk_umem_info *umem = xsk->umem;
+	struct pollfd fds = { };
 	struct pkt *pkt;
+	u64 first_addr;
 	int ret;
 
-	ret = gettimeofday(&tv_now, NULL);
-	if (ret)
-		exit_with_error(errno);
-	timeradd(&tv_now, &tv_timeout, &tv_end);
-
-	pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
-	while (pkt) {
-		u32 frags_processed = 0, nb_frags = 0, pkt_len = 0;
-		u64 first_addr;
+	fds.fd = xsk_socket__fd(xsk->xsk);
+	fds.events = POLLIN;
 
-		ret = gettimeofday(&tv_now, NULL);
-		if (ret)
-			exit_with_error(errno);
-		if (timercmp(&tv_now, &tv_end, >)) {
-			ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__);
-			return TEST_FAILURE;
-		}
+	ret = kick_rx(xsk);
+	if (ret)
+		return TEST_FAILURE;
 
-		ret = kick_rx(xsk);
-		if (ret)
+	if (ifobj->use_poll) {
+		ret = poll(&fds, 1, POLL_TMOUT);
+		if (ret < 0)
 			return TEST_FAILURE;
 
-		if (ifobj->use_poll) {
-			ret = poll(fds, 1, POLL_TMOUT);
-			if (ret < 0)
-				return TEST_FAILURE;
-
-			if (!ret) {
-				if (!is_umem_valid(test->ifobj_tx))
-					return TEST_PASS;
-
-				ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
-				return TEST_FAILURE;
-			}
+		if (!ret) {
+			if (!is_umem_valid(test->ifobj_tx))
+				return TEST_PASS;
 
-			if (!(fds->revents & POLLIN))
-				continue;
+			ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
+			return TEST_CONTINUE;
 		}
 
-		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
-		if (!rcvd)
-			continue;
+		if (!(fds.revents & POLLIN))
+			return TEST_CONTINUE;
+	}
 
-		if (ifobj->use_fill_ring) {
-			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
-			while (ret != rcvd) {
-				if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
-					ret = poll(fds, 1, POLL_TMOUT);
-					if (ret < 0)
-						return TEST_FAILURE;
-				}
-				ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
+	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+	if (!rcvd)
+		return TEST_CONTINUE;
+
+	if (ifobj->use_fill_ring) {
+		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
+		while (ret != rcvd) {
+			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
+				ret = poll(&fds, 1, POLL_TMOUT);
+				if (ret < 0)
+					return TEST_FAILURE;
 			}
+			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 		}
+	}
 
-		while (frags_processed < rcvd) {
-			const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
-			u64 addr = desc->addr, orig;
+	while (frags_processed < rcvd) {
+		const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
+		u64 addr = desc->addr, orig;
 
-			orig = xsk_umem__extract_addr(addr);
-			addr = xsk_umem__add_offset_to_addr(addr);
+		orig = xsk_umem__extract_addr(addr);
+		addr = xsk_umem__add_offset_to_addr(addr);
 
+		if (!nb_frags) {
+			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
 			if (!pkt) {
 				ksft_print_msg("[%s] received too many packets addr: %lx len %u\n",
 					       __func__, addr, desc->len);
 				return TEST_FAILURE;
 			}
+		}
 
-			print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n",
-				      addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid);
+		print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n",
+			      addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid);
 
-			if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
-			    !is_offset_correct(umem, pkt, addr) ||
-			    (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr)))
-				return TEST_FAILURE;
+		if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
+		    !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata &&
+		    !is_metadata_correct(pkt, umem->buffer, addr)))
+			return TEST_FAILURE;
 
-			if (!nb_frags++)
-				first_addr = addr;
-			frags_processed++;
-			pkt_len += desc->len;
-			if (ifobj->use_fill_ring)
-				*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
+		if (!nb_frags++)
+			first_addr = addr;
+		frags_processed++;
+		pkt_len += desc->len;
+		if (ifobj->use_fill_ring)
+			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
 
-			if (pkt_continues(desc->options))
-				continue;
+		if (pkt_continues(desc->options))
+			continue;
 
-			/* The complete packet has been received */
-			if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) ||
-			    !is_offset_correct(umem, pkt, addr))
-				return TEST_FAILURE;
+		/* The complete packet has been received */
+		if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) ||
+		    !is_offset_correct(umem, pkt, addr))
+			return TEST_FAILURE;
 
-			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
-			nb_frags = 0;
-			pkt_len = 0;
-		}
+		pkt_stream->nb_rx_pkts++;
+		nb_frags = 0;
+		pkt_len = 0;
+	}
 
-		if (nb_frags) {
-			/* In the middle of a packet. Start over from beginning of packet. */
-			idx_rx -= nb_frags;
-			xsk_ring_cons__cancel(&xsk->rx, nb_frags);
-			if (ifobj->use_fill_ring) {
-				idx_fq -= nb_frags;
-				xsk_ring_prod__cancel(&umem->fq, nb_frags);
-			}
-			frags_processed -= nb_frags;
+	if (nb_frags) {
+		/* In the middle of a packet. Start over from beginning of packet. */
+		idx_rx -= nb_frags;
+		xsk_ring_cons__cancel(&xsk->rx, nb_frags);
+		if (ifobj->use_fill_ring) {
+			idx_fq -= nb_frags;
+			xsk_ring_prod__cancel(&umem->fq, nb_frags);
 		}
+		frags_processed -= nb_frags;
+	}
 
-		if (ifobj->use_fill_ring)
-			xsk_ring_prod__submit(&umem->fq, frags_processed);
-		if (ifobj->release_rx)
-			xsk_ring_cons__release(&xsk->rx, frags_processed);
+	if (ifobj->use_fill_ring)
+		xsk_ring_prod__submit(&umem->fq, frags_processed);
+	if (ifobj->release_rx)
+		xsk_ring_cons__release(&xsk->rx, frags_processed);
+
+	pthread_mutex_lock(&pacing_mutex);
+	pkts_in_flight -= pkts_sent;
+	pthread_mutex_unlock(&pacing_mutex);
+	pkts_sent = 0;
+
+return TEST_CONTINUE;
+}
+
+bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num,
+			  unsigned long *bitmap)
+{
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
+
+	if (!pkt_stream) {
+		__set_bit(sock_num, bitmap);
+		return false;
+	}
+
+	if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) {
+		__set_bit(sock_num, bitmap);
+		if (bitmap_full(bitmap, test->nb_sockets))
+			return true;
+	}
+
+	return false;
+}
+
+static int receive_pkts(struct test_spec *test)
+{
+	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
+	DECLARE_BITMAP(bitmap, test->nb_sockets);
+	struct xsk_socket_info *xsk;
+	u32 sock_num = 0;
+	int res, ret;
 
-		pthread_mutex_lock(&pacing_mutex);
-		pkts_in_flight -= pkts_sent;
-		pthread_mutex_unlock(&pacing_mutex);
-		pkts_sent = 0;
+	ret = gettimeofday(&tv_now, NULL);
+	if (ret)
+		exit_with_error(errno);
+
+	timeradd(&tv_now, &tv_timeout, &tv_end);
+
+	while (1) {
+		xsk = &test->ifobj_rx->xsk_arr[sock_num];
+
+		if ((all_packets_received(test, xsk, sock_num, bitmap)))
+			break;
+
+		res = __receive_pkts(test, xsk);
+		if (!(res == TEST_PASS || res == TEST_CONTINUE))
+			return res;
+
+		ret = gettimeofday(&tv_now, NULL);
+		if (ret)
+			exit_with_error(errno);
+
+		if (timercmp(&tv_now, &tv_end, >)) {
+			ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__);
+			return TEST_FAILURE;
+		}
+		sock_num = (sock_num + 1) % test->nb_sockets;
 	}
 
 	return TEST_PASS;
@@ -1567,7 +1624,6 @@ static void *worker_testapp_validate_rx(void *arg)
 {
 	struct test_spec *test = (struct test_spec *)arg;
 	struct ifobject *ifobject = test->ifobj_rx;
-	struct pollfd fds = { };
 	int err;
 
 	if (test->current_step == 1) {
@@ -1582,12 +1638,9 @@ static void *worker_testapp_validate_rx(void *arg)
 		}
 	}
 
-	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds.events = POLLIN;
-
 	pthread_barrier_wait(&barr);
 
-	err = receive_pkts(test, &fds);
+	err = receive_pkts(test);
 
 	if (!err && ifobject->validation_func)
 		err = ifobject->validation_func(ifobject);
@@ -1724,9 +1777,15 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i
 		pthread_join(t0, NULL);
 
 	if (test->total_steps == test->current_step || test->fail) {
+		u32 i;
+
 		if (ifobj2)
-			xsk_socket__delete(ifobj2->xsk->xsk);
-		xsk_socket__delete(ifobj1->xsk->xsk);
+			for (i = 0; i < test->nb_sockets; i++)
+				xsk_socket__delete(ifobj2->xsk_arr[i].xsk);
+
+		for (i = 0; i < test->nb_sockets; i++)
+			xsk_socket__delete(ifobj1->xsk_arr[i].xsk);
+
 		testapp_clean_xsk_umem(ifobj1);
 		if (ifobj2 && !ifobj2->shared_umem)
 			testapp_clean_xsk_umem(ifobj2);
@@ -1798,16 +1857,18 @@ static int testapp_bidirectional(struct test_spec *test)
 	return res;
 }
 
-static int swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
+static int swap_xsk_resources(struct test_spec *test)
 {
 	int ret;
 
-	xsk_socket__delete(ifobj_tx->xsk->xsk);
-	xsk_socket__delete(ifobj_rx->xsk->xsk);
-	ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
-	ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
+	test->ifobj_tx->xsk_arr[0].pkt_stream = NULL;
+	test->ifobj_rx->xsk_arr[0].pkt_stream = NULL;
+	test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default;
+	test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default;
+	test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1];
+	test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1];
 
-	ret = xsk_update_xskmap(ifobj_rx->xskmap, ifobj_rx->xsk->xsk);
+	ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk);
 	if (ret)
 		return TEST_FAILURE;
 
@@ -1821,7 +1882,7 @@ static int testapp_xdp_prog_cleanup(struct test_spec *test)
 	if (testapp_validate_traffic(test))
 		return TEST_FAILURE;
 
-	if (swap_xsk_resources(test->ifobj_tx, test->ifobj_rx))
+	if (swap_xsk_resources(test))
 		return TEST_FAILURE;
 	return testapp_validate_traffic(test);
 }
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 3d494adef792..fa409285eafd 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -108,6 +108,8 @@ struct pkt_stream {
 	u32 current_pkt_nb;
 	struct pkt *pkts;
 	u32 max_pkt_len;
+	u32 nb_rx_pkts;
+	u32 nb_valid_entries;
 	bool verbatim;
 };
 
-- 
cgit v1.2.3


From 46e43786cc60b5816a71e1ff6244d91618f01d90 Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:38 +0530
Subject: selftests/xsk: Remove unnecessary parameter from pkt_set() function
 call

The pkt_set() function no longer needs the umem parameter. This commit
removes the umem parameter from the pkt_set() function.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-6-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/xskxceiver.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 6d0cd0cc7b5f..57a5126f6182 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -651,7 +651,7 @@ static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
 	return ceil_u32(len, umem->frame_size) * umem->frame_size;
 }
 
-static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
+static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
 	u32 i;
@@ -672,30 +672,28 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	return pkt_stream;
 }
 
-static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem,
-					   struct pkt_stream *pkt_stream)
+static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
 {
-	return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
+	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
 }
 
 static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
 
-	pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len);
+	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
 	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
-	pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, nb_pkts, pkt_len);
+	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
 	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
 }
 
 static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
 				      int offset)
 {
-	struct xsk_umem_info *umem = ifobj->umem;
 	struct pkt_stream *pkt_stream;
 	u32 i;
 
-	pkt_stream = pkt_stream_clone(umem, ifobj->xsk->pkt_stream);
+	pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream);
 	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
 		pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);
 
@@ -711,11 +709,10 @@ static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int off
 
 static void pkt_stream_receive_half(struct test_spec *test)
 {
-	struct xsk_umem_info *umem = test->ifobj_rx->umem;
 	struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream;
 	u32 i;
 
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(umem, pkt_stream->nb_pkts,
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts,
 							      pkt_stream->pkts[0].len);
 	pkt_stream = test->ifobj_rx->xsk->pkt_stream;
 	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
@@ -1918,8 +1915,7 @@ static int testapp_stats_tx_invalid_descs(struct test_spec *test)
 static int testapp_stats_rx_full(struct test_spec *test)
 {
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							      DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
 
 	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
 	test->ifobj_rx->release_rx = false;
@@ -1930,8 +1926,7 @@ static int testapp_stats_rx_full(struct test_spec *test)
 static int testapp_stats_fill_empty(struct test_spec *test)
 {
 	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							      DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
 
 	test->ifobj_rx->use_fill_ring = false;
 	test->ifobj_rx->validation_func = validate_fill_empty;
@@ -2467,8 +2462,8 @@ int main(int argc, char **argv)
 	init_iface(ifobj_tx, worker_testapp_validate_tx);
 
 	test_spec_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]);
-	tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
-	rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
 	if (!tx_pkt_stream_default || !rx_pkt_stream_default)
 		exit_with_error(ENOMEM);
 	test.tx_pkt_stream_default = tx_pkt_stream_default;
-- 
cgit v1.2.3


From fd0815ae9b8aa136c11dfa040740ca035e4602c0 Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:39 +0530
Subject: selftests/xsk: Iterate over all the sockets in the send pkts function

Update send_pkts() to handle multiple sockets for sending packets.
Multiple TX sockets are utilized alternately based on the batch size for
improve packet transmission.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-7-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/xskxceiver.c | 57 +++++++++++++++++++++-----------
 1 file changed, 38 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 57a5126f6182..ce869431556c 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1194,13 +1194,13 @@ static int receive_pkts(struct test_spec *test)
 	return TEST_PASS;
 }
 
-static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout)
+static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout)
 {
 	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
-	struct pkt_stream *pkt_stream = ifobject->xsk->pkt_stream;
-	struct xsk_socket_info *xsk = ifobject->xsk;
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
 	struct xsk_umem_info *umem = ifobject->umem;
 	bool use_poll = ifobject->use_poll;
+	struct pollfd fds = { };
 	int ret;
 
 	buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len);
@@ -1212,9 +1212,12 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 		return TEST_CONTINUE;
 	}
 
+	fds.fd = xsk_socket__fd(xsk->xsk);
+	fds.events = POLLOUT;
+
 	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) {
 		if (use_poll) {
-			ret = poll(fds, 1, POLL_TMOUT);
+			ret = poll(&fds, 1, POLL_TMOUT);
 			if (timeout) {
 				if (ret < 0) {
 					ksft_print_msg("ERROR: [%s] Poll error %d\n",
@@ -1293,7 +1296,7 @@ static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeo
 	xsk->outstanding_tx += valid_frags;
 
 	if (use_poll) {
-		ret = poll(fds, 1, POLL_TMOUT);
+		ret = poll(&fds, 1, POLL_TMOUT);
 		if (ret <= 0) {
 			if (ret == 0 && timeout)
 				return TEST_PASS;
@@ -1339,27 +1342,43 @@ static int wait_for_tx_completion(struct xsk_socket_info *xsk)
 	return TEST_PASS;
 }
 
+bool all_packets_sent(struct test_spec *test, unsigned long *bitmap)
+{
+	return bitmap_full(bitmap, test->nb_sockets);
+}
+
 static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
 {
-	struct pkt_stream *pkt_stream = ifobject->xsk->pkt_stream;
 	bool timeout = !is_umem_valid(test->ifobj_rx);
-	struct pollfd fds = { };
-	u32 ret;
+	DECLARE_BITMAP(bitmap, test->nb_sockets);
+	u32 i, ret;
 
-	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds.events = POLLOUT;
+	while (!(all_packets_sent(test, bitmap))) {
+		for (i = 0; i < test->nb_sockets; i++) {
+			struct pkt_stream *pkt_stream;
 
-	while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) {
-		ret = __send_pkts(ifobject, &fds, timeout);
-		if (ret == TEST_CONTINUE && !test->fail)
-			continue;
-		if ((ret || test->fail) && !timeout)
-			return TEST_FAILURE;
-		if (ret == TEST_PASS && timeout)
-			return ret;
+			pkt_stream = ifobject->xsk_arr[i].pkt_stream;
+			if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) {
+				__set_bit(i, bitmap);
+				continue;
+			}
+			ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout);
+			if (ret == TEST_CONTINUE && !test->fail)
+				continue;
+
+			if ((ret || test->fail) && !timeout)
+				return TEST_FAILURE;
+
+			if (ret == TEST_PASS && timeout)
+				return ret;
+
+			ret = wait_for_tx_completion(&ifobject->xsk_arr[i]);
+			if (ret)
+				return TEST_FAILURE;
+		}
 	}
 
-	return wait_for_tx_completion(ifobject->xsk);
+	return TEST_PASS;
 }
 
 static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats)
-- 
cgit v1.2.3


From fc2cb86495da6b67518bedbf1a2d49af220d1521 Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:40 +0530
Subject: selftests/xsk: Modify xsk_update_xskmap() to accept the index as an
 argument

Modify xsk_update_xskmap() to accept the index as an argument, enabling
the addition of multiple sockets to xskmap.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-8-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/xsk.c        | 3 +--
 tools/testing/selftests/bpf/xsk.h        | 2 +-
 tools/testing/selftests/bpf/xskxceiver.c | 6 +++---
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index d9fb2b730a2c..e574711eeb84 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -442,10 +442,9 @@ void xsk_clear_xskmap(struct bpf_map *map)
 	bpf_map_delete_elem(map_fd, &index);
 }
 
-int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk)
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk, u32 index)
 {
 	int map_fd, sock_fd;
-	u32 index = 0;
 
 	map_fd = bpf_map__fd(map);
 	sock_fd = xsk_socket__fd(xsk);
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index d93200fdaa8d..771570bc3731 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -204,7 +204,7 @@ struct xsk_umem_config {
 
 int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);
 void xsk_detach_xdp_program(int ifindex, u32 xdp_flags);
-int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk);
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk, u32 index);
 void xsk_clear_xskmap(struct bpf_map *map);
 bool xsk_is_in_mode(u32 ifindex, int mode);
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index ce869431556c..0432c516a413 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1608,7 +1608,7 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 
 	xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring);
 
-	ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
+	ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0);
 	if (ret)
 		exit_with_error(errno);
 }
@@ -1646,7 +1646,7 @@ static void *worker_testapp_validate_rx(void *arg)
 		thread_common_ops(test, ifobject);
 	} else {
 		xsk_clear_xskmap(ifobject->xskmap);
-		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk);
+		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0);
 		if (err) {
 			ksft_print_msg("Error: Failed to update xskmap, error %s\n",
 				       strerror(-err));
@@ -1884,7 +1884,7 @@ static int swap_xsk_resources(struct test_spec *test)
 	test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1];
 	test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1];
 
-	ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk);
+	ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0);
 	if (ret)
 		return TEST_FAILURE;
 
-- 
cgit v1.2.3


From 6d198a89c004723d9d2fff469fdcb1074c9642d6 Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 27 Sep 2023 19:22:41 +0530
Subject: selftests/xsk: Add a test for shared umem feature

Add a new test for testing shared umem feature. This is accomplished by
adding a new XDP program and using the multiple sockets.

The new XDP program redirects the packets based on the destination MAC
address.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20230927135241.2287547-9-tushar.vyavahare@intel.com
---
 tools/testing/selftests/bpf/progs/xsk_xdp_progs.c | 20 ++++++++-
 tools/testing/selftests/bpf/xsk_xdp_common.h      |  2 +
 tools/testing/selftests/bpf/xskxceiver.c          | 55 ++++++++++++++++++++---
 tools/testing/selftests/bpf/xskxceiver.h          |  2 +-
 4 files changed, 72 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index 734f231a8534..ccde6a4c6319 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -3,11 +3,12 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
 #include "xsk_xdp_common.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_XSKMAP);
-	__uint(max_entries, 1);
+	__uint(max_entries, 2);
 	__uint(key_size, sizeof(int));
 	__uint(value_size, sizeof(int));
 } xsk SEC(".maps");
@@ -52,4 +53,21 @@ SEC("xdp.frags") int xsk_xdp_populate_metadata(struct xdp_md *xdp)
 	return bpf_redirect_map(&xsk, 0, XDP_DROP);
 }
 
+SEC("xdp") int xsk_xdp_shared_umem(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	void *data_end = (void *)(long)xdp->data_end;
+	struct ethhdr *eth = data;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	/* Redirecting packets based on the destination MAC address */
+	idx = ((unsigned int)(eth->h_dest[5])) / 2;
+	if (idx > MAX_SOCKETS)
+		return XDP_DROP;
+
+	return bpf_redirect_map(&xsk, idx, XDP_DROP);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h
index f55d61625336..5a6f36f07383 100644
--- a/tools/testing/selftests/bpf/xsk_xdp_common.h
+++ b/tools/testing/selftests/bpf/xsk_xdp_common.h
@@ -3,6 +3,8 @@
 #ifndef XSK_XDP_COMMON_H_
 #define XSK_XDP_COMMON_H_
 
+#define MAX_SOCKETS 2
+
 struct xdp_info {
 	__u64 count;
 } __attribute__((aligned(32)));
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 0432c516a413..837e0ffbdc47 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -651,7 +651,7 @@ static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
 	return ceil_u32(len, umem->frame_size) * umem->frame_size;
 }
 
-static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
+static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off)
 {
 	struct pkt_stream *pkt_stream;
 	u32 i;
@@ -666,12 +666,17 @@ static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
 		struct pkt *pkt = &pkt_stream->pkts[i];
 
 		pkt_set(pkt_stream, pkt, 0, pkt_len);
-		pkt->pkt_nb = i;
+		pkt->pkt_nb = nb_start + i * nb_off;
 	}
 
 	return pkt_stream;
 }
 
+static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
+{
+	return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1);
+}
+
 static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
 {
 	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
@@ -721,6 +726,24 @@ static void pkt_stream_receive_half(struct test_spec *test)
 	pkt_stream->nb_valid_entries /= 2;
 }
 
+static void pkt_stream_even_odd_sequence(struct test_spec *test)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	for (i = 0; i < test->nb_sockets; i++) {
+		pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream;
+		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
+						   pkt_stream->pkts[0].len, i, 2);
+		test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream;
+
+		pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream;
+		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
+						   pkt_stream->pkts[0].len, i, 2);
+		test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream;
+	}
+}
+
 static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem)
 {
 	if (!pkt->valid)
@@ -1584,6 +1607,7 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
 	void *bufs;
 	int ret;
+	u32 i;
 
 	if (ifobject->umem->unaligned_mode)
 		mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB;
@@ -1608,9 +1632,12 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 
 	xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring);
 
-	ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0);
-	if (ret)
-		exit_with_error(errno);
+	for (i = 0; i < test->nb_sockets; i++) {
+		ifobject->xsk = &ifobject->xsk_arr[i];
+		ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i);
+		if (ret)
+			exit_with_error(errno);
+	}
 }
 
 static void *worker_testapp_validate_tx(void *arg)
@@ -2111,6 +2138,23 @@ static int testapp_xdp_metadata_copy(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_xdp_shared_umem(struct test_spec *test)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test->total_steps = 1;
+	test->nb_sockets = 2;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem,
+			       skel_tx->progs.xsk_xdp_shared_umem,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	pkt_stream_even_odd_sequence(test);
+
+	return testapp_validate_traffic(test);
+}
+
 static int testapp_poll_txq_tmout(struct test_spec *test)
 {
 	test->ifobj_tx->use_poll = true;
@@ -2412,6 +2456,7 @@ static const struct test_spec tests[] = {
 	{.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty},
 	{.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup},
 	{.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop},
+	{.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem},
 	{.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata},
 	{.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb},
 	{.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb},
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index fa409285eafd..f174df2d693f 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -8,6 +8,7 @@
 #include <limits.h>
 
 #include "xsk_xdp_progs.skel.h"
+#include "xsk_xdp_common.h"
 
 #ifndef SOL_XDP
 #define SOL_XDP 283
@@ -35,7 +36,6 @@
 #define TEST_SKIP 2
 #define MAX_INTERFACES 2
 #define MAX_INTERFACE_NAME_CHARS 16
-#define MAX_SOCKETS 2
 #define MAX_TEST_NAME_SIZE 48
 #define MAX_TEARDOWN_ITER 10
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
-- 
cgit v1.2.3


From 8a412c5c1cd6cc6c55e8b9b84fbb789fc395fe78 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 4 Oct 2023 13:09:03 +0200
Subject: libbpf: Fix syscall access arguments on riscv

Since commit 08d0ce30e0e4 ("riscv: Implement syscall wrappers"), riscv
selects ARCH_HAS_SYSCALL_WRAPPER so let's use the generic implementation
of PT_REGS_SYSCALL_REGS().

Fixes: 08d0ce30e0e4 ("riscv: Implement syscall wrappers")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/bpf/20231004110905.49024-2-bjorn@kernel.org
---
 tools/lib/bpf/bpf_tracing.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 3803479dbe10..1c13f8e88833 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -362,8 +362,6 @@ struct pt_regs___arm64 {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
-/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */
-#define PT_REGS_SYSCALL_REGS(ctx) ctx
 #define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
 #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
-- 
cgit v1.2.3


From 0f2692ee4324679df6c80ccbb75660564009d187 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn@rivosinc.com>
Date: Wed, 4 Oct 2023 13:09:04 +0200
Subject: selftests/bpf: Define SYS_PREFIX for riscv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SYS_PREFIX was missing for a RISC-V, which made a couple of kprobe
tests fail.

Add missing SYS_PREFIX for RISC-V.

Fixes: 08d0ce30e0e4 ("riscv: Implement syscall wrappers")
Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/bpf/20231004110905.49024-3-bjorn@kernel.org
---
 tools/testing/selftests/bpf/progs/bpf_misc.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 38a57a2e70db..799fff4995d8 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -99,6 +99,9 @@
 #elif defined(__TARGET_ARCH_arm64)
 #define SYSCALL_WRAPPER 1
 #define SYS_PREFIX "__arm64_"
+#elif defined(__TARGET_ARCH_riscv)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX "__riscv_"
 #else
 #define SYSCALL_WRAPPER 0
 #define SYS_PREFIX "__se_"
-- 
cgit v1.2.3


From b55b775f03166b8da60af80ef33da8bf83ca96c1 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn@rivosinc.com>
Date: Wed, 4 Oct 2023 13:09:05 +0200
Subject: selftests/bpf: Define SYS_NANOSLEEP_KPROBE_NAME for riscv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add missing sys_nanosleep name for RISC-V, which is used by some tests
(e.g. attach_probe).

Fixes: 08d0ce30e0e4 ("riscv: Implement syscall wrappers")
Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/bpf/20231004110905.49024-4-bjorn@kernel.org
---
 tools/testing/selftests/bpf/test_progs.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 77bd492c6024..2f9f6f250f17 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -417,6 +417,8 @@ int get_bpf_max_tramp_links(void);
 #define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep"
 #elif defined(__aarch64__)
 #define SYS_NANOSLEEP_KPROBE_NAME "__arm64_sys_nanosleep"
+#elif defined(__riscv)
+#define SYS_NANOSLEEP_KPROBE_NAME "__riscv_sys_nanosleep"
 #else
 #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
 #endif
-- 
cgit v1.2.3


From 97a79e502e25e27a65b0506c9fb210cb2d89b52e Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn@rivosinc.com>
Date: Wed, 4 Oct 2023 14:27:19 +0200
Subject: selftests/bpf: Add cross-build support for urandom_read et al
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some userland programs in the BPF test suite, e.g. urandom_read, is
missing cross-build support. Add cross-build support for these
programs

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231004122721.54525-2-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index db01ef82d6b1..dca2d4dadb2c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -198,7 +198,8 @@ endif
 # do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
 $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c liburandom_read.map
 	$(call msg,LIB,,$@)
-	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS))   \
+	$(Q)$(CLANG) $(CLANG_TARGET_ARCH) \
+		     $(filter-out -static,$(CFLAGS) $(LDFLAGS)) \
 		     $(filter %.c,$^) $(filter-out -static,$(LDLIBS)) \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
 		     -Wl,--version-script=liburandom_read.map \
@@ -206,8 +207,9 @@ $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c liburandom
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
 	$(call msg,BINARY,,$@)
-	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
-		     -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT)  \
+	$(Q)$(CLANG) $(CLANG_TARGET_ARCH) \
+		     $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
+		     -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
 		     -Wl,-rpath=. -o $@
 
-- 
cgit v1.2.3


From 72fae6319962fca2ecd8bb4f4e8dbdda7fe9af6f Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn@rivosinc.com>
Date: Wed, 4 Oct 2023 14:27:20 +0200
Subject: selftests/bpf: Enable lld usage for RISC-V
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RISC-V has proper lld support. Use that, similar to what x86 does, for
urandom_read et al.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231004122721.54525-3-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dca2d4dadb2c..a28cf927bc59 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -188,7 +188,7 @@ $(OUTPUT)/%:%.c
 	$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
 
 # LLVM's ld.lld doesn't support all the architectures, so use it only on x86
-ifeq ($(SRCARCH),x86)
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 riscv))
 LLD := lld
 else
 LLD := ld
-- 
cgit v1.2.3


From e096ab9d9f45bea9fb8126c46f6151d81aa0836f Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn@rivosinc.com>
Date: Wed, 4 Oct 2023 14:27:21 +0200
Subject: selftests/bpf: Add uprobe_multi to gen_tar target
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The uprobe_multi program was not picked up for the gen_tar target. Fix
by adding it to TEST_GEN_FILES.

Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20231004122721.54525-4-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a28cf927bc59..12a60521d624 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -104,7 +104,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
 	xdp_features
 
-TEST_GEN_FILES += liburandom_read.so urandom_read sign-file
+TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
 
 # Emit succinct information message describing current building step
 # $1 - generic step name (e.g., CC, LINK, etc);
-- 
cgit v1.2.3


From a50660173c7329c5d2ce1780a0f712a7f584d378 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Oct 2023 08:34:15 -0700
Subject: tools: ynl: don't regen on every make

As far as I can tell the normal Makefile dependency tracking
works, generated files get re-generated if the YAML was updated.
Let make do its job, don't force the re-generation.
make hardclean can be used to force regeneration.

Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231003153416.2479808-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/Makefile           | 1 -
 tools/net/ynl/generated/Makefile | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile
index 8156f03e23ac..d664b36deb5b 100644
--- a/tools/net/ynl/Makefile
+++ b/tools/net/ynl/Makefile
@@ -3,7 +3,6 @@
 SUBDIRS = lib generated samples
 
 all: $(SUBDIRS)
-	./ynl-regen.sh -f -p $(PWD)/../../../
 
 $(SUBDIRS):
 	@if [ -f "$@/Makefile" ] ; then \
diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile
index f8817d2e56e4..0f359ee3c46a 100644
--- a/tools/net/ynl/generated/Makefile
+++ b/tools/net/ynl/generated/Makefile
@@ -19,7 +19,7 @@ SRCS=$(patsubst %,%-user.c,${GENS})
 HDRS=$(patsubst %,%-user.h,${GENS})
 OBJS=$(patsubst %,%-user.o,${GENS})
 
-all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) regen
+all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI)
 
 protos.a: $(OBJS)
 	@echo -e "\tAR $@"
-- 
cgit v1.2.3


From e2ca31cee9095244885f2cd0df602a5eef11c826 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Oct 2023 08:34:16 -0700
Subject: tools: ynl: use uAPI include magic for samples

Makefile.deps provides direct includes in CFLAGS_$(obj).
We just need to rewrite the rules to make use of the extra
flags, no need to hard-include all of tools/include/uapi.

Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231003153416.2479808-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/samples/Makefile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile
index 32abbc0af39e..3dbb106e87d9 100644
--- a/tools/net/ynl/samples/Makefile
+++ b/tools/net/ynl/samples/Makefile
@@ -4,7 +4,7 @@ include ../Makefile.deps
 
 CC=gcc
 CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \
-	-I../../../include/uapi -I../lib/ -I../generated/ -idirafter $(UAPI_PATH)
+	-I../lib/ -I../generated/ -idirafter $(UAPI_PATH)
 ifeq ("$(DEBUG)","1")
   CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan
 endif
@@ -19,6 +19,9 @@ include $(wildcard *.d)
 all: $(BINS)
 
 $(BINS): ../lib/ynl.a ../generated/protos.a
+	@echo -e '\tCC sample $@'
+	@$(COMPILE.c) $(CFLAGS_$@) $@.c -o $@.o
+	@$(LINK.c) $@.o -o $@  $(LDLIBS)
 
 clean:
 	rm -f *.o *.d *~
-- 
cgit v1.2.3


From d549854bc58f05af9ab660b3461383eea623ff89 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Thu, 5 Oct 2023 15:21:51 +0800
Subject: selftests/bpf: Enable CONFIG_VSOCKETS in config

CONFIG_VSOCKETS is required by BPF selftests, otherwise we get errors
like this:

    ./test_progs:socket_loopback_reuseport:386: socket:
		Address family not supported by protocol
    socket_loopback_reuseport:FAIL:386
    ./test_progs:vsock_unix_redir_connectible:1496:
		vsock_socketpair_connectible() failed
    vsock_unix_redir_connectible:FAIL:1496

So this patch enables it in tools/testing/selftests/bpf/config.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/472e73d285db2ea59aca9bbb95eb5d4048327588.1696490003.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index e41eb33b2704..02dd4409200e 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -84,3 +84,4 @@ CONFIG_USERFAULTFD=y
 CONFIG_VXLAN=y
 CONFIG_XDP_SOCKETS=y
 CONFIG_XFRM_INTERFACE=y
+CONFIG_VSOCKETS=y
-- 
cgit v1.2.3


From 71ce60d375f5be15ef6db19aa63ebd2d72f1457c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Oct 2023 15:57:35 -0700
Subject: tools: ynl-gen: use uapi header name for the header guard

Chuck points out that we should use the uapi-header property
when generating the guard. Otherwise we may generate the same
guard as another file in the tree.

Tested-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/ynl/ynl-gen-c.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 897af958cee8..168fe612b029 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -805,6 +805,10 @@ class Family(SpecFamily):
             self.uapi_header = self.yaml['uapi-header']
         else:
             self.uapi_header = f"linux/{self.name}.h"
+        if self.uapi_header.startswith("linux/") and self.uapi_header.endswith('.h'):
+            self.uapi_header_name = self.uapi_header[6:-2]
+        else:
+            self.uapi_header_name = self.name
 
     def resolve(self):
         self.resolve_up(super())
@@ -2124,7 +2128,7 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'):
 
 
 def render_uapi(family, cw):
-    hdr_prot = f"_UAPI_LINUX_{family.name.upper()}_H"
+    hdr_prot = f"_UAPI_LINUX_{c_upper(family.uapi_header_name)}_H"
     cw.p('#ifndef ' + hdr_prot)
     cw.p('#define ' + hdr_prot)
     cw.nl()
-- 
cgit v1.2.3


From 925a01577ea5a70416731c00e42b74c97f41cb6a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 6 Oct 2023 10:57:42 -0700
Subject: selftests/bpf: Fix compiler warnings reported in -O2 mode

Fix a bunch of potentially unitialized variable usage warnings that are
reported by GCC in -O2 mode. Also silence overzealous stringop-truncation
class of warnings.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20231006175744.3136675-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile                         | 4 +++-
 tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c | 4 ++--
 tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c    | 4 ++--
 tools/testing/selftests/bpf/prog_tests/connect_ping.c        | 4 ++--
 tools/testing/selftests/bpf/prog_tests/linked_list.c         | 2 +-
 tools/testing/selftests/bpf/prog_tests/lwt_helpers.h         | 3 ++-
 tools/testing/selftests/bpf/prog_tests/queue_stack_map.c     | 2 +-
 tools/testing/selftests/bpf/prog_tests/sockmap_basic.c       | 8 ++++----
 tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h     | 2 +-
 tools/testing/selftests/bpf/prog_tests/sockmap_listen.c      | 4 ++--
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c        | 2 +-
 tools/testing/selftests/bpf/test_loader.c                    | 4 ++--
 tools/testing/selftests/bpf/xdp_features.c                   | 4 ++--
 tools/testing/selftests/bpf/xdp_hw_metadata.c                | 2 +-
 tools/testing/selftests/bpf/xskxceiver.c                     | 2 +-
 15 files changed, 27 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 12a60521d624..99f66bdf7698 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -27,7 +27,9 @@ endif
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
-CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS)	\
+CFLAGS += -g -O0 -rdynamic						\
+	  -Wall -Werror 						\
+	  $(GENFLAGS) $(SAN_CFLAGS)					\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
 LDFLAGS += $(SAN_LDFLAGS)
diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
index 16f1671e4bde..66191ae9863c 100644
--- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
@@ -33,11 +33,11 @@ static void create_inner_maps(enum bpf_map_type map_type,
 {
 	int map_fd, map_index, ret;
 	__u32 map_key = 0, map_id;
-	char map_name[15];
+	char map_name[16];
 
 	for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++) {
 		memset(map_name, 0, sizeof(map_name));
-		sprintf(map_name, "inner_map_fd_%d", map_index);
+		snprintf(map_name, sizeof(map_name), "inner_map_fd_%d", map_index);
 		map_fd = bpf_map_create(map_type, map_name, sizeof(__u32),
 					sizeof(__u32), 1, NULL);
 		CHECK(map_fd < 0,
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index d2d9e965eba5..053f4d6da77a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -193,8 +193,8 @@ error:
 
 void test_bloom_filter_map(void)
 {
-	__u32 *rand_vals, nr_rand_vals;
-	struct bloom_filter_map *skel;
+	__u32 *rand_vals = NULL, nr_rand_vals = 0;
+	struct bloom_filter_map *skel = NULL;
 	int err;
 
 	test_fail_cases();
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_ping.c b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
index 289218c2216c..40fe571f2fe7 100644
--- a/tools/testing/selftests/bpf/prog_tests/connect_ping.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
@@ -28,9 +28,9 @@ static void subtest(int cgroup_fd, struct connect_ping *skel,
 		.sin6_family = AF_INET6,
 		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
 	};
-	struct sockaddr *sa;
+	struct sockaddr *sa = NULL;
 	socklen_t sa_len;
-	int protocol;
+	int protocol = -1;
 	int sock_fd;
 
 	switch (family) {
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index db3bf6bbe01a..69dc31383b78 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -268,7 +268,7 @@ end:
 
 static void list_and_rb_node_same_struct(bool refcount_field)
 {
-	int bpf_rb_node_btf_id, bpf_refcount_btf_id, foo_btf_id;
+	int bpf_rb_node_btf_id, bpf_refcount_btf_id = 0, foo_btf_id;
 	struct btf *btf;
 	int id, err;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
index 61333f2a03f9..e9190574e79f 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
@@ -49,7 +49,8 @@ static int open_tuntap(const char *dev_name, bool need_mac)
 		return -1;
 
 	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
-	memcpy(ifr.ifr_name, dev_name, IFNAMSIZ);
+	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
+	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
 
 	err = ioctl(fd, TUNSETIFF, &ifr);
 	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index 722c5f2a7776..a043af9cd6d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -14,7 +14,7 @@ static void test_queue_stack_map_by_type(int type)
 	int i, err, prog_fd, map_in_fd, map_out_fd;
 	char file[32], buf[128];
 	struct bpf_object *obj;
-	struct iphdr iph;
+	struct iphdr iph = {};
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 064cc5e8d9ad..2535d0653cc8 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -359,7 +359,7 @@ out:
 static void test_sockmap_skb_verdict_shutdown(void)
 {
 	struct epoll_event ev, events[MAX_EVENTS];
-	int n, err, map, verdict, s, c1, p1;
+	int n, err, map, verdict, s, c1 = -1, p1 = -1;
 	struct test_sockmap_pass_prog *skel;
 	int epollfd;
 	int zero = 0;
@@ -414,9 +414,9 @@ out:
 static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 {
 	int expected, zero = 0, sent, recvd, avail;
-	int err, map, verdict, s, c0, c1, p0, p1;
-	struct test_sockmap_pass_prog *pass;
-	struct test_sockmap_drop_prog *drop;
+	int err, map, verdict, s, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
+	struct test_sockmap_pass_prog *pass = NULL;
+	struct test_sockmap_drop_prog *drop = NULL;
 	char buf[256] = "0123456789";
 
 	if (pass_prog) {
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 36d829a65aa4..e880f97bc44d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -378,7 +378,7 @@ static inline int enable_reuseport(int s, int progfd)
 static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
 {
 	struct sockaddr_storage addr;
-	socklen_t len;
+	socklen_t len = 0;
 	int err, s;
 
 	init_addr_loopback(family, &addr, &len);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 8df8cbb447f1..e08e590b2cf8 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -73,7 +73,7 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
 			      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
-	socklen_t len;
+	socklen_t len = 0;
 	u32 key = 0;
 	u64 value;
 	int err, s;
@@ -871,7 +871,7 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel,
 
 static void redir_partial(int family, int sotype, int sock_map, int parser_map)
 {
-	int s, c0, c1, p0, p1;
+	int s, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
 	int err, n, key, value;
 	char buf[] = "abc";
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 626c461fa34d..4439ba9392f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -226,7 +226,7 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	__u64 comp_addr;
 	void *data;
 	__u64 addr;
-	__u32 idx;
+	__u32 idx = 0;
 	int ret;
 
 	ret = recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index b4edd8454934..37ffa57f28a1 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -69,7 +69,7 @@ static int tester_init(struct test_loader *tester)
 {
 	if (!tester->log_buf) {
 		tester->log_buf_sz = TEST_LOADER_LOG_BUF_SZ;
-		tester->log_buf = malloc(tester->log_buf_sz);
+		tester->log_buf = calloc(tester->log_buf_sz, 1);
 		if (!ASSERT_OK_PTR(tester->log_buf, "tester_log_buf"))
 			return -ENOMEM;
 	}
@@ -538,7 +538,7 @@ void run_subtest(struct test_loader *tester,
 		 bool unpriv)
 {
 	struct test_subspec *subspec = unpriv ? &spec->unpriv : &spec->priv;
-	struct bpf_program *tprog, *tprog_iter;
+	struct bpf_program *tprog = NULL, *tprog_iter;
 	struct test_spec *spec_iter;
 	struct cap_state caps = {};
 	struct bpf_object *tobj;
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
index b449788fbd39..595c79141cf3 100644
--- a/tools/testing/selftests/bpf/xdp_features.c
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -360,9 +360,9 @@ static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val,
 static int dut_run(struct xdp_features *skel)
 {
 	int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
-	int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
+	int state, err = 0, *sockfd, ctrl_sockfd, echo_sockfd;
 	struct sockaddr_storage ctrl_addr;
-	pthread_t dut_thread;
+	pthread_t dut_thread = 0;
 	socklen_t addrlen;
 
 	sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL,
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 613321eb84c1..17c980138796 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -234,7 +234,7 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 	struct pollfd fds[rxq + 1];
 	__u64 comp_addr;
 	__u64 addr;
-	__u32 idx;
+	__u32 idx = 0;
 	int ret;
 	int i;
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 837e0ffbdc47..591ca9637b23 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1049,7 +1049,7 @@ static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk)
 	struct xsk_umem_info *umem = xsk->umem;
 	struct pollfd fds = { };
 	struct pkt *pkt;
-	u64 first_addr;
+	u64 first_addr = 0;
 	int ret;
 
 	fds.fd = xsk_socket__fd(xsk->xsk);
-- 
cgit v1.2.3


From 46475cc0dded2cd832a906fae4f91fd0ab73904b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 6 Oct 2023 10:57:43 -0700
Subject: selftests/bpf: Support building selftests in optimized -O2 mode

Add support for building selftests with -O2 level of optimization, which
allows more compiler warnings detection (like lots of potentially
uninitialized usage), but also is useful to have a faster-running test
for some CPU-intensive tests.

One can build optimized versions of libbpf and selftests by running:

  $ make RELEASE=1

There is a measurable speed up of about 10 seconds for me locally,
though it's mostly capped by non-parallelized serial tests. User CPU
time goes down by total 40 seconds, from 1m10s to 0m28s.

Unoptimized build (-O0)
=======================
Summary: 430/3544 PASSED, 25 SKIPPED, 4 FAILED

real    1m59.937s
user    1m10.877s
sys     3m14.880s

Optimized build (-O2)
=====================
Summary: 425/3543 PASSED, 25 SKIPPED, 9 FAILED

real    1m50.540s
user    0m28.406s
sys     3m13.198s

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20231006175744.3136675-2-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 99f66bdf7698..4225f975fce3 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -27,7 +27,9 @@ endif
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
-CFLAGS += -g -O0 -rdynamic						\
+RELEASE		?=
+OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
+CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 	  -Wall -Werror 						\
 	  $(GENFLAGS) $(SAN_CFLAGS)					\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
@@ -243,7 +245,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
 		    BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/		       \
 		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf			       \
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)		       \
-		    EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)'			       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS)'	       \
 		    EXTRA_LDFLAGS='$(SAN_LDFLAGS)' &&			       \
 		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
 
@@ -281,7 +283,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" 	       \
-		    EXTRA_CFLAGS='-g -O0'				       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS)'			       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
 		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
@@ -292,7 +294,7 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
 		    $(BPFOBJ) | $(BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
 		    ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE)			\
-		    EXTRA_CFLAGS='-g -O0'					\
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS)'				\
 		    OUTPUT=$(BUILD_DIR)/bpftool/				\
 		    LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/				\
 		    LIBBPF_DESTDIR=$(SCRATCH_DIR)/				\
@@ -315,7 +317,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   $(APIDIR)/linux/bpf.h					       \
 	   | $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
-		    EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)'			       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS)'	       \
 		    EXTRA_LDFLAGS='$(SAN_LDFLAGS)'			       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
@@ -324,7 +326,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 		$(APIDIR)/linux/bpf.h					       \
 		| $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		    EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE=		       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS)' ARCH= CROSS_COMPILE=	       \
 		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/			       \
 		    CC="$(HOSTCC)" LD="$(HOSTLD)"			       \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
-- 
cgit v1.2.3


From 0af3aace5b91b0e46b33f4e5eb137bea5730fa76 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 6 Oct 2023 10:57:44 -0700
Subject: selftests/bpf: Don't truncate #test/subtest field

We currently expect up to a three-digit number of tests and subtests, so:

  #999/999: some_test/some_subtest: ...

Is the largest test/subtest we can see. If we happen to cross into
1000s, current logic will just truncate everything after 7th character.
This patch fixes this truncate and allows to go way higher (up to 31
characters in total). We still nicely align test numbers:

  #60/66   core_reloc_btfgen/type_based___incompat:OK
  #60/67   core_reloc_btfgen/type_based___fn_wrong_args:OK
  #60/68   core_reloc_btfgen/type_id:OK
  #60/69   core_reloc_btfgen/type_id___missing_targets:OK
  #60/70   core_reloc_btfgen/enumval:OK

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20231006175744.3136675-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/test_progs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 4d582cac2c09..1b9387890148 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -255,7 +255,7 @@ static void print_subtest_name(int test_num, int subtest_num,
 			       const char *test_name, char *subtest_name,
 			       char *result)
 {
-	char test_num_str[TEST_NUM_WIDTH + 1];
+	char test_num_str[32];
 
 	snprintf(test_num_str, sizeof(test_num_str), "%d/%d", test_num, subtest_num);
 
-- 
cgit v1.2.3


From fdd11c14c33b949a4d59fab159fb2da834073914 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Fri, 6 Oct 2023 18:32:16 +0800
Subject: selftests/bpf: Add pairs_redir_to_connected helper

Extract duplicate code from these four functions

 unix_redir_to_connected()
 udp_redir_to_connected()
 inet_unix_redir_to_connected()
 unix_inet_redir_to_connected()

to generate a new helper pairs_redir_to_connected(). Create the
different socketpairs in these four functions, then pass the
socketpairs info to the new common helper to do the connections.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Link: https://lore.kernel.org/r/54bb28dcf764e7d4227ab160883931d2173f4f3d.1696588133.git.geliang.tang@suse.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_listen.c      | 146 +++++----------------
 1 file changed, 31 insertions(+), 115 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index e08e590b2cf8..a934d430c20c 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1336,53 +1336,59 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 	}
 }
 
-static void unix_redir_to_connected(int sotype, int sock_mapfd,
-			       int verd_mapfd, enum redir_mode mode)
+static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
+				     int sock_mapfd, int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
-	int c0, c1, p0, p1;
 	unsigned int pass;
 	int err, n;
-	int sfd[2];
 	u32 key;
 	char b;
 
 	zero_verdict_count(verd_mapfd);
 
-	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
-		return;
-	c0 = sfd[0], p0 = sfd[1];
-
-	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
-		goto close0;
-	c1 = sfd[0], p1 = sfd[1];
-
-	err = add_to_sockmap(sock_mapfd, p0, p1);
+	err = add_to_sockmap(sock_mapfd, peer0, peer1);
 	if (err)
-		goto close;
+		return;
 
-	n = write(c1, "a", 1);
+	n = write(cli1, "a", 1);
 	if (n < 0)
 		FAIL_ERRNO("%s: write", log_prefix);
 	if (n == 0)
 		FAIL("%s: incomplete write", log_prefix);
 	if (n < 1)
-		goto close;
+		return;
 
 	key = SK_PASS;
 	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
 	if (err)
-		goto close;
+		return;
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	n = recv_timeout(mode == REDIR_INGRESS ? peer0 : cli0, &b, 1, 0, IO_TIMEOUT_SEC);
 	if (n < 0)
 		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
 		FAIL("%s: incomplete recv", log_prefix);
+}
+
+static void unix_redir_to_connected(int sotype, int sock_mapfd,
+			       int verd_mapfd, enum redir_mode mode)
+{
+	int c0, c1, p0, p1;
+	int sfd[2];
+
+	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+		return;
+	c0 = sfd[0], p0 = sfd[1];
+
+	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+		goto close0;
+	c1 = sfd[0], p1 = sfd[1];
+
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
 
-close:
 	xclose(c1);
 	xclose(p1);
 close0:
@@ -1661,14 +1667,8 @@ close_peer0:
 static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 				   enum redir_mode mode)
 {
-	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
+	int err;
 
 	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
 	if (err)
@@ -1677,32 +1677,8 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (err)
 		goto close_cli0;
 
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close_cli1;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close_cli1;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close_cli1;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
 
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
-
-close_cli1:
 	xclose(c1);
 	xclose(p1);
 close_cli0:
@@ -1747,15 +1723,9 @@ static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map
 static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 					int verd_mapfd, enum redir_mode mode)
 {
-	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
 	int sfd[2];
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
+	int err;
 
 	if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
 		return;
@@ -1765,32 +1735,8 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (err)
 		goto close;
 
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close_cli1;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close_cli1;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close_cli1;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
 
-close_cli1:
 	xclose(c1);
 	xclose(p1);
 close:
@@ -1827,15 +1773,9 @@ static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 					int verd_mapfd, enum redir_mode mode)
 {
-	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
 	int sfd[2];
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
+	int err;
 
 	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
 	if (err)
@@ -1845,32 +1785,8 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 		goto close_cli0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
 
-close:
 	xclose(c1);
 	xclose(p1);
 close_cli0:
-- 
cgit v1.2.3


From d6247ecb6c1e17d7a33317090627f5bfe563cbb2 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Wed, 4 Oct 2023 11:23:38 -0500
Subject: bpf: Add ability to pin bpf timer to calling CPU

BPF supports creating high resolution timers using bpf_timer_* helper
functions. Currently, only the BPF_F_TIMER_ABS flag is supported, which
specifies that the timeout should be interpreted as absolute time. It
would also be useful to be able to pin that timer to a core. For
example, if you wanted to make a subset of cores run without timer
interrupts, and only have the timer be invoked on a single core.

This patch adds support for this with a new BPF_F_TIMER_CPU_PIN flag.
When specified, the HRTIMER_MODE_PINNED flag is passed to
hrtimer_start(). A subsequent patch will update selftests to validate.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20231004162339.200702-2-void@manifault.com
---
 include/uapi/linux/bpf.h       | 4 ++++
 kernel/bpf/helpers.c           | 5 ++++-
 tools/include/uapi/linux/bpf.h | 4 ++++
 3 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 70bfa997e896..a7d4a1a69f21 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5096,6 +5096,8 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
+ *		**BPF_F_TIMER_CPU_PIN**
+ *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -7309,9 +7311,11 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
+ *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
+	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index dd1c69ee3375..d2840dd5b00d 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1272,7 +1272,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
 
 	if (in_nmi())
 		return -EOPNOTSUPP;
-	if (flags > BPF_F_TIMER_ABS)
+	if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN))
 		return -EINVAL;
 	__bpf_spin_lock_irqsave(&timer->lock);
 	t = timer->timer;
@@ -1286,6 +1286,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
 	else
 		mode = HRTIMER_MODE_REL_SOFT;
 
+	if (flags & BPF_F_TIMER_CPU_PIN)
+		mode |= HRTIMER_MODE_PINNED;
+
 	hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 70bfa997e896..a7d4a1a69f21 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5096,6 +5096,8 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
+ *		**BPF_F_TIMER_CPU_PIN**
+ *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -7309,9 +7311,11 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
+ *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
+	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
-- 
cgit v1.2.3


From 0d7ae06860753bb30b3731302b994da071120d00 Mon Sep 17 00:00:00 2001
From: David Vernet <void@manifault.com>
Date: Wed, 4 Oct 2023 11:23:39 -0500
Subject: selftests/bpf: Test pinning bpf timer to a core

Now that we support pinning a BPF timer to the current core, we should
test it with some selftests. This patch adds two new testcases to the
timer suite, which verifies that a BPF timer both with and without
BPF_F_TIMER_ABS, can be pinned to the calling core with BPF_F_TIMER_CPU_PIN.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20231004162339.200702-3-void@manifault.com
---
 tools/testing/selftests/bpf/prog_tests/timer.c |  4 ++
 tools/testing/selftests/bpf/progs/timer.c      | 63 +++++++++++++++++++++++++-
 2 files changed, 66 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 290c21dbe65a..d8bc838445ec 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -14,6 +14,7 @@ static int timer(struct timer *timer_skel)
 
 	ASSERT_EQ(timer_skel->data->callback_check, 52, "callback_check1");
 	ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1");
+	ASSERT_EQ(timer_skel->bss->pinned_callback_check, 0, "pinned_callback_check1");
 
 	prog_fd = bpf_program__fd(timer_skel->progs.test1);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
@@ -32,6 +33,9 @@ static int timer(struct timer *timer_skel)
 	/* check that timer_cb3() was executed twice */
 	ASSERT_EQ(timer_skel->bss->abs_data, 12, "abs_data");
 
+	/* check that timer_cb_pinned() was executed twice */
+	ASSERT_EQ(timer_skel->bss->pinned_callback_check, 2, "pinned_callback_check");
+
 	/* check that there were no errors in timer execution */
 	ASSERT_EQ(timer_skel->bss->err, 0, "err");
 
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 9a16d95213e1..8b946c8188c6 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -51,7 +51,7 @@ struct {
 	__uint(max_entries, 1);
 	__type(key, int);
 	__type(value, struct elem);
-} abs_timer SEC(".maps");
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps");
 
 __u64 bss_data;
 __u64 abs_data;
@@ -59,6 +59,8 @@ __u64 err;
 __u64 ok;
 __u64 callback_check = 52;
 __u64 callback2_check = 52;
+__u64 pinned_callback_check;
+__s32 pinned_cpu;
 
 #define ARRAY 1
 #define HTAB 2
@@ -329,3 +331,62 @@ int BPF_PROG2(test3, int, a)
 
 	return 0;
 }
+
+/* callback for pinned timer */
+static int timer_cb_pinned(void *map, int *key, struct bpf_timer *timer)
+{
+	__s32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu != pinned_cpu)
+		err |= 16384;
+
+	pinned_callback_check++;
+	return 0;
+}
+
+static void test_pinned_timer(bool soft)
+{
+	int key = 0;
+	void *map;
+	struct bpf_timer *timer;
+	__u64 flags = BPF_F_TIMER_CPU_PIN;
+	__u64 start_time;
+
+	if (soft) {
+		map = &soft_timer_pinned;
+		start_time = 0;
+	} else {
+		map = &abs_timer_pinned;
+		start_time = bpf_ktime_get_boot_ns();
+		flags |= BPF_F_TIMER_ABS;
+	}
+
+	timer = bpf_map_lookup_elem(map, &key);
+	if (timer) {
+		if (bpf_timer_init(timer, map, CLOCK_BOOTTIME) != 0)
+			err |= 4096;
+		bpf_timer_set_callback(timer, timer_cb_pinned);
+		pinned_cpu = bpf_get_smp_processor_id();
+		bpf_timer_start(timer, start_time + 1000, flags);
+	} else {
+		err |= 8192;
+	}
+}
+
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG2(test4, int, a)
+{
+	bpf_printk("test4");
+	test_pinned_timer(true);
+
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test5")
+int BPF_PROG2(test5, int, a)
+{
+	bpf_printk("test5");
+	test_pinned_timer(false);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 23671f4dfd10b48b4a2fee4768886f0d8ec55b7e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Oct 2023 21:44:38 -0700
Subject: bpftool: Align output skeleton ELF code

libbpf accesses the ELF data requiring at least 8 byte alignment,
however, the data is generated into a C string that doesn't guarantee
alignment. Fix this by assigning to an aligned char array. Use sizeof
on the array, less one for the \0 terminator, rather than generating a
constant.

Fixes: a6cc6b34b93e ("bpftool: Provide a helper method for accessing skeleton's embedded ELF data")
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20231007044439.25171-1-irogers@google.com
---
 tools/bpf/bpftool/gen.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 04c47745b3ea..882bf8e6e70e 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -1209,7 +1209,7 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
-			s->data = %2$s__elf_bytes(&s->data_sz);		    \n\
+			s->data = %1$s__elf_bytes(&s->data_sz);		    \n\
 									    \n\
 			obj->skeleton = s;				    \n\
 			return 0;					    \n\
@@ -1218,12 +1218,12 @@ static int do_skeleton(int argc, char **argv)
 			return err;					    \n\
 		}							    \n\
 									    \n\
-		static inline const void *%2$s__elf_bytes(size_t *sz)	    \n\
+		static inline const void *%1$s__elf_bytes(size_t *sz)	    \n\
 		{							    \n\
-			*sz = %1$d;					    \n\
-			return (const void *)\"\\			    \n\
-		"
-		, file_sz, obj_name);
+			static const char data[] __attribute__((__aligned__(8))) = \"\\\n\
+		",
+		obj_name
+	);
 
 	/* embed contents of BPF object file */
 	print_hex(obj_data, file_sz);
@@ -1231,6 +1231,9 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 		\";							    \n\
+									    \n\
+			*sz = sizeof(data) - 1;				    \n\
+			return (const void *)data;			    \n\
 		}							    \n\
 									    \n\
 		#ifdef __cplusplus					    \n\
-- 
cgit v1.2.3


From 1be84ca53ca0421c781f9ec007cd8bccbb58f763 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Oct 2023 21:44:39 -0700
Subject: bpftool: Align bpf_load_and_run_opts insns and data

A C string lacks alignment so use aligned arrays to avoid potential
alignment problems. Switch to using sizeof (less 1 for the \0
terminator) rather than a hardcode size constant.

Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20231007044439.25171-2-irogers@google.com
---
 tools/bpf/bpftool/gen.c | 43 +++++++++++++++++++++++--------------------
 1 file changed, 23 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 882bf8e6e70e..ee3ce2b8000d 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -708,17 +708,22 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 
 		codegen("\
 		\n\
-			skel->%1$s = skel_prep_map_data((void *)\"\\	    \n\
-		", ident);
+			{						    \n\
+				static const char data[] __attribute__((__aligned__(8))) = \"\\\n\
+		");
 		mmap_data = bpf_map__initial_value(map, &mmap_size);
 		print_hex(mmap_data, mmap_size);
 		codegen("\
 		\n\
-		\", %1$zd, %2$zd);					    \n\
-			if (!skel->%3$s)				    \n\
-				goto cleanup;				    \n\
-			skel->maps.%3$s.initial_value = (__u64) (long) skel->%3$s;\n\
-		", bpf_map_mmap_sz(map), mmap_size, ident);
+		\";							    \n\
+									    \n\
+				skel->%1$s = skel_prep_map_data((void *)data, %2$zd,\n\
+								sizeof(data) - 1);\n\
+				if (!skel->%1$s)			    \n\
+					goto cleanup;			    \n\
+				skel->maps.%1$s.initial_value = (__u64) (long) skel->%1$s;\n\
+			}						    \n\
+			", ident, bpf_map_mmap_sz(map));
 	}
 	codegen("\
 		\n\
@@ -733,32 +738,30 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		{							    \n\
 			struct bpf_load_and_run_opts opts = {};		    \n\
 			int err;					    \n\
-									    \n\
-			opts.ctx = (struct bpf_loader_ctx *)skel;	    \n\
-			opts.data_sz = %2$d;				    \n\
-			opts.data = (void *)\"\\			    \n\
+			static const char opts_data[] __attribute__((__aligned__(8))) = \"\\\n\
 		",
-		obj_name, opts.data_sz);
+		obj_name);
 	print_hex(opts.data, opts.data_sz);
 	codegen("\
 		\n\
 		\";							    \n\
+			static const char opts_insn[] __attribute__((__aligned__(8))) = \"\\\n\
 		");
-
-	codegen("\
-		\n\
-			opts.insns_sz = %d;				    \n\
-			opts.insns = (void *)\"\\			    \n\
-		",
-		opts.insns_sz);
 	print_hex(opts.insns, opts.insns_sz);
 	codegen("\
 		\n\
 		\";							    \n\
+									    \n\
+			opts.ctx = (struct bpf_loader_ctx *)skel;	    \n\
+			opts.data_sz = sizeof(opts_data) - 1;		    \n\
+			opts.data = (void *)opts_data;			    \n\
+			opts.insns_sz = sizeof(opts_insn) - 1;		    \n\
+			opts.insns = (void *)opts_insn;			    \n\
+									    \n\
 			err = bpf_load_and_run(&opts);			    \n\
 			if (err < 0)					    \n\
 				return err;				    \n\
-		", obj_name);
+		");
 	bpf_object__for_each_map(map, obj) {
 		const char *mmap_flags;
 
-- 
cgit v1.2.3


From dab4e1f06cabb6834de14264394ccab197007302 Mon Sep 17 00:00:00 2001
From: Martynas Pumputis <m@lambda.lt>
Date: Sat, 7 Oct 2023 10:14:14 +0200
Subject: bpf: Derive source IP addr via bpf_*_fib_lookup()

Extend the bpf_fib_lookup() helper by making it to return the source
IPv4/IPv6 address if the BPF_FIB_LOOKUP_SRC flag is set.

For example, the following snippet can be used to derive the desired
source IP address:

    struct bpf_fib_lookup p = { .ipv4_dst = ip4->daddr };

    ret = bpf_skb_fib_lookup(skb, p, sizeof(p),
            BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH);
    if (ret != BPF_FIB_LKUP_RET_SUCCESS)
        return TC_ACT_SHOT;

    /* the p.ipv4_src now contains the source address */

The inability to derive the proper source address may cause malfunctions
in BPF-based dataplanes for hosts containing netdevs with more than one
routable IP address or for multi-homed hosts.

For example, Cilium implements packet masquerading in BPF. If an
egressing netdev to which the Cilium's BPF prog is attached has
multiple IP addresses, then only one [hardcoded] IP address can be used for
masquerading. This breaks connectivity if any other IP address should have
been selected instead, for example, when a public and private addresses
are attached to the same egress interface.

The change was tested with Cilium [1].

Nikolay Aleksandrov helped to figure out the IPv6 addr selection.

[1]: https://github.com/cilium/cilium/pull/28283

Signed-off-by: Martynas Pumputis <m@lambda.lt>
Link: https://lore.kernel.org/r/20231007081415.33502-2-m@lambda.lt
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/ipv6_stubs.h       |  5 +++++
 include/uapi/linux/bpf.h       | 10 ++++++++++
 net/core/filter.c              | 18 +++++++++++++++++-
 net/ipv6/af_inet6.c            |  1 +
 tools/include/uapi/linux/bpf.h | 10 ++++++++++
 5 files changed, 43 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index c48186bf4737..21da31e1dff5 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -85,6 +85,11 @@ struct ipv6_bpf_stub {
 			       sockptr_t optval, unsigned int optlen);
 	int (*ipv6_getsockopt)(struct sock *sk, int level, int optname,
 			       sockptr_t optval, sockptr_t optlen);
+	int (*ipv6_dev_get_saddr)(struct net *net,
+				  const struct net_device *dst_dev,
+				  const struct in6_addr *daddr,
+				  unsigned int prefs,
+				  struct in6_addr *saddr);
 };
 extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a7d4a1a69f21..e0aa457f94a9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3264,6 +3264,11 @@ union bpf_attr {
  *			and *params*->smac will not be set as output. A common
  *			use case is to call **bpf_redirect_neigh**\ () after
  *			doing **bpf_fib_lookup**\ ().
+ *		**BPF_FIB_LOOKUP_SRC**
+ *			Derive and set source IP addr in *params*->ipv{4,6}_src
+ *			for the nexthop. If the src addr cannot be derived,
+ *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
+ *			case, *params*->dmac and *params*->smac are not set either.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -6964,6 +6969,7 @@ enum {
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
+	BPF_FIB_LOOKUP_SRC     = (1U << 4),
 };
 
 enum {
@@ -6976,6 +6982,7 @@ enum {
 	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
 	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
 	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_FIB_LKUP_RET_NO_SRC_ADDR,  /* failed to derive IP src addr */
 };
 
 struct bpf_fib_lookup {
@@ -7010,6 +7017,9 @@ struct bpf_fib_lookup {
 		__u32	rt_metric;
 	};
 
+	/* input: source address to consider for lookup
+	 * output: source address result from lookup
+	 */
 	union {
 		__be32		ipv4_src;
 		__u32		ipv6_src[4];  /* in6_addr; network order */
diff --git a/net/core/filter.c b/net/core/filter.c
index a094694899c9..3880bf0b740d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5850,6 +5850,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = res.fi->fib_priority;
 	params->ifindex = dev->ifindex;
 
+	if (flags & BPF_FIB_LOOKUP_SRC)
+		params->ipv4_src = fib_result_prefsrc(net, &res);
+
 	/* xdp and cls_bpf programs are run in RCU-bh so
 	 * rcu_read_lock_bh is not needed here
 	 */
@@ -5992,6 +5995,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = res.f6i->fib6_metric;
 	params->ifindex = dev->ifindex;
 
+	if (flags & BPF_FIB_LOOKUP_SRC) {
+		if (res.f6i->fib6_prefsrc.plen) {
+			*src = res.f6i->fib6_prefsrc.addr;
+		} else {
+			err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev,
+								&fl6.daddr, 0,
+								src);
+			if (err)
+				return BPF_FIB_LKUP_RET_NO_SRC_ADDR;
+		}
+	}
+
 	if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH)
 		goto set_fwd_params;
 
@@ -6010,7 +6025,8 @@ set_fwd_params:
 #endif
 
 #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
-			     BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID)
+			     BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \
+			     BPF_FIB_LOOKUP_SRC)
 
 BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c6ad0d6e99b5..6337fb4504fd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1061,6 +1061,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
 	.udp6_lib_lookup = __udp6_lib_lookup,
 	.ipv6_setsockopt = do_ipv6_setsockopt,
 	.ipv6_getsockopt = do_ipv6_getsockopt,
+	.ipv6_dev_get_saddr = ipv6_dev_get_saddr,
 };
 
 static int __init inet6_init(void)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a7d4a1a69f21..e0aa457f94a9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3264,6 +3264,11 @@ union bpf_attr {
  *			and *params*->smac will not be set as output. A common
  *			use case is to call **bpf_redirect_neigh**\ () after
  *			doing **bpf_fib_lookup**\ ().
+ *		**BPF_FIB_LOOKUP_SRC**
+ *			Derive and set source IP addr in *params*->ipv{4,6}_src
+ *			for the nexthop. If the src addr cannot be derived,
+ *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
+ *			case, *params*->dmac and *params*->smac are not set either.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -6964,6 +6969,7 @@ enum {
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
+	BPF_FIB_LOOKUP_SRC     = (1U << 4),
 };
 
 enum {
@@ -6976,6 +6982,7 @@ enum {
 	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
 	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
 	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_FIB_LKUP_RET_NO_SRC_ADDR,  /* failed to derive IP src addr */
 };
 
 struct bpf_fib_lookup {
@@ -7010,6 +7017,9 @@ struct bpf_fib_lookup {
 		__u32	rt_metric;
 	};
 
+	/* input: source address to consider for lookup
+	 * output: source address result from lookup
+	 */
 	union {
 		__be32		ipv4_src;
 		__u32		ipv6_src[4];  /* in6_addr; network order */
-- 
cgit v1.2.3


From b0f7a8ca11795541f09060ccf583a341a9c94d5f Mon Sep 17 00:00:00 2001
From: Martynas Pumputis <m@lambda.lt>
Date: Sat, 7 Oct 2023 10:14:15 +0200
Subject: selftests/bpf: Add BPF_FIB_LOOKUP_SRC tests

This patch extends the existing fib_lookup test suite by adding two test
cases (for each IP family):

* Test source IP selection from the egressing netdev.
* Test source IP selection when an IP route has a preferred src IP addr.

Signed-off-by: Martynas Pumputis <m@lambda.lt>
Link: https://lore.kernel.org/r/20231007081415.33502-3-m@lambda.lt
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/fib_lookup.c  | 83 ++++++++++++++++++++--
 1 file changed, 77 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
index 2fd05649bad1..4ad4cd69152e 100644
--- a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
@@ -11,9 +11,13 @@
 
 #define NS_TEST			"fib_lookup_ns"
 #define IPV6_IFACE_ADDR		"face::face"
+#define IPV6_IFACE_ADDR_SEC	"cafe::cafe"
+#define IPV6_ADDR_DST		"face::3"
 #define IPV6_NUD_FAILED_ADDR	"face::1"
 #define IPV6_NUD_STALE_ADDR	"face::2"
 #define IPV4_IFACE_ADDR		"10.0.0.254"
+#define IPV4_IFACE_ADDR_SEC	"10.1.0.254"
+#define IPV4_ADDR_DST		"10.2.0.254"
 #define IPV4_NUD_FAILED_ADDR	"10.0.0.1"
 #define IPV4_NUD_STALE_ADDR	"10.0.0.2"
 #define IPV4_TBID_ADDR		"172.0.0.254"
@@ -31,6 +35,7 @@ struct fib_lookup_test {
 	const char *desc;
 	const char *daddr;
 	int expected_ret;
+	const char *expected_src;
 	int lookup_flags;
 	__u32 tbid;
 	__u8 dmac[6];
@@ -69,6 +74,22 @@ static const struct fib_lookup_test tests[] = {
 	  .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
 	  .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100,
 	  .dmac = DMAC_INIT2, },
+	{ .desc = "IPv4 set src addr from netdev",
+	  .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV4_IFACE_ADDR,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv6 set src addr from netdev",
+	  .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV6_IFACE_ADDR,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv4 set prefsrc addr from route",
+	  .daddr = IPV4_ADDR_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV4_IFACE_ADDR_SEC,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv6 set prefsrc addr route",
+	  .daddr = IPV6_ADDR_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV6_IFACE_ADDR_SEC,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
 };
 
 static int ifindex;
@@ -97,6 +118,13 @@ static int setup_netns(void)
 	SYS(fail, "ip neigh add %s dev veth1 nud failed", IPV4_NUD_FAILED_ADDR);
 	SYS(fail, "ip neigh add %s dev veth1 lladdr %s nud stale", IPV4_NUD_STALE_ADDR, DMAC);
 
+	/* Setup for prefsrc IP addr selection */
+	SYS(fail, "ip addr add %s/24 dev veth1", IPV4_IFACE_ADDR_SEC);
+	SYS(fail, "ip route add %s/32 dev veth1 src %s", IPV4_ADDR_DST, IPV4_IFACE_ADDR_SEC);
+
+	SYS(fail, "ip addr add %s/64 dev veth1 nodad", IPV6_IFACE_ADDR_SEC);
+	SYS(fail, "ip route add %s/128 dev veth1 src %s", IPV6_ADDR_DST, IPV6_IFACE_ADDR_SEC);
+
 	/* Setup for tbid lookup tests */
 	SYS(fail, "ip addr add %s/24 dev veth2", IPV4_TBID_ADDR);
 	SYS(fail, "ip route del %s/24 dev veth2", IPV4_TBID_NET);
@@ -133,9 +161,12 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const struct fib_loo
 
 	if (inet_pton(AF_INET6, test->daddr, params->ipv6_dst) == 1) {
 		params->family = AF_INET6;
-		ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src);
-		if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)"))
-			return -1;
+		if (!(test->lookup_flags & BPF_FIB_LOOKUP_SRC)) {
+			ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src);
+			if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)"))
+				return -1;
+		}
+
 		return 0;
 	}
 
@@ -143,9 +174,12 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const struct fib_loo
 	if (!ASSERT_EQ(ret, 1, "convert IP[46] address"))
 		return -1;
 	params->family = AF_INET;
-	ret = inet_pton(AF_INET, IPV4_IFACE_ADDR, &params->ipv4_src);
-	if (!ASSERT_EQ(ret, 1, "inet_pton(IPV4_IFACE_ADDR)"))
-		return -1;
+
+	if (!(test->lookup_flags & BPF_FIB_LOOKUP_SRC)) {
+		ret = inet_pton(AF_INET, IPV4_IFACE_ADDR, &params->ipv4_src);
+		if (!ASSERT_EQ(ret, 1, "inet_pton(IPV4_IFACE_ADDR)"))
+			return -1;
+	}
 
 	return 0;
 }
@@ -156,6 +190,40 @@ static void mac_str(char *b, const __u8 *mac)
 		mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
 }
 
+static void assert_src_ip(struct bpf_fib_lookup *fib_params, const char *expected_src)
+{
+	int ret;
+	__u32 src6[4];
+	__be32 src4;
+
+	switch (fib_params->family) {
+	case AF_INET6:
+		ret = inet_pton(AF_INET6, expected_src, src6);
+		ASSERT_EQ(ret, 1, "inet_pton(expected_src)");
+
+		ret = memcmp(src6, fib_params->ipv6_src, sizeof(fib_params->ipv6_src));
+		if (!ASSERT_EQ(ret, 0, "fib_lookup ipv6 src")) {
+			char str_src6[64];
+
+			inet_ntop(AF_INET6, fib_params->ipv6_src, str_src6,
+				  sizeof(str_src6));
+			printf("ipv6 expected %s actual %s ", expected_src,
+			       str_src6);
+		}
+
+		break;
+	case AF_INET:
+		ret = inet_pton(AF_INET, expected_src, &src4);
+		ASSERT_EQ(ret, 1, "inet_pton(expected_src)");
+
+		ASSERT_EQ(fib_params->ipv4_src, src4, "fib_lookup ipv4 src");
+
+		break;
+	default:
+		PRINT_FAIL("invalid addr family: %d", fib_params->family);
+	}
+}
+
 void test_fib_lookup(void)
 {
 	struct bpf_fib_lookup *fib_params;
@@ -207,6 +275,9 @@ void test_fib_lookup(void)
 		ASSERT_EQ(skel->bss->fib_lookup_ret, tests[i].expected_ret,
 			  "fib_lookup_ret");
 
+		if (tests[i].expected_src)
+			assert_src_ip(fib_params, tests[i].expected_src);
+
 		ret = memcmp(tests[i].dmac, fib_params->dmac, sizeof(tests[i].dmac));
 		if (!ASSERT_EQ(ret, 0, "dmac not match")) {
 			char expected[18], actual[18];
-- 
cgit v1.2.3


From 8cea95b0bd7930367f11e2abceda6e096dd18943 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 6 Oct 2023 06:50:32 -0700
Subject: tools: ynl-gen: handle do ops with no input attrs

The code supports dumps with no input attributes currently
thru a combination of special-casing and luck.
Clean up the handling of ops with no inputs. Create empty
Structs, and skip printing of empty types.
This makes dos with no inputs work.

Tested-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Link: https://lore.kernel.org/r/20231006135032.3328523-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 168fe612b029..f125b5f704ba 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1041,9 +1041,11 @@ class RenderInfo:
         if op_mode == 'notify':
             op_mode = 'do'
         for op_dir in ['request', 'reply']:
-            if op and op_dir in op[op_mode]:
-                self.struct[op_dir] = Struct(family, self.attr_set,
-                                             type_list=op[op_mode][op_dir]['attributes'])
+            if op:
+                type_list = []
+                if op_dir in op[op_mode]:
+                    type_list = op[op_mode][op_dir]['attributes']
+                self.struct[op_dir] = Struct(family, self.attr_set, type_list=type_list)
         if op_mode == 'event':
             self.struct['reply'] = Struct(family, self.attr_set, type_list=op['event']['attributes'])
 
@@ -1752,6 +1754,8 @@ def print_type_helpers(ri, direction, deref=False):
 
 
 def print_req_type_helpers(ri):
+    if len(ri.struct["request"].attr_list) == 0:
+        return
     print_alloc_wrapper(ri, "request")
     print_type_helpers(ri, "request")
 
@@ -1773,6 +1777,8 @@ def print_parse_prototype(ri, direction, terminate=True):
 
 
 def print_req_type(ri):
+    if len(ri.struct["request"].attr_list) == 0:
+        return
     print_type(ri, "request")
 
 
@@ -2515,9 +2521,8 @@ def main():
                 if 'dump' in op:
                     cw.p(f"/* {op.enum_name} - dump */")
                     ri = RenderInfo(cw, parsed, args.mode, op, 'dump')
-                    if 'request' in op['dump']:
-                        print_req_type(ri)
-                        print_req_type_helpers(ri)
+                    print_req_type(ri)
+                    print_req_type_helpers(ri)
                     if not ri.type_consistent:
                         print_rsp_type(ri)
                     print_wrapped_type(ri)
-- 
cgit v1.2.3


From feba7b634ef0d003184d6988d96c34ab3c50de59 Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:03 +0200
Subject: selftests/bpf: Add missing section name tests for
 getpeername/getsockname

These were missed when these hooks were first added so add them now
instead to make sure every sockaddr hook has a matching section name
test.

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-2-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/section_names.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 8b571890c57e..fc5248e94a01 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -158,6 +158,26 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT},
 		{0, BPF_CGROUP_SETSOCKOPT},
 	},
+	{
+		"cgroup/getpeername4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME},
+		{0, BPF_CGROUP_INET4_GETPEERNAME},
+	},
+	{
+		"cgroup/getpeername6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME},
+		{0, BPF_CGROUP_INET6_GETPEERNAME},
+	},
+	{
+		"cgroup/getsockname4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME},
+		{0, BPF_CGROUP_INET4_GETSOCKNAME},
+	},
+	{
+		"cgroup/getsockname6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME},
+		{0, BPF_CGROUP_INET6_GETSOCKNAME},
+	},
 };
 
 static void test_prog_type_by_name(const struct sec_name_test *test)
-- 
cgit v1.2.3


From cb7fb0aa3cd80c6bf13abd1d4a75b0640c2e7eaf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Oct 2023 13:27:14 -0700
Subject: tools: ynl: use ynl-gen -o instead of stdout in Makefile

Jiri added more careful handling of output of the code generator
to avoid wiping out existing files in
commit f65f305ae008 ("tools: ynl-gen: use temporary file for rendering")
Make use of the -o option in the Makefiles, it is already used
by ynl-regen.sh.

Link: https://lore.kernel.org/r/20231010202714.4045168-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/generated/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile
index 0f359ee3c46a..2f47b9cac757 100644
--- a/tools/net/ynl/generated/Makefile
+++ b/tools/net/ynl/generated/Makefile
@@ -27,11 +27,11 @@ protos.a: $(OBJS)
 
 %-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL)
 	@echo -e "\tGEN $@"
-	@$(TOOL) --mode user --header --spec $< $(YNL_GEN_ARG_$*) > $@
+	@$(TOOL) --mode user --header --spec $< -o $@ $(YNL_GEN_ARG_$*)
 
 %-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL)
 	@echo -e "\tGEN $@"
-	@$(TOOL) --mode user --source --spec $< $(YNL_GEN_ARG_$*) > $@
+	@$(TOOL) --mode user --source --spec $< -o $@ $(YNL_GEN_ARG_$*)
 
 %-user.o: %-user.c %-user.h
 	@echo -e "\tCC $@"
-- 
cgit v1.2.3


From 859051dd165ec6cc915f0f2114699021144fd249 Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:06 +0200
Subject: bpf: Implement cgroup sockaddr hooks for unix sockets

These hooks allows intercepting connect(), getsockname(),
getpeername(), sendmsg() and recvmsg() for unix sockets. The unix
socket hooks get write access to the address length because the
address length is not fixed when dealing with unix sockets and
needs to be modified when a unix socket address is modified by
the hook. Because abstract socket unix addresses start with a
NUL byte, we cannot recalculate the socket address in kernelspace
after running the hook by calculating the length of the unix socket
path using strlen().

These hooks can be used when users want to multiplex syscall to a
single unix socket to multiple different processes behind the scenes
by redirecting the connect() and other syscalls to process specific
sockets.

We do not implement support for intercepting bind() because when
using bind() with unix sockets with a pathname address, this creates
an inode in the filesystem which must be cleaned up. If we rewrite
the address, the user might try to clean up the wrong file, leaking
the socket in the filesystem where it is never cleaned up. Until we
figure out a solution for this (and a use case for intercepting bind()),
we opt to not allow rewriting the sockaddr in bind() calls.

We also implement recvmsg() support for connected streams so that
after a connect() that is modified by a sockaddr hook, any corresponding
recmvsg() on the connected socket can also be modified to make the
connected program think it is connected to the "intended" remote.

Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/bpf-cgroup-defs.h |  5 +++++
 include/linux/bpf-cgroup.h      | 17 +++++++++++++++++
 include/uapi/linux/bpf.h        | 13 +++++++++----
 kernel/bpf/cgroup.c             | 11 +++++++++--
 kernel/bpf/syscall.c            | 15 +++++++++++++++
 kernel/bpf/verifier.c           |  5 ++++-
 net/core/filter.c               | 14 ++++++++++++--
 net/unix/af_unix.c              | 35 ++++++++++++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h  | 13 +++++++++----
 9 files changed, 114 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
index 7b121bd780eb..0985221d5478 100644
--- a/include/linux/bpf-cgroup-defs.h
+++ b/include/linux/bpf-cgroup-defs.h
@@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type {
 	CGROUP_INET6_BIND,
 	CGROUP_INET4_CONNECT,
 	CGROUP_INET6_CONNECT,
+	CGROUP_UNIX_CONNECT,
 	CGROUP_INET4_POST_BIND,
 	CGROUP_INET6_POST_BIND,
 	CGROUP_UDP4_SENDMSG,
 	CGROUP_UDP6_SENDMSG,
+	CGROUP_UNIX_SENDMSG,
 	CGROUP_SYSCTL,
 	CGROUP_UDP4_RECVMSG,
 	CGROUP_UDP6_RECVMSG,
+	CGROUP_UNIX_RECVMSG,
 	CGROUP_GETSOCKOPT,
 	CGROUP_SETSOCKOPT,
 	CGROUP_INET4_GETPEERNAME,
 	CGROUP_INET6_GETPEERNAME,
+	CGROUP_UNIX_GETPEERNAME,
 	CGROUP_INET4_GETSOCKNAME,
 	CGROUP_INET6_GETSOCKNAME,
+	CGROUP_UNIX_GETSOCKNAME,
 	CGROUP_INET_SOCK_RELEASE,
 	CGROUP_LSM_START,
 	CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1,
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 31561e789715..98b8cea904fe 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 	CGROUP_ATYPE(CGROUP_INET6_BIND);
 	CGROUP_ATYPE(CGROUP_INET4_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET6_CONNECT);
+	CGROUP_ATYPE(CGROUP_UNIX_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET4_POST_BIND);
 	CGROUP_ATYPE(CGROUP_INET6_POST_BIND);
 	CGROUP_ATYPE(CGROUP_UDP4_SENDMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_SENDMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_SENDMSG);
 	CGROUP_ATYPE(CGROUP_SYSCTL);
 	CGROUP_ATYPE(CGROUP_UDP4_RECVMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_RECVMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_RECVMSG);
 	CGROUP_ATYPE(CGROUP_GETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_SETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE);
 	default:
 		return CGROUP_BPF_ATTACH_TYPE_INVALID;
@@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL)
+
 #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx)
 
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx)
+
 #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL)
 
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL)
 
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL)
+
 /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
  * fullsock and its parent fullsock cannot be traced by
  * sk_to_full_sk().
@@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e0aa457f94a9..7ba61b75bc0e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1047,6 +1047,11 @@ enum bpf_attach_type {
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
 	BPF_TRACE_UPROBE_MULTI,
+	BPF_CGROUP_UNIX_CONNECT,
+	BPF_CGROUP_UNIX_SENDMSG,
+	BPF_CGROUP_UNIX_RECVMSG,
+	BPF_CGROUP_UNIX_GETPEERNAME,
+	BPF_CGROUP_UNIX_GETSOCKNAME,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -2704,8 +2709,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
@@ -2943,8 +2948,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the same set of *optname*\ s that is supported by
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac37bd53aee0..74ad2215e1ba 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  * @flags: Pointer to u32 which contains higher bits of BPF program
  *         return value (OR'ed together).
  *
- * socket is expected to be of type INET or INET6.
+ * socket is expected to be of type INET, INET6 or UNIX.
  *
  * This function will return %-EPERM if an attached program is found and
  * returned value != 1 during execution. In all other cases, 0 is returned.
@@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	/* Check socket family since not all sockets represent network
 	 * endpoint (e.g. AF_UNIX).
 	 */
-	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 &&
+	    sk->sk_family != AF_UNIX)
 		return 0;
 
 	if (!ctx.uaddr) {
@@ -2533,10 +2534,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_SOCK_OPS:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return NULL;
 		default:
 			return &bpf_get_retval_proto;
@@ -2548,10 +2552,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_SOCK_OPS:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return NULL;
 		default:
 			return &bpf_set_retval_proto;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6b5280f14a53..8677837f3deb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2446,14 +2446,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 			return 0;
 		default:
 			return -EINVAL;
@@ -3678,14 +3683,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_UNIX_CONNECT:
 	case BPF_CGROUP_INET4_GETPEERNAME:
 	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_UNIX_GETPEERNAME:
 	case BPF_CGROUP_INET4_GETSOCKNAME:
 	case BPF_CGROUP_INET6_GETSOCKNAME:
+	case BPF_CGROUP_UNIX_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UNIX_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
 	case BPF_CGROUP_UDP6_RECVMSG:
+	case BPF_CGROUP_UNIX_RECVMSG:
 		return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 	case BPF_CGROUP_SOCK_OPS:
 		return BPF_PROG_TYPE_SOCK_OPS;
@@ -3942,14 +3952,19 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET6_POST_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_UNIX_CONNECT:
 	case BPF_CGROUP_INET4_GETPEERNAME:
 	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_UNIX_GETPEERNAME:
 	case BPF_CGROUP_INET4_GETSOCKNAME:
 	case BPF_CGROUP_INET6_GETSOCKNAME:
+	case BPF_CGROUP_UNIX_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UNIX_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
 	case BPF_CGROUP_UDP6_RECVMSG:
+	case BPF_CGROUP_UNIX_RECVMSG:
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 	case BPF_CGROUP_SYSCTL:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eed7350e15f4..e777f50401b6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -14797,10 +14797,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
 		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
-		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
 			range = tnum_range(1, 1);
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
 		    env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
diff --git a/net/core/filter.c b/net/core/filter.c
index ff0bd9f20b95..cc2e4babc85f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7875,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_setsockopt_proto;
 		default:
 			return NULL;
@@ -7893,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UNIX_CONNECT:
 		case BPF_CGROUP_UDP4_RECVMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_UNIX_RECVMSG:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UNIX_SENDMSG:
 		case BPF_CGROUP_INET4_GETPEERNAME:
 		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_UNIX_GETPEERNAME:
 		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_INET6_GETSOCKNAME:
+		case BPF_CGROUP_UNIX_GETSOCKNAME:
 			return &bpf_sock_addr_getsockopt_proto;
 		default:
 			return NULL;
@@ -8948,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size,
 	if (off % size != 0)
 		return false;
 
-	/* Disallow access to IPv6 fields from IPv4 contex and vise
-	 * versa.
+	/* Disallow access to fields not belonging to the attach type's address
+	 * family.
 	 */
 	switch (off) {
 	case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3e8a04a13668..e10d07c76044 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -116,6 +116,7 @@
 #include <linux/freezer.h>
 #include <linux/file.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf-cgroup.h>
 
 #include "scm.h"
 
@@ -1381,6 +1382,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
+		err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen);
+		if (err)
+			goto out;
+
 		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
 		    !unix_sk(sk)->addr) {
@@ -1490,6 +1495,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	if (err)
 		goto out;
 
+	err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len);
+	if (err)
+		goto out;
+
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
 		err = unix_autobind(sk);
@@ -1770,6 +1779,13 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	} else {
 		err = addr->len;
 		memcpy(sunaddr, addr->name, addr->len);
+
+		if (peer)
+			BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err,
+					       CGROUP_UNIX_GETPEERNAME);
+		else
+			BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err,
+					       CGROUP_UNIX_GETSOCKNAME);
 	}
 	sock_put(sk);
 out:
@@ -1922,6 +1938,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 		err = unix_validate_addr(sunaddr, msg->msg_namelen);
 		if (err)
 			goto out;
+
+		err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk,
+							    msg->msg_name,
+							    &msg->msg_namelen,
+							    NULL);
+		if (err)
+			goto out;
 	} else {
 		sunaddr = NULL;
 		err = -ENOTCONN;
@@ -2390,9 +2413,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
 						EPOLLOUT | EPOLLWRNORM |
 						EPOLLWRBAND);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
 		unix_copy_addr(msg, skb->sk);
 
+		BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk,
+						      msg->msg_name,
+						      &msg->msg_namelen);
+	}
+
 	if (size > skb->len - skip)
 		size = skb->len - skip;
 	else if (size < skb->len - skip)
@@ -2744,6 +2772,11 @@ unlock:
 			DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr,
 					 state->msg->msg_name);
 			unix_copy_addr(state->msg, skb->sk);
+
+			BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk,
+							      state->msg->msg_name,
+							      &state->msg->msg_namelen);
+
 			sunaddr = NULL;
 		}
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0aa457f94a9..7ba61b75bc0e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1047,6 +1047,11 @@ enum bpf_attach_type {
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
 	BPF_TRACE_UPROBE_MULTI,
+	BPF_CGROUP_UNIX_CONNECT,
+	BPF_CGROUP_UNIX_SENDMSG,
+	BPF_CGROUP_UNIX_RECVMSG,
+	BPF_CGROUP_UNIX_GETPEERNAME,
+	BPF_CGROUP_UNIX_GETSOCKNAME,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -2704,8 +2709,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
@@ -2943,8 +2948,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the same set of *optname*\ s that is supported by
-- 
cgit v1.2.3


From bf90438c78df885c17a3474276ed39abb4a7c026 Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:07 +0200
Subject: libbpf: Add support for cgroup unix socket address hooks

Add the necessary plumbing to hook up the new cgroup unix sockaddr
hooks into libbpf.

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-6-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/lib/bpf/libbpf.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 31b8b252e614..a295f6acf98f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -82,17 +82,22 @@ static const char * const attach_type_name[] = {
 	[BPF_CGROUP_INET6_BIND]		= "cgroup_inet6_bind",
 	[BPF_CGROUP_INET4_CONNECT]	= "cgroup_inet4_connect",
 	[BPF_CGROUP_INET6_CONNECT]	= "cgroup_inet6_connect",
+	[BPF_CGROUP_UNIX_CONNECT]       = "cgroup_unix_connect",
 	[BPF_CGROUP_INET4_POST_BIND]	= "cgroup_inet4_post_bind",
 	[BPF_CGROUP_INET6_POST_BIND]	= "cgroup_inet6_post_bind",
 	[BPF_CGROUP_INET4_GETPEERNAME]	= "cgroup_inet4_getpeername",
 	[BPF_CGROUP_INET6_GETPEERNAME]	= "cgroup_inet6_getpeername",
+	[BPF_CGROUP_UNIX_GETPEERNAME]	= "cgroup_unix_getpeername",
 	[BPF_CGROUP_INET4_GETSOCKNAME]	= "cgroup_inet4_getsockname",
 	[BPF_CGROUP_INET6_GETSOCKNAME]	= "cgroup_inet6_getsockname",
+	[BPF_CGROUP_UNIX_GETSOCKNAME]	= "cgroup_unix_getsockname",
 	[BPF_CGROUP_UDP4_SENDMSG]	= "cgroup_udp4_sendmsg",
 	[BPF_CGROUP_UDP6_SENDMSG]	= "cgroup_udp6_sendmsg",
+	[BPF_CGROUP_UNIX_SENDMSG]	= "cgroup_unix_sendmsg",
 	[BPF_CGROUP_SYSCTL]		= "cgroup_sysctl",
 	[BPF_CGROUP_UDP4_RECVMSG]	= "cgroup_udp4_recvmsg",
 	[BPF_CGROUP_UDP6_RECVMSG]	= "cgroup_udp6_recvmsg",
+	[BPF_CGROUP_UNIX_RECVMSG]	= "cgroup_unix_recvmsg",
 	[BPF_CGROUP_GETSOCKOPT]		= "cgroup_getsockopt",
 	[BPF_CGROUP_SETSOCKOPT]		= "cgroup_setsockopt",
 	[BPF_SK_SKB_STREAM_PARSER]	= "sk_skb_stream_parser",
@@ -8960,14 +8965,19 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("cgroup/bind6",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/connect4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/connect6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/connect_unix",	CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_CONNECT, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/sendmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/sendmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sendmsg_unix",	CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_SENDMSG, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/recvmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/recvmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/recvmsg_unix",	CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_RECVMSG, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/getpeername4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/getpeername6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getpeername_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETPEERNAME, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/getsockname4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/getsockname6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getsockname_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETSOCKNAME, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/sysctl",	CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
-- 
cgit v1.2.3


From 8b3cba987e6d9464bb533d957de923f891b57bf8 Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:08 +0200
Subject: bpftool: Add support for cgroup unix socket address hooks

Add the necessary plumbing to hook up the new cgroup unix sockaddr
hooks into bpftool.

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/r/20231011185113.140426-7-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 16 +++++++++++++---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst   |  8 +++++---
 tools/bpf/bpftool/bash-completion/bpftool          | 14 +++++++-------
 tools/bpf/bpftool/cgroup.c                         | 16 +++++++++-------
 tools/bpf/bpftool/prog.c                           |  7 ++++---
 5 files changed, 38 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index bd015ec9847b..2ce900f66d6e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -36,11 +36,14 @@ CGROUP COMMANDS
 |		**cgroup_device** | **cgroup_inet4_bind** | **cgroup_inet6_bind** |
 |		**cgroup_inet4_post_bind** | **cgroup_inet6_post_bind** |
 |		**cgroup_inet4_connect** | **cgroup_inet6_connect** |
-|		**cgroup_inet4_getpeername** | **cgroup_inet6_getpeername** |
+|		**cgroup_unix_connect** | **cgroup_inet4_getpeername** |
+|		**cgroup_inet6_getpeername** | **cgroup_unix_getpeername** |
 |		**cgroup_inet4_getsockname** | **cgroup_inet6_getsockname** |
-|		**cgroup_udp4_sendmsg** | **cgroup_udp6_sendmsg** |
+|		**cgroup_unix_getsockname** | **cgroup_udp4_sendmsg** |
+|		**cgroup_udp6_sendmsg** | **cgroup_unix_sendmsg** |
 |		**cgroup_udp4_recvmsg** | **cgroup_udp6_recvmsg** |
-|		**cgroup_sysctl** | **cgroup_getsockopt** | **cgroup_setsockopt** |
+|		**cgroup_unix_recvmsg** | **cgroup_sysctl** |
+|		**cgroup_getsockopt** | **cgroup_setsockopt** |
 |		**cgroup_inet_sock_release** }
 |	*ATTACH_FLAGS* := { **multi** | **override** }
 
@@ -102,21 +105,28 @@ DESCRIPTION
 		  **post_bind6** return from bind(2) for an inet6 socket (since 4.17);
 		  **connect4** call to connect(2) for an inet4 socket (since 4.17);
 		  **connect6** call to connect(2) for an inet6 socket (since 4.17);
+		  **connect_unix** call to connect(2) for a unix socket (since 6.7);
 		  **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an
 		  unconnected udp4 socket (since 4.18);
 		  **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an
 		  unconnected udp6 socket (since 4.18);
+		  **sendmsg_unix** call to sendto(2), sendmsg(2), sendmmsg(2) for
+		  an unconnected unix socket (since 6.7);
 		  **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
 		  an unconnected udp4 socket (since 5.2);
 		  **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
 		  an unconnected udp6 socket (since 5.2);
+		  **recvmsg_unix** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
+		  an unconnected unix socket (since 6.7);
 		  **sysctl** sysctl access (since 5.2);
 		  **getsockopt** call to getsockopt (since 5.3);
 		  **setsockopt** call to setsockopt (since 5.3);
 		  **getpeername4** call to getpeername(2) for an inet4 socket (since 5.8);
 		  **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8);
+		  **getpeername_unix** call to getpeername(2) for a unix socket (since 6.7);
 		  **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8);
 		  **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8).
+		  **getsockname_unix** call to getsockname(2) for a unix socket (since 6.7);
 		  **sock_release** closing an userspace inet socket (since 5.9).
 
 	**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index dcae81bd27ed..58e6a5b10ef7 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -47,9 +47,11 @@ PROG COMMANDS
 |		**cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
 |		**lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
-|		**cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** |
-|               **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
-|		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** |
+|		**cgroup/connect4** | **cgroup/connect6** | **cgroup/connect_unix** |
+|		**cgroup/getpeername4** | **cgroup/getpeername6** | **cgroup/getpeername_unix** |
+|		**cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/getsockname_unix** |
+|		**cgroup/sendmsg4** | **cgroup/sendmsg6** | **cgroup/sendmsg_unix** |
+|		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/recvmsg_unix** | **cgroup/sysctl** |
 |		**cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** |
 |		**struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup**
 |	}
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 085bf18f3659..6e4f7ce6bc01 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -480,13 +480,13 @@ _bpftool()
                                 action tracepoint raw_tracepoint \
                                 xdp perf_event cgroup/skb cgroup/sock \
                                 cgroup/dev lwt_in lwt_out lwt_xmit \
-                                lwt_seg6local sockops sk_skb sk_msg \
-                                lirc_mode2 cgroup/bind4 cgroup/bind6 \
-                                cgroup/connect4 cgroup/connect6 \
-                                cgroup/getpeername4 cgroup/getpeername6 \
-                                cgroup/getsockname4 cgroup/getsockname6 \
-                                cgroup/sendmsg4 cgroup/sendmsg6 \
-                                cgroup/recvmsg4 cgroup/recvmsg6 \
+                                lwt_seg6local sockops sk_skb sk_msg lirc_mode2 \
+                                cgroup/bind4 cgroup/bind6 \
+                                cgroup/connect4 cgroup/connect6 cgroup/connect_unix \
+                                cgroup/getpeername4 cgroup/getpeername6 cgroup/getpeername_unix \
+                                cgroup/getsockname4 cgroup/getsockname6 cgroup/getsockname_unix \
+                                cgroup/sendmsg4 cgroup/sendmsg6 cgroup/sendmsg_unix \
+                                cgroup/recvmsg4 cgroup/recvmsg6 cgroup/recvmsg_unix \
                                 cgroup/post_bind4 cgroup/post_bind6 \
                                 cgroup/sysctl cgroup/getsockopt \
                                 cgroup/setsockopt cgroup/sock_release struct_ops \
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index ac846b0805b4..af6898c0f388 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -28,13 +28,15 @@
 	"                        cgroup_device | cgroup_inet4_bind |\n" \
 	"                        cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \
 	"                        cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \
-	"                        cgroup_inet6_connect | cgroup_inet4_getpeername |\n" \
-	"                        cgroup_inet6_getpeername | cgroup_inet4_getsockname |\n" \
-	"                        cgroup_inet6_getsockname | cgroup_udp4_sendmsg |\n" \
-	"                        cgroup_udp6_sendmsg | cgroup_udp4_recvmsg |\n" \
-	"                        cgroup_udp6_recvmsg | cgroup_sysctl |\n" \
-	"                        cgroup_getsockopt | cgroup_setsockopt |\n" \
-	"                        cgroup_inet_sock_release }"
+	"                        cgroup_inet6_connect | cgroup_unix_connect |\n" \
+	"                        cgroup_inet4_getpeername | cgroup_inet6_getpeername |\n" \
+	"                        cgroup_unix_getpeername | cgroup_inet4_getsockname |\n" \
+	"                        cgroup_inet6_getsockname | cgroup_unix_getsockname |\n" \
+	"                        cgroup_udp4_sendmsg | cgroup_udp6_sendmsg |\n" \
+	"                        cgroup_unix_sendmsg | cgroup_udp4_recvmsg |\n" \
+	"                        cgroup_udp6_recvmsg | cgroup_unix_recvmsg |\n" \
+	"                        cgroup_sysctl | cgroup_getsockopt |\n" \
+	"                        cgroup_setsockopt | cgroup_inet_sock_release }"
 
 static unsigned int query_flags;
 static struct btf *btf_vmlinux;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 8443a149dd17..7ec4f5671e7a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -2475,9 +2475,10 @@ static int do_help(int argc, char **argv)
 		"                 sk_reuseport | flow_dissector | cgroup/sysctl |\n"
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
-		"                 cgroup/getpeername4 | cgroup/getpeername6 |\n"
-		"                 cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n"
-		"                 cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n"
+		"                 cgroup/connect_unix | cgroup/getpeername4 | cgroup/getpeername6 |\n"
+		"                 cgroup/getpeername_unix | cgroup/getsockname4 | cgroup/getsockname6 |\n"
+		"                 cgroup/getsockname_unix | cgroup/sendmsg4 | cgroup/sendmsg6 |\n"
+		"                 cgroup/sendmsg°unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n"
 		"                 cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n"
 		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
 		"       ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n"
-- 
cgit v1.2.3


From af2752ed450e71fc0bd596d0b4b9b805a64ae2c1 Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:10 +0200
Subject: selftests/bpf: Make sure mount directory exists

The mount directory for the selftests cgroup tree might
not exist so let's make sure it does exist by creating
it ourselves if it doesn't exist.

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-9-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/cgroup_helpers.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 24ba56d42f2d..5b1da2a32ea7 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -199,6 +199,11 @@ int setup_cgroup_environment(void)
 
 	format_cgroup_path(cgroup_workdir, "");
 
+	if (mkdir(CGROUP_MOUNT_PATH, 0777) && errno != EEXIST) {
+		log_err("mkdir mount");
+		return 1;
+	}
+
 	if (unshare(CLONE_NEWNS)) {
 		log_err("unshare");
 		return 1;
-- 
cgit v1.2.3


From 82ab6b505e8199cc4537f00025a7391973c3847e Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Wed, 11 Oct 2023 20:51:11 +0200
Subject: selftests/bpf: Add tests for cgroup unix socket address hooks

These selftests are written in prog_tests style instead of adding
them to the existing test_sock_addr tests. Migrating the existing
sock addr tests to prog_tests style is left for future work. This
commit adds support for testing bind() sockaddr hooks, even though
there's no unix socket sockaddr hook for bind(). We leave this code
intact for when the INET and INET6 tests are migrated in the future
which do support intercepting bind().

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-10-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/bpf_kfuncs.h           |  14 +
 tools/testing/selftests/bpf/network_helpers.c      |  34 ++
 tools/testing/selftests/bpf/network_helpers.h      |   1 +
 .../selftests/bpf/prog_tests/section_names.c       |  25 +
 tools/testing/selftests/bpf/prog_tests/sock_addr.c | 612 +++++++++++++++++++++
 .../selftests/bpf/progs/connect_unix_prog.c        |  40 ++
 .../selftests/bpf/progs/getpeername_unix_prog.c    |  39 ++
 .../selftests/bpf/progs/getsockname_unix_prog.c    |  39 ++
 .../selftests/bpf/progs/recvmsg_unix_prog.c        |  39 ++
 .../selftests/bpf/progs/sendmsg_unix_prog.c        |  40 ++
 10 files changed, 883 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/sock_addr.c
 create mode 100644 tools/testing/selftests/bpf/progs/connect_unix_prog.c
 create mode 100644 tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
 create mode 100644 tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
 create mode 100644 tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
 create mode 100644 tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 642dda0e758a..5ca68ff0b59f 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -1,6 +1,8 @@
 #ifndef __BPF_KFUNCS__
 #define __BPF_KFUNCS__
 
+struct bpf_sock_addr_kern;
+
 /* Description
  *  Initializes an skb-type dynptr
  * Returns
@@ -41,4 +43,16 @@ extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym;
 extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym;
 extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym;
 
+/* Description
+ *  Modify the address of a AF_UNIX sockaddr.
+ * Returns__bpf_kfunc
+ *  -EINVAL if the address size is too big or, 0 if the sockaddr was successfully modified.
+ */
+extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
+				      const __u8 *sun_path, __u32 sun_path__sz) __ksym;
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+
+void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym;
+
 #endif
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index da72a3a66230..6db27a9088e9 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -11,6 +11,7 @@
 #include <arpa/inet.h>
 #include <sys/mount.h>
 #include <sys/stat.h>
+#include <sys/un.h>
 
 #include <linux/err.h>
 #include <linux/in.h>
@@ -257,6 +258,26 @@ static int connect_fd_to_addr(int fd,
 	return 0;
 }
 
+int connect_to_addr(const struct sockaddr_storage *addr, socklen_t addrlen, int type)
+{
+	int fd;
+
+	fd = socket(addr->ss_family, type, 0);
+	if (fd < 0) {
+		log_err("Failed to create client socket");
+		return -1;
+	}
+
+	if (connect_fd_to_addr(fd, addr, addrlen, false))
+		goto error_close;
+
+	return fd;
+
+error_close:
+	save_errno_close(fd);
+	return -1;
+}
+
 static const struct network_helper_opts default_opts;
 
 int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
@@ -380,6 +401,19 @@ int make_sockaddr(int family, const char *addr_str, __u16 port,
 		if (len)
 			*len = sizeof(*sin6);
 		return 0;
+	} else if (family == AF_UNIX) {
+		/* Note that we always use abstract unix sockets to avoid having
+		 * to clean up leftover files.
+		 */
+		struct sockaddr_un *sun = (void *)addr;
+
+		memset(addr, 0, sizeof(*sun));
+		sun->sun_family = family;
+		sun->sun_path[0] = 0;
+		strcpy(sun->sun_path + 1, addr_str);
+		if (len)
+			*len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str);
+		return 0;
 	}
 	return -1;
 }
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 5eccc67d1a99..34f1200a781b 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -51,6 +51,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 			    __u16 port, int timeout_ms,
 			    unsigned int nr_listens);
 void free_fds(int *fds, unsigned int nr_close_fds);
+int connect_to_addr(const struct sockaddr_storage *addr, socklen_t len, int type);
 int connect_to_fd(int server_fd, int timeout_ms);
 int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index fc5248e94a01..c3d78846f31a 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -123,6 +123,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT},
 		{0, BPF_CGROUP_INET6_CONNECT},
 	},
+	{
+		"cgroup/connect_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_CONNECT},
+		{0, BPF_CGROUP_UNIX_CONNECT},
+	},
 	{
 		"cgroup/sendmsg4",
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG},
@@ -133,6 +138,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG},
 		{0, BPF_CGROUP_UDP6_SENDMSG},
 	},
+	{
+		"cgroup/sendmsg_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_SENDMSG},
+		{0, BPF_CGROUP_UNIX_SENDMSG},
+	},
 	{
 		"cgroup/recvmsg4",
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG},
@@ -143,6 +153,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG},
 		{0, BPF_CGROUP_UDP6_RECVMSG},
 	},
+	{
+		"cgroup/recvmsg_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_RECVMSG},
+		{0, BPF_CGROUP_UNIX_RECVMSG},
+	},
 	{
 		"cgroup/sysctl",
 		{0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL},
@@ -168,6 +183,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME},
 		{0, BPF_CGROUP_INET6_GETPEERNAME},
 	},
+	{
+		"cgroup/getpeername_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETPEERNAME},
+		{0, BPF_CGROUP_UNIX_GETPEERNAME},
+	},
 	{
 		"cgroup/getsockname4",
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME},
@@ -178,6 +198,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME},
 		{0, BPF_CGROUP_INET6_GETSOCKNAME},
 	},
+	{
+		"cgroup/getsockname_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETSOCKNAME},
+		{0, BPF_CGROUP_UNIX_GETSOCKNAME},
+	},
 };
 
 static void test_prog_type_by_name(const struct sec_name_test *test)
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_addr.c b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
new file mode 100644
index 000000000000..5fd617718991
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
@@ -0,0 +1,612 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/un.h>
+
+#include "test_progs.h"
+
+#include "connect_unix_prog.skel.h"
+#include "sendmsg_unix_prog.skel.h"
+#include "recvmsg_unix_prog.skel.h"
+#include "getsockname_unix_prog.skel.h"
+#include "getpeername_unix_prog.skel.h"
+#include "network_helpers.h"
+
+#define SERVUN_ADDRESS         "bpf_cgroup_unix_test"
+#define SERVUN_REWRITE_ADDRESS "bpf_cgroup_unix_test_rewrite"
+#define SRCUN_ADDRESS	       "bpf_cgroup_unix_test_src"
+
+enum sock_addr_test_type {
+	SOCK_ADDR_TEST_BIND,
+	SOCK_ADDR_TEST_CONNECT,
+	SOCK_ADDR_TEST_SENDMSG,
+	SOCK_ADDR_TEST_RECVMSG,
+	SOCK_ADDR_TEST_GETSOCKNAME,
+	SOCK_ADDR_TEST_GETPEERNAME,
+};
+
+typedef void *(*load_fn)(int cgroup_fd);
+typedef void (*destroy_fn)(void *skel);
+
+struct sock_addr_test {
+	enum sock_addr_test_type type;
+	const char *name;
+	/* BPF prog properties */
+	load_fn loadfn;
+	destroy_fn destroyfn;
+	/* Socket properties */
+	int socket_family;
+	int socket_type;
+	/* IP:port pairs for BPF prog to override */
+	const char *requested_addr;
+	unsigned short requested_port;
+	const char *expected_addr;
+	unsigned short expected_port;
+	const char *expected_src_addr;
+};
+
+static void *connect_unix_prog_load(int cgroup_fd)
+{
+	struct connect_unix_prog *skel;
+
+	skel = connect_unix_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->links.connect_unix_prog = bpf_program__attach_cgroup(
+		skel->progs.connect_unix_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.connect_unix_prog, "prog_attach"))
+		goto cleanup;
+
+	return skel;
+cleanup:
+	connect_unix_prog__destroy(skel);
+	return NULL;
+}
+
+static void connect_unix_prog_destroy(void *skel)
+{
+	connect_unix_prog__destroy(skel);
+}
+
+static void *sendmsg_unix_prog_load(int cgroup_fd)
+{
+	struct sendmsg_unix_prog *skel;
+
+	skel = sendmsg_unix_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->links.sendmsg_unix_prog = bpf_program__attach_cgroup(
+		skel->progs.sendmsg_unix_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.sendmsg_unix_prog, "prog_attach"))
+		goto cleanup;
+
+	return skel;
+cleanup:
+	sendmsg_unix_prog__destroy(skel);
+	return NULL;
+}
+
+static void sendmsg_unix_prog_destroy(void *skel)
+{
+	sendmsg_unix_prog__destroy(skel);
+}
+
+static void *recvmsg_unix_prog_load(int cgroup_fd)
+{
+	struct recvmsg_unix_prog *skel;
+
+	skel = recvmsg_unix_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->links.recvmsg_unix_prog = bpf_program__attach_cgroup(
+		skel->progs.recvmsg_unix_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.recvmsg_unix_prog, "prog_attach"))
+		goto cleanup;
+
+	return skel;
+cleanup:
+	recvmsg_unix_prog__destroy(skel);
+	return NULL;
+}
+
+static void recvmsg_unix_prog_destroy(void *skel)
+{
+	recvmsg_unix_prog__destroy(skel);
+}
+
+static void *getsockname_unix_prog_load(int cgroup_fd)
+{
+	struct getsockname_unix_prog *skel;
+
+	skel = getsockname_unix_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->links.getsockname_unix_prog = bpf_program__attach_cgroup(
+		skel->progs.getsockname_unix_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.getsockname_unix_prog, "prog_attach"))
+		goto cleanup;
+
+	return skel;
+cleanup:
+	getsockname_unix_prog__destroy(skel);
+	return NULL;
+}
+
+static void getsockname_unix_prog_destroy(void *skel)
+{
+	getsockname_unix_prog__destroy(skel);
+}
+
+static void *getpeername_unix_prog_load(int cgroup_fd)
+{
+	struct getpeername_unix_prog *skel;
+
+	skel = getpeername_unix_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->links.getpeername_unix_prog = bpf_program__attach_cgroup(
+		skel->progs.getpeername_unix_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.getpeername_unix_prog, "prog_attach"))
+		goto cleanup;
+
+	return skel;
+cleanup:
+	getpeername_unix_prog__destroy(skel);
+	return NULL;
+}
+
+static void getpeername_unix_prog_destroy(void *skel)
+{
+	getpeername_unix_prog__destroy(skel);
+}
+
+static struct sock_addr_test tests[] = {
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix",
+		connect_unix_prog_load,
+		connect_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix",
+		sendmsg_unix_prog_load,
+		sendmsg_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg_unix-dgram",
+		recvmsg_unix_prog_load,
+		recvmsg_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_ADDRESS,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg_unix-stream",
+		recvmsg_unix_prog_load,
+		recvmsg_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_ADDRESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname_unix",
+		getsockname_unix_prog_load,
+		getsockname_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername_unix",
+		getpeername_unix_prog_load,
+		getpeername_unix_prog_destroy,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+	},
+};
+
+typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
+
+static int cmp_addr(const struct sockaddr_storage *addr1, socklen_t addr1_len,
+		    const struct sockaddr_storage *addr2, socklen_t addr2_len,
+		    bool cmp_port)
+{
+	const struct sockaddr_in *four1, *four2;
+	const struct sockaddr_in6 *six1, *six2;
+	const struct sockaddr_un *un1, *un2;
+
+	if (addr1->ss_family != addr2->ss_family)
+		return -1;
+
+	if (addr1_len != addr2_len)
+		return -1;
+
+	if (addr1->ss_family == AF_INET) {
+		four1 = (const struct sockaddr_in *)addr1;
+		four2 = (const struct sockaddr_in *)addr2;
+		return !((four1->sin_port == four2->sin_port || !cmp_port) &&
+			 four1->sin_addr.s_addr == four2->sin_addr.s_addr);
+	} else if (addr1->ss_family == AF_INET6) {
+		six1 = (const struct sockaddr_in6 *)addr1;
+		six2 = (const struct sockaddr_in6 *)addr2;
+		return !((six1->sin6_port == six2->sin6_port || !cmp_port) &&
+			 !memcmp(&six1->sin6_addr, &six2->sin6_addr,
+				 sizeof(struct in6_addr)));
+	} else if (addr1->ss_family == AF_UNIX) {
+		un1 = (const struct sockaddr_un *)addr1;
+		un2 = (const struct sockaddr_un *)addr2;
+		return memcmp(un1, un2, addr1_len);
+	}
+
+	return -1;
+}
+
+static int cmp_sock_addr(info_fn fn, int sock1,
+			 const struct sockaddr_storage *addr2,
+			 socklen_t addr2_len, bool cmp_port)
+{
+	struct sockaddr_storage addr1;
+	socklen_t len1 = sizeof(addr1);
+
+	memset(&addr1, 0, len1);
+	if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0)
+		return -1;
+
+	return cmp_addr(&addr1, len1, addr2, addr2_len, cmp_port);
+}
+
+static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2,
+			  socklen_t addr2_len, bool cmp_port)
+{
+	return cmp_sock_addr(getsockname, sock1, addr2, addr2_len, cmp_port);
+}
+
+static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2,
+			 socklen_t addr2_len, bool cmp_port)
+{
+	return cmp_sock_addr(getpeername, sock1, addr2, addr2_len, cmp_port);
+}
+
+static void test_bind(struct sock_addr_test *test)
+{
+	struct sockaddr_storage expected_addr;
+	socklen_t expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->requested_addr, test->requested_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family,
+			    test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_local_addr(serv, &expected_addr, expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+		goto cleanup;
+
+	/* Try to connect to server just in case */
+	client = connect_to_addr(&expected_addr, expected_addr_len, test->socket_type);
+	if (!ASSERT_GE(client, 0, "connect_to_addr"))
+		goto cleanup;
+
+cleanup:
+	if (client != -1)
+		close(client);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_connect(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, expected_addr, expected_src_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  expected_addr_len = sizeof(struct sockaddr_storage),
+		  expected_src_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->expected_addr, test->expected_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	client = connect_to_addr(&addr, addr_len, test->socket_type);
+	if (!ASSERT_GE(client, 0, "connect_to_addr"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	if (test->expected_src_addr) {
+		err = make_sockaddr(test->socket_family, test->expected_src_addr, 0,
+				    &expected_src_addr, &expected_src_addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+	}
+
+	err = cmp_peer_addr(client, &expected_addr, expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_peer_addr"))
+		goto cleanup;
+
+	if (test->expected_src_addr) {
+		err = cmp_local_addr(client, &expected_src_addr, expected_src_addr_len, false);
+		if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+			goto cleanup;
+	}
+cleanup:
+	if (client != -1)
+		close(client);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_xmsg(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, src_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  src_addr_len = sizeof(struct sockaddr_storage);
+	struct msghdr hdr;
+	struct iovec iov;
+	char data = 'a';
+	int serv = -1, client = -1, err;
+
+	/* Unlike the other tests, here we test that we can rewrite the src addr
+	 * with a recvmsg() hook.
+	 */
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->expected_addr, test->expected_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	client = socket(test->socket_family, test->socket_type, 0);
+	if (!ASSERT_GE(client, 0, "socket"))
+		goto cleanup;
+
+	/* AF_UNIX sockets have to be bound to something to trigger the recvmsg bpf program. */
+	if (test->socket_family == AF_UNIX) {
+		err = make_sockaddr(AF_UNIX, SRCUN_ADDRESS, 0, &src_addr, &src_addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+
+		err = bind(client, (const struct sockaddr *) &src_addr, src_addr_len);
+		if (!ASSERT_OK(err, "bind"))
+			goto cleanup;
+	}
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	if (test->socket_type == SOCK_DGRAM) {
+		memset(&iov, 0, sizeof(iov));
+		iov.iov_base = &data;
+		iov.iov_len = sizeof(data);
+
+		memset(&hdr, 0, sizeof(hdr));
+		hdr.msg_name = (void *)&addr;
+		hdr.msg_namelen = addr_len;
+		hdr.msg_iov = &iov;
+		hdr.msg_iovlen = 1;
+
+		err = sendmsg(client, &hdr, 0);
+		if (!ASSERT_EQ(err, sizeof(data), "sendmsg"))
+			goto cleanup;
+	} else {
+		/* Testing with connection-oriented sockets is only valid for
+		 * recvmsg() tests.
+		 */
+		if (!ASSERT_EQ(test->type, SOCK_ADDR_TEST_RECVMSG, "recvmsg"))
+			goto cleanup;
+
+		err = connect(client, (const struct sockaddr *)&addr, addr_len);
+		if (!ASSERT_OK(err, "connect"))
+			goto cleanup;
+
+		err = send(client, &data, sizeof(data), 0);
+		if (!ASSERT_EQ(err, sizeof(data), "send"))
+			goto cleanup;
+
+		err = listen(serv, 0);
+		if (!ASSERT_OK(err, "listen"))
+			goto cleanup;
+
+		err = accept(serv, NULL, NULL);
+		if (!ASSERT_GE(err, 0, "accept"))
+			goto cleanup;
+
+		close(serv);
+		serv = err;
+	}
+
+	addr_len = src_addr_len = sizeof(struct sockaddr_storage);
+
+	err = recvfrom(serv, &data, sizeof(data), 0, (struct sockaddr *) &src_addr, &src_addr_len);
+	if (!ASSERT_EQ(err, sizeof(data), "recvfrom"))
+		goto cleanup;
+
+	ASSERT_EQ(data, 'a', "data mismatch");
+
+	if (test->expected_src_addr) {
+		err = make_sockaddr(test->socket_family, test->expected_src_addr, 0,
+				    &addr, &addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+
+		err = cmp_addr(&src_addr, src_addr_len, &addr, addr_len, false);
+		if (!ASSERT_EQ(err, 0, "cmp_addr"))
+			goto cleanup;
+	}
+
+cleanup:
+	if (client != -1)
+		close(client);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_getsockname(struct sock_addr_test *test)
+{
+	struct sockaddr_storage expected_addr;
+	socklen_t expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->requested_addr, test->requested_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family,
+			    test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_local_addr(serv, &expected_addr, expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+		goto cleanup;
+
+cleanup:
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_getpeername(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, expected_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->requested_addr, test->requested_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	client = connect_to_addr(&addr, addr_len, test->socket_type);
+	if (!ASSERT_GE(client, 0, "connect_to_addr"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_peer_addr(client, &expected_addr, expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_peer_addr"))
+		goto cleanup;
+
+cleanup:
+	if (client != -1)
+		close(client);
+	if (serv != -1)
+		close(serv);
+}
+
+void test_sock_addr(void)
+{
+	int cgroup_fd = -1;
+	void *skel;
+
+	cgroup_fd = test__join_cgroup("/sock_addr");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		goto cleanup;
+
+	for (size_t i = 0; i < ARRAY_SIZE(tests); ++i) {
+		struct sock_addr_test *test = &tests[i];
+
+		if (!test__start_subtest(test->name))
+			continue;
+
+		skel = test->loadfn(cgroup_fd);
+		if (!skel)
+			continue;
+
+		switch (test->type) {
+		/* Not exercised yet but we leave this code here for when the
+		 * INET and INET6 sockaddr tests are migrated to this file in
+		 * the future.
+		 */
+		case SOCK_ADDR_TEST_BIND:
+			test_bind(test);
+			break;
+		case SOCK_ADDR_TEST_CONNECT:
+			test_connect(test);
+			break;
+		case SOCK_ADDR_TEST_SENDMSG:
+		case SOCK_ADDR_TEST_RECVMSG:
+			test_xmsg(test);
+			break;
+		case SOCK_ADDR_TEST_GETSOCKNAME:
+			test_getsockname(test);
+			break;
+		case SOCK_ADDR_TEST_GETPEERNAME:
+			test_getpeername(test);
+			break;
+		default:
+			ASSERT_TRUE(false, "Unknown sock addr test type");
+			break;
+		}
+
+		test->destroyfn(skel);
+	}
+
+cleanup:
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/connect_unix_prog.c b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
new file mode 100644
index 000000000000..ca8aa2f116b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/connect_unix")
+int connect_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	/* Rewrite destination. */
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 0;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 0;
+
+	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
+						bpf_core_type_id_kernel(struct sockaddr_un));
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 0;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
new file mode 100644
index 000000000000..9c078f34bbb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/getpeername_unix")
+int getpeername_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
+						bpf_core_type_id_kernel(struct sockaddr_un));
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
new file mode 100644
index 000000000000..ac7145111497
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/getsockname_unix")
+int getsockname_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
+						bpf_core_type_id_kernel(struct sockaddr_un));
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
new file mode 100644
index 000000000000..4dfbc8552558
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_ADDRESS[] = "\0bpf_cgroup_unix_test";
+
+SEC("cgroup/recvmsg_unix")
+int recvmsg_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_ADDRESS,
+					 sizeof(SERVUN_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
+						bpf_core_type_id_kernel(struct sockaddr_un));
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_ADDRESS,
+			sizeof(SERVUN_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
new file mode 100644
index 000000000000..1f67e832666e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/sendmsg_unix")
+int sendmsg_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	/* Rewrite destination. */
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 0;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 0;
+
+	sa_kern_unaddr = bpf_rdonly_cast(sa_kern->uaddr,
+						bpf_core_type_id_kernel(struct sockaddr_un));
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 0;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 96eece6933304b09af6849a66f123a00c5a53313 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 9 Oct 2023 13:06:17 +0300
Subject: selftests: Add test cases for FDB flush with VXLAN device

Test all the supported arguments for FDB flush. The test checks
configuration, not traffic. Note that the flag 'offloaded' is not checked
as it is not relevant when there is no hardware.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile     |   1 +
 tools/testing/selftests/net/fdb_flush.sh | 716 +++++++++++++++++++++++++++++++
 2 files changed, 717 insertions(+)
 create mode 100755 tools/testing/selftests/net/fdb_flush.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8b017070960d..61939a695f95 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -89,6 +89,7 @@ TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
+TEST_PROGS += fdb_flush.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh
new file mode 100755
index 000000000000..3050b031f46d
--- /dev/null
+++ b/tools/testing/selftests/net/fdb_flush.sh
@@ -0,0 +1,716 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking functionality of flushing FDB entries.
+# Check that flush works as expected with all the supported arguments and verify
+# some combinations of arguments.
+
+FLUSH_BY_STATE_TESTS="
+	vxlan_test_flush_by_permanent
+	vxlan_test_flush_by_nopermanent
+	vxlan_test_flush_by_static
+	vxlan_test_flush_by_nostatic
+	vxlan_test_flush_by_dynamic
+	vxlan_test_flush_by_nodynamic
+"
+
+FLUSH_BY_FLAG_TESTS="
+	vxlan_test_flush_by_extern_learn
+	vxlan_test_flush_by_noextern_learn
+	vxlan_test_flush_by_router
+	vxlan_test_flush_by_norouter
+"
+
+TESTS="
+	vxlan_test_flush_by_dev
+	vxlan_test_flush_by_vni
+	vxlan_test_flush_by_src_vni
+	vxlan_test_flush_by_port
+	vxlan_test_flush_by_dst_ip
+	vxlan_test_flush_by_nhid
+	$FLUSH_BY_STATE_TESTS
+	$FLUSH_BY_FLAG_TESTS
+	vxlan_test_flush_by_several_args
+	vxlan_test_flush_by_remote_attributes
+"
+
+: ${VERBOSE:=0}
+: ${PAUSE_ON_FAIL:=no}
+: ${PAUSE:=no}
+: ${VXPORT:=4789}
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local rc
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "COMMAND: $cmd\n"
+		stderr=
+	fi
+
+	out=$(eval $cmd $stderr)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	return $rc
+}
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+	local nsuccess
+	local nfail
+	local ret
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "$VERBOSE" = "1" ]; then
+			echo "    rc=$rc, expected $expected"
+		fi
+
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+		echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo
+		echo "hit enter to continue, 'q' to quit"
+		read a
+		[ "$a" = "q" ] && exit 1
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+}
+
+MAC_POOL_1="
+	de:ad:be:ef:13:10
+	de:ad:be:ef:13:11
+	de:ad:be:ef:13:12
+	de:ad:be:ef:13:13
+	de:ad:be:ef:13:14
+"
+mac_pool_1_len=$(echo "$MAC_POOL_1" | grep -c .)
+
+MAC_POOL_2="
+	ca:fe:be:ef:13:10
+	ca:fe:be:ef:13:11
+	ca:fe:be:ef:13:12
+	ca:fe:be:ef:13:13
+	ca:fe:be:ef:13:14
+"
+mac_pool_2_len=$(echo "$MAC_POOL_2" | grep -c .)
+
+fdb_add_mac_pool_1()
+{
+	local dev=$1; shift
+	local args="$@"
+
+	for mac in $MAC_POOL_1
+	do
+		$BRIDGE fdb add $mac dev $dev $args
+	done
+}
+
+fdb_add_mac_pool_2()
+{
+	local dev=$1; shift
+	local args="$@"
+
+	for mac in $MAC_POOL_2
+	do
+		$BRIDGE fdb add $mac dev $dev $args
+	done
+}
+
+fdb_check_n_entries_by_dev_filter()
+{
+	local dev=$1; shift
+	local exp_entries=$1; shift
+	local filter="$@"
+
+	local entries=$($BRIDGE fdb show dev $dev | grep "$filter" | wc -l)
+
+	[[ $entries -eq $exp_entries ]]
+	rc=$?
+
+	log_test $rc 0 "$dev: Expected $exp_entries FDB entries, got $entries"
+	return $rc
+}
+
+vxlan_test_flush_by_dev()
+{
+	local vni=3000
+	local dst_ip=192.0.2.1
+
+	fdb_add_mac_pool_1 vx10 vni $vni dst $dst_ip
+	fdb_add_mac_pool_2 vx20 vni $vni dst $dst_ip
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len
+	fdb_check_n_entries_by_dev_filter vx20 $mac_pool_2_len
+
+	run_cmd "$BRIDGE fdb flush dev vx10"
+	log_test $? 0 "Flush FDB by dev vx10"
+
+	fdb_check_n_entries_by_dev_filter vx10 0
+	log_test $? 0 "Flush FDB by dev vx10 - test vx10 entries"
+
+	fdb_check_n_entries_by_dev_filter vx20 $mac_pool_2_len
+	log_test $? 0 "Flush FDB by dev vx10 - test vx20 entries"
+}
+
+vxlan_test_flush_by_vni()
+{
+	local vni_1=3000
+	local vni_2=4000
+	local dst_ip=192.0.2.1
+
+	fdb_add_mac_pool_1 vx10 vni $vni_1 dst $dst_ip
+	fdb_add_mac_pool_2 vx10 vni $vni_2 dst $dst_ip
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len vni $vni_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len vni $vni_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 vni $vni_2"
+	log_test $? 0 "Flush FDB by dev vx10 and vni $vni_2"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len vni $vni_1
+	log_test $? 0 "Test entries with vni $vni_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 vni $vni_2
+	log_test $? 0 "Test entries with vni $vni_2"
+}
+
+vxlan_test_flush_by_src_vni()
+{
+	# Set some entries with {vni=x,src_vni=y} and some with the opposite -
+	# {vni=y,src_vni=x}, to verify that when we flush by src_vni=x, entries
+	# with vni=x are not flused.
+	local vni_1=3000
+	local vni_2=4000
+	local src_vni_1=4000
+	local src_vni_2=3000
+	local dst_ip=192.0.2.1
+
+	# Reconfigure vx10 with 'external' to get 'src_vni' details in
+	# 'bridge fdb' output
+	$IP link del dev vx10
+	$IP link add name vx10 type vxlan dstport "$VXPORT" external
+
+	fdb_add_mac_pool_1 vx10 vni $vni_1 src_vni $src_vni_1 dst $dst_ip
+	fdb_add_mac_pool_2 vx10 vni $vni_2 src_vni $src_vni_2 dst $dst_ip
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len \
+		src_vni $src_vni_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len \
+		src_vni $src_vni_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 src_vni $src_vni_2"
+	log_test $? 0 "Flush FDB by dev vx10 and src_vni $src_vni_2"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len \
+		src_vni $src_vni_1
+	log_test $? 0 "Test entries with src_vni $src_vni_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 src_vni $src_vni_2
+	log_test $? 0 "Test entries with src_vni $src_vni_2"
+}
+
+vxlan_test_flush_by_port()
+{
+	local port_1=1234
+	local port_2=4321
+	local dst_ip=192.0.2.1
+
+	fdb_add_mac_pool_1 vx10 port $port_1 dst $dst_ip
+	fdb_add_mac_pool_2 vx10 port $port_2 dst $dst_ip
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len port $port_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len port $port_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 port $port_2"
+	log_test $? 0 "Flush FDB by dev vx10 and port $port_2"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len port $port_1
+	log_test $? 0 "Test entries with port $port_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 port $port_2
+	log_test $? 0 "Test entries with port $port_2"
+}
+
+vxlan_test_flush_by_dst_ip()
+{
+	local dst_ip_1=192.0.2.1
+	local dst_ip_2=192.0.2.2
+
+	fdb_add_mac_pool_1 vx10 dst $dst_ip_1
+	fdb_add_mac_pool_2 vx10 dst $dst_ip_2
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len dst $dst_ip_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 dst $dst_ip_2"
+	log_test $? 0 "Flush FDB by dev vx10 and dst $dst_ip_2"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip_1
+	log_test $? 0 "Test entries with dst $dst_ip_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 dst $dst_ip_2
+	log_test $? 0 "Test entries with dst $dst_ip_2"
+}
+
+nexthops_add()
+{
+	local nhid_1=$1; shift
+	local nhid_2=$1; shift
+
+	$IP nexthop add id 10 via 192.0.2.1 fdb
+	$IP nexthop add id $nhid_1 group 10 fdb
+
+	$IP nexthop add id 20 via 192.0.2.2 fdb
+	$IP nexthop add id $nhid_2 group 20 fdb
+}
+
+vxlan_test_flush_by_nhid()
+{
+	local nhid_1=100
+	local nhid_2=200
+
+	nexthops_add $nhid_1 $nhid_2
+
+	fdb_add_mac_pool_1 vx10 nhid $nhid_1
+	fdb_add_mac_pool_2 vx10 nhid $nhid_2
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len nhid $nhid_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len nhid $nhid_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 nhid $nhid_2"
+	log_test $? 0 "Flush FDB by dev vx10 and nhid $nhid_2"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len nhid $nhid_1
+	log_test $? 0 "Test entries with nhid $nhid_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 nhid $nhid_2
+	log_test $? 0 "Test entries with nhid $nhid_2"
+
+	# Flush also entries with $nhid_1, and then verify that flushing by
+	# 'nhid' does not return an error when there are no entries with
+	# nexthops.
+	run_cmd "$BRIDGE fdb flush dev vx10 nhid $nhid_1"
+	log_test $? 0 "Flush FDB by dev vx10 and nhid $nhid_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 nhid
+	log_test $? 0 "Test entries with 'nhid' keyword"
+
+	run_cmd "$BRIDGE fdb flush dev vx10 nhid $nhid_1"
+	log_test $? 0 "Flush FDB by nhid when there are no entries with nexthop"
+}
+
+vxlan_test_flush_by_state()
+{
+	local flush_by_state=$1; shift
+	local state_1=$1; shift
+	local exp_state_1=$1; shift
+	local state_2=$1; shift
+	local exp_state_2=$1; shift
+
+	local dst_ip_1=192.0.2.1
+	local dst_ip_2=192.0.2.2
+
+	fdb_add_mac_pool_1 vx10 dst $dst_ip_1 $state_1
+	fdb_add_mac_pool_2 vx10 dst $dst_ip_2 $state_2
+
+	# Check the entries by dst_ip as not all states appear in 'bridge fdb'
+	# output.
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len dst $dst_ip_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_by_state"
+	log_test $? 0 "Flush FDB by dev vx10 and state $flush_by_state"
+
+	fdb_check_n_entries_by_dev_filter vx10 $exp_state_1 dst $dst_ip_1
+	log_test $? 0 "Test entries with state $state_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 $exp_state_2 dst $dst_ip_2
+	log_test $? 0 "Test entries with state $state_2"
+}
+
+vxlan_test_flush_by_permanent()
+{
+	# Entries that are added without state get 'permanent' state by
+	# default, add some entries with flag 'extern_learn' instead of state,
+	# so they will be added with 'permanent' and should be flushed also.
+	local flush_by_state="permanent"
+	local state_1="permanent"
+	local exp_state_1=0
+	local state_2="extern_learn"
+	local exp_state_2=0
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_nopermanent()
+{
+	local flush_by_state="nopermanent"
+	local state_1="permanent"
+	local exp_state_1=$mac_pool_1_len
+	local state_2="static"
+	local exp_state_2=0
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_static()
+{
+	local flush_by_state="static"
+	local state_1="static"
+	local exp_state_1=0
+	local state_2="dynamic"
+	local exp_state_2=$mac_pool_2_len
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_nostatic()
+{
+	local flush_by_state="nostatic"
+	local state_1="permanent"
+	local exp_state_1=$mac_pool_1_len
+	local state_2="dynamic"
+	local exp_state_2=0
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_dynamic()
+{
+	local flush_by_state="dynamic"
+	local state_1="dynamic"
+	local exp_state_1=0
+	local state_2="static"
+	local exp_state_2=$mac_pool_2_len
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_nodynamic()
+{
+	local flush_by_state="nodynamic"
+	local state_1="permanent"
+	local exp_state_1=0
+	local state_2="dynamic"
+	local exp_state_2=$mac_pool_2_len
+
+	vxlan_test_flush_by_state $flush_by_state $state_1 $exp_state_1 \
+		$state_2 $exp_state_2
+}
+
+vxlan_test_flush_by_flag()
+{
+	local flush_by_flag=$1; shift
+	local flag_1=$1; shift
+	local exp_flag_1=$1; shift
+	local flag_2=$1; shift
+	local exp_flag_2=$1; shift
+
+	local dst_ip_1=192.0.2.1
+	local dst_ip_2=192.0.2.2
+
+	fdb_add_mac_pool_1 vx10 dst $dst_ip_1 $flag_1
+	fdb_add_mac_pool_2 vx10 dst $dst_ip_2 $flag_2
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len $flag_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len $flag_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_by_flag"
+	log_test $? 0 "Flush FDB by dev vx10 and flag $flush_by_flag"
+
+	fdb_check_n_entries_by_dev_filter vx10 $exp_flag_1 dst $dst_ip_1
+	log_test $? 0 "Test entries with flag $flag_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 $exp_flag_2 dst $dst_ip_2
+	log_test $? 0 "Test entries with flag $flag_2"
+}
+
+vxlan_test_flush_by_extern_learn()
+{
+	local flush_by_flag="extern_learn"
+	local flag_1="extern_learn"
+	local exp_flag_1=0
+	local flag_2="router"
+	local exp_flag_2=$mac_pool_2_len
+
+	vxlan_test_flush_by_flag $flush_by_flag $flag_1 $exp_flag_1 \
+		$flag_2 $exp_flag_2
+}
+
+vxlan_test_flush_by_noextern_learn()
+{
+	local flush_by_flag="noextern_learn"
+	local flag_1="extern_learn"
+	local exp_flag_1=$mac_pool_1_len
+	local flag_2="router"
+	local exp_flag_2=0
+
+	vxlan_test_flush_by_flag $flush_by_flag $flag_1 $exp_flag_1 \
+		$flag_2 $exp_flag_2
+}
+
+vxlan_test_flush_by_router()
+{
+	local flush_by_flag="router"
+	local flag_1="router"
+	local exp_flag_1=0
+	local flag_2="extern_learn"
+	local exp_flag_2=$mac_pool_2_len
+
+	vxlan_test_flush_by_flag $flush_by_flag $flag_1 $exp_flag_1 \
+		$flag_2 $exp_flag_2
+}
+
+vxlan_test_flush_by_norouter()
+{
+
+	local flush_by_flag="norouter"
+	local flag_1="router"
+	local exp_flag_1=$mac_pool_1_len
+	local flag_2="extern_learn"
+	local exp_flag_2=0
+
+	vxlan_test_flush_by_flag $flush_by_flag $flag_1 $exp_flag_1 \
+		$flag_2 $exp_flag_2
+}
+
+vxlan_test_flush_by_several_args()
+{
+	local dst_ip_1=192.0.2.1
+	local dst_ip_2=192.0.2.2
+	local state_1=permanent
+	local state_2=static
+	local vni=3000
+	local port=1234
+	local nhid=100
+	local flag=router
+	local flush_args
+
+	################### Flush by 2 args - nhid and flag ####################
+	$IP nexthop add id 10 via 192.0.2.1 fdb
+	$IP nexthop add id $nhid group 10 fdb
+
+	fdb_add_mac_pool_1 vx10 nhid $nhid $flag $state_1
+	fdb_add_mac_pool_2 vx10 nhid $nhid $flag $state_2
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len $state_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len $state_2
+
+	run_cmd "$BRIDGE fdb flush dev vx10 nhid $nhid $flag"
+	log_test $? 0 "Flush FDB by dev vx10 nhid $nhid $flag"
+
+	# All entries should be flushed as 'state' is not an argument for flush
+	# filtering.
+	fdb_check_n_entries_by_dev_filter vx10 0 $state_1
+	log_test $? 0 "Test entries with state $state_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 $state_2
+	log_test $? 0 "Test entries with state $state_2"
+
+	################ Flush by 3 args - VNI, port and dst_ip ################
+	fdb_add_mac_pool_1 vx10 vni $vni port $port dst $dst_ip_1
+	fdb_add_mac_pool_2 vx10 vni $vni port $port dst $dst_ip_2
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_2_len dst $dst_ip_2
+
+	flush_args="vni $vni port $port dst $dst_ip_2"
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_args"
+	log_test $? 0 "Flush FDB by dev vx10 $flush_args"
+
+	# Only entries with $dst_ip_2 should be flushed, even the rest arguments
+	# match the filter, the flush should be AND of all the arguments.
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip_1
+	log_test $? 0 "Test entries with dst $dst_ip_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 dst $dst_ip_2
+	log_test $? 0 "Test entries with dst $dst_ip_2"
+}
+
+multicast_fdb_entries_add()
+{
+	mac=00:00:00:00:00:00
+	vnis=(2000 3000)
+
+	for vni in "${vnis[@]}"; do
+		$BRIDGE fdb append $mac dev vx10 dst 192.0.2.1 vni $vni \
+			src_vni 5000
+		$BRIDGE fdb append $mac dev vx10 dst 192.0.2.1 vni $vni \
+			port 1111
+		$BRIDGE fdb append $mac dev vx10 dst 192.0.2.2 vni $vni \
+			port 2222
+	done
+}
+
+vxlan_test_flush_by_remote_attributes()
+{
+	local flush_args
+
+	# Reconfigure vx10 with 'external' to get 'src_vni' details in
+	# 'bridge fdb' output
+	$IP link del dev vx10
+	$IP link add name vx10 type vxlan dstport "$VXPORT" external
+
+	# For multicat FDB entries, the VXLAN driver stores a linked list of
+	# remotes for a given key. Verify that only the expected remotes are
+	# flushed.
+	multicast_fdb_entries_add
+
+	## Flush by 3 remote's attributes - destination IP, port and VNI ##
+	flush_args="dst 192.0.2.1 port 1111 vni 2000"
+	fdb_check_n_entries_by_dev_filter vx10 1 $flush_args
+
+	t0_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_args"
+	log_test $? 0 "Flush FDB by dev vx10 $flush_args"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 $flush_args
+
+	exp_n_entries=$((t0_n_entries - 1))
+	t1_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	[[ $t1_n_entries -eq $exp_n_entries ]]
+	log_test $? 0 "Check how many entries were flushed"
+
+	## Flush by 2 remote's attributes - destination IP and port ##
+	flush_args="dst 192.0.2.2 port 2222"
+
+	fdb_check_n_entries_by_dev_filter vx10 2 $flush_args
+
+	t0_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_args"
+	log_test $? 0 "Flush FDB by dev vx10 $flush_args"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 $flush_args
+
+	exp_n_entries=$((t0_n_entries - 2))
+	t1_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	[[ $t1_n_entries -eq $exp_n_entries ]]
+	log_test $? 0 "Check how many entries were flushed"
+
+	## Flush by source VNI, which is not remote's attribute and VNI ##
+	flush_args="vni 3000 src_vni 5000"
+
+	fdb_check_n_entries_by_dev_filter vx10 1 $flush_args
+
+	t0_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_args"
+	log_test $? 0 "Flush FDB by dev vx10 $flush_args"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 $flush_args
+
+	exp_n_entries=$((t0_n_entries -1))
+	t1_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	[[ $t1_n_entries -eq $exp_n_entries ]]
+	log_test $? 0 "Check how many entries were flushed"
+
+	# Flush by 1 remote's attribute - destination IP ##
+	flush_args="dst 192.0.2.1"
+
+	fdb_check_n_entries_by_dev_filter vx10 2 $flush_args
+
+	t0_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	run_cmd "$BRIDGE fdb flush dev vx10 $flush_args"
+	log_test $? 0 "Flush FDB by dev vx10 $flush_args"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 $flush_args
+
+	exp_n_entries=$((t0_n_entries -2))
+	t1_n_entries=$($BRIDGE fdb show dev vx10 | wc -l)
+	[[ $t1_n_entries -eq $exp_n_entries ]]
+	log_test $? 0 "Check how many entries were flushed"
+}
+
+setup()
+{
+	IP="ip -netns ns1"
+	BRIDGE="bridge -netns ns1"
+
+	ip netns add ns1
+
+	$IP link add name vx10 type vxlan id 1000 dstport "$VXPORT"
+	$IP link add name vx20 type vxlan id 2000 dstport "$VXPORT"
+}
+
+cleanup()
+{
+	$IP link del dev vx20
+	$IP link del dev vx10
+
+	ip netns del ns1
+}
+
+################################################################################
+# main
+
+while getopts :t:pPhvw: o
+do
+	case $o in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		w) PING_TIMEOUT=$OPTARG;;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+# make sure we don't pause twice
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+# Check a flag that is added to flush command as part of VXLAN flush support
+bridge fdb help 2>&1 | grep -q "\[no\]router"
+if [ $? -ne 0 ]; then
+	echo "SKIP: iproute2 too old, missing flush command for VXLAN"
+	exit $ksft_skip
+fi
+
+ip link add dev vx10 type vxlan id 1000 2> /dev/null
+out=$(bridge fdb flush dev vx10 2>&1 | grep -q "Operation not supported")
+if [ $? -eq 0 ]; then
+	echo "SKIP: kernel lacks vxlan flush support"
+	exit $ksft_skip
+fi
+ip link del dev vx10
+
+for t in $TESTS
+do
+	setup; $t; cleanup;
+done
-- 
cgit v1.2.3


From f826f2a2ee1ed648c59b792f93bb4466bfe367a1 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 9 Oct 2023 13:06:18 +0300
Subject: selftests: fdb_flush: Add test cases for FDB flush with bridge device

Extend the test to check flushing with bridge device, test flush by device
and by VID.

Add test case for flushing with "self" and "master" and attributes that are
supported only in one driver, this is unrecommended configuration, check it
to verify that user gets an error.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fdb_flush.sh | 96 ++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh
index 3050b031f46d..90e7a29e0476 100755
--- a/tools/testing/selftests/net/fdb_flush.sh
+++ b/tools/testing/selftests/net/fdb_flush.sh
@@ -32,6 +32,9 @@ TESTS="
 	$FLUSH_BY_FLAG_TESTS
 	vxlan_test_flush_by_several_args
 	vxlan_test_flush_by_remote_attributes
+	bridge_test_flush_by_dev
+	bridge_test_flush_by_vlan
+	bridge_vxlan_test_flush
 "
 
 : ${VERBOSE:=0}
@@ -647,6 +650,93 @@ vxlan_test_flush_by_remote_attributes()
 	log_test $? 0 "Check how many entries were flushed"
 }
 
+bridge_test_flush_by_dev()
+{
+	local dst_ip=192.0.2.1
+	local br0_n_ent_t0=$($BRIDGE fdb show dev br0 | wc -l)
+	local br1_n_ent_t0=$($BRIDGE fdb show dev br1 | wc -l)
+
+	fdb_add_mac_pool_1 br0 dst $dst_ip
+	fdb_add_mac_pool_2 br1 dst $dst_ip
+
+	# Each 'fdb add' command adds one extra entry in the bridge with the
+	# default vlan.
+	local exp_br0_n_ent=$(($br0_n_ent_t0 + 2 * $mac_pool_1_len))
+	local exp_br1_n_ent=$(($br1_n_ent_t0 + 2 * $mac_pool_2_len))
+
+	fdb_check_n_entries_by_dev_filter br0 $exp_br0_n_ent
+	fdb_check_n_entries_by_dev_filter br1 $exp_br1_n_ent
+
+	run_cmd "$BRIDGE fdb flush dev br0"
+	log_test $? 0 "Flush FDB by dev br0"
+
+	# The default entry should not be flushed
+	fdb_check_n_entries_by_dev_filter br0 1
+	log_test $? 0 "Flush FDB by dev br0 - test br0 entries"
+
+	fdb_check_n_entries_by_dev_filter br1 $exp_br1_n_ent
+	log_test $? 0 "Flush FDB by dev br0 - test br1 entries"
+}
+
+bridge_test_flush_by_vlan()
+{
+	local vlan_1=10
+	local vlan_2=20
+	local vlan_1_ent_t0
+	local vlan_2_ent_t0
+
+	$BRIDGE vlan add vid $vlan_1 dev br0 self
+	$BRIDGE vlan add vid $vlan_2 dev br0 self
+
+	vlan_1_ent_t0=$($BRIDGE fdb show dev br0 | grep "vlan $vlan_1" | wc -l)
+	vlan_2_ent_t0=$($BRIDGE fdb show dev br0 | grep "vlan $vlan_2" | wc -l)
+
+	fdb_add_mac_pool_1 br0 vlan $vlan_1
+	fdb_add_mac_pool_2 br0 vlan $vlan_2
+
+	local exp_vlan_1_ent=$(($vlan_1_ent_t0 + $mac_pool_1_len))
+	local exp_vlan_2_ent=$(($vlan_2_ent_t0 + $mac_pool_2_len))
+
+	fdb_check_n_entries_by_dev_filter br0 $exp_vlan_1_ent vlan $vlan_1
+	fdb_check_n_entries_by_dev_filter br0 $exp_vlan_2_ent vlan $vlan_2
+
+	run_cmd "$BRIDGE fdb flush dev br0 vlan $vlan_1"
+	log_test $? 0 "Flush FDB by dev br0 and vlan $vlan_1"
+
+	fdb_check_n_entries_by_dev_filter br0 0 vlan $vlan_1
+	log_test $? 0 "Test entries with vlan $vlan_1"
+
+	fdb_check_n_entries_by_dev_filter br0 $exp_vlan_2_ent vlan $vlan_2
+	log_test $? 0 "Test entries with vlan $vlan_2"
+}
+
+bridge_vxlan_test_flush()
+{
+	local vlan_1=10
+	local dst_ip=192.0.2.1
+
+	$IP link set dev vx10 master br0
+	$BRIDGE vlan add vid $vlan_1 dev br0 self
+	$BRIDGE vlan add vid $vlan_1 dev vx10
+
+	fdb_add_mac_pool_1 vx10 vni 3000 dst $dst_ip self master
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len vlan $vlan_1
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len vni 3000
+
+	# Such command should fail in VXLAN driver as vlan is not supported,
+	# but the command should flush the entries in the bridge
+	run_cmd "$BRIDGE fdb flush dev vx10 vlan $vlan_1 master self"
+	log_test $? 255 \
+		"Flush FDB by dev vx10, vlan $vlan_1, master and self"
+
+	fdb_check_n_entries_by_dev_filter vx10 0 vlan $vlan_1
+	log_test $? 0 "Test entries with vlan $vlan_1"
+
+	fdb_check_n_entries_by_dev_filter vx10 $mac_pool_1_len dst $dst_ip
+	log_test $? 0 "Test entries with dst $dst_ip"
+}
+
 setup()
 {
 	IP="ip -netns ns1"
@@ -656,10 +746,16 @@ setup()
 
 	$IP link add name vx10 type vxlan id 1000 dstport "$VXPORT"
 	$IP link add name vx20 type vxlan id 2000 dstport "$VXPORT"
+
+	$IP link add br0 type bridge vlan_filtering 1
+	$IP link add br1 type bridge vlan_filtering 1
 }
 
 cleanup()
 {
+	$IP link del dev br1
+	$IP link del dev br0
+
 	$IP link del dev vx20
 	$IP link del dev vx10
 
-- 
cgit v1.2.3


From 6151ff9c75210c0f9d3d9ddcd3de6325de12c2a0 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 10 Oct 2023 16:44:00 +0200
Subject: selftests: netdevsim: use suitable existing dummy file for flash test

The file name used in flash test was "dummy" because at the time test
was written, drivers were responsible for file request and as netdevsim
didn't do that, name was unused. However, the file load request is
now done in devlink code and therefore the file has to exist.
Use first random file from /lib/firmware for this purpose.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/netdevsim/devlink.sh      | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 7f7d20f22207..46e20b13473c 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -31,36 +31,43 @@ devlink_wait()
 
 fw_flash_test()
 {
+	DUMMYFILE=$(find /lib/firmware -maxdepth 1 -type f  -printf '%f\n' |head -1)
 	RET=0
 
-	devlink dev flash $DL_HANDLE file dummy
+	if [ -z "$DUMMYFILE" ]
+	then
+		echo "SKIP: unable to find suitable dummy firmware file"
+		return
+	fi
+
+	devlink dev flash $DL_HANDLE file $DUMMYFILE
 	check_err $? "Failed to flash with status updates on"
 
-	devlink dev flash $DL_HANDLE file dummy component fw.mgmt
+	devlink dev flash $DL_HANDLE file $DUMMYFILE component fw.mgmt
 	check_err $? "Failed to flash with component attribute"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite settings
 	check_fail $? "Flash with overwrite settings should be rejected"
 
 	echo "1"> $DEBUGFS_DIR/fw_update_overwrite_mask
 	check_err $? "Failed to change allowed overwrite mask"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite settings
 	check_err $? "Failed to flash with settings overwrite enabled"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite identifiers
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite identifiers
 	check_fail $? "Flash with overwrite settings should be identifiers"
 
 	echo "3"> $DEBUGFS_DIR/fw_update_overwrite_mask
 	check_err $? "Failed to change allowed overwrite mask"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite identifiers overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite identifiers overwrite settings
 	check_err $? "Failed to flash with settings and identifiers overwrite enabled"
 
 	echo "n"> $DEBUGFS_DIR/fw_update_status
 	check_err $? "Failed to disable status updates"
 
-	devlink dev flash $DL_HANDLE file dummy
+	devlink dev flash $DL_HANDLE file $DUMMYFILE
 	check_err $? "Failed to flash with status updates off"
 
 	log_test "fw flash test"
-- 
cgit v1.2.3


From ba8ea72388a192c10f1ee5f5a4a32332e7cced76 Mon Sep 17 00:00:00 2001
From: Artem Savkov <asavkov@redhat.com>
Date: Fri, 13 Oct 2023 07:42:19 +0200
Subject: bpf: Change syscall_nr type to int in struct syscall_tp_t

linux-rt-devel tree contains a patch (b1773eac3f29c ("sched: Add support
for lazy preemption")) that adds an extra member to struct trace_entry.
This causes the offset of args field in struct trace_event_raw_sys_enter
be different from the one in struct syscall_trace_enter:

struct trace_event_raw_sys_enter {
        struct trace_entry         ent;                  /*     0    12 */

        /* XXX last struct has 3 bytes of padding */
        /* XXX 4 bytes hole, try to pack */

        long int                   id;                   /*    16     8 */
        long unsigned int          args[6];              /*    24    48 */
        /* --- cacheline 1 boundary (64 bytes) was 8 bytes ago --- */
        char                       __data[];             /*    72     0 */

        /* size: 72, cachelines: 2, members: 4 */
        /* sum members: 68, holes: 1, sum holes: 4 */
        /* paddings: 1, sum paddings: 3 */
        /* last cacheline: 8 bytes */
};

struct syscall_trace_enter {
        struct trace_entry         ent;                  /*     0    12 */

        /* XXX last struct has 3 bytes of padding */

        int                        nr;                   /*    12     4 */
        long unsigned int          args[];               /*    16     0 */

        /* size: 16, cachelines: 1, members: 3 */
        /* paddings: 1, sum paddings: 3 */
        /* last cacheline: 16 bytes */
};

This, in turn, causes perf_event_set_bpf_prog() fail while running bpf
test_profiler testcase because max_ctx_offset is calculated based on the
former struct, while off on the latter:

  10488         if (is_tracepoint || is_syscall_tp) {
  10489                 int off = trace_event_get_offsets(event->tp_event);
  10490
  10491                 if (prog->aux->max_ctx_offset > off)
  10492                         return -EACCES;
  10493         }

What bpf program is actually getting is a pointer to struct
syscall_tp_t, defined in kernel/trace/trace_syscalls.c. This patch fixes
the problem by aligning struct syscall_tp_t with struct
syscall_trace_(enter|exit) and changing the tests to use these structs
to dereference context.

Signed-off-by: Artem Savkov <asavkov@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20231013054219.172920-1-asavkov@redhat.com
---
 kernel/trace/trace_syscalls.c                    | 4 ++--
 tools/testing/selftests/bpf/progs/profiler.inc.h | 2 +-
 tools/testing/selftests/bpf/progs/test_vmlinux.c | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index de753403cdaf..9c581d6da843 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -556,7 +556,7 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
 {
 	struct syscall_tp_t {
 		struct trace_entry ent;
-		unsigned long syscall_nr;
+		int syscall_nr;
 		unsigned long args[SYSCALL_DEFINE_MAXARGS];
 	} __aligned(8) param;
 	int i;
@@ -661,7 +661,7 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
 {
 	struct syscall_tp_t {
 		struct trace_entry ent;
-		unsigned long syscall_nr;
+		int syscall_nr;
 		unsigned long ret;
 	} __aligned(8) param;
 
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index f799d87e8700..897061930cb7 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -609,7 +609,7 @@ out:
 }
 
 SEC("tracepoint/syscalls/sys_enter_kill")
-int tracepoint__syscalls__sys_enter_kill(struct trace_event_raw_sys_enter* ctx)
+int tracepoint__syscalls__sys_enter_kill(struct syscall_trace_enter* ctx)
 {
 	struct bpf_func_stats_ctx stats_ctx;
 
diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
index 4b8e37f7fd06..78b23934d9f8 100644
--- a/tools/testing/selftests/bpf/progs/test_vmlinux.c
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -16,12 +16,12 @@ bool kprobe_called = false;
 bool fentry_called = false;
 
 SEC("tp/syscalls/sys_enter_nanosleep")
-int handle__tp(struct trace_event_raw_sys_enter *args)
+int handle__tp(struct syscall_trace_enter *args)
 {
 	struct __kernel_timespec *ts;
 	long tv_nsec;
 
-	if (args->id != __NR_nanosleep)
+	if (args->nr != __NR_nanosleep)
 		return 0;
 
 	ts = (void *)args->args[0];
-- 
cgit v1.2.3


From 45b38941c81f16bb2e9b0115f03e164a3576ea8b Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 13 Oct 2023 13:44:23 -0700
Subject: selftests/bpf: Rename bpf_iter_task_vma.c to bpf_iter_task_vmas.c

Further patches in this series will add a struct bpf_iter_task_vma,
which will result in a name collision with the selftest prog renamed in
this patch. Rename the selftest to avoid the collision.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231013204426.1074286-3-davemarchevsky@fb.com
---
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c  | 26 ++++-----
 .../selftests/bpf/progs/bpf_iter_task_vma.c        | 62 ----------------------
 .../selftests/bpf/progs/bpf_iter_task_vmas.c       | 62 ++++++++++++++++++++++
 3 files changed, 75 insertions(+), 75 deletions(-)
 delete mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 1f02168103dd..41aba139b20b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -10,7 +10,7 @@
 #include "bpf_iter_task.skel.h"
 #include "bpf_iter_task_stack.skel.h"
 #include "bpf_iter_task_file.skel.h"
-#include "bpf_iter_task_vma.skel.h"
+#include "bpf_iter_task_vmas.skel.h"
 #include "bpf_iter_task_btf.skel.h"
 #include "bpf_iter_tcp4.skel.h"
 #include "bpf_iter_tcp6.skel.h"
@@ -1399,19 +1399,19 @@ static void str_strip_first_line(char *str)
 static void test_task_vma_common(struct bpf_iter_attach_opts *opts)
 {
 	int err, iter_fd = -1, proc_maps_fd = -1;
-	struct bpf_iter_task_vma *skel;
+	struct bpf_iter_task_vmas *skel;
 	int len, read_size = 4;
 	char maps_path[64];
 
-	skel = bpf_iter_task_vma__open();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+	skel = bpf_iter_task_vmas__open();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open"))
 		return;
 
 	skel->bss->pid = getpid();
 	skel->bss->one_task = opts ? 1 : 0;
 
-	err = bpf_iter_task_vma__load(skel);
-	if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+	err = bpf_iter_task_vmas__load(skel);
+	if (!ASSERT_OK(err, "bpf_iter_task_vmas__load"))
 		goto out;
 
 	skel->links.proc_maps = bpf_program__attach_iter(
@@ -1462,25 +1462,25 @@ static void test_task_vma_common(struct bpf_iter_attach_opts *opts)
 out:
 	close(proc_maps_fd);
 	close(iter_fd);
-	bpf_iter_task_vma__destroy(skel);
+	bpf_iter_task_vmas__destroy(skel);
 }
 
 static void test_task_vma_dead_task(void)
 {
-	struct bpf_iter_task_vma *skel;
+	struct bpf_iter_task_vmas *skel;
 	int wstatus, child_pid = -1;
 	time_t start_tm, cur_tm;
 	int err, iter_fd = -1;
 	int wait_sec = 3;
 
-	skel = bpf_iter_task_vma__open();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+	skel = bpf_iter_task_vmas__open();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open"))
 		return;
 
 	skel->bss->pid = getpid();
 
-	err = bpf_iter_task_vma__load(skel);
-	if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+	err = bpf_iter_task_vmas__load(skel);
+	if (!ASSERT_OK(err, "bpf_iter_task_vmas__load"))
 		goto out;
 
 	skel->links.proc_maps = bpf_program__attach_iter(
@@ -1533,7 +1533,7 @@ static void test_task_vma_dead_task(void)
 out:
 	waitpid(child_pid, &wstatus, 0);
 	close(iter_fd);
-	bpf_iter_task_vma__destroy(skel);
+	bpf_iter_task_vmas__destroy(skel);
 }
 
 void test_bpf_sockmap_map_iter_fd(void)
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
deleted file mode 100644
index dd923dc637d5..000000000000
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
+++ /dev/null
@@ -1,62 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
-#include <bpf/bpf_helpers.h>
-
-char _license[] SEC("license") = "GPL";
-
-/* Copied from mm.h */
-#define VM_READ		0x00000001
-#define VM_WRITE	0x00000002
-#define VM_EXEC		0x00000004
-#define VM_MAYSHARE	0x00000080
-
-/* Copied from kdev_t.h */
-#define MINORBITS	20
-#define MINORMASK	((1U << MINORBITS) - 1)
-#define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
-#define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
-
-#define D_PATH_BUF_SIZE 1024
-char d_path_buf[D_PATH_BUF_SIZE] = {};
-__u32 pid = 0;
-__u32 one_task = 0;
-__u32 one_task_error = 0;
-
-SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
-{
-	struct vm_area_struct *vma = ctx->vma;
-	struct seq_file *seq = ctx->meta->seq;
-	struct task_struct *task = ctx->task;
-	struct file *file;
-	char perm_str[] = "----";
-
-	if (task == (void *)0 || vma == (void *)0)
-		return 0;
-
-	file = vma->vm_file;
-	if (task->tgid != pid) {
-		if (one_task)
-			one_task_error = 1;
-		return 0;
-	}
-	perm_str[0] = (vma->vm_flags & VM_READ) ? 'r' : '-';
-	perm_str[1] = (vma->vm_flags & VM_WRITE) ? 'w' : '-';
-	perm_str[2] = (vma->vm_flags & VM_EXEC) ? 'x' : '-';
-	perm_str[3] = (vma->vm_flags & VM_MAYSHARE) ? 's' : 'p';
-	BPF_SEQ_PRINTF(seq, "%08llx-%08llx %s ", vma->vm_start, vma->vm_end, perm_str);
-
-	if (file) {
-		__u32 dev = file->f_inode->i_sb->s_dev;
-
-		bpf_d_path(&file->f_path, d_path_buf, D_PATH_BUF_SIZE);
-
-		BPF_SEQ_PRINTF(seq, "%08llx ", vma->vm_pgoff << 12);
-		BPF_SEQ_PRINTF(seq, "%02x:%02x %u", MAJOR(dev), MINOR(dev),
-			       file->f_inode->i_ino);
-		BPF_SEQ_PRINTF(seq, "\t%s\n", d_path_buf);
-	} else {
-		BPF_SEQ_PRINTF(seq, "%08llx 00:00 0\n", 0ULL);
-	}
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
new file mode 100644
index 000000000000..dd923dc637d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Copied from mm.h */
+#define VM_READ		0x00000001
+#define VM_WRITE	0x00000002
+#define VM_EXEC		0x00000004
+#define VM_MAYSHARE	0x00000080
+
+/* Copied from kdev_t.h */
+#define MINORBITS	20
+#define MINORMASK	((1U << MINORBITS) - 1)
+#define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
+#define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
+
+#define D_PATH_BUF_SIZE 1024
+char d_path_buf[D_PATH_BUF_SIZE] = {};
+__u32 pid = 0;
+__u32 one_task = 0;
+__u32 one_task_error = 0;
+
+SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
+{
+	struct vm_area_struct *vma = ctx->vma;
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	struct file *file;
+	char perm_str[] = "----";
+
+	if (task == (void *)0 || vma == (void *)0)
+		return 0;
+
+	file = vma->vm_file;
+	if (task->tgid != pid) {
+		if (one_task)
+			one_task_error = 1;
+		return 0;
+	}
+	perm_str[0] = (vma->vm_flags & VM_READ) ? 'r' : '-';
+	perm_str[1] = (vma->vm_flags & VM_WRITE) ? 'w' : '-';
+	perm_str[2] = (vma->vm_flags & VM_EXEC) ? 'x' : '-';
+	perm_str[3] = (vma->vm_flags & VM_MAYSHARE) ? 's' : 'p';
+	BPF_SEQ_PRINTF(seq, "%08llx-%08llx %s ", vma->vm_start, vma->vm_end, perm_str);
+
+	if (file) {
+		__u32 dev = file->f_inode->i_sb->s_dev;
+
+		bpf_d_path(&file->f_path, d_path_buf, D_PATH_BUF_SIZE);
+
+		BPF_SEQ_PRINTF(seq, "%08llx ", vma->vm_pgoff << 12);
+		BPF_SEQ_PRINTF(seq, "%02x:%02x %u", MAJOR(dev), MINOR(dev),
+			       file->f_inode->i_ino);
+		BPF_SEQ_PRINTF(seq, "\t%s\n", d_path_buf);
+	} else {
+		BPF_SEQ_PRINTF(seq, "%08llx 00:00 0\n", 0ULL);
+	}
+	return 0;
+}
-- 
cgit v1.2.3


From e0e1a7a5fc377d54bd792c6368a375d41fc316ef Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 13 Oct 2023 13:44:25 -0700
Subject: selftests/bpf: Add tests for open-coded task_vma iter

The open-coded task_vma iter added earlier in this series allows for
natural iteration over a task's vmas using existing open-coded iter
infrastructure, specifically bpf_for_each.

This patch adds a test demonstrating this pattern and validating
correctness. The vma->vm_start and vma->vm_end addresses of the first
1000 vmas are recorded and compared to /proc/PID/maps output. As
expected, both see the same vmas and addresses - with the exception of
the [vsyscall] vma - which is explained in a comment in the prog_tests
program.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231013204426.1074286-5-davemarchevsky@fb.com
---
 tools/testing/selftests/bpf/bpf_experimental.h     |  8 +++
 tools/testing/selftests/bpf/prog_tests/iters.c     | 58 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/iters_task_vma.c | 43 ++++++++++++++++
 3 files changed, 109 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/iters_task_vma.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 9aa29564bd74..2c8cb3f61529 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -159,6 +159,14 @@ extern void *bpf_percpu_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
  */
 extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
 
+struct bpf_iter_task_vma;
+
+extern int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
+				 struct task_struct *task,
+				 unsigned long addr) __ksym;
+extern struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) __ksym;
+extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym;
+
 /* Convenience macro to wrap over bpf_obj_drop_impl */
 #define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL)
 
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index 10804ae5ae97..b696873c5455 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -8,6 +8,7 @@
 #include "iters_looping.skel.h"
 #include "iters_num.skel.h"
 #include "iters_testmod_seq.skel.h"
+#include "iters_task_vma.skel.h"
 
 static void subtest_num_iters(void)
 {
@@ -90,6 +91,61 @@ cleanup:
 	iters_testmod_seq__destroy(skel);
 }
 
+static void subtest_task_vma_iters(void)
+{
+	unsigned long start, end, bpf_iter_start, bpf_iter_end;
+	struct iters_task_vma *skel;
+	char rest_of_line[1000];
+	unsigned int seen;
+	FILE *f = NULL;
+	int err;
+
+	skel = iters_task_vma__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+
+	err = iters_task_vma__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	getpgid(skel->bss->target_pid);
+	iters_task_vma__detach(skel);
+
+	if (!ASSERT_GT(skel->bss->vmas_seen, 0, "vmas_seen_gt_zero"))
+		goto cleanup;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!ASSERT_OK_PTR(f, "proc_maps_fopen"))
+		goto cleanup;
+
+	seen = 0;
+	while (fscanf(f, "%lx-%lx %[^\n]\n", &start, &end, rest_of_line) == 3) {
+		/* [vsyscall] vma isn't _really_ part of task->mm vmas.
+		 * /proc/PID/maps returns it when out of vmas - see get_gate_vma
+		 * calls in fs/proc/task_mmu.c
+		 */
+		if (strstr(rest_of_line, "[vsyscall]"))
+			continue;
+
+		bpf_iter_start = skel->bss->vm_ranges[seen].vm_start;
+		bpf_iter_end = skel->bss->vm_ranges[seen].vm_end;
+
+		ASSERT_EQ(bpf_iter_start, start, "vma->vm_start match");
+		ASSERT_EQ(bpf_iter_end, end, "vma->vm_end match");
+		seen++;
+	}
+
+	if (!ASSERT_EQ(skel->bss->vmas_seen, seen, "vmas_seen_eq"))
+		goto cleanup;
+
+cleanup:
+	if (f)
+		fclose(f);
+	iters_task_vma__destroy(skel);
+}
+
 void test_iters(void)
 {
 	RUN_TESTS(iters_state_safety);
@@ -103,4 +159,6 @@ void test_iters(void)
 		subtest_num_iters();
 	if (test__start_subtest("testmod_seq"))
 		subtest_testmod_seq_iters();
+	if (test__start_subtest("task_vma"))
+		subtest_task_vma_iters();
 }
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
new file mode 100644
index 000000000000..44edecfdfaee
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+pid_t target_pid = 0;
+unsigned int vmas_seen = 0;
+
+struct {
+	__u64 vm_start;
+	__u64 vm_end;
+} vm_ranges[1000];
+
+SEC("raw_tp/sys_enter")
+int iter_task_vma_for_each(const void *ctx)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct vm_area_struct *vma;
+	unsigned int seen = 0;
+
+	if (task->pid != target_pid)
+		return 0;
+
+	if (vmas_seen)
+		return 0;
+
+	bpf_for_each(task_vma, vma, task, 0) {
+		if (seen >= 1000)
+			break;
+
+		vm_ranges[seen].vm_start = vma->vm_start;
+		vm_ranges[seen].vm_end = vma->vm_end;
+		seen++;
+	}
+
+	vmas_seen = seen;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From bc36442ef3b776ee6d5148a4e175c367af057ce1 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Tue, 10 Oct 2023 22:15:22 +0300
Subject: test/vsock: MSG_ZEROCOPY flag tests

This adds three tests for MSG_ZEROCOPY feature:
1) SOCK_STREAM tx with different buffers.
2) SOCK_SEQPACKET tx with different buffers.
3) SOCK_STREAM test to read empty error queue of the socket.

Patch also works as preparation for the next patches for tools in this
patchset: vsock_perf and vsock_uring_test:
1) Adds several new functions to util.c - they will be also used by
   vsock_uring_test.
2) Adds two new functions for MSG_ZEROCOPY handling to a new source
   file - such source will be shared between vsock_test, vsock_perf and
   vsock_uring_test, thus avoiding code copy-pasting.

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/Makefile              |   2 +-
 tools/testing/vsock/msg_zerocopy_common.c |  87 ++++++++
 tools/testing/vsock/msg_zerocopy_common.h |  18 ++
 tools/testing/vsock/util.c                | 133 +++++++++++
 tools/testing/vsock/util.h                |   5 +
 tools/testing/vsock/vsock_test.c          |  16 ++
 tools/testing/vsock/vsock_test_zerocopy.c | 358 ++++++++++++++++++++++++++++++
 tools/testing/vsock/vsock_test_zerocopy.h |  15 ++
 8 files changed, 633 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/vsock/msg_zerocopy_common.c
 create mode 100644 tools/testing/vsock/msg_zerocopy_common.h
 create mode 100644 tools/testing/vsock/vsock_test_zerocopy.c
 create mode 100644 tools/testing/vsock/vsock_test_zerocopy.h

(limited to 'tools')

diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
index 21a98ba565ab..bb938e4790b5 100644
--- a/tools/testing/vsock/Makefile
+++ b/tools/testing/vsock/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 all: test vsock_perf
 test: vsock_test vsock_diag_test
-vsock_test: vsock_test.o timeout.o control.o util.o
+vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_zerocopy_common.o
 vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o
 vsock_perf: vsock_perf.o
 
diff --git a/tools/testing/vsock/msg_zerocopy_common.c b/tools/testing/vsock/msg_zerocopy_common.c
new file mode 100644
index 000000000000..5a4bdf7b5132
--- /dev/null
+++ b/tools/testing/vsock/msg_zerocopy_common.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Some common code for MSG_ZEROCOPY logic
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <linux/errqueue.h>
+
+#include "msg_zerocopy_common.h"
+
+void enable_so_zerocopy(int fd)
+{
+	int val = 1;
+
+	if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) {
+		perror("setsockopt");
+		exit(EXIT_FAILURE);
+	}
+}
+
+void vsock_recv_completion(int fd, const bool *zerocopied)
+{
+	struct sock_extended_err *serr;
+	struct msghdr msg = { 0 };
+	char cmsg_data[128];
+	struct cmsghdr *cm;
+	ssize_t res;
+
+	msg.msg_control = cmsg_data;
+	msg.msg_controllen = sizeof(cmsg_data);
+
+	res = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (res) {
+		fprintf(stderr, "failed to read error queue: %zi\n", res);
+		exit(EXIT_FAILURE);
+	}
+
+	cm = CMSG_FIRSTHDR(&msg);
+	if (!cm) {
+		fprintf(stderr, "cmsg: no cmsg\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (cm->cmsg_level != SOL_VSOCK) {
+		fprintf(stderr, "cmsg: unexpected 'cmsg_level'\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (cm->cmsg_type != VSOCK_RECVERR) {
+		fprintf(stderr, "cmsg: unexpected 'cmsg_type'\n");
+		exit(EXIT_FAILURE);
+	}
+
+	serr = (void *)CMSG_DATA(cm);
+	if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+		fprintf(stderr, "serr: wrong origin: %u\n", serr->ee_origin);
+		exit(EXIT_FAILURE);
+	}
+
+	if (serr->ee_errno) {
+		fprintf(stderr, "serr: wrong error code: %u\n", serr->ee_errno);
+		exit(EXIT_FAILURE);
+	}
+
+	/* This flag is used for tests, to check that transmission was
+	 * performed as expected: zerocopy or fallback to copy. If NULL
+	 * - don't care.
+	 */
+	if (!zerocopied)
+		return;
+
+	if (*zerocopied && (serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED)) {
+		fprintf(stderr, "serr: was copy instead of zerocopy\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!*zerocopied && !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED)) {
+		fprintf(stderr, "serr: was zerocopy instead of copy\n");
+		exit(EXIT_FAILURE);
+	}
+}
diff --git a/tools/testing/vsock/msg_zerocopy_common.h b/tools/testing/vsock/msg_zerocopy_common.h
new file mode 100644
index 000000000000..3763c5ccedb9
--- /dev/null
+++ b/tools/testing/vsock/msg_zerocopy_common.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef MSG_ZEROCOPY_COMMON_H
+#define MSG_ZEROCOPY_COMMON_H
+
+#include <stdbool.h>
+
+#ifndef SOL_VSOCK
+#define SOL_VSOCK	287
+#endif
+
+#ifndef VSOCK_RECVERR
+#define VSOCK_RECVERR	1
+#endif
+
+void enable_so_zerocopy(int fd);
+void vsock_recv_completion(int fd, const bool *zerocopied);
+
+#endif /* MSG_ZEROCOPY_COMMON_H */
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 6779d5008b27..92336721321a 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -11,10 +11,12 @@
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
+#include <string.h>
 #include <signal.h>
 #include <unistd.h>
 #include <assert.h>
 #include <sys/epoll.h>
+#include <sys/mman.h>
 
 #include "timeout.h"
 #include "control.h"
@@ -444,3 +446,134 @@ unsigned long hash_djb2(const void *data, size_t len)
 
 	return hash;
 }
+
+size_t iovec_bytes(const struct iovec *iov, size_t iovnum)
+{
+	size_t bytes;
+	int i;
+
+	for (bytes = 0, i = 0; i < iovnum; i++)
+		bytes += iov[i].iov_len;
+
+	return bytes;
+}
+
+unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum)
+{
+	unsigned long hash;
+	size_t iov_bytes;
+	size_t offs;
+	void *tmp;
+	int i;
+
+	iov_bytes = iovec_bytes(iov, iovnum);
+
+	tmp = malloc(iov_bytes);
+	if (!tmp) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	for (offs = 0, i = 0; i < iovnum; i++) {
+		memcpy(tmp + offs, iov[i].iov_base, iov[i].iov_len);
+		offs += iov[i].iov_len;
+	}
+
+	hash = hash_djb2(tmp, iov_bytes);
+	free(tmp);
+
+	return hash;
+}
+
+/* Allocates and returns new 'struct iovec *' according pattern
+ * in the 'test_iovec'. For each element in the 'test_iovec' it
+ * allocates new element in the resulting 'iovec'. 'iov_len'
+ * of the new element is copied from 'test_iovec'. 'iov_base' is
+ * allocated depending on the 'iov_base' of 'test_iovec':
+ *
+ * 'iov_base' == NULL -> valid buf: mmap('iov_len').
+ *
+ * 'iov_base' == MAP_FAILED -> invalid buf:
+ *               mmap('iov_len'), then munmap('iov_len').
+ *               'iov_base' still contains result of
+ *               mmap().
+ *
+ * 'iov_base' == number -> unaligned valid buf:
+ *               mmap('iov_len') + number.
+ *
+ * 'iovnum' is number of elements in 'test_iovec'.
+ *
+ * Returns new 'iovec' or calls 'exit()' on error.
+ */
+struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum)
+{
+	struct iovec *iovec;
+	int i;
+
+	iovec = malloc(sizeof(*iovec) * iovnum);
+	if (!iovec) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < iovnum; i++) {
+		iovec[i].iov_len = test_iovec[i].iov_len;
+
+		iovec[i].iov_base = mmap(NULL, iovec[i].iov_len,
+					 PROT_READ | PROT_WRITE,
+					 MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE,
+					 -1, 0);
+		if (iovec[i].iov_base == MAP_FAILED) {
+			perror("mmap");
+			exit(EXIT_FAILURE);
+		}
+
+		if (test_iovec[i].iov_base != MAP_FAILED)
+			iovec[i].iov_base += (uintptr_t)test_iovec[i].iov_base;
+	}
+
+	/* Unmap "invalid" elements. */
+	for (i = 0; i < iovnum; i++) {
+		if (test_iovec[i].iov_base == MAP_FAILED) {
+			if (munmap(iovec[i].iov_base, iovec[i].iov_len)) {
+				perror("munmap");
+				exit(EXIT_FAILURE);
+			}
+		}
+	}
+
+	for (i = 0; i < iovnum; i++) {
+		int j;
+
+		if (test_iovec[i].iov_base == MAP_FAILED)
+			continue;
+
+		for (j = 0; j < iovec[i].iov_len; j++)
+			((uint8_t *)iovec[i].iov_base)[j] = rand() & 0xff;
+	}
+
+	return iovec;
+}
+
+/* Frees 'iovec *', previously allocated by 'alloc_test_iovec()'.
+ * On error calls 'exit()'.
+ */
+void free_test_iovec(const struct iovec *test_iovec,
+		     struct iovec *iovec, int iovnum)
+{
+	int i;
+
+	for (i = 0; i < iovnum; i++) {
+		if (test_iovec[i].iov_base != MAP_FAILED) {
+			if (test_iovec[i].iov_base)
+				iovec[i].iov_base -= (uintptr_t)test_iovec[i].iov_base;
+
+			if (munmap(iovec[i].iov_base, iovec[i].iov_len)) {
+				perror("munmap");
+				exit(EXIT_FAILURE);
+			}
+		}
+	}
+
+	free(iovec);
+}
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index e5407677ce05..a77175d25864 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -53,4 +53,9 @@ void list_tests(const struct test_case *test_cases);
 void skip_test(struct test_case *test_cases, size_t test_cases_len,
 	       const char *test_id_str);
 unsigned long hash_djb2(const void *data, size_t len);
+size_t iovec_bytes(const struct iovec *iov, size_t iovnum);
+unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum);
+struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum);
+void free_test_iovec(const struct iovec *test_iovec,
+		     struct iovec *iovec, int iovnum);
 #endif /* UTIL_H */
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index da4cb819a183..c1f7bc9abd22 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -21,6 +21,7 @@
 #include <poll.h>
 #include <signal.h>
 
+#include "vsock_test_zerocopy.h"
 #include "timeout.h"
 #include "control.h"
 #include "util.h"
@@ -1269,6 +1270,21 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_shutrd_client,
 		.run_server = test_stream_shutrd_server,
 	},
+	{
+		.name = "SOCK_STREAM MSG_ZEROCOPY",
+		.run_client = test_stream_msgzcopy_client,
+		.run_server = test_stream_msgzcopy_server,
+	},
+	{
+		.name = "SOCK_SEQPACKET MSG_ZEROCOPY",
+		.run_client = test_seqpacket_msgzcopy_client,
+		.run_server = test_seqpacket_msgzcopy_server,
+	},
+	{
+		.name = "SOCK_STREAM MSG_ZEROCOPY empty MSG_ERRQUEUE",
+		.run_client = test_stream_msgzcopy_empty_errq_client,
+		.run_server = test_stream_msgzcopy_empty_errq_server,
+	},
 	{},
 };
 
diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c
new file mode 100644
index 000000000000..a16ff76484e6
--- /dev/null
+++ b/tools/testing/vsock/vsock_test_zerocopy.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* MSG_ZEROCOPY feature tests for vsock
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <poll.h>
+#include <linux/errqueue.h>
+#include <linux/kernel.h>
+#include <errno.h>
+
+#include "control.h"
+#include "vsock_test_zerocopy.h"
+#include "msg_zerocopy_common.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE		4096
+#endif
+
+#define VSOCK_TEST_DATA_MAX_IOV 3
+
+struct vsock_test_data {
+	/* This test case if for SOCK_STREAM only. */
+	bool stream_only;
+	/* Data must be zerocopied. This field is checked against
+	 * field 'ee_code' of the 'struct sock_extended_err', which
+	 * contains bit to detect that zerocopy transmission was
+	 * fallbacked to copy mode.
+	 */
+	bool zerocopied;
+	/* Enable SO_ZEROCOPY option on the socket. Without enabled
+	 * SO_ZEROCOPY, every MSG_ZEROCOPY transmission will behave
+	 * like without MSG_ZEROCOPY flag.
+	 */
+	bool so_zerocopy;
+	/* 'errno' after 'sendmsg()' call. */
+	int sendmsg_errno;
+	/* Number of valid elements in 'vecs'. */
+	int vecs_cnt;
+	struct iovec vecs[VSOCK_TEST_DATA_MAX_IOV];
+};
+
+static struct vsock_test_data test_data_array[] = {
+	/* Last element has non-page aligned size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, PAGE_SIZE },
+			{ NULL, 200 }
+		}
+	},
+	/* All elements have page aligned base and size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, PAGE_SIZE * 2 },
+			{ NULL, PAGE_SIZE * 3 }
+		}
+	},
+	/* All elements have page aligned base and size. But
+	 * data length is bigger than 64Kb.
+	 */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE * 16 },
+			{ NULL, PAGE_SIZE * 16 },
+			{ NULL, PAGE_SIZE * 16 }
+		}
+	},
+	/* Middle element has both non-page aligned base and size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ (void *)1, 100 },
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Middle element is unmapped. */
+	{
+		.zerocopied = false,
+		.so_zerocopy = true,
+		.sendmsg_errno = ENOMEM,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ MAP_FAILED, PAGE_SIZE },
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Valid data, but SO_ZEROCOPY is off. This
+	 * will trigger fallback to copy.
+	 */
+	{
+		.zerocopied = false,
+		.so_zerocopy = false,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 1,
+		{
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Valid data, but message is bigger than peer's
+	 * buffer, so this will trigger fallback to copy.
+	 * This test is for SOCK_STREAM only, because
+	 * for SOCK_SEQPACKET, 'sendmsg()' returns EMSGSIZE.
+	 */
+	{
+		.stream_only = true,
+		.zerocopied = false,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 1,
+		{
+			{ NULL, 100 * PAGE_SIZE }
+		}
+	},
+};
+
+#define POLL_TIMEOUT_MS		100
+
+static void test_client(const struct test_opts *opts,
+			const struct vsock_test_data *test_data,
+			bool sock_seqpacket)
+{
+	struct pollfd fds = { 0 };
+	struct msghdr msg = { 0 };
+	ssize_t sendmsg_res;
+	struct iovec *iovec;
+	int fd;
+
+	if (sock_seqpacket)
+		fd = vsock_seqpacket_connect(opts->peer_cid, 1234);
+	else
+		fd = vsock_stream_connect(opts->peer_cid, 1234);
+
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (test_data->so_zerocopy)
+		enable_so_zerocopy(fd);
+
+	iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
+
+	msg.msg_iov = iovec;
+	msg.msg_iovlen = test_data->vecs_cnt;
+
+	errno = 0;
+
+	sendmsg_res = sendmsg(fd, &msg, MSG_ZEROCOPY);
+	if (errno != test_data->sendmsg_errno) {
+		fprintf(stderr, "expected 'errno' == %i, got %i\n",
+			test_data->sendmsg_errno, errno);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!errno) {
+		if (sendmsg_res != iovec_bytes(iovec, test_data->vecs_cnt)) {
+			fprintf(stderr, "expected 'sendmsg()' == %li, got %li\n",
+				iovec_bytes(iovec, test_data->vecs_cnt),
+				sendmsg_res);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	fds.fd = fd;
+	fds.events = 0;
+
+	if (poll(&fds, 1, POLL_TIMEOUT_MS) < 0) {
+		perror("poll");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & POLLERR) {
+		vsock_recv_completion(fd, &test_data->zerocopied);
+	} else if (test_data->so_zerocopy && !test_data->sendmsg_errno) {
+		/* If we don't have data in the error queue, but
+		 * SO_ZEROCOPY was enabled and 'sendmsg()' was
+		 * successful - this is an error.
+		 */
+		fprintf(stderr, "POLLERR expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!test_data->sendmsg_errno)
+		control_writeulong(iovec_hash_djb2(iovec, test_data->vecs_cnt));
+	else
+		control_writeulong(0);
+
+	control_writeln("DONE");
+	free_test_iovec(test_data->vecs, iovec, test_data->vecs_cnt);
+	close(fd);
+}
+
+void test_stream_msgzcopy_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		test_client(opts, &test_data_array[i], false);
+}
+
+void test_seqpacket_msgzcopy_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++) {
+		if (test_data_array[i].stream_only)
+			continue;
+
+		test_client(opts, &test_data_array[i], true);
+	}
+}
+
+static void test_server(const struct test_opts *opts,
+			const struct vsock_test_data *test_data,
+			bool sock_seqpacket)
+{
+	unsigned long remote_hash;
+	unsigned long local_hash;
+	ssize_t total_bytes_rec;
+	unsigned char *data;
+	size_t data_len;
+	int fd;
+
+	if (sock_seqpacket)
+		fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL);
+	else
+		fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	data_len = iovec_bytes(test_data->vecs, test_data->vecs_cnt);
+
+	data = malloc(data_len);
+	if (!data) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	total_bytes_rec = 0;
+
+	while (total_bytes_rec != data_len) {
+		ssize_t bytes_rec;
+
+		bytes_rec = read(fd, data + total_bytes_rec,
+				 data_len - total_bytes_rec);
+		if (bytes_rec <= 0)
+			break;
+
+		total_bytes_rec += bytes_rec;
+	}
+
+	if (test_data->sendmsg_errno == 0)
+		local_hash = hash_djb2(data, data_len);
+	else
+		local_hash = 0;
+
+	free(data);
+
+	/* Waiting for some result. */
+	remote_hash = control_readulong();
+	if (remote_hash != local_hash) {
+		fprintf(stderr, "hash mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	close(fd);
+}
+
+void test_stream_msgzcopy_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		test_server(opts, &test_data_array[i], false);
+}
+
+void test_seqpacket_msgzcopy_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++) {
+		if (test_data_array[i].stream_only)
+			continue;
+
+		test_server(opts, &test_data_array[i], true);
+	}
+}
+
+void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts)
+{
+	struct msghdr msg = { 0 };
+	char cmsg_data[128];
+	ssize_t res;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	msg.msg_control = cmsg_data;
+	msg.msg_controllen = sizeof(cmsg_data);
+
+	res = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (res != -1) {
+		fprintf(stderr, "expected 'recvmsg(2)' failure, got %zi\n",
+			res);
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("DONE");
+	close(fd);
+}
+
+void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	close(fd);
+}
diff --git a/tools/testing/vsock/vsock_test_zerocopy.h b/tools/testing/vsock/vsock_test_zerocopy.h
new file mode 100644
index 000000000000..3ef2579e024d
--- /dev/null
+++ b/tools/testing/vsock/vsock_test_zerocopy.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef VSOCK_TEST_ZEROCOPY_H
+#define VSOCK_TEST_ZEROCOPY_H
+#include "util.h"
+
+void test_stream_msgzcopy_client(const struct test_opts *opts);
+void test_stream_msgzcopy_server(const struct test_opts *opts);
+
+void test_seqpacket_msgzcopy_client(const struct test_opts *opts);
+void test_seqpacket_msgzcopy_server(const struct test_opts *opts);
+
+void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts);
+void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts);
+
+#endif /* VSOCK_TEST_ZEROCOPY_H */
-- 
cgit v1.2.3


From e846d679ad131c71c190123f3b6176c108567c85 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Tue, 10 Oct 2023 22:15:23 +0300
Subject: test/vsock: MSG_ZEROCOPY support for vsock_perf

To use this option pass '--zerocopy' parameter:

./vsock_perf --zerocopy --sender <cid> ...

With this option MSG_ZEROCOPY flag will be passed to the 'send()' call.

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/Makefile     |  2 +-
 tools/testing/vsock/vsock_perf.c | 80 +++++++++++++++++++++++++++++++++++-----
 2 files changed, 72 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
index bb938e4790b5..228470ae33c2 100644
--- a/tools/testing/vsock/Makefile
+++ b/tools/testing/vsock/Makefile
@@ -3,7 +3,7 @@ all: test vsock_perf
 test: vsock_test vsock_diag_test
 vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_zerocopy_common.o
 vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o
-vsock_perf: vsock_perf.o
+vsock_perf: vsock_perf.o msg_zerocopy_common.o
 
 CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
 .PHONY: all test clean
diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c
index a72520338f84..4e8578f815e0 100644
--- a/tools/testing/vsock/vsock_perf.c
+++ b/tools/testing/vsock/vsock_perf.c
@@ -18,6 +18,9 @@
 #include <poll.h>
 #include <sys/socket.h>
 #include <linux/vm_sockets.h>
+#include <sys/mman.h>
+
+#include "msg_zerocopy_common.h"
 
 #define DEFAULT_BUF_SIZE_BYTES	(128 * 1024)
 #define DEFAULT_TO_SEND_BYTES	(64 * 1024)
@@ -31,6 +34,7 @@
 static unsigned int port = DEFAULT_PORT;
 static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES;
 static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES;
+static bool zerocopy;
 
 static void error(const char *s)
 {
@@ -252,10 +256,15 @@ static void run_sender(int peer_cid, unsigned long to_send_bytes)
 	time_t tx_begin_ns;
 	time_t tx_total_ns;
 	size_t total_send;
+	time_t time_in_send;
 	void *data;
 	int fd;
 
-	printf("Run as sender\n");
+	if (zerocopy)
+		printf("Run as sender MSG_ZEROCOPY\n");
+	else
+		printf("Run as sender\n");
+
 	printf("Connect to %i:%u\n", peer_cid, port);
 	printf("Send %lu bytes\n", to_send_bytes);
 	printf("TX buffer %lu bytes\n", buf_size_bytes);
@@ -265,38 +274,82 @@ static void run_sender(int peer_cid, unsigned long to_send_bytes)
 	if (fd < 0)
 		exit(EXIT_FAILURE);
 
-	data = malloc(buf_size_bytes);
+	if (zerocopy) {
+		enable_so_zerocopy(fd);
 
-	if (!data) {
-		fprintf(stderr, "'malloc()' failed\n");
-		exit(EXIT_FAILURE);
+		data = mmap(NULL, buf_size_bytes, PROT_READ | PROT_WRITE,
+			    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (data == MAP_FAILED) {
+			perror("mmap");
+			exit(EXIT_FAILURE);
+		}
+	} else {
+		data = malloc(buf_size_bytes);
+
+		if (!data) {
+			fprintf(stderr, "'malloc()' failed\n");
+			exit(EXIT_FAILURE);
+		}
 	}
 
 	memset(data, 0, buf_size_bytes);
 	total_send = 0;
+	time_in_send = 0;
 	tx_begin_ns = current_nsec();
 
 	while (total_send < to_send_bytes) {
 		ssize_t sent;
+		size_t rest_bytes;
+		time_t before;
 
-		sent = write(fd, data, buf_size_bytes);
+		rest_bytes = to_send_bytes - total_send;
+
+		before = current_nsec();
+		sent = send(fd, data, (rest_bytes > buf_size_bytes) ?
+			    buf_size_bytes : rest_bytes,
+			    zerocopy ? MSG_ZEROCOPY : 0);
+		time_in_send += (current_nsec() - before);
 
 		if (sent <= 0)
 			error("write");
 
 		total_send += sent;
+
+		if (zerocopy) {
+			struct pollfd fds = { 0 };
+
+			fds.fd = fd;
+
+			if (poll(&fds, 1, -1) < 0) {
+				perror("poll");
+				exit(EXIT_FAILURE);
+			}
+
+			if (!(fds.revents & POLLERR)) {
+				fprintf(stderr, "POLLERR expected\n");
+				exit(EXIT_FAILURE);
+			}
+
+			vsock_recv_completion(fd, NULL);
+		}
 	}
 
 	tx_total_ns = current_nsec() - tx_begin_ns;
 
 	printf("total bytes sent: %zu\n", total_send);
 	printf("tx performance: %f Gbits/s\n",
-	       get_gbps(total_send * 8, tx_total_ns));
-	printf("total time in 'write()': %f sec\n",
+	       get_gbps(total_send * 8, time_in_send));
+	printf("total time in tx loop: %f sec\n",
 	       (float)tx_total_ns / NSEC_PER_SEC);
+	printf("time in 'send()': %f sec\n",
+	       (float)time_in_send / NSEC_PER_SEC);
 
 	close(fd);
-	free(data);
+
+	if (zerocopy)
+		munmap(data, buf_size_bytes);
+	else
+		free(data);
 }
 
 static const char optstring[] = "";
@@ -336,6 +389,11 @@ static const struct option longopts[] = {
 		.has_arg = required_argument,
 		.val = 'R',
 	},
+	{
+		.name = "zerocopy",
+		.has_arg = no_argument,
+		.val = 'Z',
+	},
 	{},
 };
 
@@ -351,6 +409,7 @@ static void usage(void)
 	       "  --help			This message\n"
 	       "  --sender   <cid>		Sender mode (receiver default)\n"
 	       "                                <cid> of the receiver to connect to\n"
+	       "  --zerocopy			Enable zerocopy (for sender mode only)\n"
 	       "  --port     <port>		Port (default %d)\n"
 	       "  --bytes    <bytes>KMG		Bytes to send (default %d)\n"
 	       "  --buf-size <bytes>KMG		Data buffer size (default %d). In sender mode\n"
@@ -413,6 +472,9 @@ int main(int argc, char **argv)
 		case 'H': /* Help. */
 			usage();
 			break;
+		case 'Z': /* Zerocopy. */
+			zerocopy = true;
+			break;
 		default:
 			usage();
 		}
-- 
cgit v1.2.3


From 8d211285c6d48baca4934c54b1965d4e75ce35e2 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Tue, 10 Oct 2023 22:15:24 +0300
Subject: test/vsock: io_uring rx/tx tests

This adds set of tests which use io_uring for rx/tx. This test suite is
implemented as separated util like 'vsock_test' and has the same set of
input arguments as 'vsock_test'. These tests only cover cases of data
transmission (no connect/bind/accept etc).

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/.gitignore         |   1 +
 tools/testing/vsock/Makefile           |   7 +-
 tools/testing/vsock/vsock_uring_test.c | 342 +++++++++++++++++++++++++++++++++
 3 files changed, 348 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/vsock/vsock_uring_test.c

(limited to 'tools')

diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore
index a8adcfdc292b..d9f798713cd7 100644
--- a/tools/testing/vsock/.gitignore
+++ b/tools/testing/vsock/.gitignore
@@ -3,3 +3,4 @@
 vsock_test
 vsock_diag_test
 vsock_perf
+vsock_uring_test
diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
index 228470ae33c2..a7f56a09ca9f 100644
--- a/tools/testing/vsock/Makefile
+++ b/tools/testing/vsock/Makefile
@@ -1,12 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0-only
 all: test vsock_perf
-test: vsock_test vsock_diag_test
+test: vsock_test vsock_diag_test vsock_uring_test
 vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_zerocopy_common.o
 vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o
 vsock_perf: vsock_perf.o msg_zerocopy_common.o
 
+vsock_uring_test: LDLIBS = -luring
+vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o
+
 CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
 .PHONY: all test clean
 clean:
-	${RM} *.o *.d vsock_test vsock_diag_test vsock_perf
+	${RM} *.o *.d vsock_test vsock_diag_test vsock_perf vsock_uring_test
 -include *.d
diff --git a/tools/testing/vsock/vsock_uring_test.c b/tools/testing/vsock/vsock_uring_test.c
new file mode 100644
index 000000000000..d976d35f0ba9
--- /dev/null
+++ b/tools/testing/vsock/vsock_uring_test.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* io_uring tests for vsock
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <liburing.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/kernel.h>
+#include <error.h>
+
+#include "util.h"
+#include "control.h"
+#include "msg_zerocopy_common.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE		4096
+#endif
+
+#define RING_ENTRIES_NUM	4
+
+#define VSOCK_TEST_DATA_MAX_IOV 3
+
+struct vsock_io_uring_test {
+	/* Number of valid elements in 'vecs'. */
+	int vecs_cnt;
+	struct iovec vecs[VSOCK_TEST_DATA_MAX_IOV];
+};
+
+static struct vsock_io_uring_test test_data_array[] = {
+	/* All elements have page aligned base and size. */
+	{
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, 2 * PAGE_SIZE },
+			{ NULL, 3 * PAGE_SIZE },
+		}
+	},
+	/* Middle element has both non-page aligned base and size. */
+	{
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ (void *)1, 200  },
+			{ NULL, 3 * PAGE_SIZE },
+		}
+	}
+};
+
+static void vsock_io_uring_client(const struct test_opts *opts,
+				  const struct vsock_io_uring_test *test_data,
+				  bool msg_zerocopy)
+{
+	struct io_uring_sqe *sqe;
+	struct io_uring_cqe *cqe;
+	struct io_uring ring;
+	struct iovec *iovec;
+	struct msghdr msg;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (msg_zerocopy)
+		enable_so_zerocopy(fd);
+
+	iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
+
+	if (io_uring_queue_init(RING_ENTRIES_NUM, &ring, 0))
+		error(1, errno, "io_uring_queue_init");
+
+	if (io_uring_register_buffers(&ring, iovec, test_data->vecs_cnt))
+		error(1, errno, "io_uring_register_buffers");
+
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = iovec;
+	msg.msg_iovlen = test_data->vecs_cnt;
+	sqe = io_uring_get_sqe(&ring);
+
+	if (msg_zerocopy)
+		io_uring_prep_sendmsg_zc(sqe, fd, &msg, 0);
+	else
+		io_uring_prep_sendmsg(sqe, fd, &msg, 0);
+
+	if (io_uring_submit(&ring) != 1)
+		error(1, errno, "io_uring_submit");
+
+	if (io_uring_wait_cqe(&ring, &cqe))
+		error(1, errno, "io_uring_wait_cqe");
+
+	io_uring_cqe_seen(&ring, cqe);
+
+	control_writeulong(iovec_hash_djb2(iovec, test_data->vecs_cnt));
+
+	control_writeln("DONE");
+	io_uring_queue_exit(&ring);
+	free_test_iovec(test_data->vecs, iovec, test_data->vecs_cnt);
+	close(fd);
+}
+
+static void vsock_io_uring_server(const struct test_opts *opts,
+				  const struct vsock_io_uring_test *test_data)
+{
+	unsigned long remote_hash;
+	unsigned long local_hash;
+	struct io_uring ring;
+	size_t data_len;
+	size_t recv_len;
+	void *data;
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	data_len = iovec_bytes(test_data->vecs, test_data->vecs_cnt);
+
+	data = malloc(data_len);
+	if (!data) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	if (io_uring_queue_init(RING_ENTRIES_NUM, &ring, 0))
+		error(1, errno, "io_uring_queue_init");
+
+	recv_len = 0;
+
+	while (recv_len < data_len) {
+		struct io_uring_sqe *sqe;
+		struct io_uring_cqe *cqe;
+		struct iovec iovec;
+
+		sqe = io_uring_get_sqe(&ring);
+		iovec.iov_base = data + recv_len;
+		iovec.iov_len = data_len;
+
+		io_uring_prep_readv(sqe, fd, &iovec, 1, 0);
+
+		if (io_uring_submit(&ring) != 1)
+			error(1, errno, "io_uring_submit");
+
+		if (io_uring_wait_cqe(&ring, &cqe))
+			error(1, errno, "io_uring_wait_cqe");
+
+		recv_len += cqe->res;
+		io_uring_cqe_seen(&ring, cqe);
+	}
+
+	if (recv_len != data_len) {
+		fprintf(stderr, "expected %zu, got %zu\n", data_len,
+			recv_len);
+		exit(EXIT_FAILURE);
+	}
+
+	local_hash = hash_djb2(data, data_len);
+
+	remote_hash = control_readulong();
+	if (remote_hash != local_hash) {
+		fprintf(stderr, "hash mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	io_uring_queue_exit(&ring);
+	free(data);
+}
+
+void test_stream_uring_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_server(opts, &test_data_array[i]);
+}
+
+void test_stream_uring_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_client(opts, &test_data_array[i], false);
+}
+
+void test_stream_uring_msg_zc_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_server(opts, &test_data_array[i]);
+}
+
+void test_stream_uring_msg_zc_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_client(opts, &test_data_array[i], true);
+}
+
+static struct test_case test_cases[] = {
+	{
+		.name = "SOCK_STREAM io_uring test",
+		.run_server = test_stream_uring_server,
+		.run_client = test_stream_uring_client,
+	},
+	{
+		.name = "SOCK_STREAM io_uring MSG_ZEROCOPY test",
+		.run_server = test_stream_uring_msg_zc_server,
+		.run_client = test_stream_uring_msg_zc_client,
+	},
+	{},
+};
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "control-host",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "control-port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "mode",
+		.has_arg = required_argument,
+		.val = 'm',
+	},
+	{
+		.name = "peer-cid",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = '?',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: vsock_uring_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n"
+		"\n"
+		"  Server: vsock_uring_test --control-port=1234 --mode=server --peer-cid=3\n"
+		"  Client: vsock_uring_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+		"\n"
+		"Run transmission tests using io_uring. Usage is the same as\n"
+		"in ./vsock_test\n"
+		"\n"
+		"Options:\n"
+		"  --help                 This help message\n"
+		"  --control-host <host>  Server IP address to connect to\n"
+		"  --control-port <port>  Server port to listen on/connect to\n"
+		"  --mode client|server   Server or client mode\n"
+		"  --peer-cid <cid>       CID of the other side\n"
+		);
+	exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+	const char *control_host = NULL;
+	const char *control_port = NULL;
+	struct test_opts opts = {
+		.mode = TEST_MODE_UNSET,
+		.peer_cid = VMADDR_CID_ANY,
+	};
+
+	init_signals();
+
+	for (;;) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'H':
+			control_host = optarg;
+			break;
+		case 'm':
+			if (strcmp(optarg, "client") == 0) {
+				opts.mode = TEST_MODE_CLIENT;
+			} else if (strcmp(optarg, "server") == 0) {
+				opts.mode = TEST_MODE_SERVER;
+			} else {
+				fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'p':
+			opts.peer_cid = parse_cid(optarg);
+			break;
+		case 'P':
+			control_port = optarg;
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	}
+
+	if (!control_port)
+		usage();
+	if (opts.mode == TEST_MODE_UNSET)
+		usage();
+	if (opts.peer_cid == VMADDR_CID_ANY)
+		usage();
+
+	if (!control_host) {
+		if (opts.mode != TEST_MODE_SERVER)
+			usage();
+		control_host = "0.0.0.0";
+	}
+
+	control_init(control_host, control_port,
+		     opts.mode == TEST_MODE_SERVER);
+
+	run_tests(test_cases, &opts);
+
+	control_cleanup();
+
+	return 0;
+}
-- 
cgit v1.2.3


From 403376ddb4221be9db5326ae334773807df71ffe Mon Sep 17 00:00:00 2001
From: Xabier Marquiegui <reibax@gmail.com>
Date: Thu, 12 Oct 2023 00:39:57 +0200
Subject: ptp: add debugfs interface to see applied channel masks

Use debugfs to be able to view channel mask applied to every timestamp
event queue.

Every time the device is opened, a new entry is created in
`$DEBUGFS_MOUNTPOINT/ptpN/$INSTANCE_ADDRESS/mask`.

The mask value can be viewed grouped in 32bit decimal values using cat,
or converted to hexadecimal with the included `ptpchmaskfmt.sh` script.
32 bit values are listed from least significant to most significant.

Signed-off-by: Xabier Marquiegui <reibax@gmail.com>
Suggested-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c                   | 14 ++++++++++++++
 drivers/ptp/ptp_clock.c                     |  7 +++++++
 drivers/ptp/ptp_private.h                   |  4 ++++
 tools/testing/selftests/ptp/ptpchmaskfmt.sh | 14 ++++++++++++++
 4 files changed, 39 insertions(+)
 create mode 100644 tools/testing/selftests/ptp/ptpchmaskfmt.sh

(limited to 'tools')

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index ac2f2b5ea0b7..282cd7d24077 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/timekeeping.h>
+#include <linux/debugfs.h>
 
 #include <linux/nospec.h>
 
@@ -106,6 +107,7 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode)
 	struct ptp_clock *ptp =
 		container_of(pccontext->clk, struct ptp_clock, clock);
 	struct timestamp_event_queue *queue;
+	char debugfsname[32];
 
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 	if (!queue)
@@ -119,6 +121,17 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode)
 	spin_lock_init(&queue->lock);
 	list_add_tail(&queue->qlist, &ptp->tsevqs);
 	pccontext->private_clkdata = queue;
+
+	/* Debugfs contents */
+	sprintf(debugfsname, "0x%p", queue);
+	queue->debugfs_instance =
+		debugfs_create_dir(debugfsname, ptp->debugfs_root);
+	queue->dfs_bitmap.array = (u32 *)queue->mask;
+	queue->dfs_bitmap.n_elements =
+		DIV_ROUND_UP(PTP_MAX_CHANNELS, BITS_PER_BYTE * sizeof(u32));
+	debugfs_create_u32_array("mask", 0444, queue->debugfs_instance,
+				 &queue->dfs_bitmap);
+
 	return 0;
 }
 
@@ -128,6 +141,7 @@ int ptp_release(struct posix_clock_context *pccontext)
 	unsigned long flags;
 
 	if (queue) {
+		debugfs_remove(queue->debugfs_instance);
 		pccontext->private_clkdata = NULL;
 		spin_lock_irqsave(&queue->lock, flags);
 		list_del(&queue->qlist);
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index ed16d9787ce9..2e801cd33220 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/debugfs.h>
 #include <uapi/linux/sched/types.h>
 
 #include "ptp_private.h"
@@ -185,6 +186,7 @@ static void ptp_clock_release(struct device *dev)
 	spin_unlock_irqrestore(&tsevq->lock, flags);
 	bitmap_free(tsevq->mask);
 	kfree(tsevq);
+	debugfs_remove(ptp->debugfs_root);
 	ida_free(&ptp_clocks_map, ptp->index);
 	kfree(ptp);
 }
@@ -218,6 +220,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	struct ptp_clock *ptp;
 	struct timestamp_event_queue *queue = NULL;
 	int err = 0, index, major = MAJOR(ptp_devt);
+	char debugfsname[8];
 	size_t size;
 
 	if (info->n_alarm > PTP_MAX_ALARMS)
@@ -339,6 +342,10 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 		return ERR_PTR(err);
 	}
 
+	/* Debugfs initialization */
+	sprintf(debugfsname, "ptp%d", ptp->index);
+	ptp->debugfs_root = debugfs_create_dir(debugfsname, NULL);
+
 	return ptp;
 
 no_pps:
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index ad4ce1b25c86..52f87e394aa6 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -17,6 +17,7 @@
 #include <linux/time.h>
 #include <linux/list.h>
 #include <linux/bitmap.h>
+#include <linux/debugfs.h>
 
 #define PTP_MAX_TIMESTAMPS 128
 #define PTP_BUF_TIMESTAMPS 30
@@ -30,6 +31,8 @@ struct timestamp_event_queue {
 	spinlock_t lock;
 	struct list_head qlist;
 	unsigned long *mask;
+	struct dentry *debugfs_instance;
+	struct debugfs_u32_array dfs_bitmap;
 };
 
 struct ptp_clock {
@@ -57,6 +60,7 @@ struct ptp_clock {
 	struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */
 	bool is_virtual_clock;
 	bool has_cycles;
+	struct dentry *debugfs_root;
 };
 
 #define info_to_vclock(d) container_of((d), struct ptp_vclock, info)
diff --git a/tools/testing/selftests/ptp/ptpchmaskfmt.sh b/tools/testing/selftests/ptp/ptpchmaskfmt.sh
new file mode 100644
index 000000000000..0a06ba8af300
--- /dev/null
+++ b/tools/testing/selftests/ptp/ptpchmaskfmt.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Simple helper script to transform ptp debugfs timestamp event queue filtering
+# masks from decimal values to hexadecimal values
+
+# Only takes the debugfs mask file path as an argument
+DEBUGFS_MASKFILE="${1}"
+
+#shellcheck disable=SC2013,SC2086
+for int in $(cat "$DEBUGFS_MASKFILE") ; do
+    printf '0x%08X ' "$int"
+done
+echo
-- 
cgit v1.2.3


From 26285e689c6cd2cf3849568c83b2ebe53f467143 Mon Sep 17 00:00:00 2001
From: Xabier Marquiegui <reibax@gmail.com>
Date: Thu, 12 Oct 2023 00:39:58 +0200
Subject: ptp: add testptp mask test

Add option to test timestamp event queue mask manipulation in testptp.

Option -F allows the user to specify a single channel that will be
applied on the mask filter via IOCTL.

The test program will maintain the file open until user input is
received.

This allows checking the effect of the IOCTL in debugfs.

eg:

Console 1:
```
Channel 12 exclusively enabled. Check on debugfs.
Press any key to continue
```

Console 2:
```
0x00000000 0x00000001 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000
0x00000000 0x00000000 0x00000000 0x00000000
```

Signed-off-by: Xabier Marquiegui <reibax@gmail.com>
Suggested-by: Richard Cochran <richardcochran@gmail.com>
Suggested-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/ptp/testptp.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index c9f6cca4feb4..011252fe238c 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -121,6 +121,7 @@ static void usage(char *progname)
 		" -d name    device to open\n"
 		" -e val     read 'val' external time stamp events\n"
 		" -f val     adjust the ptp clock frequency by 'val' ppb\n"
+		" -F chan    Enable single channel mask and keep device open for debugfs verification.\n"
 		" -g         get the ptp clock time\n"
 		" -h         prints this message\n"
 		" -i val     index for event/trigger\n"
@@ -187,6 +188,7 @@ int main(int argc, char *argv[])
 	int pps = -1;
 	int seconds = 0;
 	int settime = 0;
+	int channel = -1;
 
 	int64_t t1, t2, tp;
 	int64_t interval, offset;
@@ -196,7 +198,7 @@ int main(int argc, char *argv[])
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xz"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -210,6 +212,9 @@ int main(int argc, char *argv[])
 		case 'f':
 			adjfreq = atoi(optarg);
 			break;
+		case 'F':
+			channel = atoi(optarg);
+			break;
 		case 'g':
 			gettime = 1;
 			break;
@@ -604,6 +609,18 @@ int main(int argc, char *argv[])
 		free(xts);
 	}
 
+	if (channel >= 0) {
+		if (ioctl(fd, PTP_MASK_CLEAR_ALL)) {
+			perror("PTP_MASK_CLEAR_ALL");
+		} else if (ioctl(fd, PTP_MASK_EN_SINGLE, (unsigned int *)&channel)) {
+			perror("PTP_MASK_EN_SINGLE");
+		} else {
+			printf("Channel %d exclusively enabled. Check on debugfs.\n", channel);
+			printf("Press any key to continue\n.");
+			getchar();
+		}
+	}
+
 	close(fd);
 	return 0;
 }
-- 
cgit v1.2.3


From 3c4fe89878feb57bea6ad9f14997298fddf8dc10 Mon Sep 17 00:00:00 2001
From: zhujun2 <zhujun2@cmss.chinamobile.com>
Date: Sun, 15 Oct 2023 23:30:39 -0700
Subject: selftests: net: remove unused variables

These variables are never referenced in the code, just remove them

Signed-off-by: zhujun2 <zhujun2@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/af_unix/scm_pidfd.c     | 1 -
 tools/testing/selftests/net/af_unix/test_unix_oob.c | 2 --
 tools/testing/selftests/net/nettest.c               | 5 +++--
 3 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c
index a86222143d79..7e534594167e 100644
--- a/tools/testing/selftests/net/af_unix/scm_pidfd.c
+++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c
@@ -294,7 +294,6 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract)
 static void client(FIXTURE_DATA(scm_pidfd) *self,
 		   const FIXTURE_VARIANT(scm_pidfd) *variant)
 {
-	int err;
 	int cfd;
 	socklen_t len;
 	struct ucred peer_cred;
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
index 532459a15067..a7c51889acd5 100644
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c
@@ -180,9 +180,7 @@ main(int argc, char **argv)
 	char buf[1024];
 	int on = 0;
 	char oob;
-	int flags;
 	int atmark;
-	char *tmp_file;
 
 	lfd = socket(AF_UNIX, SOCK_STREAM, 0);
 	memset(&consumer_addr, 0, sizeof(consumer_addr));
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 39a0e01f8554..cd8a58097448 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -1864,8 +1864,9 @@ static char *random_msg(int len)
 		n += i;
 		len -= i;
 	}
-	i = snprintf(m + n, olen - n, "%.*s", len,
-		     "abcdefghijklmnopqrstuvwxyz");
+
+	snprintf(m + n, olen - n, "%.*s", len,
+	     "abcdefghijklmnopqrstuvwxyz");
 	return m;
 }
 
-- 
cgit v1.2.3


From 2d78928c9cf7bee08c3e2344e6e1755412855448 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 11 Oct 2023 15:37:24 -0700
Subject: selftests/bpf: Improve percpu_alloc test robustness

Make these non-serial tests filter BPF programs by intended PID of
a test runner process. This makes it isolated from other parallel tests
that might interfere accidentally.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20231011223728.3188086-2-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/percpu_alloc.c              | 3 +++
 tools/testing/selftests/bpf/progs/percpu_alloc_array.c             | 7 +++++++
 .../testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c  | 4 ++++
 3 files changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 9541e9b3a034..343da65864d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -19,6 +19,7 @@ static void test_array(void)
 	bpf_program__set_autoload(skel->progs.test_array_map_3, true);
 	bpf_program__set_autoload(skel->progs.test_array_map_4, true);
 
+	skel->bss->my_pid = getpid();
 	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
 
 	err = percpu_alloc_array__load(skel);
@@ -51,6 +52,7 @@ static void test_array_sleepable(void)
 
 	bpf_program__set_autoload(skel->progs.test_array_map_10, true);
 
+	skel->bss->my_pid = getpid();
 	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
 
 	err = percpu_alloc_array__load(skel);
@@ -85,6 +87,7 @@ static void test_cgrp_local_storage(void)
 	if (!ASSERT_OK_PTR(skel, "percpu_alloc_cgrp_local_storage__open"))
 		goto close_fd;
 
+	skel->bss->my_pid = getpid();
 	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
 
 	err = percpu_alloc_cgrp_local_storage__load(skel);
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
index bbc45346e006..37c2d2608ec0 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -71,6 +71,7 @@ int BPF_PROG(test_array_map_2)
 }
 
 int cpu0_field_d, sum_field_c;
+int my_pid;
 
 /* Summarize percpu data */
 SEC("?fentry/bpf_fentry_test3")
@@ -81,6 +82,9 @@ int BPF_PROG(test_array_map_3)
 	struct val_t *v;
 	struct elem *e;
 
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
 	e = bpf_map_lookup_elem(&array, &index);
 	if (!e)
 		return 0;
@@ -130,6 +134,9 @@ int BPF_PROG(test_array_map_10)
 	struct val_t *v;
 	struct elem *e;
 
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
 	e = bpf_map_lookup_elem(&array, &index);
 	if (!e)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
index 1c36a241852c..a2acf9aa6c24 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
@@ -70,6 +70,7 @@ int BPF_PROG(test_cgrp_local_storage_2)
 }
 
 int cpu0_field_d, sum_field_c;
+int my_pid;
 
 /* Summarize percpu data collection */
 SEC("fentry/bpf_fentry_test3")
@@ -81,6 +82,9 @@ int BPF_PROG(test_cgrp_local_storage_3)
 	struct elem *e;
 	int i;
 
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
 	task = bpf_get_current_task_btf();
 	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0);
 	if (!e)
-- 
cgit v1.2.3


From 08a7078feacf419305d86d36b974c48347f3abb0 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 11 Oct 2023 15:37:25 -0700
Subject: selftests/bpf: Improve missed_kprobe_recursion test robustness

Given missed_kprobe_recursion is non-serial and uses common testing
kfuncs to count number of recursion misses it's possible that some other
parallel test can trigger extraneous recursion misses. So we can't
expect exactly 1 miss. Relax conditions and expect at least one.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20231011223728.3188086-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/missed.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
index 24ade11f5c05..70d90c43537c 100644
--- a/tools/testing/selftests/bpf/prog_tests/missed.c
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -81,10 +81,10 @@ static void test_missed_kprobe_recursion(void)
 	ASSERT_EQ(topts.retval, 0, "test_run");
 
 	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test1)), 0, "test1_recursion_misses");
-	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
-	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
-	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
-	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses");
 
 cleanup:
 	missed_kprobe_recursion__destroy(skel);
-- 
cgit v1.2.3


From cde785142885e1fc62a9ae92e7aae90285ed3d79 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 11 Oct 2023 15:37:26 -0700
Subject: selftests/bpf: Make align selftests more robust

Align subtest is very specific and finicky about expected verifier log
output and format. This is often completely unnecessary as in a bunch of
situations test actually cares about var_off part of register state. But
given how exact it is right now, any tiny verifier log changes can lead
to align tests failures, requiring constant adjustment.

This patch tries to make this a bit more robust by making logic first
search for specified register and then allowing to match only portion of
register state, not everything exactly. This will come handly with
follow up changes to SCALAR register output disambiguation.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20231011223728.3188086-4-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/align.c | 241 +++++++++++++------------
 1 file changed, 121 insertions(+), 120 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index b92770592563..465c1c3a3d3c 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -6,6 +6,7 @@
 
 struct bpf_reg_match {
 	unsigned int line;
+	const char *reg;
 	const char *match;
 };
 
@@ -39,13 +40,13 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=2"},
-			{1, "R3_w=4"},
-			{2, "R3_w=8"},
-			{3, "R3_w=16"},
-			{4, "R3_w=32"},
+			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R10", "fp0"},
+			{0, "R3_w", "2"},
+			{1, "R3_w", "4"},
+			{2, "R3_w", "8"},
+			{3, "R3_w", "16"},
+			{4, "R3_w", "32"},
 		},
 	},
 	{
@@ -67,19 +68,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=1"},
-			{1, "R3_w=2"},
-			{2, "R3_w=4"},
-			{3, "R3_w=8"},
-			{4, "R3_w=16"},
-			{5, "R3_w=1"},
-			{6, "R4_w=32"},
-			{7, "R4_w=16"},
-			{8, "R4_w=8"},
-			{9, "R4_w=4"},
-			{10, "R4_w=2"},
+			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R10", "fp0"},
+			{0, "R3_w", "1"},
+			{1, "R3_w", "2"},
+			{2, "R3_w", "4"},
+			{3, "R3_w", "8"},
+			{4, "R3_w", "16"},
+			{5, "R3_w", "1"},
+			{6, "R4_w", "32"},
+			{7, "R4_w", "16"},
+			{8, "R4_w", "8"},
+			{9, "R4_w", "4"},
+			{10, "R4_w", "2"},
 		},
 	},
 	{
@@ -96,14 +97,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=4"},
-			{1, "R3_w=8"},
-			{2, "R3_w=10"},
-			{3, "R4_w=8"},
-			{4, "R4_w=12"},
-			{5, "R4_w=14"},
+			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R10", "fp0"},
+			{0, "R3_w", "4"},
+			{1, "R3_w", "8"},
+			{2, "R3_w", "10"},
+			{3, "R4_w", "8"},
+			{4, "R4_w", "12"},
+			{5, "R4_w", "14"},
 		},
 	},
 	{
@@ -118,12 +119,12 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=7"},
-			{1, "R3_w=7"},
-			{2, "R3_w=14"},
-			{3, "R3_w=56"},
+			{0, "R1", "ctx(off=0,imm=0)"},
+			{0, "R10", "fp0"},
+			{0, "R3_w", "7"},
+			{1, "R3_w", "7"},
+			{2, "R3_w", "14"},
+			{3, "R3_w", "56"},
 		},
 	},
 
@@ -161,19 +162,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R0_w=pkt(off=8,r=8,imm=0)"},
-			{6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{7, "R3_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
-			{8, "R3_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{9, "R3_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{10, "R3_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
-			{12, "R3_w=pkt_end(off=0,imm=0)"},
-			{17, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{18, "R4_w=scalar(umax=8160,var_off=(0x0; 0x1fe0))"},
-			{19, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
-			{20, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{21, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{22, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
+			{6, "R0_w", "pkt(off=8,r=8,imm=0)"},
+			{6, "R3_w", "var_off=(0x0; 0xff)"},
+			{7, "R3_w", "var_off=(0x0; 0x1fe)"},
+			{8, "R3_w", "var_off=(0x0; 0x3fc)"},
+			{9, "R3_w", "var_off=(0x0; 0x7f8)"},
+			{10, "R3_w", "var_off=(0x0; 0xff0)"},
+			{12, "R3_w", "pkt_end(off=0,imm=0)"},
+			{17, "R4_w", "var_off=(0x0; 0xff)"},
+			{18, "R4_w", "var_off=(0x0; 0x1fe0)"},
+			{19, "R4_w", "var_off=(0x0; 0xff0)"},
+			{20, "R4_w", "var_off=(0x0; 0x7f8)"},
+			{21, "R4_w", "var_off=(0x0; 0x3fc)"},
+			{22, "R4_w", "var_off=(0x0; 0x1fe)"},
 		},
 	},
 	{
@@ -194,16 +195,16 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{7, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{8, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{9, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{10, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
-			{11, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{12, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{13, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{14, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{15, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
+			{6, "R3_w", "var_off=(0x0; 0xff)"},
+			{7, "R4_w", "var_off=(0x0; 0xff)"},
+			{8, "R4_w", "var_off=(0x0; 0xff)"},
+			{9, "R4_w", "var_off=(0x0; 0xff)"},
+			{10, "R4_w", "var_off=(0x0; 0x1fe)"},
+			{11, "R4_w", "var_off=(0x0; 0xff)"},
+			{12, "R4_w", "var_off=(0x0; 0x3fc)"},
+			{13, "R4_w", "var_off=(0x0; 0xff)"},
+			{14, "R4_w", "var_off=(0x0; 0x7f8)"},
+			{15, "R4_w", "var_off=(0x0; 0xff0)"},
 		},
 	},
 	{
@@ -234,14 +235,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{2, "R5_w=pkt(off=0,r=0,imm=0)"},
-			{4, "R5_w=pkt(off=14,r=0,imm=0)"},
-			{5, "R4_w=pkt(off=14,r=0,imm=0)"},
-			{9, "R2=pkt(off=0,r=18,imm=0)"},
-			{10, "R5=pkt(off=14,r=18,imm=0)"},
-			{10, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{13, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"},
-			{14, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"},
+			{2, "R5_w", "pkt(off=0,r=0,imm=0)"},
+			{4, "R5_w", "pkt(off=14,r=0,imm=0)"},
+			{5, "R4_w", "pkt(off=14,r=0,imm=0)"},
+			{9, "R2", "pkt(off=0,r=18,imm=0)"},
+			{10, "R5", "pkt(off=14,r=18,imm=0)"},
+			{10, "R4_w", "var_off=(0x0; 0xff)"},
+			{13, "R4_w", "var_off=(0x0; 0xffff)"},
+			{14, "R4_w", "var_off=(0x0; 0xffff)"},
 		},
 	},
 	{
@@ -298,20 +299,20 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
 			 */
-			{11, "R5_w=pkt(id=1,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{11, "R5_w", "pkt(id=1,off=14,"},
 			/* At the time the word size load is performed from R5,
 			 * it's total offset is NET_IP_ALIGN + reg->off (0) +
 			 * reg->aux_off (14) which is 16.  Then the variable
 			 * offset is considered using reg->aux_off_align which
 			 * is 4 and meets the load's requirements.
 			 */
-			{15, "R4=pkt(id=1,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
-			{15, "R5=pkt(id=1,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{15, "R4", "var_off=(0x0; 0x3fc)"},
+			{15, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Variable offset is added to R5 packet pointer,
 			 * resulting in auxiliary alignment of 4. To avoid BPF
 			 * verifier's precision backtracking logging
@@ -319,46 +320,46 @@ static struct bpf_align_test tests[] = {
 			 * instruction to validate R5 state. We also check
 			 * that R4 is what it should be in such case.
 			 */
-			{18, "R4_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
-			{18, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R4_w", "var_off=(0x0; 0x3fc)"},
+			{18, "R5_w", "var_off=(0x0; 0x3fc)"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{19, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R5_w", "pkt(id=2,off=14,"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
 			 * aligned, so the total offset is 4-byte aligned and
 			 * meets the load's requirements.
 			 */
-			{24, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
-			{24, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R4", "var_off=(0x0; 0x3fc)"},
+			{24, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w=pkt(off=14,r=8"},
+			{26, "R5_w", "pkt(off=14,r=8,"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n). See comment for insn #18
 			 * for R4 = R5 trick.
 			 */
-			{28, "R4_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
-			{28, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{28, "R4_w", "var_off=(0x0; 0x3fc)"},
+			{28, "R5_w", "var_off=(0x0; 0x3fc)"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{29, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{29, "R5_w", "pkt(id=3,off=18,"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{31, "R4_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
-			{31, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
+			{31, "R4_w", "var_off=(0x0; 0x7fc)"},
+			{31, "R5_w", "var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{35, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
-			{35, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R4", "var_off=(0x0; 0x7fc)"},
+			{35, "R5", "var_off=(0x0; 0x7fc)"},
 		},
 	},
 	{
@@ -396,36 +397,36 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{7, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{8, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"},
+			{8, "R6_w", "var_off=(0x2; 0x7fc)"},
 			/* Packet pointer has (4n+2) offset */
-			{11, "R5_w=pkt(id=1,off=0,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
-			{12, "R4=pkt(id=1,off=4,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
+			{11, "R5_w", "var_off=(0x2; 0x7fc)"},
+			{12, "R4", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{15, "R5=pkt(id=1,off=0,r=4,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
+			{15, "R5", "var_off=(0x2; 0x7fc)"},
 			/* Newly read value in R6 was shifted left by 2, so has
 			 * known alignment of 4.
 			 */
-			{17, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{17, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Added (4n) to packet pointer's (4n+2) var_off, giving
 			 * another (4n+2).
 			 */
-			{19, "R5_w=pkt(id=2,off=0,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
-			{20, "R4=pkt(id=2,off=4,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
+			{19, "R5_w", "var_off=(0x2; 0xffc)"},
+			{20, "R4", "var_off=(0x2; 0xffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{23, "R5=pkt(id=2,off=0,r=4,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
+			{23, "R5", "var_off=(0x2; 0xffc)"},
 		},
 	},
 	{
@@ -458,18 +459,18 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{3, "R5_w=pkt_end(off=0,imm=0)"},
+			{3, "R5_w", "pkt_end(off=0,imm=0)"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
-			{5, "R5_w=scalar(smax=9223372036854775804,umax=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
+			{5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
 			 * the add could overflow.
 			 */
-			{6, "R5_w=scalar(smin=-9223372036854775806,smax=9223372036854775806,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{6, "R5_w", "var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>=0 */
-			{9, "R5=scalar(umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{9, "R5", "var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* packet pointer + nonnegative (4n+2) */
-			{11, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
-			{12, "R4_w=pkt(id=1,off=4,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{11, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
+			{12, "R4_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@@ -477,7 +478,7 @@ static struct bpf_align_test tests[] = {
 			 * So we did not get a 'range' on R6, and the access
 			 * attempt will fail.
 			 */
-			{15, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{15, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
 		}
 	},
 	{
@@ -512,24 +513,23 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{8, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{8, "R6_w", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{9, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"},
+			{9, "R6_w", "var_off=(0x2; 0x7fc)"},
 			/* New unknown value in R7 is (4n) */
-			{10, "R7_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{10, "R7_w", "var_off=(0x0; 0x3fc)"},
 			/* Subtracting it from R6 blows our unsigned bounds */
-			{11, "R6=scalar(smin=-1006,smax=1034,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{11, "R6", "var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>= 0 */
-			{14, "R6=scalar(umin=2,umax=1034,var_off=(0x2; 0x7fc))"},
+			{14, "R6", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=2,off=0,r=4,umin=2,umax=1034,var_off=(0x2; 0x7fc)"},
-
+			{20, "R5", "var_off=(0x2; 0x7fc)"},
 		},
 	},
 	{
@@ -566,23 +566,23 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{9, "R6_w=scalar(umax=60,var_off=(0x0; 0x3c))"},
+			{6, "R2_w", "pkt(off=0,r=8,imm=0)"},
+			{9, "R6_w", "var_off=(0x0; 0x3c)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{10, "R6_w=scalar(umin=14,umax=74,var_off=(0x2; 0x7c))"},
+			{10, "R6_w", "var_off=(0x2; 0x7c)"},
 			/* Subtracting from packet pointer overflows ubounds */
-			{13, "R5_w=pkt(id=2,off=0,r=8,umin=18446744073709551542,umax=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
+			{13, "R5_w", "var_off=(0xffffffffffffff82; 0x7c)"},
 			/* New unknown value in R7 is (4n), >= 76 */
-			{14, "R7_w=scalar(umin=76,umax=1096,var_off=(0x0; 0x7fc))"},
+			{14, "R7_w", "var_off=(0x0; 0x7fc)"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5_w=pkt(id=3,off=0,r=0,umin=2,umax=1082,var_off=(0x2; 0x7fc)"},
+			{16, "R5_w", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=3,off=0,r=4,umin=2,umax=1082,var_off=(0x2; 0x7fc)"},
+			{20, "R5", "var_off=(0x2; 0x7fc)"},
 		},
 	},
 };
@@ -635,6 +635,7 @@ static int do_test_single(struct bpf_align_test *test)
 		line_ptr = strtok(bpf_vlog_copy, "\n");
 		for (i = 0; i < MAX_MATCHES; i++) {
 			struct bpf_reg_match m = test->matches[i];
+			const char *p;
 			int tmp;
 
 			if (!m.match)
@@ -649,8 +650,8 @@ static int do_test_single(struct bpf_align_test *test)
 				line_ptr = strtok(NULL, "\n");
 			}
 			if (!line_ptr) {
-				printf("Failed to find line %u for match: %s\n",
-				       m.line, m.match);
+				printf("Failed to find line %u for match: %s=%s\n",
+				       m.line, m.reg, m.match);
 				ret = 1;
 				printf("%s", bpf_vlog);
 				break;
@@ -667,15 +668,15 @@ static int do_test_single(struct bpf_align_test *test)
 			 *   6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0
 			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(off=0,r=8,imm=0) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
 			 */
-			while (!strstr(line_ptr, m.match)) {
+			while (!(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
 				cur_line = -1;
 				line_ptr = strtok(NULL, "\n");
 				sscanf(line_ptr ?: "", "%u: ", &cur_line);
 				if (!line_ptr || cur_line != m.line)
 					break;
 			}
-			if (cur_line != m.line || !line_ptr || !strstr(line_ptr, m.match)) {
-				printf("Failed to find match %u: %s\n", m.line, m.match);
+			if (cur_line != m.line || !line_ptr || !(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
+				printf("Failed to find match %u: %s=%s\n", m.line, m.reg, m.match);
 				ret = 1;
 				printf("%s", bpf_vlog);
 				break;
-- 
cgit v1.2.3


From 72f8a1de4a7ecb23393a920dface58d5a96f42d8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 11 Oct 2023 15:37:27 -0700
Subject: bpf: Disambiguate SCALAR register state output in verifier logs

Currently the way that verifier prints SCALAR_VALUE register state (and
PTR_TO_PACKET, which can have var_off and ranges info as well) is very
ambiguous.

In the name of brevity we are trying to eliminate "unnecessary" output
of umin/umax, smin/smax, u32_min/u32_max, and s32_min/s32_max values, if
possible. Current rules are that if any of those have their default
value (which for mins is the minimal value of its respective types: 0,
S32_MIN, or S64_MIN, while for maxs it's U32_MAX, S32_MAX, S64_MAX, or
U64_MAX) *OR* if there is another min/max value that as matching value.
E.g., if smin=100 and umin=100, we'll emit only umin=10, omitting smin
altogether. This approach has a few problems, being both ambiguous and
sort-of incorrect in some cases.

Ambiguity is due to missing value could be either default value or value
of umin/umax or smin/smax. This is especially confusing when we mix
signed and unsigned ranges. Quite often, umin=0 and smin=0, and so we'll
have only `umin=0` leaving anyone reading verifier log to guess whether
smin is actually 0 or it's actually -9223372036854775808 (S64_MIN). And
often times it's important to know, especially when debugging tricky
issues.

"Sort-of incorrectness" comes from mixing negative and positive values.
E.g., if umin is some large positive number, it can be equal to smin
which is, interpreted as signed value, is actually some negative value.
Currently, that smin will be omitted and only umin will be emitted with
a large positive value, giving an impression that smin is also positive.

Anyway, ambiguity is the biggest issue making it impossible to have an
exact understanding of register state, preventing any sort of automated
testing of verifier state based on verifier log. This patch is
attempting to rectify the situation by removing ambiguity, while
minimizing the verboseness of register state output.

The rules are straightforward:
  - if some of the values are missing, then it definitely has a default
  value. I.e., `umin=0` means that umin is zero, but smin is actually
  S64_MIN;
  - all the various boundaries that happen to have the same value are
  emitted in one equality separated sequence. E.g., if umin and smin are
  both 100, we'll emit `smin=umin=100`, making this explicit;
  - we do not mix negative and positive values together, and even if
  they happen to have the same bit-level value, they will be emitted
  separately with proper sign. I.e., if both umax and smax happen to be
  0xffffffffffffffff, we'll emit them both separately as
  `smax=-1,umax=18446744073709551615`;
  - in the name of a bit more uniformity and consistency,
  {u32,s32}_{min,max} are renamed to {s,u}{min,max}32, which seems to
  improve readability.

The above means that in case of all 4 ranges being, say, [50, 100] range,
we'd previously see hugely ambiguous:

    R1=scalar(umin=50,umax=100)

Now, we'll be more explicit:

    R1=scalar(smin=umin=smin32=umin32=50,smax=umax=smax32=umax32=100)

This is slightly more verbose, but distinct from the case when we don't
know anything about signed boundaries and 32-bit boundaries, which under
new rules will match the old case:

    R1=scalar(umin=50,umax=100)

Also, in the name of simplicity of implementation and consistency, order
for {s,u}32_{min,max} are emitted *before* var_off. Previously they were
emitted afterwards, for unclear reasons.

This patch also includes a few fixes to selftests that expect exact
register state to accommodate slight changes to verifier format. You can
see that the changes are pretty minimal in common cases.

Note, the special case when SCALAR_VALUE register is a known constant
isn't changed, we'll emit constant value once, interpreted as signed
value.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20231011223728.3188086-5-andrii@kernel.org
---
 kernel/bpf/verifier.c                              | 67 +++++++++++++++-------
 .../selftests/bpf/progs/exceptions_assert.c        | 18 +++---
 tools/testing/selftests/bpf/progs/verifier_ldsx.c  |  2 +-
 3 files changed, 55 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e777f50401b6..82ae14f32a01 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1342,6 +1342,50 @@ static void scrub_spilled_slot(u8 *stype)
 		*stype = STACK_MISC;
 }
 
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+				const struct bpf_reg_state *reg,
+				const char **sep)
+{
+	struct {
+		const char *name;
+		u64 val;
+		bool omit;
+	} minmaxs[] = {
+		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
+		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
+		{"umin",   reg->umin_value,         reg->umin_value == 0},
+		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
+		{"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+		{"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
+		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
+	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+	bool neg1, neg2;
+
+	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+		if (m1->omit)
+			continue;
+
+		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+		verbose(env, "%s%s=", *sep, m1->name);
+		*sep = ",";
+
+		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+			if (m2->omit || m2->val != m1->val)
+				continue;
+			/* don't mix negatives with positives */
+			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+			if (neg2 != neg1)
+				continue;
+			m2->omit = true;
+			verbose(env, "%s=", m2->name);
+		}
+
+		verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
+	}
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
 				 const struct bpf_func_state *state,
 				 bool print_all)
@@ -1405,34 +1449,13 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 				 */
 				verbose_a("imm=%llx", reg->var_off.value);
 			} else {
-				if (reg->smin_value != reg->umin_value &&
-				    reg->smin_value != S64_MIN)
-					verbose_a("smin=%lld", (long long)reg->smin_value);
-				if (reg->smax_value != reg->umax_value &&
-				    reg->smax_value != S64_MAX)
-					verbose_a("smax=%lld", (long long)reg->smax_value);
-				if (reg->umin_value != 0)
-					verbose_a("umin=%llu", (unsigned long long)reg->umin_value);
-				if (reg->umax_value != U64_MAX)
-					verbose_a("umax=%llu", (unsigned long long)reg->umax_value);
+				print_scalar_ranges(env, reg, &sep);
 				if (!tnum_is_unknown(reg->var_off)) {
 					char tn_buf[48];
 
 					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
 					verbose_a("var_off=%s", tn_buf);
 				}
-				if (reg->s32_min_value != reg->smin_value &&
-				    reg->s32_min_value != S32_MIN)
-					verbose_a("s32_min=%d", (int)(reg->s32_min_value));
-				if (reg->s32_max_value != reg->smax_value &&
-				    reg->s32_max_value != S32_MAX)
-					verbose_a("s32_max=%d", (int)(reg->s32_max_value));
-				if (reg->u32_min_value != reg->umin_value &&
-				    reg->u32_min_value != U32_MIN)
-					verbose_a("u32_min=%d", (int)(reg->u32_min_value));
-				if (reg->u32_max_value != reg->umax_value &&
-				    reg->u32_max_value != U32_MAX)
-					verbose_a("u32_max=%d", (int)(reg->u32_max_value));
 			}
 #undef verbose_a
 
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index fa35832e6748..e1e5c54a6a11 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -31,35 +31,35 @@ check_assert(s64, eq, llong_max, LLONG_MAX);
 
 __msg(": R0_w=scalar(smax=2147483646) R10=fp0")
 check_assert(s64, lt, pos, INT_MAX);
-__msg(": R0_w=scalar(umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, lt, zero, 0);
-__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, lt, neg, INT_MIN);
 
 __msg(": R0_w=scalar(smax=2147483647) R10=fp0")
 check_assert(s64, le, pos, INT_MAX);
 __msg(": R0_w=scalar(smax=0) R10=fp0")
 check_assert(s64, le, zero, 0);
-__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, le, neg, INT_MIN);
 
-__msg(": R0_w=scalar(umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, gt, pos, INT_MAX);
-__msg(": R0_w=scalar(umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, gt, zero, 0);
 __msg(": R0_w=scalar(smin=-2147483647) R10=fp0")
 check_assert(s64, gt, neg, INT_MIN);
 
-__msg(": R0_w=scalar(umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, ge, pos, INT_MAX);
-__msg(": R0_w=scalar(umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
+__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
 check_assert(s64, ge, zero, 0);
 __msg(": R0_w=scalar(smin=-2147483648) R10=fp0")
 check_assert(s64, ge, neg, INT_MIN);
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=-2147483646,smax=2147483645) R10=fp0")
+__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0")
 int check_assert_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;
@@ -75,7 +75,7 @@ int check_assert_range_s64(struct __sk_buff *ctx)
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R1=ctx(off=0,imm=0) R2=scalar(umin=4096,umax=8192,var_off=(0x0; 0x3fff))")
+__msg(": R1=ctx(off=0,imm=0) R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
 int check_assert_range_u64(struct __sk_buff *ctx)
 {
 	u64 num = ctx->len;
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index f90016a57eec..375525329637 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -64,7 +64,7 @@ __naked void ldsx_s32(void)
 SEC("socket")
 __description("LDSX, S8 range checking, privileged")
 __log_level(2) __success __retval(1)
-__msg("R1_w=scalar(smin=-128,smax=127)")
+__msg("R1_w=scalar(smin=smin32=-128,smax=smax32=127)")
 __naked void ldsx_s8_range_priv(void)
 {
 	asm volatile (
-- 
cgit v1.2.3


From 137df1189d128a6b5dee2f653e054b40ef36b94c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 16 Oct 2023 11:28:40 -0700
Subject: libbpf: Don't assume SHT_GNU_verdef presence for SHT_GNU_versym
 section

Fix too eager assumption that SHT_GNU_verdef ELF section is going to be
present whenever binary has SHT_GNU_versym section. It seems like either
SHT_GNU_verdef or SHT_GNU_verneed can be used, so failing on missing
SHT_GNU_verdef actually breaks use cases in production.

One specific reported issue, which was used to manually test this fix,
was trying to attach to `readline` function in BASH binary.

Fixes: bb7fa09399b9 ("libbpf: Support symbol versioning for uprobe")
Reported-by: Liam Wisehart <liamwisehart@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Manu Bretelle <chantr4@gmail.com>
Reviewed-by: Fangrui Song <maskray@google.com>
Acked-by: Hengqi Chen <hengqi.chen@gmail.com>
Link: https://lore.kernel.org/bpf/20231016182840.4033346-1-andrii@kernel.org
---
 tools/lib/bpf/elf.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 2a158e8a8b7c..2a62bf411bb3 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -141,14 +141,15 @@ static int elf_sym_iter_new(struct elf_sym_iter *iter,
 	iter->versyms = elf_getdata(scn, 0);
 
 	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
-	if (!scn) {
-		pr_debug("elf: failed to find verdef ELF sections in '%s'\n", binary_path);
-		return -ENOENT;
-	}
-	if (!gelf_getshdr(scn, &sh))
+	if (!scn)
+		return 0;
+
+	iter->verdefs = elf_getdata(scn, 0);
+	if (!iter->verdefs || !gelf_getshdr(scn, &sh)) {
+		pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path);
 		return -EINVAL;
+	}
 	iter->verdef_strtabidx = sh.sh_link;
-	iter->verdefs = elf_getdata(scn, 0);
 
 	return 0;
 }
@@ -199,6 +200,9 @@ static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
 	GElf_Verdef verdef;
 	int offset;
 
+	if (!iter->verdefs)
+		return NULL;
+
 	offset = 0;
 	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
 		if (verdef.vd_ndx != ver) {
-- 
cgit v1.2.3


From 44cb03f19b38c11cfc5bf76ea6d6885da210ded2 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sat, 7 Oct 2023 13:59:45 +0000
Subject: selftests/bpf: Add selftest for bpf_task_under_cgroup() in sleepable
 prog

The result is as follows:

  $ tools/testing/selftests/bpf/test_progs --name=task_under_cgroup
  #237     task_under_cgroup:OK
  Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED

Without the previous patch, there will be RCU warnings in dmesg when
CONFIG_PROVE_RCU is enabled. While with the previous patch, there will
be no warnings.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20231007135945.4306-2-laoar.shao@gmail.com
---
 .../selftests/bpf/prog_tests/task_under_cgroup.c   | 11 +++++++--
 .../selftests/bpf/progs/test_task_under_cgroup.c   | 28 +++++++++++++++++++++-
 2 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c
index 4224727fb364..626d76fe43a2 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c
@@ -30,8 +30,15 @@ void test_task_under_cgroup(void)
 	if (!ASSERT_OK(ret, "test_task_under_cgroup__load"))
 		goto cleanup;
 
-	ret = test_task_under_cgroup__attach(skel);
-	if (!ASSERT_OK(ret, "test_task_under_cgroup__attach"))
+	/* First, attach the LSM program, and then it will be triggered when the
+	 * TP_BTF program is attached.
+	 */
+	skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(skel->links.lsm_run, "attach_lsm"))
+		goto cleanup;
+
+	skel->links.tp_btf_run = bpf_program__attach_trace(skel->progs.tp_btf_run);
+	if (!ASSERT_OK_PTR(skel->links.tp_btf_run, "attach_tp_btf"))
 		goto cleanup;
 
 	pid = fork();
diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
index 56cdc0a553f0..7e750309ce27 100644
--- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
@@ -18,7 +18,7 @@ const volatile __u64 cgid;
 int remote_pid;
 
 SEC("tp_btf/task_newtask")
-int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags)
+int BPF_PROG(tp_btf_run, struct task_struct *task, u64 clone_flags)
 {
 	struct cgroup *cgrp = NULL;
 	struct task_struct *acquired;
@@ -48,4 +48,30 @@ out:
 	return 0;
 }
 
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	struct cgroup *cgrp = NULL;
+	struct task_struct *task;
+	int ret = 0;
+
+	task = bpf_get_current_task_btf();
+	if (local_pid != task->pid)
+		return 0;
+
+	if (cmd != BPF_LINK_CREATE)
+		return 0;
+
+	/* 1 is the root cgroup */
+	cgrp = bpf_cgroup_from_id(1);
+	if (!cgrp)
+		goto out;
+	if (!bpf_task_under_cgroup(task, cgrp))
+		ret = -1;
+	bpf_cgroup_release(cgrp);
+
+out:
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 24516309e330cd592c04d0467313d885584af4e8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 17 Oct 2023 10:17:28 +0200
Subject: selftests/bpf: Add additional mprog query test coverage

Add several new test cases which assert corner cases on the mprog query
mechanism, for example, around passing in a too small or a larger array
than the current count.

  ./test_progs -t tc_opts
  #252     tc_opts_after:OK
  #253     tc_opts_append:OK
  #254     tc_opts_basic:OK
  #255     tc_opts_before:OK
  #256     tc_opts_chain_classic:OK
  #257     tc_opts_chain_mixed:OK
  #258     tc_opts_delete_empty:OK
  #259     tc_opts_demixed:OK
  #260     tc_opts_detach:OK
  #261     tc_opts_detach_after:OK
  #262     tc_opts_detach_before:OK
  #263     tc_opts_dev_cleanup:OK
  #264     tc_opts_invalid:OK
  #265     tc_opts_max:OK
  #266     tc_opts_mixed:OK
  #267     tc_opts_prepend:OK
  #268     tc_opts_query:OK
  #269     tc_opts_query_attach:OK
  #270     tc_opts_replace:OK
  #271     tc_opts_revision:OK
  Summary: 20/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/bpf/20231017081728.24769-1-daniel@iogearbox.net
---
 tools/testing/selftests/bpf/prog_tests/tc_opts.c | 131 ++++++++++++++++++++++-
 1 file changed, 130 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index ca506d2fcf58..51883ccb8020 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -2471,7 +2471,7 @@ static void test_tc_opts_query_target(int target)
 	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
 	struct test_tc_link *skel;
 	union bpf_attr attr;
-	__u32 prog_ids[5];
+	__u32 prog_ids[10];
 	int err;
 
 	skel = test_tc_link__open_and_load();
@@ -2599,6 +2599,135 @@ static void test_tc_opts_query_target(int target)
 	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
 	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
 
+	/* Test 3: Query with smaller prog_ids array */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+	attr.query.count = 2;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, ENOSPC, "prog_query_should_fail");
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 4: Query with larger prog_ids array */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+	attr.query.count = 10;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 5: Query with NULL prog_ids array but with count > 0 */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.count = sizeof(prog_ids);
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_ids, 0, "prog_ids");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 6: Query with non-NULL prog_ids array but with count == 0 */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 7: Query with invalid flags */
+	attr.query.attach_flags = 0;
+	attr.query.query_flags = 1;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, EINVAL, "prog_query_should_fail");
+
+	attr.query.attach_flags = 1;
+	attr.query.query_flags = 0;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, EINVAL, "prog_query_should_fail");
+
 cleanup4:
 	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
 	ASSERT_OK(err, "prog_detach");
-- 
cgit v1.2.3


From 6f84090333bbff3473235a13eb99c308a53e3725 Mon Sep 17 00:00:00 2001
From: Johannes Nixdorf <jnixdorf-oss@avm.de>
Date: Mon, 16 Oct 2023 15:27:24 +0200
Subject: selftests: forwarding: bridge_fdb_learning_limit: Add a new selftest

Add a suite covering the fdb_n_learned and fdb_max_learned bridge
features, touching all special cases in accounting at least once.

Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Johannes Nixdorf <jnixdorf-oss@avm.de>
Link: https://lore.kernel.org/r/20231016-fdb_limit-v5-5-32cddff87758@avm.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/Makefile    |   3 +-
 .../net/forwarding/bridge_fdb_learning_limit.sh    | 283 +++++++++++++++++++++
 2 files changed, 285 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 74e754e266c3..df593b7b3e6b 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+ OR MIT
 
-TEST_PROGS = bridge_igmp.sh \
+TEST_PROGS = bridge_fdb_learning_limit.sh \
+	bridge_igmp.sh \
 	bridge_locked_port.sh \
 	bridge_mdb.sh \
 	bridge_mdb_host.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
new file mode 100755
index 000000000000..0760a34b7114
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
@@ -0,0 +1,283 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# ShellCheck incorrectly believes that most of the code here is unreachable
+# because it's invoked by variable name following ALL_TESTS.
+#
+# shellcheck disable=SC2317
+
+ALL_TESTS="check_accounting check_limit"
+NUM_NETIFS=6
+source lib.sh
+
+TEST_MAC_BASE=de:ad:be:ef:42:
+
+NUM_PKTS=16
+FDB_LIMIT=8
+
+FDB_TYPES=(
+	# name		is counted?	overrides learned?
+	'learned	1		0'
+	'static		0		1'
+	'user		0		1'
+	'extern_learn	0		1'
+	'local		0		1'
+)
+
+mac()
+{
+	printf "${TEST_MAC_BASE}%02x" "$1"
+}
+
+H1_DEFAULT_MAC=$(mac 42)
+
+switch_create()
+{
+	ip link add dev br0 type bridge
+
+	ip link set dev "$swp1" master br0
+	ip link set dev "$swp2" master br0
+	# swp3 is used to add local MACs, so do not add it to the bridge yet.
+
+	# swp2 is only used for replying when learning on swp1, its MAC should not be learned.
+	ip link set dev "$swp2" type bridge_slave learning off
+
+	ip link set dev br0 up
+
+	ip link set dev "$swp1" up
+	ip link set dev "$swp2" up
+	ip link set dev "$swp3" up
+}
+
+switch_destroy()
+{
+	ip link set dev "$swp3" down
+	ip link set dev "$swp2" down
+	ip link set dev "$swp1" down
+
+	ip link del dev br0
+}
+
+h_create()
+{
+	ip link set "$h1" addr "$H1_DEFAULT_MAC"
+
+	simple_if_init "$h1" 192.0.2.1/24
+	simple_if_init "$h2" 192.0.2.2/24
+}
+
+h_destroy()
+{
+	simple_if_fini "$h1" 192.0.2.1/24
+	simple_if_fini "$h2" 192.0.2.2/24
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	h2=${NETIFS[p3]}
+	swp2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p6]}
+
+	vrf_prepare
+
+	h_create
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+
+	h_destroy
+
+	vrf_cleanup
+}
+
+fdb_get_n_learned()
+{
+	ip -d -j link show dev br0 type bridge | \
+		jq '.[]["linkinfo"]["info_data"]["fdb_n_learned"]'
+}
+
+fdb_get_n_mac()
+{
+	local mac=${1}
+
+	bridge -j fdb show br br0 | \
+		jq "map(select(.mac == \"${mac}\" and (has(\"vlan\") | not))) | length"
+}
+
+fdb_fill_learned()
+{
+	local i
+
+	for i in $(seq 1 "$NUM_PKTS"); do
+		fdb_add learned "$(mac "$i")"
+	done
+}
+
+fdb_reset()
+{
+	bridge fdb flush dev br0
+
+	# Keep the default MAC address of h1 in the table. We set it to a different one when
+	# testing dynamic learning.
+	bridge fdb add "$H1_DEFAULT_MAC" dev "$swp1" master static use
+}
+
+fdb_add()
+{
+	local type=$1 mac=$2
+
+	case "$type" in
+		learned)
+			ip link set "$h1" addr "$mac"
+			# Wait for a reply so we implicitly wait until after the forwarding
+			# code finished and the FDB entry was created.
+			PING_COUNT=1 ping_do "$h1" 192.0.2.2
+			check_err $? "Failed to ping another bridge port"
+			ip link set "$h1" addr "$H1_DEFAULT_MAC"
+			;;
+		local)
+			ip link set dev "$swp3" addr "$mac" && ip link set "$swp3" master br0
+			;;
+		static)
+			bridge fdb replace "$mac" dev "$swp1" master static
+			;;
+		user)
+			bridge fdb replace "$mac" dev "$swp1" master static use
+			;;
+		extern_learn)
+			bridge fdb replace "$mac" dev "$swp1" master extern_learn
+			;;
+	esac
+
+	check_err $? "Failed to add a FDB entry of type ${type}"
+}
+
+fdb_del()
+{
+	local type=$1 mac=$2
+
+	case "$type" in
+		local)
+			ip link set "$swp3" nomaster
+			;;
+		*)
+			bridge fdb del "$mac" dev "$swp1" master
+			;;
+	esac
+
+	check_err $? "Failed to remove a FDB entry of type ${type}"
+}
+
+check_accounting_one_type()
+{
+	local type=$1 is_counted=$2 overrides_learned=$3
+	shift 3
+	RET=0
+
+	fdb_reset
+	fdb_add "$type" "$(mac 0)"
+	learned=$(fdb_get_n_learned)
+	[ "$learned" -ne "$is_counted" ]
+	check_fail $? "Inserted FDB type ${type}: Expected the count ${is_counted}, but got ${learned}"
+
+	fdb_del "$type" "$(mac 0)"
+	learned=$(fdb_get_n_learned)
+	[ "$learned" -ne 0 ]
+	check_fail $? "Removed FDB type ${type}: Expected the count 0, but got ${learned}"
+
+	if [ "$overrides_learned" -eq 1 ]; then
+		fdb_reset
+		fdb_add learned "$(mac 0)"
+		fdb_add "$type" "$(mac 0)"
+		learned=$(fdb_get_n_learned)
+		[ "$learned" -ne "$is_counted" ]
+		check_fail $? "Set a learned entry to FDB type ${type}: Expected the count ${is_counted}, but got ${learned}"
+		fdb_del "$type" "$(mac 0)"
+	fi
+
+	log_test "FDB accounting interacting with FDB type ${type}"
+}
+
+check_accounting()
+{
+	local type_args learned
+	RET=0
+
+	fdb_reset
+	learned=$(fdb_get_n_learned)
+	[ "$learned" -ne 0 ]
+	check_fail $? "Flushed the FDB table: Expected the count 0, but got ${learned}"
+
+	fdb_fill_learned
+	sleep 1
+
+	learned=$(fdb_get_n_learned)
+	[ "$learned" -ne "$NUM_PKTS" ]
+	check_fail $? "Filled the FDB table: Expected the count ${NUM_PKTS}, but got ${learned}"
+
+	log_test "FDB accounting"
+
+	for type_args in "${FDB_TYPES[@]}"; do
+		# This is intentional use of word splitting.
+		# shellcheck disable=SC2086
+		check_accounting_one_type $type_args
+	done
+}
+
+check_limit_one_type()
+{
+	local type=$1 is_counted=$2
+	local n_mac expected=$((1 - is_counted))
+	RET=0
+
+	fdb_reset
+	fdb_fill_learned
+
+	fdb_add "$type" "$(mac 0)"
+	n_mac=$(fdb_get_n_mac "$(mac 0)")
+	[ "$n_mac" -ne "$expected" ]
+	check_fail $? "Inserted FDB type ${type} at limit: Expected the count ${expected}, but got ${n_mac}"
+
+	log_test "FDB limits interacting with FDB type ${type}"
+}
+
+check_limit()
+{
+	local learned
+	RET=0
+
+	ip link set br0 type bridge fdb_max_learned "$FDB_LIMIT"
+
+	fdb_reset
+	fdb_fill_learned
+
+	learned=$(fdb_get_n_learned)
+	[ "$learned" -ne "$FDB_LIMIT" ]
+	check_fail $? "Filled the limited FDB table: Expected the count ${FDB_LIMIT}, but got ${learned}"
+
+	log_test "FDB limits"
+
+	for type_args in "${FDB_TYPES[@]}"; do
+		# This is intentional use of word splitting.
+		# shellcheck disable=SC2086
+		check_limit_one_type $type_args
+	done
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 9fea94d3a8cadd83f5de22eae953bd9e951d5215 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 16 Oct 2023 14:39:37 -0700
Subject: tools: ynl: fix converting flags to names after recent cleanup

I recently cleaned up specs to not specify enum-as-flags
when target enum is already defined as flags.
YNL Python library did not convert flags, unfortunately,
so this caused breakage for Stan and Willem.

Note that the nlspec.py abstraction already hides the differences
between flags and enums (value vs user_value), so the changes
are pretty trivial.

Fixes: 0629f22ec130 ("ynl: netdev: drop unnecessary enum-as-flags")
Reported-and-tested-by: Willem de Bruijn <willemb@google.com>
Reported-and-tested-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/all/ZS10NtQgd_BJZ3RU@google.com/
Link: https://lore.kernel.org/r/20231016213937.1820386-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 13c4b019a881..28ac35008e65 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -474,7 +474,7 @@ class YnlFamily(SpecFamily):
 
     def _decode_enum(self, raw, attr_spec):
         enum = self.consts[attr_spec['enum']]
-        if 'enum-as-flags' in attr_spec and attr_spec['enum-as-flags']:
+        if enum.type == 'flags' or attr_spec.get('enum-as-flags', False):
             i = 0
             value = set()
             while raw:
-- 
cgit v1.2.3


From bb6a88885fde24835afdaa1c5bb976a1bf5c5d71 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 17 Oct 2023 18:27:57 +0200
Subject: selftests/bpf: Add options and frags to xdp_hw_metadata

This is a follow-up to the commit 9b2b86332a9b ("bpf: Allow to use kfunc
XDP hints and frags together").

The are some possible implementations problems that may arise when providing
metadata specifically for multi-buffer packets, therefore there must be a
possibility to test such option separately.

Add an option to use multi-buffer AF_XDP xdp_hw_metadata and mark used XDP
program as capable to use frags.

As for now, xdp_hw_metadata accepts no options, so add simple option
parsing logic and a help message.

For quick reference, also add an ingress packet generation command to the
help message. The command comes from [0].

Example of output for multi-buffer packet:

  xsk_ring_cons__peek: 1
  0xead018: rx_desc[15]->addr=10000000000f000 addr=f100 comp_addr=f000
  rx_hash: 0x5789FCBB with RSS type:0x29
  rx_timestamp:  1696856851535324697 (sec:1696856851.5353)
  XDP RX-time:   1696856843158256391 (sec:1696856843.1583)
  	delta sec:-8.3771 (-8377068.306 usec)
  AF_XDP time:   1696856843158413078 (sec:1696856843.1584)
  	delta sec:0.0002 (156.687 usec)
  0xead018: complete idx=23 addr=f000
  xsk_ring_cons__peek: 1
  0xead018: rx_desc[16]->addr=100000000008000 addr=8100 comp_addr=8000
  0xead018: complete idx=24 addr=8000
  xsk_ring_cons__peek: 1
  0xead018: rx_desc[17]->addr=100000000009000 addr=9100 comp_addr=9000 EoP
  0xead018: complete idx=25 addr=9000

Metadata is printed for the first packet only.

  [0] https://lore.kernel.org/all/20230119221536.3349901-18-sdf@google.com/

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20231017162800.24080-1-larysa.zaremba@intel.com
---
 .../testing/selftests/bpf/progs/xdp_hw_metadata.c  |  2 +-
 tools/testing/selftests/bpf/xdp_hw_metadata.c      | 78 ++++++++++++++++++----
 2 files changed, 67 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index b2dfd7066c6e..f6d1cc9ad892 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -21,7 +21,7 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
 
-SEC("xdp")
+SEC("xdp.frags")
 int rx(struct xdp_md *ctx)
 {
 	void *data, *data_meta, *data_end;
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 17c980138796..17c0f92ff160 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -26,6 +26,7 @@
 #include <linux/sockios.h>
 #include <sys/mman.h>
 #include <net/if.h>
+#include <ctype.h>
 #include <poll.h>
 #include <time.h>
 
@@ -47,6 +48,7 @@ struct xsk {
 };
 
 struct xdp_hw_metadata *bpf_obj;
+__u16 bind_flags = XDP_COPY;
 struct xsk *rx_xsk;
 const char *ifname;
 int ifindex;
@@ -60,7 +62,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 	const struct xsk_socket_config socket_config = {
 		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
-		.bind_flags = XDP_COPY,
+		.bind_flags = bind_flags,
 	};
 	const struct xsk_umem_config umem_config = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
@@ -263,11 +265,14 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 			verify_skb_metadata(server_fd);
 
 		for (i = 0; i < rxq; i++) {
+			bool first_seg = true;
+			bool is_eop = true;
+
 			if (fds[i].revents == 0)
 				continue;
 
 			struct xsk *xsk = &rx_xsk[i];
-
+peek:
 			ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
 			printf("xsk_ring_cons__peek: %d\n", ret);
 			if (ret != 1)
@@ -276,12 +281,19 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 			rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
 			comp_addr = xsk_umem__extract_addr(rx_desc->addr);
 			addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
-			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
-			       xsk, idx, rx_desc->addr, addr, comp_addr);
-			verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
-					    clock_id);
+			is_eop = !(rx_desc->options & XDP_PKT_CONTD);
+			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx%s\n",
+			       xsk, idx, rx_desc->addr, addr, comp_addr, is_eop ? " EoP" : "");
+			if (first_seg) {
+				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
+						    clock_id);
+				first_seg = false;
+			}
+
 			xsk_ring_cons__release(&xsk->rx, 1);
 			refill_rx(xsk, comp_addr);
+			if (!is_eop)
+				goto peek;
 		}
 	}
 
@@ -404,6 +416,53 @@ static void timestamping_enable(int fd, int val)
 		error(1, errno, "setsockopt(SO_TIMESTAMPING)");
 }
 
+static void print_usage(void)
+{
+	const char *usage =
+		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -h    Display this help and exit\n\n"
+		"Generate test packets on the other machine with:\n"
+		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
+
+	printf("%s", usage);
+}
+
+static void read_args(int argc, char *argv[])
+{
+	char opt;
+
+	while ((opt = getopt(argc, argv, "mh")) != -1) {
+		switch (opt) {
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'h':
+			print_usage();
+			exit(0);
+		case '?':
+			if (isprint(optopt))
+				fprintf(stderr, "Unknown option: -%c\n", optopt);
+			fallthrough;
+		default:
+			print_usage();
+			error(-1, opterr, "Command line options error");
+		}
+	}
+
+	if (optind >= argc) {
+		fprintf(stderr, "No device name provided\n");
+		print_usage();
+		exit(-1);
+	}
+
+	ifname = argv[optind];
+	ifindex = if_nametoindex(ifname);
+
+	if (!ifname)
+		error(-1, errno, "Invalid interface name");
+}
+
 int main(int argc, char *argv[])
 {
 	clockid_t clock_id = CLOCK_TAI;
@@ -413,13 +472,8 @@ int main(int argc, char *argv[])
 
 	struct bpf_program *prog;
 
-	if (argc != 2) {
-		fprintf(stderr, "pass device name\n");
-		return -1;
-	}
+	read_args(argc, argv);
 
-	ifname = argv[1];
-	ifindex = if_nametoindex(ifname);
 	rxq = rxq_num(ifname);
 
 	printf("rxq: %d\n", rxq);
-- 
cgit v1.2.3


From c4eee56e14fe001e1cff54f0b438a5e2d0dd7454 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 17 Oct 2023 11:39:06 +0200
Subject: net: skb_find_text: Ignore patterns extending past 'to'

Assume that caller's 'to' offset really represents an upper boundary for
the pattern search, so patterns extending past this offset are to be
rejected.

The old behaviour also was kind of inconsistent when it comes to
fragmentation (or otherwise non-linear skbs): If the pattern started in
between 'to' and 'from' offsets but extended to the next fragment, it
was not found if 'to' offset was still within the current fragment.

Test the new behaviour in a kselftest using iptables' string match.

Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Fixes: f72b948dcbb8 ("[NET]: skb_find_text ignores to argument")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c                              |   3 +-
 tools/testing/selftests/netfilter/Makefile     |   2 +-
 tools/testing/selftests/netfilter/xt_string.sh | 128 +++++++++++++++++++++++++
 3 files changed, 131 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/netfilter/xt_string.sh

(limited to 'tools')

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0401f40973a5..975c9a6ffb4a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4267,6 +4267,7 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
 unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 			   unsigned int to, struct ts_config *config)
 {
+	unsigned int patlen = config->ops->get_pattern_len(config);
 	struct ts_state state;
 	unsigned int ret;
 
@@ -4278,7 +4279,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 	skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state));
 
 	ret = textsearch_find(config, &state);
-	return (ret <= to - from ? ret : UINT_MAX);
+	return (ret + patlen <= to - from ? ret : UINT_MAX);
 }
 EXPORT_SYMBOL(skb_find_text);
 
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index ef90aca4cc96..bced422b78f7 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -7,7 +7,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
 	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
 	conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \
-	conntrack_sctp_collision.sh
+	conntrack_sctp_collision.sh xt_string.sh
 
 HOSTPKG_CONFIG := pkg-config
 
diff --git a/tools/testing/selftests/netfilter/xt_string.sh b/tools/testing/selftests/netfilter/xt_string.sh
new file mode 100755
index 000000000000..1802653a4728
--- /dev/null
+++ b/tools/testing/selftests/netfilter/xt_string.sh
@@ -0,0 +1,128 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# return code to signal skipped test
+ksft_skip=4
+rc=0
+
+if ! iptables --version >/dev/null 2>&1; then
+	echo "SKIP: Test needs iptables"
+	exit $ksft_skip
+fi
+if ! ip -V >/dev/null 2>&1; then
+	echo "SKIP: Test needs iproute2"
+	exit $ksft_skip
+fi
+if ! nc -h >/dev/null 2>&1; then
+	echo "SKIP: Test needs netcat"
+	exit $ksft_skip
+fi
+
+pattern="foo bar baz"
+patlen=11
+hdrlen=$((20 + 8)) # IPv4 + UDP
+ns="ns-$(mktemp -u XXXXXXXX)"
+trap 'ip netns del $ns' EXIT
+ip netns add "$ns"
+ip -net "$ns" link add d0 type dummy
+ip -net "$ns" link set d0 up
+ip -net "$ns" addr add 10.1.2.1/24 dev d0
+
+#ip netns exec "$ns" tcpdump -npXi d0 &
+#tcpdump_pid=$!
+#trap 'kill $tcpdump_pid; ip netns del $ns' EXIT
+
+add_rule() { # (alg, from, to)
+	ip netns exec "$ns" \
+		iptables -A OUTPUT -o d0 -m string \
+			--string "$pattern" --algo $1 --from $2 --to $3
+}
+showrules() { # ()
+	ip netns exec "$ns" iptables -v -S OUTPUT | grep '^-A'
+}
+zerorules() {
+	ip netns exec "$ns" iptables -Z OUTPUT
+}
+countrule() { # (pattern)
+	showrules | grep -c -- "$*"
+}
+send() { # (offset)
+	( for ((i = 0; i < $1 - $hdrlen; i++)); do
+		printf " "
+	  done
+	  printf "$pattern"
+	) | ip netns exec "$ns" nc -w 1 -u 10.1.2.2 27374
+}
+
+add_rule bm 1000 1500
+add_rule bm 1400 1600
+add_rule kmp 1000 1500
+add_rule kmp 1400 1600
+
+zerorules
+send 0
+send $((1000 - $patlen))
+if [ $(countrule -c 0 0) -ne 4 ]; then
+	echo "FAIL: rules match data before --from"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send 1000
+send $((1400 - $patlen))
+if [ $(countrule -c 2) -ne 2 ]; then
+	echo "FAIL: only two rules should match at low offset"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send $((1500 - $patlen))
+if [ $(countrule -c 1) -ne 4 ]; then
+	echo "FAIL: all rules should match at end of packet"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send 1495
+if [ $(countrule -c 1) -ne 1 ]; then
+	echo "FAIL: only kmp with proper --to should match pattern spanning fragments"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send 1500
+if [ $(countrule -c 1) -ne 2 ]; then
+	echo "FAIL: two rules should match pattern at start of second fragment"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send $((1600 - $patlen))
+if [ $(countrule -c 1) -ne 2 ]; then
+	echo "FAIL: two rules should match pattern at end of largest --to"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send $((1600 - $patlen + 1))
+if [ $(countrule -c 1) -ne 0 ]; then
+	echo "FAIL: no rules should match pattern extending largest --to"
+	showrules
+	((rc--))
+fi
+
+zerorules
+send 1600
+if [ $(countrule -c 1) -ne 0 ]; then
+	echo "FAIL: no rule should match pattern past largest --to"
+	showrules
+	((rc--))
+fi
+
+exit $rc
-- 
cgit v1.2.3


From f157b73d511416226f70c3cb1750eb6fdfa76a2a Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 17 Oct 2023 12:23:08 -0300
Subject: selftests: tc-testing: add missing Kconfig options to 'config'

Make sure CI builds using just tc-testing/config can run all tdc tests.
Some tests were broken because of missing knobs.

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20231017152309.3196320-2-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/config | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index 5aa8705751f0..012aa33b341b 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -1,12 +1,21 @@
+#
+# Network
+#
+
+CONFIG_DUMMY=y
+CONFIG_VETH=y
+
 #
 # Core Netfilter Configuration
 #
+CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_CONNTRACK_LABELS=y
 CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_TABLES=m
 CONFIG_NF_NAT=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 
-- 
cgit v1.2.3


From 35027c790970c40a5093550af7c9f1c77de182b4 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 17 Oct 2023 12:23:09 -0300
Subject: selftests: tc-testing: move auxiliary scripts to a dedicated folder

Some taprio tests need auxiliary scripts to wait for workqueue events to
process. Move them to a dedicated folder in order to package them for
the kselftests tarball.

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20231017152309.3196320-3-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/Makefile              |  2 +-
 .../tc-testing/scripts/taprio_wait_for_admin.sh          | 16 ++++++++++++++++
 .../selftests/tc-testing/taprio_wait_for_admin.sh        | 16 ----------------
 .../selftests/tc-testing/tc-tests/qdiscs/taprio.json     |  8 ++++----
 4 files changed, 21 insertions(+), 21 deletions(-)
 create mode 100755 tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh
 delete mode 100755 tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile
index 3c4b7fa05075..b1fa2e177e2f 100644
--- a/tools/testing/selftests/tc-testing/Makefile
+++ b/tools/testing/selftests/tc-testing/Makefile
@@ -28,4 +28,4 @@ $(OUTPUT)/%.o: %.c
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 
 TEST_PROGS += ./tdc.sh
-TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests
+TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts
diff --git a/tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh b/tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh
new file mode 100755
index 000000000000..f5335e8ad6b4
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh
@@ -0,0 +1,16 @@
+#!/bin/bash
+
+TC="$1"; shift
+ETH="$1"; shift
+
+# The taprio architecture changes the admin schedule from a hrtimer and not
+# from process context, so we need to wait in order to make sure that any
+# schedule change actually took place.
+while :; do
+	has_admin="$($TC -j qdisc show dev $ETH root | jq '.[].options | has("admin")')"
+	if [ "$has_admin" = "false" ]; then
+		break;
+	fi
+
+	sleep 1
+done
diff --git a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh b/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh
deleted file mode 100755
index f5335e8ad6b4..000000000000
--- a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh
+++ /dev/null
@@ -1,16 +0,0 @@
-#!/bin/bash
-
-TC="$1"; shift
-ETH="$1"; shift
-
-# The taprio architecture changes the admin schedule from a hrtimer and not
-# from process context, so we need to wait in order to make sure that any
-# schedule change actually took place.
-while :; do
-	has_admin="$($TC -j qdisc show dev $ETH root | jq '.[].options | has("admin")')"
-	if [ "$has_admin" = "false" ]; then
-		break;
-	fi
-
-	sleep 1
-done
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 0599635c4bc6..2d603ef2e375 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -170,11 +170,11 @@
         "setup": [
             "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
             "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI",
-            "./taprio_wait_for_admin.sh $TC $ETH"
+            "./scripts/taprio_wait_for_admin.sh $TC $ETH"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 clockid CLOCK_TAI",
         "expExitCode": "2",
-        "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
+        "verifyCmd": "bash -c \"./scripts/taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
         "matchPattern": "0",
         "matchCount": "1",
         "teardown": [
@@ -195,11 +195,11 @@
         "setup": [
             "echo \"1 1 8\" > /sys/bus/netdevsim/new_device",
             "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2",
-            "./taprio_wait_for_admin.sh $TC $ETH"
+            "./scripts/taprio_wait_for_admin.sh $TC $ETH"
         ],
         "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 flags 0x2",
         "expExitCode": "2",
-        "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
+        "verifyCmd": "bash -c \"./scripts/taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"",
         "matchPattern": "0",
         "matchCount": "1",
         "teardown": [
-- 
cgit v1.2.3


From 878d951c6712b655c38e78ac1ee63c35cd913b22 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Oct 2023 09:00:13 +0000
Subject: inet: lock the socket in ip_sock_set_tos()

Christoph Paasch reported a panic in TCP stack [1]

Indeed, we should not call sk_dst_reset() without holding
the socket lock, as __sk_dst_get() callers do not all rely
on bare RCU.

[1]
BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 12bad6067 P4D 12bad6067 PUD 12bad5067 PMD 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 1 PID: 2750 Comm: syz-executor.5 Not tainted 6.6.0-rc4-g7a5720a344e7 #49
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014
RIP: 0010:tcp_get_metrics+0x118/0x8f0 net/ipv4/tcp_metrics.c:321
Code: c7 44 24 70 02 00 8b 03 89 44 24 48 c7 44 24 4c 00 00 00 00 66 c7 44 24 58 02 00 66 ba 02 00 b1 01 89 4c 24 04 4c 89 7c 24 10 <49> 8b 0f 48 8b 89 50 05 00 00 48 89 4c 24 30 33 81 00 02 00 00 69
RSP: 0018:ffffc90000af79b8 EFLAGS: 00010293
RAX: 000000000100007f RBX: ffff88812ae8f500 RCX: ffff88812b5f8f01
RDX: 0000000000000002 RSI: ffffffff8300f080 RDI: 0000000000000002
RBP: 0000000000000002 R08: 0000000000000003 R09: ffffffff8205eca0
R10: 0000000000000002 R11: ffff88812b5f8f00 R12: ffff88812a9e0580
R13: 0000000000000000 R14: ffff88812ae8fbd2 R15: 0000000000000000
FS: 00007f70a006b640(0000) GS:ffff88813bd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 000000012bad7003 CR4: 0000000000170ee0
Call Trace:
<TASK>
tcp_fastopen_cache_get+0x32/0x140 net/ipv4/tcp_metrics.c:567
tcp_fastopen_cookie_check+0x28/0x180 net/ipv4/tcp_fastopen.c:419
tcp_connect+0x9c8/0x12a0 net/ipv4/tcp_output.c:3839
tcp_v4_connect+0x645/0x6e0 net/ipv4/tcp_ipv4.c:323
__inet_stream_connect+0x120/0x590 net/ipv4/af_inet.c:676
tcp_sendmsg_fastopen+0x2d6/0x3a0 net/ipv4/tcp.c:1021
tcp_sendmsg_locked+0x1957/0x1b00 net/ipv4/tcp.c:1073
tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1336
__sock_sendmsg+0x83/0xd0 net/socket.c:730
__sys_sendto+0x20a/0x2a0 net/socket.c:2194
__do_sys_sendto net/socket.c:2206 [inline]

Fixes: e08d0b3d1723 ("inet: implement lockless IP_TOS")
Reported-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231018090014.345158-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip.h                                   |  1 +
 net/ipv4/ip_sockglue.c                             | 11 +++++++++--
 net/mptcp/sockopt.c                                |  4 ++--
 tools/testing/selftests/net/mptcp/mptcp_connect.sh |  2 +-
 4 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/include/net/ip.h b/include/net/ip.h
index 6fbc0dcf4b97..1fc4c8d69e33 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -810,5 +810,6 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val);
 void ip_sock_set_pktinfo(struct sock *sk);
 void ip_sock_set_recverr(struct sock *sk);
 void ip_sock_set_tos(struct sock *sk, int val);
+void  __ip_sock_set_tos(struct sock *sk, int val);
 
 #endif	/* _IP_H */
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 0b74ac49d6a6..9c68b6b74d9f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -585,9 +585,9 @@ out:
 	return err;
 }
 
-void ip_sock_set_tos(struct sock *sk, int val)
+void __ip_sock_set_tos(struct sock *sk, int val)
 {
-	u8 old_tos = READ_ONCE(inet_sk(sk)->tos);
+	u8 old_tos = inet_sk(sk)->tos;
 
 	if (sk->sk_type == SOCK_STREAM) {
 		val &= ~INET_ECN_MASK;
@@ -599,6 +599,13 @@ void ip_sock_set_tos(struct sock *sk, int val)
 		sk_dst_reset(sk);
 	}
 }
+
+void ip_sock_set_tos(struct sock *sk, int val)
+{
+	lock_sock(sk);
+	__ip_sock_set_tos(sk, val);
+	release_sock(sk);
+}
 EXPORT_SYMBOL(ip_sock_set_tos);
 
 void ip_sock_set_freebind(struct sock *sk)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 18ce624bfde2..59bd5e114392 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -738,7 +738,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
-		ip_sock_set_tos(ssk, val);
+		__ip_sock_set_tos(ssk, val);
 	}
 	release_sock(sk);
 
@@ -1411,7 +1411,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	ssk->sk_incoming_cpu = sk->sk_incoming_cpu;
 	ssk->sk_ipv6only = sk->sk_ipv6only;
-	ip_sock_set_tos(ssk, inet_sk(sk)->tos);
+	__ip_sock_set_tos(ssk, inet_sk(sk)->tos);
 
 	if (sk->sk_userlocks & tx_rx_locks) {
 		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 61a2a1988ce6..b1fc8afd072d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -716,7 +716,7 @@ run_test_transparent()
 	# the required infrastructure in MPTCP sockopt code. To support TOS, the
 	# following function has been exported (T). Not great but better than
 	# checking for a specific kernel version.
-	if ! mptcp_lib_kallsyms_has "T ip_sock_set_tos$"; then
+	if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then
 		echo "INFO: ${msg} not supported by the kernel: SKIP"
 		mptcp_lib_result_skip "${TEST_GROUP}"
 		return
-- 
cgit v1.2.3


From 90704b4be0b0d6d0a7a9369d4b9aae6a579602c7 Mon Sep 17 00:00:00 2001
From: Manu Bretelle <chantr4@gmail.com>
Date: Wed, 18 Oct 2023 16:01:32 -0700
Subject: bpftool: Fix printing of pointer value

When printing a pointer value, "%p" will either print the hexadecimal
value of the pointer (e.g `0x1234`), or `(nil)` when NULL.

Both of those are invalid json "integer" values and need to be wrapped
in quotes.

Before:
```
$ sudo bpftool struct_ops dump  name ned_dummy_cca | grep next
                    "next": (nil),
$ sudo bpftool struct_ops dump  name ned_dummy_cca | \
    jq '.[1].bpf_struct_ops_tcp_congestion_ops.data.list.next'
parse error: Invalid numeric literal at line 29, column 34
```

After:
```
$ sudo ./bpftool struct_ops dump  name ned_dummy_cca | grep next
                    "next": "(nil)",
$ sudo ./bpftool struct_ops dump  name ned_dummy_cca | \
    jq '.[1].bpf_struct_ops_tcp_congestion_ops.data.list.next'
"(nil)"
```

Signed-off-by: Manu Bretelle <chantr4@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20231018230133.1593152-2-chantr4@gmail.com
---
 tools/bpf/bpftool/btf_dumper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 1b7f69714604..527fe867a8fb 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -127,7 +127,7 @@ static void btf_dumper_ptr(const struct btf_dumper *d,
 
 print_ptr_value:
 	if (d->is_plain_text)
-		jsonw_printf(d->jw, "%p", (void *)value);
+		jsonw_printf(d->jw, "\"%p\"", (void *)value);
 	else
 		jsonw_printf(d->jw, "%lu", value);
 }
-- 
cgit v1.2.3


From 6bd5e167af2e9d1aa79e4a1a2598abcdc8fafd59 Mon Sep 17 00:00:00 2001
From: Manu Bretelle <chantr4@gmail.com>
Date: Wed, 18 Oct 2023 16:01:33 -0700
Subject: bpftool: Wrap struct_ops dump in an array

When dumping a struct_ops, 2 dictionaries are emitted.

When using `name`, they were already wrapped in an array, but not when
using `id`. Causing `jq` to fail at parsing the payload as it reached
the comma following the first dict.

This change wraps those dictionaries in an array so valid json is emitted.

Before, jq fails to parse the output:
```
 $ sudo bpftool struct_ops dump id 1523612 | jq . > /dev/null
parse error: Expected value before ',' at line 19, column 2
```

After, no error parsing the output:
```
sudo ./bpftool  struct_ops dump id 1523612 | jq . > /dev/null
```

Signed-off-by: Manu Bretelle <chantr4@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20231018230133.1593152-3-chantr4@gmail.com
---
 tools/bpf/bpftool/struct_ops.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c
index 3ebc9fe91e0e..d573f2640d8e 100644
--- a/tools/bpf/bpftool/struct_ops.c
+++ b/tools/bpf/bpftool/struct_ops.c
@@ -276,6 +276,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data,
 
 	res.nr_maps++;
 
+	if (wtr)
+		jsonw_start_array(wtr);
+
 	if (func(fd, info, data, wtr))
 		res.nr_errs++;
 	else if (!wtr && json_output)
@@ -288,6 +291,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data,
 		 */
 		jsonw_null(json_wtr);
 
+	if (wtr)
+		jsonw_end_array(wtr);
+
 done:
 	free(info);
 	close(fd);
-- 
cgit v1.2.3


From ee0a4cfcbdcc6a7b2b35dba475e68187ebdafbf1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Oct 2023 09:39:15 -0700
Subject: tools: ynl-gen: track attribute use

For range validation we'll need to know if any individual
attribute is used on input (i.e. whether we will generate
a policy for it). Track this information.

Link: https://lore.kernel.org/r/20231018163917.2514503-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index f125b5f704ba..7f4ad4014d17 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -42,6 +42,9 @@ class Type(SpecAttr):
         self.type = attr['type']
         self.checks = attr.get('checks', {})
 
+        self.request = False
+        self.reply = False
+
         if 'len' in attr:
             self.len = attr['len']
         if 'nested-attributes' in attr:
@@ -846,6 +849,7 @@ class Family(SpecFamily):
 
         self._load_root_sets()
         self._load_nested_sets()
+        self._load_attr_use()
         self._load_hooks()
 
         self.kernel_policy = self.yaml.get('kernel-policy', 'split')
@@ -966,6 +970,22 @@ class Family(SpecFamily):
                         child.request |= struct.request
                         child.reply |= struct.reply
 
+    def _load_attr_use(self):
+        for _, struct in self.pure_nested_structs.items():
+            if struct.request:
+                for _, arg in struct.member_list():
+                    arg.request = True
+            if struct.reply:
+                for _, arg in struct.member_list():
+                    arg.reply = True
+
+        for root_set, rs_members in self.root_sets.items():
+            for attr, spec in self.attr_sets[root_set].items():
+                if attr in rs_members['request']:
+                    spec.request = True
+                if attr in rs_members['reply']:
+                    spec.reply = True
+
     def _load_global_policy(self):
         global_set = set()
         attr_set_name = None
-- 
cgit v1.2.3


From 668c1ac828fb546b81da6b36dae09d754bd0f59e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Oct 2023 09:39:16 -0700
Subject: tools: ynl-gen: support full range of min/max checks for integer
 values

Extend the support to full range of min/max checks.
None of the existing YNL families required complex integer validation.

The support is less than trivial, because we try to keep struct nla_policy
tiny the min/max members it holds in place are s16. Meaning we can only
express checks in range of s16. For larger ranges we need to define
a structure and link it in the policy.

Link: https://lore.kernel.org/r/20231018163917.2514503-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      |  3 ++
 Documentation/netlink/genetlink-legacy.yaml |  3 ++
 Documentation/netlink/genetlink.yaml        |  3 ++
 tools/net/ynl/ynl-gen-c.py                  | 66 ++++++++++++++++++++++++++---
 4 files changed, 68 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index f9366aaddd21..75af0b51f3d7 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -184,6 +184,9 @@ properties:
                   min:
                     description: Min value for an integer attribute.
                     type: integer
+                  max:
+                    description: Max value for an integer attribute.
+                    type: integer
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index a6a490333a1a..c0f17a8bfe0d 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -227,6 +227,9 @@ properties:
                   min:
                     description: Min value for an integer attribute.
                     type: integer
+                  max:
+                    description: Max value for an integer attribute.
+                    type: integer
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 2b788e607a14..4fd56e3b1553 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -157,6 +157,9 @@ properties:
                   min:
                     description: Min value for an integer attribute.
                     type: integer
+                  max:
+                    description: Max value for an integer attribute.
+                    type: integer
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 7f4ad4014d17..9d008346dd50 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -47,6 +47,7 @@ class Type(SpecAttr):
 
         if 'len' in attr:
             self.len = attr['len']
+
         if 'nested-attributes' in attr:
             self.nested_attrs = attr['nested-attributes']
             if self.nested_attrs == family.name:
@@ -262,6 +263,27 @@ class TypeScalar(Type):
         if 'byte-order' in attr:
             self.byte_order_comment = f" /* {attr['byte-order']} */"
 
+        if 'enum' in self.attr:
+            enum = self.family.consts[self.attr['enum']]
+            low, high = enum.value_range()
+            if 'min' not in self.checks:
+                if low != 0 or self.type[0] == 's':
+                    self.checks['min'] = low
+            if 'max' not in self.checks:
+                self.checks['max'] = high
+
+        if 'min' in self.checks and 'max' in self.checks:
+            if self.checks['min'] > self.checks['max']:
+                raise Exception(f'Invalid limit for "{self.name}" min: {self.checks["min"]} max: {self.checks["max"]}')
+            self.checks['range'] = True
+
+        low = min(self.checks.get('min', 0), self.checks.get('max', 0))
+        high = max(self.checks.get('min', 0), self.checks.get('max', 0))
+        if low < 0 and self.type[0] == 'u':
+            raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
+        if low < -32768 or high > 32767:
+            self.checks['full-range'] = True
+
         # Added by resolve():
         self.is_bitfield = None
         delattr(self, "is_bitfield")
@@ -301,14 +323,14 @@ class TypeScalar(Type):
                 flag_cnt = len(flags['entries'])
                 mask = (1 << flag_cnt) - 1
             return f"NLA_POLICY_MASK({policy}, 0x{mask:x})"
+        elif 'full-range' in self.checks:
+            return f"NLA_POLICY_FULL_RANGE({policy}, &{c_lower(self.enum_name)}_range)"
+        elif 'range' in self.checks:
+            return f"NLA_POLICY_RANGE({policy}, {self.checks['min']}, {self.checks['max']})"
         elif 'min' in self.checks:
             return f"NLA_POLICY_MIN({policy}, {self.checks['min']})"
-        elif 'enum' in self.attr:
-            enum = self.family.consts[self.attr['enum']]
-            low, high = enum.value_range()
-            if low == 0:
-                return f"NLA_POLICY_MAX({policy}, {high})"
-            return f"NLA_POLICY_RANGE({policy}, {low}, {high})"
+        elif 'max' in self.checks:
+            return f"NLA_POLICY_MAX({policy}, {self.checks['max']})"
         return super()._attr_policy(policy)
 
     def _attr_typol(self):
@@ -1241,7 +1263,7 @@ class CodeWriter:
         for one in members:
             line = '.' + one[0]
             line += '\t' * ((longest - len(one[0]) - 1 + 7) // 8)
-            line += '= ' + one[1] + ','
+            line += '= ' + str(one[1]) + ','
             self.p(line)
 
 
@@ -1940,6 +1962,34 @@ def policy_should_be_static(family):
     return family.kernel_policy == 'split' or kernel_can_gen_family_struct(family)
 
 
+def print_kernel_policy_ranges(family, cw):
+    first = True
+    for _, attr_set in family.attr_sets.items():
+        if attr_set.subset_of:
+            continue
+
+        for _, attr in attr_set.items():
+            if not attr.request:
+                continue
+            if 'full-range' not in attr.checks:
+                continue
+
+            if first:
+                cw.p('/* Integer value ranges */')
+                first = False
+
+            sign = '' if attr.type[0] == 'u' else '_signed'
+            cw.block_start(line=f'struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =')
+            members = []
+            if 'min' in attr.checks:
+                members.append(('min', attr.checks['min']))
+            if 'max' in attr.checks:
+                members.append(('max', attr.checks['max']))
+            cw.write_struct_init(members)
+            cw.block_end(line=';')
+            cw.nl()
+
+
 def print_kernel_op_table_fwd(family, cw, terminate):
     exported = not kernel_can_gen_family_struct(family)
 
@@ -2479,6 +2529,8 @@ def main():
             print_kernel_mcgrp_hdr(parsed, cw)
             print_kernel_family_struct_hdr(parsed, cw)
         else:
+            print_kernel_policy_ranges(parsed, cw)
+
             for _, struct in sorted(parsed.pure_nested_structs.items()):
                 if struct.request:
                     cw.p('/* Common nested types */')
-- 
cgit v1.2.3


From f9bc3cbc20d08c5c7b89a91e07ba46ab8042561e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Oct 2023 09:39:17 -0700
Subject: tools: ynl-gen: support limit names

Support the use of symbolic names like s8-min or u32-max in checks
to make writing specs less painful.

Link: https://lore.kernel.org/r/20231018163917.2514503-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      |  9 ++++--
 Documentation/netlink/genetlink-legacy.yaml |  9 ++++--
 Documentation/netlink/genetlink.yaml        |  9 ++++--
 tools/net/ynl/ynl-gen-c.py                  | 45 ++++++++++++++++++++++-------
 4 files changed, 55 insertions(+), 17 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 75af0b51f3d7..dee11c514896 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -13,6 +13,11 @@ $defs:
     type: [ string, integer ]
     pattern: ^[0-9A-Za-z_]+( - 1)?$
     minimum: 0
+  len-or-limit:
+    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    type: [ string, integer ]
+    pattern: ^[su](8|16|32|64)-(min|max)$
+    minimum: 0
 
 # Schema for specs
 title: Protocol
@@ -183,10 +188,10 @@ properties:
                     type: string
                   min:
                     description: Min value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   max:
                     description: Max value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index c0f17a8bfe0d..9194f3e223ef 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -13,6 +13,11 @@ $defs:
     type: [ string, integer ]
     pattern: ^[0-9A-Za-z_]+( - 1)?$
     minimum: 0
+  len-or-limit:
+    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    type: [ string, integer ]
+    pattern: ^[su](8|16|32|64)-(min|max)$
+    minimum: 0
 
 # Schema for specs
 title: Protocol
@@ -226,10 +231,10 @@ properties:
                     type: string
                   min:
                     description: Min value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   max:
                     description: Max value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 4fd56e3b1553..0a4ae861d011 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -13,6 +13,11 @@ $defs:
     type: [ string, integer ]
     pattern: ^[0-9A-Za-z_]+( - 1)?$
     minimum: 0
+  len-or-limit:
+    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    type: [ string, integer ]
+    pattern: ^[su](8|16|32|64)-(min|max)$
+    minimum: 0
 
 # Schema for specs
 title: Protocol
@@ -156,10 +161,10 @@ properties:
                     type: string
                   min:
                     description: Min value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   max:
                     description: Max value for an integer attribute.
-                    type: integer
+                    $ref: '#/$defs/len-or-limit'
                   min-len:
                     description: Min length for a binary attribute.
                     $ref: '#/$defs/len-or-define'
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 9d008346dd50..552ba49a444c 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -20,6 +20,21 @@ def c_lower(name):
     return name.lower().replace('-', '_')
 
 
+def limit_to_number(name):
+    """
+    Turn a string limit like u32-max or s64-min into its numerical value
+    """
+    if name[0] == 'u' and name.endswith('-min'):
+        return 0
+    width = int(name[1:-4])
+    if name[0] == 's':
+        width -= 1
+    value = (1 << width) - 1
+    if name[0] == 's' and name.endswith('-min'):
+        value = -value - 1
+    return value
+
+
 class BaseNlLib:
     def get_family_id(self):
         return 'ys->family_id'
@@ -68,6 +83,14 @@ class Type(SpecAttr):
         self.enum_name = None
         delattr(self, "enum_name")
 
+    def get_limit(self, limit, default=None):
+        value = self.checks.get(limit, default)
+        if value is None:
+            return value
+        if not isinstance(value, int):
+            value = limit_to_number(value)
+        return value
+
     def resolve(self):
         if 'name-prefix' in self.attr:
             enum_name = f"{self.attr['name-prefix']}{self.name}"
@@ -273,12 +296,12 @@ class TypeScalar(Type):
                 self.checks['max'] = high
 
         if 'min' in self.checks and 'max' in self.checks:
-            if self.checks['min'] > self.checks['max']:
-                raise Exception(f'Invalid limit for "{self.name}" min: {self.checks["min"]} max: {self.checks["max"]}')
+            if self.get_limit('min') > self.get_limit('max'):
+                raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}')
             self.checks['range'] = True
 
-        low = min(self.checks.get('min', 0), self.checks.get('max', 0))
-        high = max(self.checks.get('min', 0), self.checks.get('max', 0))
+        low = min(self.get_limit('min', 0), self.get_limit('max', 0))
+        high = max(self.get_limit('min', 0), self.get_limit('max', 0))
         if low < 0 and self.type[0] == 'u':
             raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
         if low < -32768 or high > 32767:
@@ -326,11 +349,11 @@ class TypeScalar(Type):
         elif 'full-range' in self.checks:
             return f"NLA_POLICY_FULL_RANGE({policy}, &{c_lower(self.enum_name)}_range)"
         elif 'range' in self.checks:
-            return f"NLA_POLICY_RANGE({policy}, {self.checks['min']}, {self.checks['max']})"
+            return f"NLA_POLICY_RANGE({policy}, {self.get_limit('min')}, {self.get_limit('max')})"
         elif 'min' in self.checks:
-            return f"NLA_POLICY_MIN({policy}, {self.checks['min']})"
+            return f"NLA_POLICY_MIN({policy}, {self.get_limit('min')})"
         elif 'max' in self.checks:
-            return f"NLA_POLICY_MAX({policy}, {self.checks['max']})"
+            return f"NLA_POLICY_MAX({policy}, {self.get_limit('max')})"
         return super()._attr_policy(policy)
 
     def _attr_typol(self):
@@ -382,7 +405,7 @@ class TypeString(Type):
     def _attr_policy(self, policy):
         mem = '{ .type = ' + policy
         if 'max-len' in self.checks:
-            mem += ', .len = ' + str(self.checks['max-len'])
+            mem += ', .len = ' + str(self.get_limit('max-len'))
         mem += ', }'
         return mem
 
@@ -431,7 +454,7 @@ class TypeBinary(Type):
     def _attr_policy(self, policy):
         mem = '{ '
         if len(self.checks) == 1 and 'min-len' in self.checks:
-            mem += '.len = ' + str(self.checks['min-len'])
+            mem += '.len = ' + str(self.get_limit('min-len'))
         elif len(self.checks) == 0:
             mem += '.type = NLA_BINARY'
         else:
@@ -1982,9 +2005,9 @@ def print_kernel_policy_ranges(family, cw):
             cw.block_start(line=f'struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =')
             members = []
             if 'min' in attr.checks:
-                members.append(('min', attr.checks['min']))
+                members.append(('min', attr.get_limit('min')))
             if 'max' in attr.checks:
-                members.append(('max', attr.checks['max']))
+                members.append(('max', attr.get_limit('max')))
             cw.write_struct_init(members)
             cw.block_end(line=';')
             cw.nl()
-- 
cgit v1.2.3


From 9c66dc94b62aef23300f05f63404afb8990920b4 Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Wed, 18 Oct 2023 14:17:40 +0800
Subject: bpf: Introduce css_task open-coded iterator kfuncs

This patch adds kfuncs bpf_iter_css_task_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_css_task in open-coded
iterator style. These kfuncs actually wrapps css_task_iter_{start,next,
end}. BPF programs can use these kfuncs through bpf_for_each macro for
iteration of all tasks under a css.

css_task_iter_*() would try to get the global spin-lock *css_set_lock*, so
the bpf side has to be careful in where it allows to use this iter.
Currently we only allow it in bpf_lsm and bpf iter-s.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-3-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c                           |  3 ++
 kernel/bpf/task_iter.c                         | 58 ++++++++++++++++++++++++++
 kernel/bpf/verifier.c                          | 23 ++++++++++
 tools/testing/selftests/bpf/bpf_experimental.h |  8 ++++
 4 files changed, 92 insertions(+)

(limited to 'tools')

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 61f51dee8448..c01441db9fd5 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2560,6 +2560,9 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index fef17628341f..e4126698cecf 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -894,6 +894,64 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 
 __diag_pop();
 
+struct bpf_iter_css_task {
+	__u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_task_kern {
+	struct css_task_iter *css_it;
+} __attribute__((aligned(8)));
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+		struct cgroup_subsys_state *css, unsigned int flags)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) !=
+					__alignof__(struct bpf_iter_css_task));
+	kit->css_it = NULL;
+	switch (flags) {
+	case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED:
+	case CSS_TASK_ITER_PROCS:
+	case 0:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter));
+	if (!kit->css_it)
+		return -ENOMEM;
+	css_task_iter_start(css, flags, kit->css_it);
+	return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	if (!kit->css_it)
+		return NULL;
+	return css_task_iter_next(kit->css_it);
+}
+
+__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	if (!kit->css_it)
+		return;
+	css_task_iter_end(kit->css_it);
+	bpf_mem_free(&bpf_global_ma, kit->css_it);
+}
+
+__diag_pop();
+
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
 static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb58987e4844..974713185269 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10472,6 +10472,7 @@ enum special_kfunc_type {
 	KF_bpf_percpu_obj_new_impl,
 	KF_bpf_percpu_obj_drop_impl,
 	KF_bpf_throw,
+	KF_bpf_iter_css_task_new,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -10495,6 +10496,7 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+BTF_ID(func, bpf_iter_css_task_new)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10520,6 +10522,7 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+BTF_ID(func, bpf_iter_css_task_new)
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -11050,6 +11053,20 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
 						  &meta->arg_rbtree_root.field);
 }
 
+static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
+{
+	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+	switch (prog_type) {
+	case BPF_PROG_TYPE_LSM:
+		return true;
+	case BPF_TRACE_ITER:
+		return env->prog->aux->sleepable;
+	default:
+		return false;
+	}
+}
+
 static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
 			    int insn_idx)
 {
@@ -11300,6 +11317,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			break;
 		}
 		case KF_ARG_PTR_TO_ITER:
+			if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
+				if (!check_css_task_iter_allowlist(env)) {
+					verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+					return -EINVAL;
+				}
+			}
 			ret = process_iter_arg(env, regno, insn_idx, meta);
 			if (ret < 0)
 				return ret;
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 2c8cb3f61529..6792ed2b45d7 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -458,4 +458,12 @@ extern void bpf_throw(u64 cookie) __ksym;
 		__bpf_assert_op(LHS, <=, END, value, false);		\
 	})
 
+struct bpf_iter_css_task;
+struct cgroup_subsys_state;
+extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+		struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym;
+extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym;
+extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym;
+
+
 #endif
-- 
cgit v1.2.3


From c68a78ffe2cb4207f64fd0f4262818c728c67be0 Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Wed, 18 Oct 2023 14:17:41 +0800
Subject: bpf: Introduce task open coded iterator kfuncs

This patch adds kfuncs bpf_iter_task_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_task in open-coded iterator
style. BPF programs can use these kfuncs or through bpf_for_each macro to
iterate all processes in the system.

The API design keep consistent with SEC("iter/task"). bpf_iter_task_new()
accepts a specific task and iterating type which allows:

1. iterating all process in the system (BPF_TASK_ITER_ALL_PROCS)

2. iterating all threads in the system (BPF_TASK_ITER_ALL_THREADS)

3. iterating all threads of a specific task (BPF_TASK_ITER_PROC_THREADS)

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Link: https://lore.kernel.org/r/20231018061746.111364-4-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c                           |  3 +
 kernel/bpf/task_iter.c                         | 90 ++++++++++++++++++++++++++
 tools/testing/selftests/bpf/bpf_experimental.h |  5 ++
 3 files changed, 98 insertions(+)

(limited to 'tools')

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index c01441db9fd5..c25941531265 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2563,6 +2563,9 @@ BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index e4126698cecf..faa1712c1df5 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -952,6 +952,96 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
 
 __diag_pop();
 
+struct bpf_iter_task {
+	__u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_task_kern {
+	struct task_struct *task;
+	struct task_struct *pos;
+	unsigned int flags;
+} __attribute__((aligned(8)));
+
+enum {
+	/* all process in the system */
+	BPF_TASK_ITER_ALL_PROCS,
+	/* all threads in the system */
+	BPF_TASK_ITER_ALL_THREADS,
+	/* all threads of a specific process */
+	BPF_TASK_ITER_PROC_THREADS
+};
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
+		struct task_struct *task, unsigned int flags)
+{
+	struct bpf_iter_task_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
+					__alignof__(struct bpf_iter_task));
+
+	kit->task = kit->pos = NULL;
+	switch (flags) {
+	case BPF_TASK_ITER_ALL_THREADS:
+	case BPF_TASK_ITER_ALL_PROCS:
+	case BPF_TASK_ITER_PROC_THREADS:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (flags == BPF_TASK_ITER_PROC_THREADS)
+		kit->task = task;
+	else
+		kit->task = &init_task;
+	kit->pos = kit->task;
+	kit->flags = flags;
+	return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
+{
+	struct bpf_iter_task_kern *kit = (void *)it;
+	struct task_struct *pos;
+	unsigned int flags;
+
+	flags = kit->flags;
+	pos = kit->pos;
+
+	if (!pos)
+		return pos;
+
+	if (flags == BPF_TASK_ITER_ALL_PROCS)
+		goto get_next_task;
+
+	kit->pos = next_thread(kit->pos);
+	if (kit->pos == kit->task) {
+		if (flags == BPF_TASK_ITER_PROC_THREADS) {
+			kit->pos = NULL;
+			return pos;
+		}
+	} else
+		return pos;
+
+get_next_task:
+	kit->pos = next_task(kit->pos);
+	kit->task = kit->pos;
+	if (kit->pos == &init_task)
+		kit->pos = NULL;
+
+	return pos;
+}
+
+__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
+{
+}
+
+__diag_pop();
+
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
 static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 6792ed2b45d7..2f6c747aa874 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -465,5 +465,10 @@ extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
 extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym;
 extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym;
 
+struct bpf_iter_task;
+extern int bpf_iter_task_new(struct bpf_iter_task *it,
+		struct task_struct *task, unsigned int flags) __weak __ksym;
+extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym;
+extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym;
 
 #endif
-- 
cgit v1.2.3


From 7251d0905e7518bcb990c8e9a3615b1bb23c78f2 Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Wed, 18 Oct 2023 14:17:42 +0800
Subject: bpf: Introduce css open-coded iterator kfuncs

This Patch adds kfuncs bpf_iter_css_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_css in open-coded iterator
style. These kfuncs actually wrapps css_next_descendant_{pre, post}.
css_iter can be used to:

1) iterating a sepcific cgroup tree with pre/post/up order

2) iterating cgroup_subsystem in BPF Prog, like
for_each_mem_cgroup_tree/cpuset_for_each_descendant_pre in kernel.

The API design is consistent with cgroup_iter. bpf_iter_css_new accepts
parameters defining iteration order and starting css. Here we also reuse
BPF_CGROUP_ITER_DESCENDANTS_PRE, BPF_CGROUP_ITER_DESCENDANTS_POST,
BPF_CGROUP_ITER_ANCESTORS_UP enums.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-5-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cgroup_iter.c                       | 65 ++++++++++++++++++++++++++
 kernel/bpf/helpers.c                           |  3 ++
 tools/testing/selftests/bpf/bpf_experimental.h |  6 +++
 3 files changed, 74 insertions(+)

(limited to 'tools')

diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 810378f04fbc..209e5135f9fb 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -294,3 +294,68 @@ static int __init bpf_cgroup_iter_init(void)
 }
 
 late_initcall(bpf_cgroup_iter_init);
+
+struct bpf_iter_css {
+	__u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_kern {
+	struct cgroup_subsys_state *start;
+	struct cgroup_subsys_state *pos;
+	unsigned int flags;
+} __attribute__((aligned(8)));
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		"Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
+		struct cgroup_subsys_state *start, unsigned int flags)
+{
+	struct bpf_iter_css_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css));
+
+	kit->start = NULL;
+	switch (flags) {
+	case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+	case BPF_CGROUP_ITER_DESCENDANTS_POST:
+	case BPF_CGROUP_ITER_ANCESTORS_UP:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	kit->start = start;
+	kit->pos = NULL;
+	kit->flags = flags;
+	return 0;
+}
+
+__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it)
+{
+	struct bpf_iter_css_kern *kit = (void *)it;
+
+	if (!kit->start)
+		return NULL;
+
+	switch (kit->flags) {
+	case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+		kit->pos = css_next_descendant_pre(kit->pos, kit->start);
+		break;
+	case BPF_CGROUP_ITER_DESCENDANTS_POST:
+		kit->pos = css_next_descendant_post(kit->pos, kit->start);
+		break;
+	case BPF_CGROUP_ITER_ANCESTORS_UP:
+		kit->pos = kit->pos ? kit->pos->parent : kit->start;
+	}
+
+	return kit->pos;
+}
+
+__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
+{
+}
+
+__diag_pop();
\ No newline at end of file
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index c25941531265..b1d285ed4796 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2566,6 +2566,9 @@ BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 2f6c747aa874..1386baf9ae4a 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -471,4 +471,10 @@ extern int bpf_iter_task_new(struct bpf_iter_task *it,
 extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym;
 extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym;
 
+struct bpf_iter_css;
+extern int bpf_iter_css_new(struct bpf_iter_css *it,
+				struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym;
+extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym;
+extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
+
 #endif
-- 
cgit v1.2.3


From ddab78cbb52f81f7f7598482602342955b2ff8b8 Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Wed, 18 Oct 2023 14:17:45 +0800
Subject: selftests/bpf: rename bpf_iter_task.c to bpf_iter_tasks.c

The newly-added struct bpf_iter_task has a name collision with a selftest
for the seq_file task iter's bpf skel, so the selftests/bpf/progs file is
renamed in order to avoid the collision.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-8-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c  | 18 ++---
 tools/testing/selftests/bpf/progs/bpf_iter_task.c  | 88 ----------------------
 tools/testing/selftests/bpf/progs/bpf_iter_tasks.c | 88 ++++++++++++++++++++++
 3 files changed, 97 insertions(+), 97 deletions(-)
 delete mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_task.c
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_tasks.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 41aba139b20b..e3498f607b49 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -7,7 +7,7 @@
 #include "bpf_iter_ipv6_route.skel.h"
 #include "bpf_iter_netlink.skel.h"
 #include "bpf_iter_bpf_map.skel.h"
-#include "bpf_iter_task.skel.h"
+#include "bpf_iter_tasks.skel.h"
 #include "bpf_iter_task_stack.skel.h"
 #include "bpf_iter_task_file.skel.h"
 #include "bpf_iter_task_vmas.skel.h"
@@ -215,12 +215,12 @@ static void *do_nothing_wait(void *arg)
 static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts,
 				     int *num_unknown, int *num_known)
 {
-	struct bpf_iter_task *skel;
+	struct bpf_iter_tasks *skel;
 	pthread_t thread_id;
 	void *ret;
 
-	skel = bpf_iter_task__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load"))
+	skel = bpf_iter_tasks__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
 		return;
 
 	ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock");
@@ -239,7 +239,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts,
 	ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL,
 		     "pthread_join");
 
-	bpf_iter_task__destroy(skel);
+	bpf_iter_tasks__destroy(skel);
 }
 
 static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known)
@@ -307,10 +307,10 @@ static void test_task_pidfd(void)
 
 static void test_task_sleepable(void)
 {
-	struct bpf_iter_task *skel;
+	struct bpf_iter_tasks *skel;
 
-	skel = bpf_iter_task__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load"))
+	skel = bpf_iter_tasks__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
 		return;
 
 	do_dummy_read(skel->progs.dump_task_sleepable);
@@ -320,7 +320,7 @@ static void test_task_sleepable(void)
 	ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0,
 		  "num_success_copy_from_user_task");
 
-	bpf_iter_task__destroy(skel);
+	bpf_iter_tasks__destroy(skel);
 }
 
 static void test_task_stack(void)
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
deleted file mode 100644
index 96131b9a1caa..000000000000
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ /dev/null
@@ -1,88 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
-
-char _license[] SEC("license") = "GPL";
-
-uint32_t tid = 0;
-int num_unknown_tid = 0;
-int num_known_tid = 0;
-
-SEC("iter/task")
-int dump_task(struct bpf_iter__task *ctx)
-{
-	struct seq_file *seq = ctx->meta->seq;
-	struct task_struct *task = ctx->task;
-	static char info[] = "    === END ===";
-
-	if (task == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	if (task->pid != tid)
-		num_unknown_tid++;
-	else
-		num_known_tid++;
-
-	if (ctx->meta->seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "    tgid      gid\n");
-
-	BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
-	return 0;
-}
-
-int num_expected_failure_copy_from_user_task = 0;
-int num_success_copy_from_user_task = 0;
-
-SEC("iter.s/task")
-int dump_task_sleepable(struct bpf_iter__task *ctx)
-{
-	struct seq_file *seq = ctx->meta->seq;
-	struct task_struct *task = ctx->task;
-	static const char info[] = "    === END ===";
-	struct pt_regs *regs;
-	void *ptr;
-	uint32_t user_data = 0;
-	int ret;
-
-	if (task == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	/* Read an invalid pointer and ensure we get an error */
-	ptr = NULL;
-	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
-	if (ret) {
-		++num_expected_failure_copy_from_user_task;
-	} else {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	/* Try to read the contents of the task's instruction pointer from the
-	 * remote task's address space.
-	 */
-	regs = (struct pt_regs *)bpf_task_pt_regs(task);
-	if (regs == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-	ptr = (void *)PT_REGS_IP(regs);
-
-	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
-	if (ret) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-	++num_success_copy_from_user_task;
-
-	if (ctx->meta->seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "    tgid      gid     data\n");
-
-	BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data);
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
new file mode 100644
index 000000000000..96131b9a1caa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+uint32_t tid = 0;
+int num_unknown_tid = 0;
+int num_known_tid = 0;
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	static char info[] = "    === END ===";
+
+	if (task == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	if (task->pid != tid)
+		num_unknown_tid++;
+	else
+		num_known_tid++;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
+	return 0;
+}
+
+int num_expected_failure_copy_from_user_task = 0;
+int num_success_copy_from_user_task = 0;
+
+SEC("iter.s/task")
+int dump_task_sleepable(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	static const char info[] = "    === END ===";
+	struct pt_regs *regs;
+	void *ptr;
+	uint32_t user_data = 0;
+	int ret;
+
+	if (task == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Read an invalid pointer and ensure we get an error */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
+	if (ret) {
+		++num_expected_failure_copy_from_user_task;
+	} else {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Try to read the contents of the task's instruction pointer from the
+	 * remote task's address space.
+	 */
+	regs = (struct pt_regs *)bpf_task_pt_regs(task);
+	if (regs == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+	ptr = (void *)PT_REGS_IP(regs);
+
+	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
+	if (ret) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+	++num_success_copy_from_user_task;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid     data\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data);
+	return 0;
+}
-- 
cgit v1.2.3


From 130e0f7af9fc7388b90fb016ca13ff3840c48d4a Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Wed, 18 Oct 2023 14:17:46 +0800
Subject: selftests/bpf: Add tests for open-coded task and css iter

This patch adds 4 subtests to demonstrate these patterns and validating
correctness.

subtest1:

1) We use task_iter to iterate all process in the system and search for the
current process with a given pid.

2) We create some threads in current process context, and use
BPF_TASK_ITER_PROC_THREADS to iterate all threads of current process. As
expected, we would find all the threads of current process.

3) We create some threads and use BPF_TASK_ITER_ALL_THREADS to iterate all
threads in the system. As expected, we would find all the threads which was
created.

subtest2:

We create a cgroup and add the current task to the cgroup. In the
BPF program, we would use bpf_for_each(css_task, task, css) to iterate all
tasks under the cgroup. As expected, we would find the current process.

subtest3:

1) We create a cgroup tree. In the BPF program, we use
bpf_for_each(css, pos, root, XXX) to iterate all descendant under the root
with pre and post order. As expected, we would find all descendant and the
last iterating cgroup in post-order is root cgroup, the first iterating
cgroup in pre-order is root cgroup.

2) We wse BPF_CGROUP_ITER_ANCESTORS_UP to traverse the cgroup tree starting
from leaf and root separately, and record the height. The diff of the
hights would be the total tree-high - 1.

subtest4:

Add some failure testcase when using css_task, task and css iters, e.g,
unlock when using task-iters to iterate tasks.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Link: https://lore.kernel.org/r/20231018061746.111364-9-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/iters.c     | 150 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/iters_css.c      |  72 ++++++++++
 tools/testing/selftests/bpf/progs/iters_css_task.c |  47 +++++++
 tools/testing/selftests/bpf/progs/iters_task.c     |  41 ++++++
 .../selftests/bpf/progs/iters_task_failure.c       | 105 +++++++++++++++
 5 files changed, 415 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/iters_css.c
 create mode 100644 tools/testing/selftests/bpf/progs/iters_css_task.c
 create mode 100644 tools/testing/selftests/bpf/progs/iters_task.c
 create mode 100644 tools/testing/selftests/bpf/progs/iters_task_failure.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index b696873c5455..c2425791c923 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -1,7 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
 
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <malloc.h>
+#include <stdlib.h>
 #include <test_progs.h>
+#include "cgroup_helpers.h"
 
 #include "iters.skel.h"
 #include "iters_state_safety.skel.h"
@@ -9,6 +16,10 @@
 #include "iters_num.skel.h"
 #include "iters_testmod_seq.skel.h"
 #include "iters_task_vma.skel.h"
+#include "iters_task.skel.h"
+#include "iters_css_task.skel.h"
+#include "iters_css.skel.h"
+#include "iters_task_failure.skel.h"
 
 static void subtest_num_iters(void)
 {
@@ -146,6 +157,138 @@ cleanup:
 	iters_task_vma__destroy(skel);
 }
 
+static pthread_mutex_t do_nothing_mutex;
+
+static void *do_nothing_wait(void *arg)
+{
+	pthread_mutex_lock(&do_nothing_mutex);
+	pthread_mutex_unlock(&do_nothing_mutex);
+
+	pthread_exit(arg);
+}
+
+#define thread_num 2
+
+static void subtest_task_iters(void)
+{
+	struct iters_task *skel = NULL;
+	pthread_t thread_ids[thread_num];
+	void *ret;
+	int err;
+
+	skel = iters_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+	skel->bss->target_pid = getpid();
+	err = iters_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	pthread_mutex_lock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL),
+			"pthread_create");
+
+	syscall(SYS_getpgid);
+	iters_task__detach(skel);
+	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
+	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
+	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	pthread_mutex_unlock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
+cleanup:
+	iters_task__destroy(skel);
+}
+
+extern int stack_mprotect(void);
+
+static void subtest_css_task_iters(void)
+{
+	struct iters_css_task *skel = NULL;
+	int err, cg_fd, cg_id;
+	const char *cgrp_path = "/cg1";
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	cg_fd = create_and_get_cgroup(cgrp_path);
+	if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup"))
+		goto cleanup;
+	cg_id = get_cgroup_id(cgrp_path);
+	err = join_cgroup(cgrp_path);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel = iters_css_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->cg_id = cg_id;
+	err = iters_css_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	err = stack_mprotect();
+	if (!ASSERT_EQ(err, -1, "stack_mprotect") ||
+	    !ASSERT_EQ(errno, EPERM, "stack_mprotect"))
+		goto cleanup;
+	iters_css_task__detach(skel);
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css_task__destroy(skel);
+}
+
+static void subtest_css_iters(void)
+{
+	struct iters_css *skel = NULL;
+	struct {
+		const char *path;
+		int fd;
+	} cgs[] = {
+		{ "/cg1" },
+		{ "/cg1/cg2" },
+		{ "/cg1/cg2/cg3" },
+		{ "/cg1/cg2/cg3/cg4" },
+	};
+	int err, cg_nr = ARRAY_SIZE(cgs);
+	int i;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	for (i = 0; i < cg_nr; i++) {
+		cgs[i].fd = create_and_get_cgroup(cgs[i].path);
+		if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup"))
+			goto cleanup;
+	}
+
+	skel = iters_css__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->root_cg_id = get_cgroup_id(cgs[0].path);
+	skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path);
+	err = iters_css__attach(skel);
+
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+
+	syscall(SYS_getpgid);
+	ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt");
+	ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id");
+
+	ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt");
+	ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id");
+	ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high");
+	iters_css__detach(skel);
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css__destroy(skel);
+}
+
 void test_iters(void)
 {
 	RUN_TESTS(iters_state_safety);
@@ -161,4 +304,11 @@ void test_iters(void)
 		subtest_testmod_seq_iters();
 	if (test__start_subtest("task_vma"))
 		subtest_task_vma_iters();
+	if (test__start_subtest("task"))
+		subtest_task_iters();
+	if (test__start_subtest("css_task"))
+		subtest_css_task_iters();
+	if (test__start_subtest("css"))
+		subtest_css_iters();
+	RUN_TESTS(iters_task_failure);
 }
diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c
new file mode 100644
index 000000000000..ec1f6c2f590b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_css.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+u64 root_cg_id, leaf_cg_id;
+u64 first_cg_id, last_cg_id;
+
+int pre_order_cnt, post_order_cnt, tree_high;
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_css_for_each(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *root_css, *leaf_css, *pos;
+	struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+
+	root_cgrp = bpf_cgroup_from_id(root_cg_id);
+
+	if (!root_cgrp)
+		return 0;
+
+	leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id);
+
+	if (!leaf_cgrp) {
+		bpf_cgroup_release(root_cgrp);
+		return 0;
+	}
+	root_css = &root_cgrp->self;
+	leaf_css = &leaf_cgrp->self;
+	pre_order_cnt = post_order_cnt = tree_high = 0;
+	first_cg_id = last_cg_id = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		cur_cgrp = pos->cgroup;
+		post_order_cnt++;
+		last_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) {
+		cur_cgrp = pos->cgroup;
+		pre_order_cnt++;
+		if (!first_cg_id)
+			first_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high++;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high--;
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(root_cgrp);
+	bpf_cgroup_release(leaf_cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c
new file mode 100644
index 000000000000..5089ce384a1c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_css_task.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+
+pid_t target_pid;
+int css_task_cnt;
+u64 cg_id;
+
+SEC("lsm/file_mprotect")
+int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
+	    unsigned long reqprot, unsigned long prot, int ret)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (cur_task->pid != target_pid)
+		return ret;
+
+	cgrp = bpf_cgroup_from_id(cg_id);
+
+	if (!cgrp)
+		return -EPERM;
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS)
+		if (task->pid == target_pid)
+			css_task_cnt++;
+
+	bpf_cgroup_release(cgrp);
+
+	return -EPERM;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
new file mode 100644
index 000000000000..c9b4055cd410
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+int procs_cnt, threads_cnt, proc_threads_cnt;
+
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_task_for_each_sleep(void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct task_struct *pos;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+	procs_cnt = threads_cnt = proc_threads_cnt = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
+		if (pos->pid == target_pid)
+			procs_cnt++;
+
+	bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS)
+		proc_threads_cnt++;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS)
+		if (pos->tgid == target_pid)
+			threads_cnt++;
+	bpf_rcu_read_unlock();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c
new file mode 100644
index 000000000000..c3bf96a67dba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+int BPF_PROG(iter_tasks_without_lock)
+{
+	struct task_struct *pos;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+
+	}
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+int BPF_PROG(iter_css_without_lock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+int BPF_PROG(iter_tasks_lock_and_unlock)
+{
+	struct task_struct *pos;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+int BPF_PROG(iter_css_lock_and_unlock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+int BPF_PROG(iter_css_task_for_each)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
-- 
cgit v1.2.3


From e1b347c5f7de2c1a112c2dd6e380241135e34be2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Oct 2023 14:39:19 -0700
Subject: tools: ynl-gen: make the mnl_type() method public

uint/sint support will add more logic to mnl_type(),
deduplicate it and make it more accessible.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/ynl/ynl-gen-c.py | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 552ba49a444c..6f4c538bda9a 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -159,6 +159,15 @@ class Type(SpecAttr):
         spec = self._attr_policy(policy)
         cw.p(f"\t[{self.enum_name}] = {spec},")
 
+    def _mnl_type(self):
+        # mnl does not have helpers for signed integer types
+        # turn signed type into unsigned
+        # this only makes sense for scalar types
+        t = self.type
+        if t[0] == 's':
+            t = 'u' + t[1:]
+        return t
+
     def _attr_typol(self):
         raise Exception(f"Type policy not implemented for class type {self.type}")
 
@@ -329,12 +338,8 @@ class TypeScalar(Type):
         else:
             self.type_name = '__' + self.type
 
-    def _mnl_type(self):
-        t = self.type
-        # mnl does not have a helper for signed types
-        if t[0] == 's':
-            t = 'u' + t[1:]
-        return t
+    def mnl_type(self):
+        return self._mnl_type()
 
     def _attr_policy(self, policy):
         if 'flags-mask' in self.checks or self.is_bitfield:
@@ -363,10 +368,10 @@ class TypeScalar(Type):
         return [f'{self.type_name} {self.c_name}{self.byte_order_comment}']
 
     def attr_put(self, ri, var):
-        self._attr_put_simple(ri, var, self._mnl_type())
+        self._attr_put_simple(ri, var, self.mnl_type())
 
     def _attr_get(self, ri, var):
-        return f"{var}->{self.c_name} = mnl_attr_get_{self._mnl_type()}(attr);", None, None
+        return f"{var}->{self.c_name} = mnl_attr_get_{self.mnl_type()}(attr);", None, None
 
     def _setter_lines(self, ri, member, presence):
         return [f"{member} = {self.c_name};"]
@@ -524,12 +529,8 @@ class TypeMultiAttr(Type):
     def presence_type(self):
         return 'count'
 
-    def _mnl_type(self):
-        t = self.type
-        # mnl does not have a helper for signed types
-        if t[0] == 's':
-            t = 'u' + t[1:]
-        return t
+    def mnl_type(self):
+        return self._mnl_type()
 
     def _complex_member_type(self, ri):
         if 'type' not in self.attr or self.attr['type'] == 'nest':
@@ -564,7 +565,7 @@ class TypeMultiAttr(Type):
 
     def attr_put(self, ri, var):
         if self.attr['type'] in scalars:
-            put_type = self._mnl_type()
+            put_type = self.mnl_type()
             ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)")
             ri.cw.p(f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);")
         elif 'type' not in self.attr or self.attr['type'] == 'nest':
@@ -1580,11 +1581,8 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];")
             ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr))")
             ri.cw.p('return MNL_CB_ERROR;')
-        elif aspec['type'] in scalars:
-            t = aspec['type']
-            if t[0] == 's':
-                t = 'u' + t[1:]
-            ri.cw.p(f"dst->{aspec.c_name}[i] = mnl_attr_get_{t}(attr);")
+        elif aspec.type in scalars:
+            ri.cw.p(f"dst->{aspec.c_name}[i] = mnl_attr_get_{aspec.mnl_type()}(attr);")
         else:
             raise Exception('Nest parsing type not supported yet')
         ri.cw.p('i++;')
-- 
cgit v1.2.3


From 7d4caf54d2e8df2ed52240fe339adb13372c6251 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Oct 2023 14:39:21 -0700
Subject: netlink: specs: add support for auto-sized scalars

Support uint / sint types in specs and YNL.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/genetlink-c.yaml      |  3 ++-
 Documentation/netlink/genetlink-legacy.yaml |  3 ++-
 Documentation/netlink/genetlink.yaml        |  3 ++-
 tools/net/ynl/lib/nlspec.py                 |  6 ++++++
 tools/net/ynl/lib/ynl.c                     |  6 ++++++
 tools/net/ynl/lib/ynl.h                     | 17 +++++++++++++++++
 tools/net/ynl/lib/ynl.py                    | 14 ++++++++++++++
 tools/net/ynl/ynl-gen-c.py                  |  6 ++++--
 8 files changed, 53 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index dee11c514896..c72c8a428911 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -149,7 +149,8 @@ properties:
               name:
                 type: string
               type: &attr-type
-                enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64,
+                enum: [ unused, pad, flag, binary,
+                        uint, sint, u8, u16, u32, u64, s32, s64,
                         string, nest, array-nest, nest-type-value ]
               doc:
                 description: Documentation of the attribute.
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 9194f3e223ef..923de0ff1a9e 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -192,7 +192,8 @@ properties:
                 type: string
               type: &attr-type
                 description: The netlink attribute type
-                enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64,
+                enum: [ unused, pad, flag, binary,
+                        uint, sint, u8, u16, u32, u64, s32, s64,
                         string, nest, array-nest, nest-type-value ]
               doc:
                 description: Documentation of the attribute.
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 0a4ae861d011..9ceb096b2df2 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -122,7 +122,8 @@ properties:
               name:
                 type: string
               type: &attr-type
-                enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64,
+                enum: [ unused, pad, flag, binary,
+                        uint, sint, u8, u16, u32, u64, s32, s64,
                         string, nest, array-nest, nest-type-value ]
               doc:
                 description: Documentation of the attribute.
diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py
index 37bcb4d8b37b..92889298b197 100644
--- a/tools/net/ynl/lib/nlspec.py
+++ b/tools/net/ynl/lib/nlspec.py
@@ -149,6 +149,7 @@ class SpecAttr(SpecElement):
     Represents a single attribute type within an attr space.
 
     Attributes:
+        type          string, attribute type
         value         numerical ID when serialized
         attr_set      Attribute Set containing this attr
         is_multi      bool, attr may repeat multiple times
@@ -157,10 +158,13 @@ class SpecAttr(SpecElement):
         len           integer, optional byte length of binary types
         display_hint  string, hint to help choose format specifier
                       when displaying the value
+
+        is_auto_scalar bool, attr is a variable-size scalar
     """
     def __init__(self, family, attr_set, yaml, value):
         super().__init__(family, yaml)
 
+        self.type = yaml['type']
         self.value = value
         self.attr_set = attr_set
         self.is_multi = yaml.get('multi-attr', False)
@@ -170,6 +174,8 @@ class SpecAttr(SpecElement):
         self.len = yaml.get('len')
         self.display_hint = yaml.get('display-hint')
 
+        self.is_auto_scalar = self.type == "sint" or self.type == "uint"
+
 
 class SpecAttrSet(SpecElement):
     """ Netlink Attribute Set class.
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 514e0d69e731..350ddc247450 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -352,6 +352,12 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
 		     "Invalid attribute (u64 %s)", policy->name);
 		return -1;
+	case YNL_PT_UINT:
+		if (len == sizeof(__u32) || len == sizeof(__u64))
+			break;
+		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
+		     "Invalid attribute (uint %s)", policy->name);
+		return -1;
 	case YNL_PT_FLAG:
 		/* Let flags grow into real attrs, why not.. */
 		break;
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index 9eafa3552c16..87b4dad832f0 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -133,6 +133,7 @@ enum ynl_policy_type {
 	YNL_PT_U16,
 	YNL_PT_U32,
 	YNL_PT_U64,
+	YNL_PT_UINT,
 	YNL_PT_NUL_STR,
 };
 
@@ -234,4 +235,20 @@ int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh,
 void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd);
 int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg);
 
+#ifndef MNL_HAS_AUTO_SCALARS
+static inline uint64_t mnl_attr_get_uint(const struct nlattr *attr)
+{
+	if (mnl_attr_get_len(attr) == 4)
+		return mnl_attr_get_u32(attr);
+	return mnl_attr_get_u64(attr);
+}
+
+static inline void
+mnl_attr_put_uint(struct nlmsghdr *nlh, uint16_t type, uint64_t data)
+{
+	if ((uint32_t)data == (uint64_t)data)
+		return mnl_attr_put_u32(nlh, type, data);
+	return mnl_attr_put_u64(nlh, type, data);
+}
+#endif
 #endif
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 28ac35008e65..3b36553a66cc 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -130,6 +130,13 @@ class NlAttr:
         format = self.get_format(attr_type, byte_order)
         return format.unpack(self.raw)[0]
 
+    def as_auto_scalar(self, attr_type, byte_order=None):
+        if len(self.raw) != 4 and len(self.raw) != 8:
+            raise Exception(f"Auto-scalar len payload be 4 or 8 bytes, got {len(self.raw)}")
+        real_type = attr_type[0] + str(len(self.raw) * 8)
+        format = self.get_format(real_type, byte_order)
+        return format.unpack(self.raw)[0]
+
     def as_strz(self):
         return self.raw.decode('ascii')[:-1]
 
@@ -463,6 +470,11 @@ class YnlFamily(SpecFamily):
                 attr_payload = bytes.fromhex(value)
             else:
                 raise Exception(f'Unknown type for binary attribute, value: {value}')
+        elif attr.is_auto_scalar:
+            scalar = int(value)
+            real_type = attr["type"][0] + ('32' if scalar.bit_length() <= 32 else '64')
+            format = NlAttr.get_format(real_type, attr.byte_order)
+            attr_payload = format.pack(int(value))
         elif attr['type'] in NlAttr.type_formats:
             format = NlAttr.get_format(attr['type'], attr.byte_order)
             attr_payload = format.pack(int(value))
@@ -529,6 +541,8 @@ class YnlFamily(SpecFamily):
                 decoded = self._decode_binary(attr, attr_spec)
             elif attr_spec["type"] == 'flag':
                 decoded = True
+            elif attr_spec.is_auto_scalar:
+                decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order)
             elif attr_spec["type"] in NlAttr.type_formats:
                 decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order)
             elif attr_spec["type"] == 'array-nest':
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 6f4c538bda9a..a9e8898c9386 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -335,6 +335,8 @@ class TypeScalar(Type):
         maybe_enum = not self.is_bitfield and 'enum' in self.attr
         if maybe_enum and self.family.consts[self.attr['enum']].enum_name:
             self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}"
+        elif self.is_auto_scalar:
+            self.type_name = '__' + self.type[0] + '64'
         else:
             self.type_name = '__' + self.type
 
@@ -362,7 +364,7 @@ class TypeScalar(Type):
         return super()._attr_policy(policy)
 
     def _attr_typol(self):
-        return f'.type = YNL_PT_U{self.type[1:]}, '
+        return f'.type = YNL_PT_U{c_upper(self.type[1:])}, '
 
     def arg_member(self, ri):
         return [f'{self.type_name} {self.c_name}{self.byte_order_comment}']
@@ -1291,7 +1293,7 @@ class CodeWriter:
             self.p(line)
 
 
-scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64'}
+scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64', 'uint', 'sint'}
 
 direction_to_suffix = {
     'reply': '_rsp',
-- 
cgit v1.2.3


From da1055b673f3baac2249571c9882ce767a0aa746 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 20 Oct 2023 14:48:39 +0000
Subject: selftests/bpf: Make linked_list failure test more robust

The linked list failure test 'pop_front_off' and 'pop_back_off'
currently rely on matching exact instruction and register values.  The
purpose of the test is to ensure the offset is correctly incremented for
the returned pointers from list pop helpers, which can then be used with
container_of to obtain the real object. Hence, somehow obtaining the
information that the offset is 48 will work for us. Make the test more
robust by relying on verifier error string of bpf_spin_lock and remove
dependence on fragile instruction index or register number, which can be
affected by different clang versions used to build the selftests.

Fixes: 300f19dcdb99 ("selftests/bpf: Add BPF linked list API tests")
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231020144839.2734006-1-memxor@gmail.com
---
 tools/testing/selftests/bpf/prog_tests/linked_list.c | 10 ++--------
 tools/testing/selftests/bpf/progs/linked_list_fail.c |  4 +++-
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index 69dc31383b78..2fb89de63bd2 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -94,14 +94,8 @@ static struct {
 	{ "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" },
 	{ "incorrect_head_off1", "bpf_list_head not found at offset=25" },
 	{ "incorrect_head_off2", "bpf_list_head not found at offset=1" },
-	{ "pop_front_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n"
-	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
-	{ "pop_back_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n"
-	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
+	{ "pop_front_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" },
+	{ "pop_back_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" },
 };
 
 static void test_linked_list_fail_prog(const char *prog_name, const char *err_msg)
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index f4c63daba229..6438982b928b 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -591,7 +591,9 @@ int pop_ptr_off(void *(*op)(void *head))
 	n = op(&p->head);
 	bpf_spin_unlock(&p->lock);
 
-	bpf_this_cpu_ptr(n);
+	if (!n)
+		return 0;
+	bpf_spin_lock((void *)n);
 	return 0;
 }
 
-- 
cgit v1.2.3


From d440ba91ca4d3004709876779d40713a99e21f6a Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Fri, 20 Oct 2023 21:32:02 +0800
Subject: selftests/bpf: Add more test cases for bpf memory allocator

Add the following 3 test cases for bpf memory allocator:
1) Do allocation in bpf program and free through map free
2) Do batch per-cpu allocation and per-cpu free in bpf program
3) Do per-cpu allocation in bpf program and free through map free

For per-cpu allocation, because per-cpu allocation can not refill timely
sometimes, so test 2) and test 3) consider it is OK for
bpf_percpu_obj_new_impl() to return NULL.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231020133202.4043247-8-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/test_bpf_ma.c |  20 ++-
 tools/testing/selftests/bpf/progs/test_bpf_ma.c    | 180 ++++++++++++++++++++-
 2 files changed, 193 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
index 0cca4e8ae38e..d3491a84b3b9 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
@@ -9,9 +9,10 @@
 
 #include "test_bpf_ma.skel.h"
 
-void test_test_bpf_ma(void)
+static void do_bpf_ma_test(const char *name)
 {
 	struct test_bpf_ma *skel;
+	struct bpf_program *prog;
 	struct btf *btf;
 	int i, err;
 
@@ -34,6 +35,11 @@ void test_test_bpf_ma(void)
 		skel->rodata->data_btf_ids[i] = id;
 	}
 
+	prog = bpf_object__find_program_by_name(skel->obj, name);
+	if (!ASSERT_OK_PTR(prog, "invalid prog name"))
+		goto out;
+	bpf_program__set_autoload(prog, true);
+
 	err = test_bpf_ma__load(skel);
 	if (!ASSERT_OK(err, "load"))
 		goto out;
@@ -48,3 +54,15 @@ void test_test_bpf_ma(void)
 out:
 	test_bpf_ma__destroy(skel);
 }
+
+void test_test_bpf_ma(void)
+{
+	if (test__start_subtest("batch_alloc_free"))
+		do_bpf_ma_test("test_batch_alloc_free");
+	if (test__start_subtest("free_through_map_free"))
+		do_bpf_ma_test("test_free_through_map_free");
+	if (test__start_subtest("batch_percpu_alloc_free"))
+		do_bpf_ma_test("test_batch_percpu_alloc_free");
+	if (test__start_subtest("percpu_free_through_map_free"))
+		do_bpf_ma_test("test_percpu_free_through_map_free");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
index ecde41ae0fc8..b685a4aba6bd 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -37,10 +37,20 @@ int pid = 0;
 		__type(key, int); \
 		__type(value, struct map_value_##_size); \
 		__uint(max_entries, 128); \
-	} array_##_size SEC(".maps");
+	} array_##_size SEC(".maps")
 
-static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch,
-					     unsigned int idx)
+#define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct map_value_percpu_##_size { \
+		struct bin_data_##_size __percpu_kptr * data; \
+	}; \
+	struct { \
+		__uint(type, BPF_MAP_TYPE_ARRAY); \
+		__type(key, int); \
+		__type(value, struct map_value_percpu_##_size); \
+		__uint(max_entries, 128); \
+	} array_percpu_##_size SEC(".maps")
+
+static __always_inline void batch_alloc(struct bpf_map *map, unsigned int batch, unsigned int idx)
 {
 	struct generic_map_value *value;
 	unsigned int i, key;
@@ -65,6 +75,14 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b
 			return;
 		}
 	}
+}
+
+static __always_inline void batch_free(struct bpf_map *map, unsigned int batch, unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old;
+
 	for (i = 0; i < batch; i++) {
 		key = i;
 		value = bpf_map_lookup_elem(map, &key);
@@ -81,8 +99,72 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b
 	}
 }
 
+static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int batch,
+					       unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old, *new;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 1;
+			return;
+		}
+		/* per-cpu allocator may not be able to refill in time */
+		new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL);
+		if (!new)
+			continue;
+
+		old = bpf_kptr_xchg(&value->data, new);
+		if (old) {
+			bpf_percpu_obj_drop(old);
+			err = 2;
+			return;
+		}
+	}
+}
+
+static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int batch,
+					      unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 3;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, NULL);
+		if (!old)
+			continue;
+		bpf_percpu_obj_drop(old);
+	}
+}
+
+#define CALL_BATCH_ALLOC(size, batch, idx) \
+	batch_alloc((struct bpf_map *)(&array_##size), batch, idx)
+
 #define CALL_BATCH_ALLOC_FREE(size, batch, idx) \
-	batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx)
+	do { \
+		batch_alloc((struct bpf_map *)(&array_##size), batch, idx); \
+		batch_free((struct bpf_map *)(&array_##size), batch, idx); \
+	} while (0)
+
+#define CALL_BATCH_PERCPU_ALLOC(size, batch, idx) \
+	batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx)
+
+#define CALL_BATCH_PERCPU_ALLOC_FREE(size, batch, idx) \
+	do { \
+		batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx); \
+		batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \
+	} while (0)
 
 DEFINE_ARRAY_WITH_KPTR(8);
 DEFINE_ARRAY_WITH_KPTR(16);
@@ -97,8 +179,21 @@ DEFINE_ARRAY_WITH_KPTR(1024);
 DEFINE_ARRAY_WITH_KPTR(2048);
 DEFINE_ARRAY_WITH_KPTR(4096);
 
-SEC("fentry/" SYS_PREFIX "sys_nanosleep")
-int test_bpf_mem_alloc_free(void *ctx)
+/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(96);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(1024);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(2048);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(4096);
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_batch_alloc_free(void *ctx)
 {
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
@@ -121,3 +216,76 @@ int test_bpf_mem_alloc_free(void *ctx)
 
 	return 0;
 }
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_free_through_map_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 8-bytes objects in batch to trigger refilling,
+	 * then free these objects through map free.
+	 */
+	CALL_BATCH_ALLOC(8, 128, 0);
+	CALL_BATCH_ALLOC(16, 128, 1);
+	CALL_BATCH_ALLOC(32, 128, 2);
+	CALL_BATCH_ALLOC(64, 128, 3);
+	CALL_BATCH_ALLOC(96, 128, 4);
+	CALL_BATCH_ALLOC(128, 128, 5);
+	CALL_BATCH_ALLOC(192, 128, 6);
+	CALL_BATCH_ALLOC(256, 128, 7);
+	CALL_BATCH_ALLOC(512, 64, 8);
+	CALL_BATCH_ALLOC(1024, 32, 9);
+	CALL_BATCH_ALLOC(2048, 16, 10);
+	CALL_BATCH_ALLOC(4096, 8, 11);
+
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_batch_percpu_alloc_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 16-bytes per-cpu objects in batch to trigger freeing.
+	 */
+	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
+	CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9);
+	CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10);
+	CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11);
+
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_percpu_free_through_map_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	 * then free these object through map free.
+	 */
+	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
+	CALL_BATCH_PERCPU_ALLOC(1024, 32, 9);
+	CALL_BATCH_PERCPU_ALLOC(2048, 16, 10);
+	CALL_BATCH_PERCPU_ALLOC(4096, 8, 11);
+
+	return 0;
+}
-- 
cgit v1.2.3


From ee3d12285471f17239af467eab11f9cb08c18dc4 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Thu, 19 Oct 2023 14:29:44 -0300
Subject: selftests: tc-testing: add test for 'rt' upgrade on hfsc

Add a test to check if inner rt curves are upgraded to sc curves.

Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/tc-testing/tc-tests/qdiscs/hfsc.json | 32 ++++++++++++++++++----
 1 file changed, 26 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
index 0ddb8e1b4369..c98c339424d4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json
@@ -9,8 +9,7 @@
         "plugins": {
             "requires": "nsPlugin"
         },
-        "setup": [
-        ],
+        "setup": [],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc",
         "expExitCode": "0",
         "verifyCmd": "$TC qdisc show dev $DUMMY",
@@ -126,8 +125,7 @@
         "verifyCmd": "$TC qdisc show dev $DUMMY",
         "matchPattern": "qdisc hfsc 1: root refcnt [0-9]+",
         "matchCount": "0",
-        "teardown": [
-        ]
+        "teardown": []
     },
     {
         "id": "8436",
@@ -139,8 +137,7 @@
         "plugins": {
             "requires": "nsPlugin"
         },
-        "setup": [
-        ],
+        "setup": [],
         "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc",
         "expExitCode": "0",
         "verifyCmd": "$TC class show dev $DUMMY",
@@ -149,5 +146,28 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "bef4",
+        "name": "HFSC rt inner class upgrade to sc",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DUMMY handle 1: root hfsc default 1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc rt rate 8"
+        ],
+        "cmdUnderTest": "$TC class add dev $DUMMY parent 1:1 classid 1:2 hfsc rt rate 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC class show dev $DUMMY",
+        "matchPattern": "class hfsc 1:1 parent 1: sc m1 0bit d 0us m2 8bit.*rt m1 0bit d 0us m2 8bit",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 2a7c8d291ffeba69a47d8528987156f625cc05b0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Oct 2023 12:57:39 +0000
Subject: tcp: introduce tcp_clock_ms()

It delivers current TCP time stamp in ms unit, and is used
in place of confusing tcp_time_stamp_raw()

It is the same family than tcp_clock_ns() and tcp_clock_ms().

tcp_time_stamp_raw() will be replaced later for TSval
contexts with a more descriptive name.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h                                     | 5 +++++
 net/ipv4/tcp.c                                        | 6 ++----
 net/ipv4/tcp_minisocks.c                              | 4 ++--
 net/netfilter/nf_synproxy_core.c                      | 2 +-
 tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c | 4 ++--
 5 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9fc6dc4ba9e2..3bdf1141f5a2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -798,6 +798,11 @@ static inline u64 tcp_clock_us(void)
 	return div_u64(tcp_clock_ns(), NSEC_PER_USEC);
 }
 
+static inline u64 tcp_clock_ms(void)
+{
+	return div_u64(tcp_clock_ns(), NSEC_PER_MSEC);
+}
+
 /* This should only be used in contexts where tp->tcp_mstamp is up to date */
 static inline u32 tcp_time_stamp(const struct tcp_sock *tp)
 {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 56a8d936000f..5b034b0356ec 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3817,10 +3817,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_rto = tp->total_rto;
 	info->tcpi_total_rto_recoveries = tp->total_rto_recoveries;
 	info->tcpi_total_rto_time = tp->total_rto_time;
-	if (tp->rto_stamp) {
-		info->tcpi_total_rto_time += tcp_time_stamp_raw() -
-						tp->rto_stamp;
-	}
+	if (tp->rto_stamp)
+		info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp;
 
 	unlock_sock_fast(sk, slow);
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3f87611077ef..a9fdba897a28 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -567,8 +567,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 					       USEC_PER_SEC / TCP_TS_HZ);
 		newtp->total_rto = req->num_timeout;
 		newtp->total_rto_recoveries = 1;
-		newtp->total_rto_time = tcp_time_stamp_raw() -
-						newtp->retrans_stamp;
+		newtp->total_rto_time = tcp_clock_ms() -
+					newtp->retrans_stamp;
 	}
 	newtp->tsoffset = treq->ts_off;
 #ifdef CONFIG_TCP_MD5SIG
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 16915f8eef2b..467671f2d42f 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -153,7 +153,7 @@ void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info,
 				    struct synproxy_options *opts)
 {
 	opts->tsecr = opts->tsval;
-	opts->tsval = tcp_time_stamp_raw() & ~0x3f;
+	opts->tsval = tcp_clock_ms() & ~0x3f;
 
 	if (opts->options & NF_SYNPROXY_OPT_WSCALE) {
 		opts->tsval |= opts->wscale;
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index 07d786329105..e959336c7a73 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -177,7 +177,7 @@ static __always_inline __u32 tcp_ns_to_ts(__u64 ns)
 	return ns / (NSEC_PER_SEC / TCP_TS_HZ);
 }
 
-static __always_inline __u32 tcp_time_stamp_raw(void)
+static __always_inline __u32 tcp_clock_ms(void)
 {
 	return tcp_ns_to_ts(tcp_clock_ns());
 }
@@ -274,7 +274,7 @@ static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
 	if (!loop_ctx.option_timestamp)
 		return false;
 
-	cookie = tcp_time_stamp_raw() & ~TSMASK;
+	cookie = tcp_clock_ms() & ~TSMASK;
 	cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK;
 	if (loop_ctx.option_sack)
 		cookie |= TS_OPT_SACK;
-- 
cgit v1.2.3


From c0119e62b2fe990a512a5ab8fb7c30e28fa619b8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 20 Oct 2023 15:18:27 -0700
Subject: tools: ynl-gen: change spacing around __attribute__

checkpatch gets confused and treats __attribute__ as a function call.
It complains about white space before "(":

WARNING:SPACING: space prohibited between function name and open parenthesis '('
+	struct netdev_queue_get_rsp obj __attribute__ ((aligned (8)));

No spaces wins in the kernel:

  $ git grep 'attribute__((.*aligned(' | wc -l
  480
  $ git grep 'attribute__ ((.*aligned (' | wc -l
  110
  $ git grep 'attribute__ ((.*aligned(' | wc -l
  94
  $ git grep 'attribute__((.*aligned (' | wc -l
  63

So, whatever, change the codegen.

Note that checkpatch also thinks we should use __aligned(),
but this is user space code.

Link: https://lore.kernel.org/all/202310190900.9Dzgkbev-lkp@intel.com/
Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231020221827.3436697-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/generated/devlink-user.h   | 32 ++++++-------
 tools/net/ynl/generated/ethtool-user.h   | 82 ++++++++++++++++----------------
 tools/net/ynl/generated/fou-user.h       |  2 +-
 tools/net/ynl/generated/handshake-user.h |  2 +-
 tools/net/ynl/generated/netdev-user.h    |  4 +-
 tools/net/ynl/lib/ynl.h                  |  4 +-
 tools/net/ynl/ynl-gen-c.py               |  2 +-
 7 files changed, 64 insertions(+), 64 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index 4b686d147613..f5656bc28db4 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -134,7 +134,7 @@ devlink_get(struct ynl_sock *ys, struct devlink_get_req *req);
 /* DEVLINK_CMD_GET - dump */
 struct devlink_get_list {
 	struct devlink_get_list *next;
-	struct devlink_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_get_list_free(struct devlink_get_list *rsp);
@@ -262,7 +262,7 @@ struct devlink_port_get_rsp_dump {
 
 struct devlink_port_get_rsp_list {
 	struct devlink_port_get_rsp_list *next;
-	struct devlink_port_get_rsp_dump obj __attribute__ ((aligned (8)));
+	struct devlink_port_get_rsp_dump obj __attribute__((aligned(8)));
 };
 
 void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp);
@@ -379,7 +379,7 @@ devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
 
 struct devlink_sb_get_list {
 	struct devlink_sb_get_list *next;
-	struct devlink_sb_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_sb_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
@@ -509,7 +509,7 @@ devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *r
 
 struct devlink_sb_pool_get_list {
 	struct devlink_sb_pool_get_list *next;
-	struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_sb_pool_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
@@ -654,7 +654,7 @@ devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_r
 
 struct devlink_sb_port_pool_get_list {
 	struct devlink_sb_port_pool_get_list *next;
-	struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_sb_port_pool_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -811,7 +811,7 @@ devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind
 
 struct devlink_sb_tc_pool_bind_get_list {
 	struct devlink_sb_tc_pool_bind_get_list *next;
-	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -933,7 +933,7 @@ devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
 
 struct devlink_param_get_list {
 	struct devlink_param_get_list *next;
-	struct devlink_param_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_param_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
@@ -1065,7 +1065,7 @@ devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req
 
 struct devlink_region_get_list {
 	struct devlink_region_get_list *next;
-	struct devlink_region_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_region_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
@@ -1144,7 +1144,7 @@ devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
 /* DEVLINK_CMD_INFO_GET - dump */
 struct devlink_info_get_list {
 	struct devlink_info_get_list *next;
-	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_info_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
@@ -1288,7 +1288,7 @@ devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_report
 
 struct devlink_health_reporter_get_list {
 	struct devlink_health_reporter_get_list *next;
-	struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_health_reporter_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -1410,7 +1410,7 @@ devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req,
 
 struct devlink_trap_get_list {
 	struct devlink_trap_get_list *next;
-	struct devlink_trap_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_trap_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp);
@@ -1534,7 +1534,7 @@ devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_d
 
 struct devlink_trap_group_get_list {
 	struct devlink_trap_group_get_list *next;
-	struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_trap_group_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp);
@@ -1657,7 +1657,7 @@ devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_r
 
 struct devlink_trap_policer_get_list {
 	struct devlink_trap_policer_get_list *next;
-	struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_trap_policer_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -1790,7 +1790,7 @@ devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req,
 
 struct devlink_rate_get_list {
 	struct devlink_rate_get_list *next;
-	struct devlink_rate_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_rate_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp);
@@ -1910,7 +1910,7 @@ devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump
 
 struct devlink_linecard_get_list {
 	struct devlink_linecard_get_list *next;
-	struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_linecard_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp);
@@ -1981,7 +1981,7 @@ devlink_selftests_get(struct ynl_sock *ys,
 /* DEVLINK_CMD_SELFTESTS_GET - dump */
 struct devlink_selftests_get_list {
 	struct devlink_selftests_get_list *next;
-	struct devlink_selftests_get_rsp obj __attribute__ ((aligned (8)));
+	struct devlink_selftests_get_rsp obj __attribute__((aligned(8)));
 };
 
 void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp);
diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h
index ddc1a5209992..ca0ec5fd7798 100644
--- a/tools/net/ynl/generated/ethtool-user.h
+++ b/tools/net/ynl/generated/ethtool-user.h
@@ -347,7 +347,7 @@ ethtool_strset_get_req_dump_set_counts_only(struct ethtool_strset_get_req_dump *
 
 struct ethtool_strset_get_list {
 	struct ethtool_strset_get_list *next;
-	struct ethtool_strset_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_strset_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp);
@@ -472,7 +472,7 @@ ethtool_linkinfo_get_req_dump_set_header_flags(struct ethtool_linkinfo_get_req_d
 
 struct ethtool_linkinfo_get_list {
 	struct ethtool_linkinfo_get_list *next;
-	struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp);
@@ -487,7 +487,7 @@ struct ethtool_linkinfo_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_linkinfo_get_ntf *ntf);
-	struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp);
@@ -712,7 +712,7 @@ ethtool_linkmodes_get_req_dump_set_header_flags(struct ethtool_linkmodes_get_req
 
 struct ethtool_linkmodes_get_list {
 	struct ethtool_linkmodes_get_list *next;
-	struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp);
@@ -727,7 +727,7 @@ struct ethtool_linkmodes_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_linkmodes_get_ntf *ntf);
-	struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp);
@@ -1014,7 +1014,7 @@ ethtool_linkstate_get_req_dump_set_header_flags(struct ethtool_linkstate_get_req
 
 struct ethtool_linkstate_get_list {
 	struct ethtool_linkstate_get_list *next;
-	struct ethtool_linkstate_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_linkstate_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp);
@@ -1129,7 +1129,7 @@ ethtool_debug_get_req_dump_set_header_flags(struct ethtool_debug_get_req_dump *r
 
 struct ethtool_debug_get_list {
 	struct ethtool_debug_get_list *next;
-	struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_debug_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp);
@@ -1144,7 +1144,7 @@ struct ethtool_debug_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_debug_get_ntf *ntf);
-	struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_debug_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp);
@@ -1330,7 +1330,7 @@ ethtool_wol_get_req_dump_set_header_flags(struct ethtool_wol_get_req_dump *req,
 
 struct ethtool_wol_get_list {
 	struct ethtool_wol_get_list *next;
-	struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_wol_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp);
@@ -1344,7 +1344,7 @@ struct ethtool_wol_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_wol_get_ntf *ntf);
-	struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_wol_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp);
@@ -1546,7 +1546,7 @@ ethtool_features_get_req_dump_set_header_flags(struct ethtool_features_get_req_d
 
 struct ethtool_features_get_list {
 	struct ethtool_features_get_list *next;
-	struct ethtool_features_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_features_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp);
@@ -1561,7 +1561,7 @@ struct ethtool_features_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_features_get_ntf *ntf);
-	struct ethtool_features_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_features_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp);
@@ -1843,7 +1843,7 @@ ethtool_privflags_get_req_dump_set_header_flags(struct ethtool_privflags_get_req
 
 struct ethtool_privflags_get_list {
 	struct ethtool_privflags_get_list *next;
-	struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_privflags_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp);
@@ -1858,7 +1858,7 @@ struct ethtool_privflags_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_privflags_get_ntf *ntf);
-	struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_privflags_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp);
@@ -2072,7 +2072,7 @@ ethtool_rings_get_req_dump_set_header_flags(struct ethtool_rings_get_req_dump *r
 
 struct ethtool_rings_get_list {
 	struct ethtool_rings_get_list *next;
-	struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_rings_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp);
@@ -2087,7 +2087,7 @@ struct ethtool_rings_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_rings_get_ntf *ntf);
-	struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_rings_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp);
@@ -2395,7 +2395,7 @@ ethtool_channels_get_req_dump_set_header_flags(struct ethtool_channels_get_req_d
 
 struct ethtool_channels_get_list {
 	struct ethtool_channels_get_list *next;
-	struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_channels_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp);
@@ -2410,7 +2410,7 @@ struct ethtool_channels_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_channels_get_ntf *ntf);
-	struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_channels_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp);
@@ -2697,7 +2697,7 @@ ethtool_coalesce_get_req_dump_set_header_flags(struct ethtool_coalesce_get_req_d
 
 struct ethtool_coalesce_get_list {
 	struct ethtool_coalesce_get_list *next;
-	struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp);
@@ -2712,7 +2712,7 @@ struct ethtool_coalesce_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_coalesce_get_ntf *ntf);
-	struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp);
@@ -3124,7 +3124,7 @@ ethtool_pause_get_req_dump_set_header_flags(struct ethtool_pause_get_req_dump *r
 
 struct ethtool_pause_get_list {
 	struct ethtool_pause_get_list *next;
-	struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_pause_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp);
@@ -3139,7 +3139,7 @@ struct ethtool_pause_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_pause_get_ntf *ntf);
-	struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_pause_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp);
@@ -3360,7 +3360,7 @@ ethtool_eee_get_req_dump_set_header_flags(struct ethtool_eee_get_req_dump *req,
 
 struct ethtool_eee_get_list {
 	struct ethtool_eee_get_list *next;
-	struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_eee_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp);
@@ -3374,7 +3374,7 @@ struct ethtool_eee_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_eee_get_ntf *ntf);
-	struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_eee_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp);
@@ -3623,7 +3623,7 @@ ethtool_tsinfo_get_req_dump_set_header_flags(struct ethtool_tsinfo_get_req_dump
 
 struct ethtool_tsinfo_get_list {
 	struct ethtool_tsinfo_get_list *next;
-	struct ethtool_tsinfo_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_tsinfo_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp);
@@ -3842,7 +3842,7 @@ ethtool_tunnel_info_get_req_dump_set_header_flags(struct ethtool_tunnel_info_get
 
 struct ethtool_tunnel_info_get_list {
 	struct ethtool_tunnel_info_get_list *next;
-	struct ethtool_tunnel_info_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_tunnel_info_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -3964,7 +3964,7 @@ ethtool_fec_get_req_dump_set_header_flags(struct ethtool_fec_get_req_dump *req,
 
 struct ethtool_fec_get_list {
 	struct ethtool_fec_get_list *next;
-	struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_fec_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp);
@@ -3978,7 +3978,7 @@ struct ethtool_fec_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_fec_get_ntf *ntf);
-	struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_fec_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp);
@@ -4221,7 +4221,7 @@ ethtool_module_eeprom_get_req_dump_set_header_flags(struct ethtool_module_eeprom
 
 struct ethtool_module_eeprom_get_list {
 	struct ethtool_module_eeprom_get_list *next;
-	struct ethtool_module_eeprom_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_module_eeprom_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -4340,7 +4340,7 @@ ethtool_phc_vclocks_get_req_dump_set_header_flags(struct ethtool_phc_vclocks_get
 
 struct ethtool_phc_vclocks_get_list {
 	struct ethtool_phc_vclocks_get_list *next;
-	struct ethtool_phc_vclocks_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_phc_vclocks_get_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -4458,7 +4458,7 @@ ethtool_module_get_req_dump_set_header_flags(struct ethtool_module_get_req_dump
 
 struct ethtool_module_get_list {
 	struct ethtool_module_get_list *next;
-	struct ethtool_module_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_module_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp);
@@ -4473,7 +4473,7 @@ struct ethtool_module_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_module_get_ntf *ntf);
-	struct ethtool_module_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_module_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp);
@@ -4654,7 +4654,7 @@ ethtool_pse_get_req_dump_set_header_flags(struct ethtool_pse_get_req_dump *req,
 
 struct ethtool_pse_get_list {
 	struct ethtool_pse_get_list *next;
-	struct ethtool_pse_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_pse_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp);
@@ -4849,7 +4849,7 @@ ethtool_rss_get_req_dump_set_header_flags(struct ethtool_rss_get_req_dump *req,
 
 struct ethtool_rss_get_list {
 	struct ethtool_rss_get_list *next;
-	struct ethtool_rss_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_rss_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp);
@@ -4979,7 +4979,7 @@ ethtool_plca_get_cfg_req_dump_set_header_flags(struct ethtool_plca_get_cfg_req_d
 
 struct ethtool_plca_get_cfg_list {
 	struct ethtool_plca_get_cfg_list *next;
-	struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp);
@@ -4994,7 +4994,7 @@ struct ethtool_plca_get_cfg_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_plca_get_cfg_ntf *ntf);
-	struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp);
@@ -5244,7 +5244,7 @@ ethtool_plca_get_status_req_dump_set_header_flags(struct ethtool_plca_get_status
 
 struct ethtool_plca_get_status_list {
 	struct ethtool_plca_get_status_list *next;
-	struct ethtool_plca_get_status_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_plca_get_status_rsp obj __attribute__((aligned(8)));
 };
 
 void
@@ -5376,7 +5376,7 @@ ethtool_mm_get_req_dump_set_header_flags(struct ethtool_mm_get_req_dump *req,
 
 struct ethtool_mm_get_list {
 	struct ethtool_mm_get_list *next;
-	struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_mm_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp);
@@ -5390,7 +5390,7 @@ struct ethtool_mm_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_mm_get_ntf *ntf);
-	struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_mm_get_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp);
@@ -5504,7 +5504,7 @@ struct ethtool_cable_test_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_cable_test_ntf *ntf);
-	struct ethtool_cable_test_ntf_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_cable_test_ntf_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp);
@@ -5527,7 +5527,7 @@ struct ethtool_cable_test_tdr_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ethtool_cable_test_tdr_ntf *ntf);
-	struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__ ((aligned (8)));
+	struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__((aligned(8)));
 };
 
 void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp);
diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h
index a8f860892540..fd566716ddd6 100644
--- a/tools/net/ynl/generated/fou-user.h
+++ b/tools/net/ynl/generated/fou-user.h
@@ -333,7 +333,7 @@ struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req);
 /* FOU_CMD_GET - dump */
 struct fou_get_list {
 	struct fou_get_list *next;
-	struct fou_get_rsp obj __attribute__ ((aligned (8)));
+	struct fou_get_rsp obj __attribute__((aligned(8)));
 };
 
 void fou_get_list_free(struct fou_get_list *rsp);
diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h
index 2b34acc608de..bce537d8b8cc 100644
--- a/tools/net/ynl/generated/handshake-user.h
+++ b/tools/net/ynl/generated/handshake-user.h
@@ -90,7 +90,7 @@ struct handshake_accept_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct handshake_accept_ntf *ntf);
-	struct handshake_accept_rsp obj __attribute__ ((aligned (8)));
+	struct handshake_accept_rsp obj __attribute__((aligned(8)));
 };
 
 void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp);
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index b4351ff34595..4fafac879df3 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -69,7 +69,7 @@ netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req);
 /* NETDEV_CMD_DEV_GET - dump */
 struct netdev_dev_get_list {
 	struct netdev_dev_get_list *next;
-	struct netdev_dev_get_rsp obj __attribute__ ((aligned (8)));
+	struct netdev_dev_get_rsp obj __attribute__((aligned(8)));
 };
 
 void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp);
@@ -82,7 +82,7 @@ struct netdev_dev_get_ntf {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct netdev_dev_get_ntf *ntf);
-	struct netdev_dev_get_rsp obj __attribute__ ((aligned (8)));
+	struct netdev_dev_get_rsp obj __attribute__((aligned(8)));
 };
 
 void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp);
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index 87b4dad832f0..cfefacb839f4 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -157,7 +157,7 @@ struct ynl_parse_arg {
 
 struct ynl_dump_list_type {
 	struct ynl_dump_list_type *next;
-	unsigned char data[] __attribute__ ((aligned (8)));
+	unsigned char data[] __attribute__((aligned(8)));
 };
 extern struct ynl_dump_list_type *YNL_LIST_END;
 
@@ -187,7 +187,7 @@ struct ynl_ntf_base_type {
 	__u8 cmd;
 	struct ynl_ntf_base_type *next;
 	void (*free)(struct ynl_ntf_base_type *ntf);
-	unsigned char data[] __attribute__ ((aligned (8)));
+	unsigned char data[] __attribute__((aligned(8)));
 };
 
 extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE];
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index a9e8898c9386..1d8b56f071b9 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1872,7 +1872,7 @@ def print_wrapped_type(ri):
         ri.cw.p('__u8 cmd;')
         ri.cw.p('struct ynl_ntf_base_type *next;')
         ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);")
-    ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));")
+    ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__((aligned(8)));")
     ri.cw.block_end(line=';')
     ri.cw.nl()
     print_free_prototype(ri, 'reply')
-- 
cgit v1.2.3


From 4e2846fd6684227c8f8129ec184fbf090279216d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 21 Oct 2023 13:27:03 +0200
Subject: tools: ynl-gen: introduce support for bitfield32 attribute type

Introduce support for attribute type bitfield32.
Note that since the generated code works with struct nla_bitfield32,
the generator adds netlink.h to the list of includes for userspace
headers in case any bitfield32 is present.

Note that this is added only to genetlink-legacy scheme as requested
by Jakub Kicinski.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20231021112711.660606-3-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-legacy.yaml        |  2 +-
 .../userspace-api/netlink/genetlink-legacy.rst     |  2 +-
 tools/net/ynl/lib/ynl.c                            |  6 ++++
 tools/net/ynl/lib/ynl.h                            |  1 +
 tools/net/ynl/lib/ynl.py                           | 13 ++++++--
 tools/net/ynl/ynl-gen-c.py                         | 39 ++++++++++++++++++++++
 6 files changed, 58 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 923de0ff1a9e..565bf615b501 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -192,7 +192,7 @@ properties:
                 type: string
               type: &attr-type
                 description: The netlink attribute type
-                enum: [ unused, pad, flag, binary,
+                enum: [ unused, pad, flag, binary, bitfield32,
                         uint, sint, u8, u16, u32, u64, s32, s64,
                         string, nest, array-nest, nest-type-value ]
               doc:
diff --git a/Documentation/userspace-api/netlink/genetlink-legacy.rst b/Documentation/userspace-api/netlink/genetlink-legacy.rst
index 0b3febd57ff5..70a77387f6c4 100644
--- a/Documentation/userspace-api/netlink/genetlink-legacy.rst
+++ b/Documentation/userspace-api/netlink/genetlink-legacy.rst
@@ -182,7 +182,7 @@ members
 
  - ``name`` - The attribute name of the struct member
  - ``type`` - One of the scalar types ``u8``, ``u16``, ``u32``, ``u64``, ``s8``,
-   ``s16``, ``s32``, ``s64``, ``string`` or ``binary``.
+   ``s16``, ``s32``, ``s64``, ``string``, ``binary`` or ``bitfield32``.
  - ``byte-order`` - ``big-endian`` or ``little-endian``
  - ``doc``, ``enum``, ``enum-as-flags``, ``display-hint`` - Same as for
    :ref:`attribute definitions <attribute_properties>`
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 350ddc247450..830d25097009 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -379,6 +379,12 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
 		     "Invalid attribute (string %s)", policy->name);
 		return -1;
+	case YNL_PT_BITFIELD32:
+		if (len == sizeof(struct nla_bitfield32))
+			break;
+		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
+		     "Invalid attribute (bitfield32 %s)", policy->name);
+		return -1;
 	default:
 		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
 		     "Invalid attribute (unknown %s)", policy->name);
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index 87b4dad832f0..c883e4747cfa 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -135,6 +135,7 @@ enum ynl_policy_type {
 	YNL_PT_U64,
 	YNL_PT_UINT,
 	YNL_PT_NUL_STR,
+	YNL_PT_BITFIELD32,
 };
 
 struct ynl_policy_attr {
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 3b36553a66cc..b1da4aea9336 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -478,6 +478,8 @@ class YnlFamily(SpecFamily):
         elif attr['type'] in NlAttr.type_formats:
             format = NlAttr.get_format(attr['type'], attr.byte_order)
             attr_payload = format.pack(int(value))
+        elif attr['type'] in "bitfield32":
+            attr_payload = struct.pack("II", int(value["value"]), int(value["selector"]))
         else:
             raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}')
 
@@ -545,14 +547,19 @@ class YnlFamily(SpecFamily):
                 decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order)
             elif attr_spec["type"] in NlAttr.type_formats:
                 decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order)
+                if 'enum' in attr_spec:
+                    decoded = self._decode_enum(decoded, attr_spec)
             elif attr_spec["type"] == 'array-nest':
                 decoded = self._decode_array_nest(attr, attr_spec)
+            elif attr_spec["type"] == 'bitfield32':
+                value, selector = struct.unpack("II", attr.raw)
+                if 'enum' in attr_spec:
+                    value = self._decode_enum(value, attr_spec)
+                    selector = self._decode_enum(selector, attr_spec)
+                decoded = {"value": value, "selector": selector}
             else:
                 raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}')
 
-            if 'enum' in attr_spec:
-                decoded = self._decode_enum(decoded, attr_spec)
-
             if not attr_spec.is_multi:
                 rsp[attr_spec['name']] = decoded
             elif attr_spec.name in rsp:
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index a9e8898c9386..7d6c318397be 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -488,6 +488,31 @@ class TypeBinary(Type):
                 f'memcpy({member}, {self.c_name}, {presence}_len);']
 
 
+class TypeBitfield32(Type):
+    def _complex_member_type(self, ri):
+        return "struct nla_bitfield32"
+
+    def _attr_typol(self):
+        return f'.type = YNL_PT_BITFIELD32, '
+
+    def _attr_policy(self, policy):
+        if not 'enum' in self.attr:
+            raise Exception('Enum required for bitfield32 attr')
+        enum = self.family.consts[self.attr['enum']]
+        mask = enum.get_mask(as_flags=True)
+        return f"NLA_POLICY_BITFIELD32({mask})"
+
+    def attr_put(self, ri, var):
+        line = f"mnl_attr_put(nlh, {self.enum_name}, sizeof(struct nla_bitfield32), &{var}->{self.c_name})"
+        self._attr_put_line(ri, var, line)
+
+    def _attr_get(self, ri, var):
+        return f"memcpy(&{var}->{self.c_name}, mnl_attr_get_payload(attr), sizeof(struct nla_bitfield32));", None, None
+
+    def _setter_lines(self, ri, member, presence):
+        return [f"memcpy(&{member}, {self.c_name}, sizeof(struct nla_bitfield32));"]
+
+
 class TypeNest(Type):
     def _complex_member_type(self, ri):
         return self.nested_struct_type
@@ -786,6 +811,8 @@ class AttrSet(SpecAttrSet):
             t = TypeString(self.family, self, elem, value)
         elif elem['type'] == 'binary':
             t = TypeBinary(self.family, self, elem, value)
+        elif elem['type'] == 'bitfield32':
+            t = TypeBitfield32(self.family, self, elem, value)
         elif elem['type'] == 'nest':
             t = TypeNest(self.family, self, elem, value)
         elif elem['type'] == 'array-nest':
@@ -2414,6 +2441,16 @@ def render_user_family(family, cw, prototype):
     cw.block_end(line=';')
 
 
+def family_contains_bitfield32(family):
+    for _, attr_set in family.attr_sets.items():
+        if attr_set.subset_of:
+            continue
+        for _, attr in attr_set.items():
+            if attr.type == "bitfield32":
+                return True
+    return False
+
+
 def find_kernel_root(full_path):
     sub_path = ''
     while True:
@@ -2499,6 +2536,8 @@ def main():
         cw.p('#include <string.h>')
         if args.header:
             cw.p('#include <linux/types.h>')
+            if family_contains_bitfield32(parsed):
+                cw.p('#include <linux/netlink.h>')
         else:
             cw.p(f'#include "{parsed.name}-user.h"')
             cw.p('#include "ynl.h"')
-- 
cgit v1.2.3


From 2260d39cd01aff3b5791db25810e40fe03ae71bf Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 21 Oct 2023 13:27:04 +0200
Subject: tools: ynl-gen: render rsp_parse() helpers if cmd has only dump op

Due to the check in RenderInfo class constructor, type_consistent
flag is set to False to avoid rendering the same response parsing
helper for do and dump ops. However, in case there is no do, the helper
needs to be rendered for dump op. So split check to achieve that.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20231021112711.660606-4-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 7d6c318397be..ed35a307c960 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1112,10 +1112,13 @@ class RenderInfo:
 
         # 'do' and 'dump' response parsing is identical
         self.type_consistent = True
-        if op_mode != 'do' and 'dump' in op and 'do' in op:
-            if ('reply' in op['do']) != ('reply' in op["dump"]):
-                self.type_consistent = False
-            elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]:
+        if op_mode != 'do' and 'dump' in op:
+            if 'do' in op:
+                if ('reply' in op['do']) != ('reply' in op["dump"]):
+                    self.type_consistent = False
+                elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]:
+                    self.type_consistent = False
+            else:
                 self.type_consistent = False
 
         self.attr_set = attr_set
-- 
cgit v1.2.3


From c48066b0cc2c02d2193a710c823e7d6f41d2ea85 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 21 Oct 2023 13:27:05 +0200
Subject: netlink: specs: devlink: remove reload-action from devlink-get cmd
 reply

devlink-get command does not contain reload-action attr in reply.
Remove it.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20231021112711.660606-5-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml | 1 -
 tools/net/ynl/generated/devlink-user.c   | 5 -----
 tools/net/ynl/generated/devlink-user.h   | 2 --
 3 files changed, 8 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index dec130d2507c..94a1ca10f5fc 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -263,7 +263,6 @@ operations:
             - bus-name
             - dev-name
             - reload-failed
-            - reload-action
             - dev-stats
       dump:
         reply: *get-reply
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 2cb2518500cb..a002f71d6068 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -475,11 +475,6 @@ int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.reload_failed = 1;
 			dst->reload_failed = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RELOAD_ACTION) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_action = 1;
-			dst->reload_action = mnl_attr_get_u8(attr);
 		} else if (type == DEVLINK_ATTR_DEV_STATS) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index 4b686d147613..d00bcf79fa0d 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -112,14 +112,12 @@ struct devlink_get_rsp {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
 		__u32 reload_failed:1;
-		__u32 reload_action:1;
 		__u32 dev_stats:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
 	__u8 reload_failed;
-	__u8 reload_action;
 	struct devlink_dl_dev_stats dev_stats;
 };
 
-- 
cgit v1.2.3


From f2f9dd164db079161a834c8698c68a94a50b4168 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 21 Oct 2023 13:27:09 +0200
Subject: netlink: specs: devlink: add the remaining command to generate
 complete split_ops

Currently, some of the commands are not described in devlink yaml file
and are manually filled in net/devlink/netlink.c in small_ops. To make
all part of split_ops, add definitions of the rest of the commands
alongside with needed attributes and enums.

Note that this focuses on the kernel side. The requests are fully
described in order to generate split_op alongside with policies.
Follow-up will describe the replies in order to make the userspace
helpers complete.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20231021112711.660606-9-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml | 1530 ++++++++-
 net/devlink/netlink_gen.c                |  757 ++++-
 net/devlink/netlink_gen.h                |   64 +-
 tools/net/ynl/generated/devlink-user.c   | 5062 ++++++++++++++++++++++++++----
 tools/net/ynl/generated/devlink-user.h   | 4213 ++++++++++++++++++++++---
 5 files changed, 10495 insertions(+), 1131 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index dd035a8f5eb4..c6ba4889575a 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -15,6 +15,161 @@ definitions:
         name: ingress
       -
         name: egress
+  -
+    type: enum
+    name: port-type
+    entries:
+      -
+        name: notset
+      -
+        name: auto
+      -
+        name: eth
+      -
+        name: ib
+  -
+    type: enum
+    name: port-flavour
+    entries:
+      -
+        name: physical
+      -
+        name: cpu
+      -
+        name: dsa
+      -
+        name: pci_pf
+      -
+        name: pci_vf
+      -
+        name: virtual
+      -
+        name: unused
+      -
+        name: pci_sf
+  -
+    type: enum
+    name: port-fn-state
+    entries:
+      -
+        name: inactive
+      -
+        name: active
+  -
+    type: enum
+    name: port-fn-opstate
+    entries:
+      -
+        name: detached
+      -
+        name: attached
+  -
+    type: enum
+    name: port-fn-attr-cap
+    entries:
+      -
+        name: roce-bit
+      -
+        name: migratable-bit
+  -
+    type: enum
+    name: sb-threshold-type
+    entries:
+      -
+        name: static
+      -
+        name: dynamic
+  -
+    type: enum
+    name: eswitch-mode
+    entries:
+      -
+        name: legacy
+      -
+        name: switchdev
+  -
+    type: enum
+    name: eswitch-inline-mode
+    entries:
+      -
+        name: none
+      -
+        name: link
+      -
+        name: network
+      -
+        name: transport
+  -
+    type: enum
+    name: eswitch-encap-mode
+    entries:
+      -
+        name: none
+      -
+        name: basic
+  -
+    type: enum
+    name: dpipe-match-type
+    entries:
+      -
+        name: field-exact
+  -
+    type: enum
+    name: dpipe-action-type
+    entries:
+      -
+        name: field-modify
+  -
+    type: enum
+    name: dpipe-field-mapping-type
+    entries:
+      -
+        name: none
+      -
+        name: ifindex
+  -
+    type: enum
+    name: resource-unit
+    entries:
+      -
+        name: entry
+  -
+    type: enum
+    name: reload-action
+    entries:
+      -
+        name: driver-reinit
+        value: 1
+      -
+        name: fw-activate
+  -
+    type: enum
+    name: param-cmode
+    entries:
+      -
+        name: runtime
+      -
+        name: driverinit
+      -
+        name: permanent
+  -
+    type: enum
+    name: flash-overwrite
+    entries:
+      -
+        name: settings-bit
+      -
+        name: identifiers-bit
+  -
+    type: enum
+    name: trap-action
+    entries:
+      -
+        name: drop
+      -
+        name: trap
+      -
+        name: mirror
 
 attribute-sets:
   -
@@ -31,6 +186,17 @@ attribute-sets:
       -
         name: port-index
         type: u32
+      -
+        name: port-type
+        type: u16
+        enum: port-type
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: port-split-count
+        type: u32
+        value: 9
 
       # TODO: fill in the attributes in between
 
@@ -45,18 +211,224 @@ attribute-sets:
         name: sb-pool-index
         type: u16
         value: 17
-
       -
         name: sb-pool-type
         type: u8
         enum: sb-pool-type
+      -
+        name: sb-pool-size
+        type: u32
+      -
+        name: sb-pool-threshold-type
+        type: u8
+        enum: sb-threshold-type
+      -
+        name: sb-threshold
+        type: u32
+      -
+        name: sb-tc-index
+        type: u16
+        value: 22
 
       # TODO: fill in the attributes in between
 
       -
-        name: sb-tc-index
+        name: eswitch-mode
         type: u16
-        value: 22
+        value: 25
+        enum: eswitch-mode
+
+      -
+        name: eswitch-inline-mode
+        type: u16
+        enum: eswitch-inline-mode
+      -
+        name: dpipe-tables
+        type: nest
+        nested-attributes: dl-dpipe-tables
+      -
+        name: dpipe-table
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-table
+      -
+        name: dpipe-table-name
+        type: string
+      -
+        name: dpipe-table-size
+        type: u64
+      -
+        name: dpipe-table-matches
+        type: nest
+        nested-attributes: dl-dpipe-table-matches
+      -
+        name: dpipe-table-actions
+        type: nest
+        nested-attributes: dl-dpipe-table-actions
+      -
+        name: dpipe-table-counters-enabled
+        type: u8
+      -
+        name: dpipe-entries
+        type: nest
+        nested-attributes: dl-dpipe-entries
+      -
+        name: dpipe-entry
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-entry
+      -
+        name: dpipe-entry-index
+        type: u64
+      -
+        name: dpipe-entry-match-values
+        type: nest
+        nested-attributes: dl-dpipe-entry-match-values
+      -
+        name: dpipe-entry-action-values
+        type: nest
+        nested-attributes: dl-dpipe-entry-action-values
+      -
+        name: dpipe-entry-counter
+        type: u64
+      -
+        name: dpipe-match
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-match
+      -
+        name: dpipe-match-value
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-match-value
+      -
+        name: dpipe-match-type
+        type: u32
+        enum: dpipe-match-type
+      -
+        name: dpipe-action
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-action
+      -
+        name: dpipe-action-value
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-action-value
+      -
+        name: dpipe-action-type
+        type: u32
+        enum: dpipe-action-type
+      -
+        name: dpipe-value
+        type: binary
+      -
+        name: dpipe-value-mask
+        type: binary
+      -
+        name: dpipe-value-mapping
+        type: u32
+      -
+        name: dpipe-headers
+        type: nest
+        nested-attributes: dl-dpipe-headers
+      -
+        name: dpipe-header
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-header
+      -
+        name: dpipe-header-name
+        type: string
+      -
+        name: dpipe-header-id
+        type: u32
+      -
+        name: dpipe-header-fields
+        type: nest
+        nested-attributes: dl-dpipe-header-fields
+      -
+        name: dpipe-header-global
+        type: u8
+      -
+        name: dpipe-header-index
+        type: u32
+      -
+        name: dpipe-field
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-dpipe-field
+      -
+        name: dpipe-field-name
+        type: string
+      -
+        name: dpipe-field-id
+        type: u32
+      -
+        name: dpipe-field-bitwidth
+        type: u32
+      -
+        name: dpipe-field-mapping-type
+        type: u32
+        enum: dpipe-field-mapping-type
+      -
+        name: pad
+        type: pad
+      -
+        name: eswitch-encap-mode
+        type: u8
+        value: 62
+        enum: eswitch-encap-mode
+      -
+        name: resource-list
+        type: nest
+        nested-attributes: dl-resource-list
+      -
+        name: resource
+        type: nest
+        multi-attr: true
+        nested-attributes: dl-resource
+      -
+        name: resource-name
+        type: string
+      -
+        name: resource-id
+        type: u64
+      -
+        name: resource-size
+        type: u64
+      -
+        name: resource-size-new
+        type: u64
+      -
+        name: resource-size-valid
+        type: u8
+      -
+        name: resource-size-min
+        type: u64
+      -
+        name: resource-size-max
+        type: u64
+      -
+        name: resource-size-gran
+        type: u64
+      -
+        name: resource-unit
+        type: u8
+        enum: resource-unit
+      -
+        name: resource-occ
+        type: u64
+      -
+        name: dpipe-table-resource-id
+        type: u64
+      -
+        name: dpipe-table-resource-units
+        type: u64
+      -
+        name: port-flavour
+        type: u16
+        enum: port-flavour
 
       # TODO: fill in the attributes in between
 
@@ -67,17 +439,41 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: param-type
+        type: u8
+        value: 83
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: param-value-cmode
+        type: u8
+        enum: param-cmode
+        value: 87
       -
         name: region-name
         type: string
-        value: 88
 
       # TODO: fill in the attributes in between
 
+      -
+        name: region-snapshot-id
+        type: u32
+        value: 92
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: region-chunk-addr
+        type: u64
+        value: 96
+      -
+        name: region-chunk-len
+        type: u64
       -
         name: info-driver-name
         type: string
-        value: 98
       -
         name: info-serial-number
         type: string
@@ -105,6 +501,29 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: fmsg
+        type: nest
+        nested-attributes: dl-fmsg
+        value: 106
+      -
+        name: fmsg-obj-nest-start
+        type: flag
+      -
+        name: fmsg-pair-nest-start
+        type: flag
+      -
+        name: fmsg-arr-nest-start
+        type: flag
+      -
+        name: fmsg-nest-end
+        type: flag
+      -
+        name: fmsg-obj-name
+        type: string
+
+      # TODO: fill in the attributes in between
+
       -
         name: health-reporter-name
         type: string
@@ -112,10 +531,37 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: health-reporter-graceful-period
+        type: u64
+        value: 120
+      -
+        name: health-reporter-auto-recover
+        type: u8
+      -
+        name: flash-update-file-name
+        type: string
+      -
+        name: flash-update-component
+        type: string
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: port-pci-pf-number
+        type: u16
+        value: 127
+
+      # TODO: fill in the attributes in between
+
       -
         name: trap-name
         type: string
         value: 130
+      -
+        name: trap-action
+        type: u8
+        enum: trap-action
 
       # TODO: fill in the attributes in between
 
@@ -131,23 +577,68 @@ attribute-sets:
       # TODO: fill in the attributes in between
 
       -
-        name: trap-policer-id
+        name: netns-fd
+        type: u32
+        value: 138
+      -
+        name: netns-pid
+        type: u32
+      -
+        name: netns-id
         type: u32
-        value: 142
 
       # TODO: fill in the attributes in between
 
       -
-        name: reload-action
+        name: health-reporter-auto-dump
         type: u8
-        value: 153
+        value: 141
+      -
+        name: trap-policer-id
+        type: u32
+      -
+        name: trap-policer-rate
+        type: u64
+      -
+        name: trap-policer-burst
+        type: u64
+      -
+        name: port-function
+        type: nest
+        nested-attributes: dl-port-function
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: port-controller-number
+        type: u32
+        value: 150
 
       # TODO: fill in the attributes in between
 
+      -
+        name: flash-update-overwrite-mask
+        type: bitfield32
+        enum: flash-overwrite
+        enum-as-flags: True
+        value: 152
+      -
+        name: reload-action
+        type: u8
+        enum: reload-action
+      -
+        name: reload-actions-performed
+        type: bitfield32
+        enum: reload-action
+        enum-as-flags: True
+      -
+        name: reload-limits
+        type: bitfield32
+        enum: reload-action
+        enum-as-flags: True
       -
         name: dev-stats
         type: nest
-        value: 156
         nested-attributes: dl-dev-stats
       -
         name: reload-stats
@@ -181,10 +672,26 @@ attribute-sets:
 
       # TODO: fill in the attributes in between
 
+      -
+        name: port-pci-sf-number
+        type: u32
+        value: 164
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: rate-tx-share
+        type: u64
+        value: 166
+      -
+        name: rate-tx-max
+        type: u64
       -
         name: rate-node-name
         type: string
-        value: 168
+      -
+        name: rate-parent-node-name
+        type: string
 
       # TODO: fill in the attributes in between
 
@@ -193,6 +700,30 @@ attribute-sets:
         type: u32
         value: 171
 
+      # TODO: fill in the attributes in between
+
+      -
+        name: linecard-type
+        type: string
+        value: 173
+
+      # TODO: fill in the attributes in between
+
+      -
+        name: selftests
+        type: nest
+        value: 176
+        nested-attributes: dl-selftest-id
+      -
+        name: rate-tx-priority
+        type: u32
+      -
+        name: rate-tx-weight
+        type: u32
+      -
+        name: region-direct
+        type: flag
+
   -
     name: dl-dev-stats
     subset-of: devlink
@@ -222,21 +753,276 @@ attribute-sets:
       -
         name: reload-stats-entry
   -
-    name: dl-reload-stats-entry
+    name: dl-reload-stats-entry
+    subset-of: devlink
+    attributes:
+      -
+        name: reload-stats-limit
+      -
+        name: reload-stats-value
+  -
+    name: dl-info-version
+    subset-of: devlink
+    attributes:
+      -
+        name: info-version-name
+      -
+        name: info-version-value
+  -
+    name: dl-port-function
+    name-prefix: devlink-port-fn-attr-
+    attr-max-name: devlink-port-function-attr-max
+    attributes:
+      -
+        name-prefix: devlink-port-function-attr-
+        name: hw-addr
+        type: binary
+        value: 1
+      -
+        name: state
+        type: u8
+        enum: port-fn-state
+      -
+        name: opstate
+        type: u8
+        enum: port-fn-opstate
+      -
+        name: caps
+        type: bitfield32
+        enum: port-fn-attr-cap
+        enum-as-flags: True
+
+  -
+    name: dl-dpipe-tables
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-table
+
+  -
+    name: dl-dpipe-table
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-table-name
+      -
+        name: dpipe-table-size
+      -
+        name: dpipe-table-name
+      -
+        name: dpipe-table-size
+      -
+        name: dpipe-table-matches
+      -
+        name: dpipe-table-actions
+      -
+        name: dpipe-table-counters-enabled
+      -
+        name: dpipe-table-resource-id
+      -
+        name: dpipe-table-resource-units
+
+  -
+    name: dl-dpipe-table-matches
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-match
+
+  -
+    name: dl-dpipe-table-actions
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-action
+
+  -
+    name: dl-dpipe-entries
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-entry
+
+  -
+    name: dl-dpipe-entry
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-entry-index
+      -
+        name: dpipe-entry-match-values
+      -
+        name: dpipe-entry-action-values
+      -
+        name: dpipe-entry-counter
+
+  -
+    name: dl-dpipe-entry-match-values
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-match-value
+
+  -
+    name: dl-dpipe-entry-action-values
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-action-value
+
+  -
+    name: dl-dpipe-match
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-match-type
+      -
+        name: dpipe-header-id
+      -
+        name: dpipe-header-global
+      -
+        name: dpipe-header-index
+      -
+        name: dpipe-field-id
+
+  -
+    name: dl-dpipe-match-value
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-match
+      -
+        name: dpipe-value
+      -
+        name: dpipe-value-mask
+      -
+        name: dpipe-value-mapping
+
+  -
+    name: dl-dpipe-action
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-action-type
+      -
+        name: dpipe-header-id
+      -
+        name: dpipe-header-global
+      -
+        name: dpipe-header-index
+      -
+        name: dpipe-field-id
+
+  -
+    name: dl-dpipe-action-value
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-action
+      -
+        name: dpipe-value
+      -
+        name: dpipe-value-mask
+      -
+        name: dpipe-value-mapping
+
+  -
+    name: dl-dpipe-headers
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-header
+
+  -
+    name: dl-dpipe-header
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-header-name
+      -
+        name: dpipe-header-id
+      -
+        name: dpipe-header-global
+      -
+        name: dpipe-header-fields
+
+  -
+    name: dl-dpipe-header-fields
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-field
+
+  -
+    name: dl-dpipe-field
+    subset-of: devlink
+    attributes:
+      -
+        name: dpipe-field-name
+      -
+        name: dpipe-field-id
+      -
+        name: dpipe-field-bitwidth
+      -
+        name: dpipe-field-mapping-type
+
+  -
+    name: dl-resource
+    subset-of: devlink
+    attributes:
+      # -
+      # name: resource-list
+      # This is currently unsupported due to circular dependency
+      -
+        name: resource-name
+      -
+        name: resource-id
+      -
+        name: resource-size
+      -
+        name: resource-size-new
+      -
+        name: resource-size-valid
+      -
+        name: resource-size-min
+      -
+        name: resource-size-max
+      -
+        name: resource-size-gran
+      -
+        name: resource-unit
+      -
+        name: resource-occ
+
+  -
+    name: dl-resource-list
+    subset-of: devlink
+    attributes:
+      -
+        name: resource
+
+  -
+    name: dl-fmsg
     subset-of: devlink
     attributes:
       -
-        name: reload-stats-limit
+        name: fmsg-obj-nest-start
       -
-        name: reload-stats-value
+        name: fmsg-pair-nest-start
+      -
+        name: fmsg-arr-nest-start
+      -
+        name: fmsg-nest-end
+      -
+        name: fmsg-obj-name
+
   -
-    name: dl-info-version
-    subset-of: devlink
+    name: dl-selftest-id
+    name-prefix: devlink-attr-selftest-id-
     attributes:
       -
-        name: info-version-name
-      -
-        name: info-version-value
+        name: flash
+        type: flag
 
 operations:
   enum-model: directional
@@ -287,8 +1073,84 @@ operations:
         reply:
           value: 3  # due to a bug, port dump returns DEVLINK_CMD_NEW
           attributes: *port-id-attrs
+    -
+      name: port-set
+      doc: Set devlink port instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - port-type
+            - port-function
+
+    -
+      name: port-new
+      doc: Create devlink port instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - port-flavour
+            - port-pci-pf-number
+            - port-pci-sf-number
+            - port-controller-number
+        reply:
+          value: 7
+          attributes: *port-id-attrs
+
+    -
+      name: port-del
+      doc: Delete devlink port instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes: *port-id-attrs
 
-      # TODO: fill in the operations in between
+    -
+      name: port-split
+      doc: Split devlink port instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - port-split-count
+
+    -
+      name: port-unsplit
+      doc: Unplit devlink port instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes: *port-id-attrs
 
     -
       name: sb-get
@@ -312,8 +1174,6 @@ operations:
           attributes: *dev-id-attrs
         reply: *sb-get-reply
 
-      # TODO: fill in the operations in between
-
     -
       name: sb-pool-get
       doc: Get shared buffer pool instances.
@@ -337,7 +1197,23 @@ operations:
           attributes: *dev-id-attrs
         reply: *sb-pool-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: sb-pool-set
+      doc: Set shared buffer pool instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - sb-index
+            - sb-pool-index
+            - sb-pool-threshold-type
+            - sb-pool-size
 
     -
       name: sb-port-pool-get
@@ -363,34 +1239,263 @@ operations:
           attributes: *dev-id-attrs
         reply: *sb-port-pool-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: sb-port-pool-set
+      doc: Set shared buffer port-pool combinations and threshold.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - sb-index
+            - sb-pool-index
+            - sb-threshold
+
+    -
+      name: sb-tc-pool-bind-get
+      doc: Get shared buffer port-TC to pool bindings and threshold.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          value: 23
+          attributes: &sb-tc-pool-bind-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - sb-index
+            - sb-pool-type
+            - sb-tc-index
+        reply: &sb-tc-pool-bind-get-reply
+          value: 25
+          attributes: *sb-tc-pool-bind-id-attrs
+      dump:
+        request:
+          attributes: *dev-id-attrs
+        reply: *sb-tc-pool-bind-get-reply
+
+    -
+      name: sb-tc-pool-bind-set
+      doc: Set shared buffer port-TC to pool bindings and threshold.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - sb-index
+            - sb-pool-index
+            - sb-pool-type
+            - sb-tc-index
+            - sb-threshold
+
+    -
+      name: sb-occ-snapshot
+      doc: Take occupancy snapshot of shared buffer.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          value: 27
+          attributes:
+            - bus-name
+            - dev-name
+            - sb-index
+
+    -
+      name: sb-occ-max-clear
+      doc: Clear occupancy watermarks of shared buffer.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - sb-index
+
+    -
+      name: eswitch-get
+      doc: Get eswitch attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes: *dev-id-attrs
+        reply:
+          value: 29
+          attributes: &eswitch-attrs
+            - bus-name
+            - dev-name
+            - eswitch-mode
+            - eswitch-inline-mode
+            - eswitch-encap-mode
+
+    -
+      name: eswitch-set
+      doc: Set eswitch attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes: *eswitch-attrs
+
+    -
+      name: dpipe-table-get
+      doc: Get dpipe table attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-table-name
+        reply:
+          value: 31
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-tables
+
+    -
+      name: dpipe-entries-get
+      doc: Get dpipe entries attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-table-name
+        reply:
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-entries
+
+    -
+      name: dpipe-headers-get
+      doc: Get dpipe headers attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+        reply:
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-headers
+
+    -
+      name: dpipe-table-counters-set
+      doc: Set dpipe counter attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - dpipe-table-name
+            - dpipe-table-counters-enabled
+
+    -
+      name: resource-set
+      doc: Set resource attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - resource-id
+            - resource-size
+
+    -
+      name: resource-dump
+      doc: Get resource attributes.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+        reply:
+          value: 36
+          attributes:
+            - bus-name
+            - dev-name
+            - resource-list
 
     -
-      name: sb-tc-pool-bind-get
-      doc: Get shared buffer port-TC to pool bindings and threshold.
+      name: reload
+      doc: Reload devlink.
       attribute-set: devlink
       dont-validate: [ strict ]
+      flags: [ admin-perm ]
       do:
-        pre: devlink-nl-pre-doit-port
+        pre: devlink-nl-pre-doit
         post: devlink-nl-post-doit
         request:
-          value: 23
-          attributes: &sb-tc-pool-bind-id-attrs
+          attributes:
             - bus-name
             - dev-name
-            - port-index
-            - sb-index
-            - sb-pool-type
-            - sb-tc-index
-        reply: &sb-tc-pool-bind-get-reply
-          value: 25
-          attributes: *sb-tc-pool-bind-id-attrs
-      dump:
-        request:
-          attributes: *dev-id-attrs
-        reply: *sb-tc-pool-bind-get-reply
-
-      # TODO: fill in the operations in between
+            - reload-action
+            - reload-limits
+            - netns-pid
+            - netns-fd
+            - netns-id
+        reply:
+          attributes:
+            - bus-name
+            - dev-name
+            - reload-actions-performed
 
     -
       name: param-get
@@ -401,20 +1506,34 @@ operations:
         pre: devlink-nl-pre-doit
         post: devlink-nl-post-doit
         request:
-          value: 38
           attributes: &param-id-attrs
             - bus-name
             - dev-name
             - param-name
         reply: &param-get-reply
-          value: 38
           attributes: *param-id-attrs
       dump:
         request:
           attributes: *dev-id-attrs
         reply: *param-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: param-set
+      doc: Set param instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - param-name
+            - param-type
+            # param-value-data is missing here as the type is variable
+            - param-value-cmode
 
     -
       name: region-get
@@ -439,7 +1558,91 @@ operations:
           attributes: *dev-id-attrs
         reply: *region-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: region-new
+      doc: Create region snapshot.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          value: 44
+          attributes: &region-snapshot-id-attrs
+            - bus-name
+            - dev-name
+            - port-index
+            - region-name
+            - region-snapshot-id
+        reply:
+          value: 44
+          attributes: *region-snapshot-id-attrs
+
+    -
+      name: region-del
+      doc: Delete region snapshot.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes: *region-snapshot-id-attrs
+
+    -
+      name: region-read
+      doc: Read region data.
+      attribute-set: devlink
+      dont-validate: [ dump-strict ]
+      flags: [ admin-perm ]
+      dump:
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - region-name
+            - region-snapshot-id
+            - region-direct
+            - region-chunk-addr
+            - region-chunk-len
+        reply:
+          value: 46
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - region-name
+
+    -
+      name: port-param-get
+      doc: Get port param instances.
+      attribute-set: devlink
+      dont-validate: [ strict, dump-strict ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes: *port-id-attrs
+        reply:
+          attributes: *port-id-attrs
+      dump:
+        reply:
+          attributes: *port-id-attrs
+
+    -
+      name: port-param-set
+      doc: Set port param instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port
+        post: devlink-nl-post-doit
+        request:
+          attributes: *port-id-attrs
 
     -
       name: info-get
@@ -486,7 +1689,91 @@ operations:
           attributes: *port-id-attrs
         reply: *health-reporter-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: health-reporter-set
+      doc: Set health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - port-index
+            - health-reporter-name
+            - health-reporter-graceful-period
+            - health-reporter-auto-recover
+            - health-reporter-auto-dump
+
+    -
+      name: health-reporter-recover
+      doc: Recover health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes: *health-reporter-id-attrs
+
+    -
+      name: health-reporter-diagnose
+      doc: Diagnose health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes: *health-reporter-id-attrs
+
+    -
+      name: health-reporter-dump-get
+      doc: Dump health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ dump-strict ]
+      flags: [ admin-perm ]
+      dump:
+        request:
+          attributes: *health-reporter-id-attrs
+        reply:
+          value: 56
+          attributes:
+            - fmsg
+
+    -
+      name: health-reporter-dump-clear
+      doc: Clear dump of health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          attributes: *health-reporter-id-attrs
+
+    -
+      name: flash-update
+      doc: Flash update devlink instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - flash-update-file-name
+            - flash-update-component
+            - flash-update-overwrite-mask
 
     -
       name: trap-get
@@ -510,7 +1797,21 @@ operations:
           attributes: *dev-id-attrs
         reply: *trap-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: trap-set
+      doc: Set trap instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - trap-name
+            - trap-action
 
     -
       name: trap-group-get
@@ -534,7 +1835,22 @@ operations:
           attributes: *dev-id-attrs
         reply: *trap-group-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: trap-group-set
+      doc: Set trap group instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - trap-group-name
+            - trap-action
+            - trap-policer-id
 
     -
       name: trap-policer-get
@@ -558,7 +1874,35 @@ operations:
           attributes: *dev-id-attrs
         reply: *trap-policer-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: trap-policer-set
+      doc: Get trap policer instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - trap-policer-id
+            - trap-policer-rate
+            - trap-policer-burst
+
+    -
+      name: health-reporter-test
+      doc: Test health reporter instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit-port-optional
+        post: devlink-nl-post-doit
+        request:
+          value: 73
+          attributes: *health-reporter-id-attrs
 
     -
       name: rate-get
@@ -583,7 +1927,60 @@ operations:
           attributes: *dev-id-attrs
         reply: *rate-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: rate-set
+      doc: Set rate instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - rate-node-name
+            - rate-tx-share
+            - rate-tx-max
+            - rate-tx-priority
+            - rate-tx-weight
+            - rate-parent-node-name
+
+    -
+      name: rate-new
+      doc: Create rate instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - rate-node-name
+            - rate-tx-share
+            - rate-tx-max
+            - rate-tx-priority
+            - rate-tx-weight
+            - rate-parent-node-name
+
+    -
+      name: rate-del
+      doc: Delete rate instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - rate-node-name
 
     -
       name: linecard-get
@@ -607,7 +2004,21 @@ operations:
           attributes: *dev-id-attrs
         reply: *linecard-get-reply
 
-      # TODO: fill in the operations in between
+    -
+      name: linecard-set
+      doc: Set line card instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - linecard-index
+            - linecard-type
 
     -
       name: selftests-get
@@ -625,3 +2036,18 @@ operations:
           attributes: *dev-id-attrs
       dump:
         reply: *selftests-get-reply
+
+    -
+      name: selftests-run
+      doc: Run device selftest instances.
+      attribute-set: devlink
+      dont-validate: [ strict ]
+      flags: [ admin-perm ]
+      do:
+        pre: devlink-nl-pre-doit
+        post: devlink-nl-post-doit
+        request:
+          attributes:
+            - bus-name
+            - dev-name
+            - selftests
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 467b7a431de1..9cbae0169249 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -10,6 +10,18 @@
 
 #include <uapi/linux/devlink.h>
 
+/* Common nested types */
+const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1] = {
+	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, },
+	[DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_MAX(NLA_U8, 1),
+	[DEVLINK_PORT_FN_ATTR_OPSTATE] = NLA_POLICY_MAX(NLA_U8, 1),
+	[DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(3),
+};
+
+const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = {
+	[DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, },
+};
+
 /* DEVLINK_CMD_GET - do */
 static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -29,6 +41,48 @@ static const struct nla_policy devlink_port_get_dump_nl_policy[DEVLINK_ATTR_DEV_
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_PORT_SET - do */
+static const struct nla_policy devlink_port_set_nl_policy[DEVLINK_ATTR_PORT_FUNCTION + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_MAX(NLA_U16, 3),
+	[DEVLINK_ATTR_PORT_FUNCTION] = NLA_POLICY_NESTED(devlink_dl_port_function_nl_policy),
+};
+
+/* DEVLINK_CMD_PORT_NEW - do */
+static const struct nla_policy devlink_port_new_nl_policy[DEVLINK_ATTR_PORT_PCI_SF_NUMBER + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_PORT_FLAVOUR] = NLA_POLICY_MAX(NLA_U16, 7),
+	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16, },
+	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_PORT_DEL - do */
+static const struct nla_policy devlink_port_del_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_PORT_SPLIT - do */
+static const struct nla_policy devlink_port_split_nl_policy[DEVLINK_ATTR_PORT_SPLIT_COUNT + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_PORT_UNSPLIT - do */
+static const struct nla_policy devlink_port_unsplit_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_SB_GET - do */
 static const struct nla_policy devlink_sb_get_do_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -56,6 +110,16 @@ static const struct nla_policy devlink_sb_pool_get_dump_nl_policy[DEVLINK_ATTR_D
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_SB_POOL_SET - do */
+static const struct nla_policy devlink_sb_pool_set_nl_policy[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
+	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = NLA_POLICY_MAX(NLA_U8, 1),
+	[DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_SB_PORT_POOL_GET - do */
 static const struct nla_policy devlink_sb_port_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -71,6 +135,16 @@ static const struct nla_policy devlink_sb_port_pool_get_dump_nl_policy[DEVLINK_A
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_SB_PORT_POOL_SET - do */
+static const struct nla_policy devlink_sb_port_pool_set_nl_policy[DEVLINK_ATTR_SB_THRESHOLD + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
+	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
 static const struct nla_policy devlink_sb_tc_pool_bind_get_do_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -87,6 +161,100 @@ static const struct nla_policy devlink_sb_tc_pool_bind_get_dump_nl_policy[DEVLIN
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */
+static const struct nla_policy devlink_sb_tc_pool_bind_set_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, },
+	[DEVLINK_ATTR_SB_POOL_TYPE] = NLA_POLICY_MAX(NLA_U8, 1),
+	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, },
+	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */
+static const struct nla_policy devlink_sb_occ_snapshot_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */
+static const struct nla_policy devlink_sb_occ_max_clear_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_ESWITCH_GET - do */
+static const struct nla_policy devlink_eswitch_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_ESWITCH_SET - do */
+static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITCH_ENCAP_MODE + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1),
+	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U16, 3),
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1),
+};
+
+/* DEVLINK_CMD_DPIPE_TABLE_GET - do */
+static const struct nla_policy devlink_dpipe_table_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */
+static const struct nla_policy devlink_dpipe_entries_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */
+static const struct nla_policy devlink_dpipe_headers_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */
+static const struct nla_policy devlink_dpipe_table_counters_set_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8, },
+};
+
+/* DEVLINK_CMD_RESOURCE_SET - do */
+static const struct nla_policy devlink_resource_set_nl_policy[DEVLINK_ATTR_RESOURCE_SIZE + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64, },
+};
+
+/* DEVLINK_CMD_RESOURCE_DUMP - do */
+static const struct nla_policy devlink_resource_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_RELOAD - do */
+static const struct nla_policy devlink_reload_nl_policy[DEVLINK_ATTR_RELOAD_LIMITS + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, 1, 2),
+	[DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(6),
+	[DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_PARAM_GET - do */
 static const struct nla_policy devlink_param_get_do_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -100,6 +268,15 @@ static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_PARAM_SET - do */
+static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VALUE_CMODE + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8, },
+	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2),
+};
+
 /* DEVLINK_CMD_REGION_GET - do */
 static const struct nla_policy devlink_region_get_do_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -114,6 +291,50 @@ static const struct nla_policy devlink_region_get_dump_nl_policy[DEVLINK_ATTR_DE
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_REGION_NEW - do */
+static const struct nla_policy devlink_region_new_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_REGION_DEL - do */
+static const struct nla_policy devlink_region_del_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_REGION_READ - dump */
+static const struct nla_policy devlink_region_read_nl_policy[DEVLINK_ATTR_REGION_DIRECT + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG, },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64, },
+};
+
+/* DEVLINK_CMD_PORT_PARAM_GET - do */
+static const struct nla_policy devlink_port_param_get_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
+/* DEVLINK_CMD_PORT_PARAM_SET - do */
+static const struct nla_policy devlink_port_param_set_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_INFO_GET - do */
 static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -135,6 +356,58 @@ static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLIN
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
 };
 
+/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */
+static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8, },
+};
+
+/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */
+static const struct nla_policy devlink_health_reporter_recover_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */
+static const struct nla_policy devlink_health_reporter_diagnose_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */
+static const struct nla_policy devlink_health_reporter_dump_get_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */
+static const struct nla_policy devlink_health_reporter_dump_clear_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_FLASH_UPDATE - do */
+static const struct nla_policy devlink_flash_update_nl_policy[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = NLA_POLICY_BITFIELD32(3),
+};
+
 /* DEVLINK_CMD_TRAP_GET - do */
 static const struct nla_policy devlink_trap_get_do_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -148,6 +421,14 @@ static const struct nla_policy devlink_trap_get_dump_nl_policy[DEVLINK_ATTR_DEV_
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_TRAP_SET - do */
+static const struct nla_policy devlink_trap_set_nl_policy[DEVLINK_ATTR_TRAP_ACTION + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2),
+};
+
 /* DEVLINK_CMD_TRAP_GROUP_GET - do */
 static const struct nla_policy devlink_trap_group_get_do_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -161,6 +442,15 @@ static const struct nla_policy devlink_trap_group_get_dump_nl_policy[DEVLINK_ATT
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_TRAP_GROUP_SET - do */
+static const struct nla_policy devlink_trap_group_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2),
+	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, },
+};
+
 /* DEVLINK_CMD_TRAP_POLICER_GET - do */
 static const struct nla_policy devlink_trap_policer_get_do_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -174,6 +464,23 @@ static const struct nla_policy devlink_trap_policer_get_dump_nl_policy[DEVLINK_A
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_TRAP_POLICER_SET - do */
+static const struct nla_policy devlink_trap_policer_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_BURST + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64, },
+};
+
+/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */
+static const struct nla_policy devlink_health_reporter_test_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_RATE_GET - do */
 static const struct nla_policy devlink_rate_get_do_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -188,6 +495,37 @@ static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_RATE_SET - do */
+static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_RATE_NEW - do */
+static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, },
+	[DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+/* DEVLINK_CMD_RATE_DEL - do */
+static const struct nla_policy devlink_rate_del_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_LINECARD_GET - do */
 static const struct nla_policy devlink_linecard_get_do_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
@@ -201,14 +539,29 @@ static const struct nla_policy devlink_linecard_get_dump_nl_policy[DEVLINK_ATTR_
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_LINECARD_SET - do */
+static const struct nla_policy devlink_linecard_set_nl_policy[DEVLINK_ATTR_LINECARD_TYPE + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, },
+	[DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING, },
+};
+
 /* DEVLINK_CMD_SELFTESTS_GET - do */
 static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 };
 
+/* DEVLINK_CMD_SELFTESTS_RUN - do */
+static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELFTESTS + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy),
+};
+
 /* Ops table for devlink */
-const struct genl_split_ops devlink_nl_ops[32] = {
+const struct genl_split_ops devlink_nl_ops[73] = {
 	{
 		.cmd		= DEVLINK_CMD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -242,6 +595,56 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_FUNCTION,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_NEW,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_port_new_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_new_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_PCI_SF_NUMBER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_DEL,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_del_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_del_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_SPLIT,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_split_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_split_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_SPLIT_COUNT,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_UNSPLIT,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_unsplit_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_unsplit_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_SB_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -276,6 +679,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_SB_POOL_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_sb_pool_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_pool_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_SB_PORT_POOL_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -293,6 +706,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_SB_PORT_POOL_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_sb_port_pool_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_port_pool_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_THRESHOLD,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_SB_TC_POOL_BIND_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -310,6 +733,126 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_sb_tc_pool_bind_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_tc_pool_bind_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_TC_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_OCC_SNAPSHOT,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_sb_occ_snapshot_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_occ_snapshot_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_sb_occ_max_clear_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_sb_occ_max_clear_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SB_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_ESWITCH_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_eswitch_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_eswitch_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_ESWITCH_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_eswitch_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_eswitch_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_ESWITCH_ENCAP_MODE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_DPIPE_TABLE_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_dpipe_table_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_dpipe_table_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DPIPE_TABLE_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_dpipe_entries_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_dpipe_entries_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DPIPE_TABLE_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_dpipe_headers_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_dpipe_headers_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_dpipe_table_counters_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_dpipe_table_counters_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RESOURCE_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_resource_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_resource_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RESOURCE_SIZE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RESOURCE_DUMP,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_resource_dump_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_resource_dump_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RELOAD,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_reload_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_reload_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RELOAD_LIMITS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_PARAM_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -327,6 +870,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_PARAM_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_param_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_param_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PARAM_VALUE_CMODE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_REGION_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -344,6 +897,60 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_REGION_NEW,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_region_new_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_region_new_nl_policy,
+		.maxattr	= DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_REGION_DEL,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_region_del_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_region_del_nl_policy,
+		.maxattr	= DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_REGION_READ,
+		.validate	= GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit		= devlink_nl_region_read_dumpit,
+		.policy		= devlink_region_read_nl_policy,
+		.maxattr	= DEVLINK_ATTR_REGION_DIRECT,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_PARAM_GET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_param_get_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_param_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_PARAM_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit		= devlink_nl_port_param_get_dumpit,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_PORT_PARAM_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port,
+		.doit		= devlink_nl_port_param_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_port_param_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_INFO_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -377,6 +984,64 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_PORT_INDEX,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_recover_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_recover_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_diagnose_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_diagnose_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+		.validate	= GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit		= devlink_nl_health_reporter_dump_get_dumpit,
+		.policy		= devlink_health_reporter_dump_get_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_dump_clear_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_dump_clear_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_FLASH_UPDATE,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_flash_update_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_flash_update_nl_policy,
+		.maxattr	= DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -394,6 +1059,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_ACTION,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_GROUP_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -411,6 +1086,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_GROUP_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_group_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_group_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_POLICER_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_TRAP_POLICER_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -428,6 +1113,26 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_TRAP_POLICER_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_trap_policer_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_trap_policer_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_TRAP_POLICER_BURST,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit_port_optional,
+		.doit		= devlink_nl_health_reporter_test_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_health_reporter_test_nl_policy,
+		.maxattr	= DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_RATE_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -445,6 +1150,36 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_RATE_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_rate_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_rate_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RATE_TX_WEIGHT,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RATE_NEW,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_rate_new_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_rate_new_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RATE_TX_WEIGHT,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DEVLINK_CMD_RATE_DEL,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_rate_del_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_rate_del_nl_policy,
+		.maxattr	= DEVLINK_ATTR_RATE_NODE_NAME,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_LINECARD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -462,6 +1197,16 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.maxattr	= DEVLINK_ATTR_DEV_NAME,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_LINECARD_SET,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_linecard_set_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_linecard_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_LINECARD_TYPE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 	{
 		.cmd		= DEVLINK_CMD_SELFTESTS_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -478,4 +1223,14 @@ const struct genl_split_ops devlink_nl_ops[32] = {
 		.dumpit		= devlink_nl_selftests_get_dumpit,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DEVLINK_CMD_SELFTESTS_RUN,
+		.validate	= GENL_DONT_VALIDATE_STRICT,
+		.pre_doit	= devlink_nl_pre_doit,
+		.doit		= devlink_nl_selftests_run_doit,
+		.post_doit	= devlink_nl_post_doit,
+		.policy		= devlink_selftests_run_nl_policy,
+		.maxattr	= DEVLINK_ATTR_SELFTESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index f8bbc93e39be..0e9e89c31c31 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -11,8 +11,12 @@
 
 #include <uapi/linux/devlink.h>
 
+/* Common nested types */
+extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1];
+extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
+
 /* Ops table for devlink */
-extern const struct genl_split_ops devlink_nl_ops[32];
+extern const struct genl_split_ops devlink_nl_ops[73];
 
 int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
@@ -30,25 +34,61 @@ int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_port_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
+int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
 				  struct netlink_callback *cb);
+int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
 				     struct genl_info *info);
 int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
 				       struct netlink_callback *cb);
+int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
 int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
 					struct genl_info *info);
 int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
 					  struct netlink_callback *cb);
+int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_param_get_dumpit(struct sk_buff *skb,
 				struct netlink_callback *cb);
+int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_region_get_dumpit(struct sk_buff *skb,
 				 struct netlink_callback *cb);
+int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_read_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_port_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_param_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_port_param_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_info_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
@@ -56,24 +96,46 @@ int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
 					struct genl_info *info);
 int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
 					  struct netlink_callback *cb);
+int devlink_nl_health_reporter_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb,
+					    struct genl_info *info);
+int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb,
+					       struct netlink_callback *cb);
+int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb,
+					       struct genl_info *info);
+int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
+int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
 				     struct netlink_callback *cb);
+int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
 				     struct genl_info *info);
 int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
 				       struct netlink_callback *cb);
+int devlink_nl_trap_policer_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_health_reporter_test_doit(struct sk_buff *skb,
+					 struct genl_info *info);
 int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_rate_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
+int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
 				   struct netlink_callback *cb);
+int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
 				    struct netlink_callback *cb);
+int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
 
 #endif /* _LINUX_DEVLINK_GEN_H */
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index a002f71d6068..75b744b47986 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -16,14 +16,25 @@
 static const char * const devlink_op_strmap[] = {
 	[3] = "get",
 	[7] = "port-get",
+	[DEVLINK_CMD_PORT_NEW] = "port-new",
 	[13] = "sb-get",
 	[17] = "sb-pool-get",
 	[21] = "sb-port-pool-get",
 	[25] = "sb-tc-pool-bind-get",
+	[DEVLINK_CMD_ESWITCH_GET] = "eswitch-get",
+	[DEVLINK_CMD_DPIPE_TABLE_GET] = "dpipe-table-get",
+	[DEVLINK_CMD_DPIPE_ENTRIES_GET] = "dpipe-entries-get",
+	[DEVLINK_CMD_DPIPE_HEADERS_GET] = "dpipe-headers-get",
+	[DEVLINK_CMD_RESOURCE_DUMP] = "resource-dump",
+	[DEVLINK_CMD_RELOAD] = "reload",
 	[DEVLINK_CMD_PARAM_GET] = "param-get",
 	[DEVLINK_CMD_REGION_GET] = "region-get",
+	[DEVLINK_CMD_REGION_NEW] = "region-new",
+	[DEVLINK_CMD_REGION_READ] = "region-read",
+	[DEVLINK_CMD_PORT_PARAM_GET] = "port-param-get",
 	[DEVLINK_CMD_INFO_GET] = "info-get",
 	[DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get",
+	[DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET] = "health-reporter-dump-get",
 	[63] = "trap-get",
 	[67] = "trap-group-get",
 	[71] = "trap-policer-get",
@@ -51,7 +62,303 @@ const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value)
 	return devlink_sb_pool_type_strmap[value];
 }
 
+static const char * const devlink_port_type_strmap[] = {
+	[0] = "notset",
+	[1] = "auto",
+	[2] = "eth",
+	[3] = "ib",
+};
+
+const char *devlink_port_type_str(enum devlink_port_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_type_strmap))
+		return NULL;
+	return devlink_port_type_strmap[value];
+}
+
+static const char * const devlink_port_flavour_strmap[] = {
+	[0] = "physical",
+	[1] = "cpu",
+	[2] = "dsa",
+	[3] = "pci_pf",
+	[4] = "pci_vf",
+	[5] = "virtual",
+	[6] = "unused",
+	[7] = "pci_sf",
+};
+
+const char *devlink_port_flavour_str(enum devlink_port_flavour value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_flavour_strmap))
+		return NULL;
+	return devlink_port_flavour_strmap[value];
+}
+
+static const char * const devlink_port_fn_state_strmap[] = {
+	[0] = "inactive",
+	[1] = "active",
+};
+
+const char *devlink_port_fn_state_str(enum devlink_port_fn_state value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_state_strmap))
+		return NULL;
+	return devlink_port_fn_state_strmap[value];
+}
+
+static const char * const devlink_port_fn_opstate_strmap[] = {
+	[0] = "detached",
+	[1] = "attached",
+};
+
+const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_opstate_strmap))
+		return NULL;
+	return devlink_port_fn_opstate_strmap[value];
+}
+
+static const char * const devlink_port_fn_attr_cap_strmap[] = {
+	[0] = "roce-bit",
+	[1] = "migratable-bit",
+};
+
+const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_attr_cap_strmap))
+		return NULL;
+	return devlink_port_fn_attr_cap_strmap[value];
+}
+
+static const char * const devlink_sb_threshold_type_strmap[] = {
+	[0] = "static",
+	[1] = "dynamic",
+};
+
+const char *devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_threshold_type_strmap))
+		return NULL;
+	return devlink_sb_threshold_type_strmap[value];
+}
+
+static const char * const devlink_eswitch_mode_strmap[] = {
+	[0] = "legacy",
+	[1] = "switchdev",
+};
+
+const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_mode_strmap))
+		return NULL;
+	return devlink_eswitch_mode_strmap[value];
+}
+
+static const char * const devlink_eswitch_inline_mode_strmap[] = {
+	[0] = "none",
+	[1] = "link",
+	[2] = "network",
+	[3] = "transport",
+};
+
+const char *
+devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_inline_mode_strmap))
+		return NULL;
+	return devlink_eswitch_inline_mode_strmap[value];
+}
+
+static const char * const devlink_eswitch_encap_mode_strmap[] = {
+	[0] = "none",
+	[1] = "basic",
+};
+
+const char *
+devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_encap_mode_strmap))
+		return NULL;
+	return devlink_eswitch_encap_mode_strmap[value];
+}
+
+static const char * const devlink_dpipe_match_type_strmap[] = {
+	[0] = "field-exact",
+};
+
+const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_match_type_strmap))
+		return NULL;
+	return devlink_dpipe_match_type_strmap[value];
+}
+
+static const char * const devlink_dpipe_action_type_strmap[] = {
+	[0] = "field-modify",
+};
+
+const char *devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_action_type_strmap))
+		return NULL;
+	return devlink_dpipe_action_type_strmap[value];
+}
+
+static const char * const devlink_dpipe_field_mapping_type_strmap[] = {
+	[0] = "none",
+	[1] = "ifindex",
+};
+
+const char *
+devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_field_mapping_type_strmap))
+		return NULL;
+	return devlink_dpipe_field_mapping_type_strmap[value];
+}
+
+static const char * const devlink_resource_unit_strmap[] = {
+	[0] = "entry",
+};
+
+const char *devlink_resource_unit_str(enum devlink_resource_unit value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_resource_unit_strmap))
+		return NULL;
+	return devlink_resource_unit_strmap[value];
+}
+
+static const char * const devlink_reload_action_strmap[] = {
+	[1] = "driver-reinit",
+	[2] = "fw-activate",
+};
+
+const char *devlink_reload_action_str(enum devlink_reload_action value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_reload_action_strmap))
+		return NULL;
+	return devlink_reload_action_strmap[value];
+}
+
+static const char * const devlink_param_cmode_strmap[] = {
+	[0] = "runtime",
+	[1] = "driverinit",
+	[2] = "permanent",
+};
+
+const char *devlink_param_cmode_str(enum devlink_param_cmode value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_param_cmode_strmap))
+		return NULL;
+	return devlink_param_cmode_strmap[value];
+}
+
+static const char * const devlink_flash_overwrite_strmap[] = {
+	[0] = "settings-bit",
+	[1] = "identifiers-bit",
+};
+
+const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_flash_overwrite_strmap))
+		return NULL;
+	return devlink_flash_overwrite_strmap[value];
+}
+
+static const char * const devlink_trap_action_strmap[] = {
+	[0] = "drop",
+	[1] = "trap",
+	[2] = "mirror",
+};
+
+const char *devlink_trap_action_str(enum devlink_trap_action value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_trap_action_strmap))
+		return NULL;
+	return devlink_trap_action_strmap[value];
+}
+
 /* Policies */
+struct ynl_policy_attr devlink_dl_dpipe_match_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_match_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_match_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_match_value_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
+	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_match_value_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_match_value_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_action_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_action_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_action_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_action_value_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
+	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_action_value_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_action_value_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_field_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_field_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_field_policy,
+};
+
+struct ynl_policy_attr devlink_dl_resource_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, },
+};
+
+struct ynl_policy_nest devlink_dl_resource_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_resource_policy,
+};
+
 struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, },
@@ -62,6 +369,31 @@ struct ynl_policy_nest devlink_dl_info_version_nest = {
 	.table = devlink_dl_info_version_policy,
 };
 
+struct ynl_policy_attr devlink_dl_fmsg_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, },
+};
+
+struct ynl_policy_nest devlink_dl_fmsg_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_fmsg_policy,
+};
+
+struct ynl_policy_attr devlink_dl_port_function_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
+	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .name = "hw-addr", .type = YNL_PT_BINARY,},
+	[DEVLINK_PORT_FN_ATTR_STATE] = { .name = "state", .type = YNL_PT_U8, },
+	[DEVLINK_PORT_FN_ATTR_OPSTATE] = { .name = "opstate", .type = YNL_PT_U8, },
+	[DEVLINK_PORT_FN_ATTR_CAPS] = { .name = "caps", .type = YNL_PT_BITFIELD32, },
+};
+
+struct ynl_policy_nest devlink_dl_port_function_nest = {
+	.max_attr = DEVLINK_PORT_FUNCTION_ATTR_MAX,
+	.table = devlink_dl_port_function_policy,
+};
+
 struct ynl_policy_attr devlink_dl_reload_stats_entry_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, },
@@ -81,6 +413,69 @@ struct ynl_policy_nest devlink_dl_reload_act_stats_nest = {
 	.table = devlink_dl_reload_act_stats_policy,
 };
 
+struct ynl_policy_attr devlink_dl_selftest_id_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = {
+	[DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .name = "flash", .type = YNL_PT_FLAG, },
+};
+
+struct ynl_policy_nest devlink_dl_selftest_id_nest = {
+	.max_attr = DEVLINK_ATTR_SELFTEST_ID_MAX,
+	.table = devlink_dl_selftest_id_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_table_matches_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_table_matches_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_table_matches_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_table_actions_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_table_actions_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_table_actions_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_entry_match_values_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_entry_match_values_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_entry_match_values_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_entry_action_values_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_entry_action_values_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_entry_action_values_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_header_fields_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_header_fields_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_header_fields_policy,
+};
+
+struct ynl_policy_attr devlink_dl_resource_list_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_resource_list_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_resource_list_policy,
+};
+
 struct ynl_policy_attr devlink_dl_reload_act_info_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, },
@@ -91,6 +486,45 @@ struct ynl_policy_nest devlink_dl_reload_act_info_nest = {
 	.table = devlink_dl_reload_act_info_policy,
 };
 
+struct ynl_policy_attr devlink_dl_dpipe_table_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_table_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_table_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_entry_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_entry_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_entry_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_header_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_header_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_header_policy,
+};
+
 struct ynl_policy_attr devlink_dl_reload_stats_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, },
 };
@@ -100,6 +534,33 @@ struct ynl_policy_nest devlink_dl_reload_stats_nest = {
 	.table = devlink_dl_reload_stats_policy,
 };
 
+struct ynl_policy_attr devlink_dl_dpipe_tables_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_tables_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_tables_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_entries_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_entries_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_entries_policy,
+};
+
+struct ynl_policy_attr devlink_dl_dpipe_headers_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, },
+};
+
+struct ynl_policy_nest devlink_dl_dpipe_headers_nest = {
+	.max_attr = DEVLINK_ATTR_MAX,
+	.table = devlink_dl_dpipe_headers_policy,
+};
+
 struct ynl_policy_attr devlink_dl_dev_stats_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
 	[DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
@@ -114,12 +575,75 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_PORT_TYPE] = { .name = "port-type", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .name = "port-split-count", .type = YNL_PT_U32, },
 	[DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, },
 	[DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, },
 	[DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_SB_POOL_SIZE] = { .name = "sb-pool-size", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .name = "sb-pool-threshold-type", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_SB_THRESHOLD] = { .name = "sb-threshold", .type = YNL_PT_U32, },
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_ESWITCH_MODE] = { .name = "eswitch-mode", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .name = "eswitch-inline-mode", .type = YNL_PT_U16, },
+	[DEVLINK_ATTR_DPIPE_TABLES] = { .name = "dpipe-tables", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_tables_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_ENTRIES] = { .name = "dpipe-entries", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entries_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, },
+	[DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, },
+	[DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, },
+	[DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, },
+	[DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, },
+	[DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,},
+	[DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADERS] = { .name = "dpipe-headers", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_headers_nest, },
+	[DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, },
+	[DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, },
+	[DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, },
+	[DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .name = "eswitch-encap-mode", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RESOURCE_LIST] = { .name = "resource-list", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_list_nest, },
+	[DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, },
+	[DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_PORT_FLAVOUR] = { .name = "port-flavour", .type = YNL_PT_U16, },
 	[DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_PARAM_TYPE] = { .name = "param-type", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .name = "param-value-cmode", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .name = "region-snapshot-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .name = "region-chunk-addr", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .name = "region-chunk-len", .type = YNL_PT_U64, },
 	[DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
@@ -127,12 +651,35 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, },
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_FMSG] = { .name = "fmsg", .type = YNL_PT_NEST, .nest = &devlink_dl_fmsg_nest, },
+	[DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, },
+	[DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .name = "health-reporter-graceful-period", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .name = "health-reporter-auto-recover", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .name = "flash-update-file-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .name = "flash-update-component", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .name = "port-pci-pf-number", .type = YNL_PT_U16, },
 	[DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_TRAP_ACTION] = { .name = "trap-action", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_NETNS_FD] = { .name = "netns-fd", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_NETNS_PID] = { .name = "netns-pid", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_NETNS_ID] = { .name = "netns-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .name = "health-reporter-auto-dump", .type = YNL_PT_U8, },
 	[DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .name = "trap-policer-rate", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .name = "trap-policer-burst", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_PORT_FUNCTION] = { .name = "port-function", .type = YNL_PT_NEST, .nest = &devlink_dl_port_function_nest, },
+	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .name = "port-controller-number", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = { .name = "flash-update-overwrite-mask", .type = YNL_PT_BITFIELD32, },
 	[DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, },
+	[DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED] = { .name = "reload-actions-performed", .type = YNL_PT_BITFIELD32, },
+	[DEVLINK_ATTR_RELOAD_LIMITS] = { .name = "reload-limits", .type = YNL_PT_BITFIELD32, },
 	[DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, },
 	[DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
 	[DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, },
@@ -141,8 +688,17 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, },
 	[DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, },
 	[DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, },
+	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .name = "port-pci-sf-number", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .name = "rate-tx-share", .type = YNL_PT_U64, },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .name = "rate-tx-max", .type = YNL_PT_U64, },
 	[DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .name = "rate-parent-node-name", .type = YNL_PT_NUL_STR, },
 	[DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_LINECARD_TYPE] = { .name = "linecard-type", .type = YNL_PT_NUL_STR, },
+	[DEVLINK_ATTR_SELFTESTS] = { .name = "selftests", .type = YNL_PT_NEST, .nest = &devlink_dl_selftest_id_nest, },
+	[DEVLINK_ATTR_RATE_TX_PRIORITY] = { .name = "rate-tx-priority", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_RATE_TX_WEIGHT] = { .name = "rate-tx-weight", .type = YNL_PT_U32, },
+	[DEVLINK_ATTR_REGION_DIRECT] = { .name = "region-direct", .type = YNL_PT_FLAG, },
 };
 
 struct ynl_policy_nest devlink_nest = {
@@ -151,43 +707,44 @@ struct ynl_policy_nest devlink_nest = {
 };
 
 /* Common nested types */
-void devlink_dl_info_version_free(struct devlink_dl_info_version *obj)
+void devlink_dl_dpipe_match_free(struct devlink_dl_dpipe_match *obj)
 {
-	free(obj->info_version_name);
-	free(obj->info_version_value);
 }
 
-int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg,
-				  const struct nlattr *nested)
+int devlink_dl_dpipe_match_parse(struct ynl_parse_arg *yarg,
+				 const struct nlattr *nested)
 {
-	struct devlink_dl_info_version *dst = yarg->data;
+	struct devlink_dl_dpipe_match *dst = yarg->data;
 	const struct nlattr *attr;
 
 	mnl_attr_for_each_nested(attr, nested) {
 		unsigned int type = mnl_attr_get_type(attr);
 
-		if (type == DEVLINK_ATTR_INFO_VERSION_NAME) {
-			unsigned int len;
-
+		if (type == DEVLINK_ATTR_DPIPE_MATCH_TYPE) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_version_name_len = len;
-			dst->info_version_name = malloc(len + 1);
-			memcpy(dst->info_version_name, mnl_attr_get_str(attr), len);
-			dst->info_version_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_INFO_VERSION_VALUE) {
-			unsigned int len;
-
+			dst->_present.dpipe_match_type = 1;
+			dst->dpipe_match_type = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.info_version_value_len = len;
-			dst->info_version_value = malloc(len + 1);
-			memcpy(dst->info_version_value, mnl_attr_get_str(attr), len);
-			dst->info_version_value[len] = 0;
+			dst->_present.dpipe_header_id = 1;
+			dst->dpipe_header_id = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_global = 1;
+			dst->dpipe_header_global = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_index = 1;
+			dst->dpipe_header_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_field_id = 1;
+			dst->dpipe_field_id = mnl_attr_get_u32(attr);
 		}
 	}
 
@@ -195,75 +752,194 @@ int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg,
 }
 
 void
-devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj)
+devlink_dl_dpipe_match_value_free(struct devlink_dl_dpipe_match_value *obj)
 {
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_match; i++)
+		devlink_dl_dpipe_match_free(&obj->dpipe_match[i]);
+	free(obj->dpipe_match);
+	free(obj->dpipe_value);
+	free(obj->dpipe_value_mask);
 }
 
-int devlink_dl_reload_stats_entry_parse(struct ynl_parse_arg *yarg,
-					const struct nlattr *nested)
+int devlink_dl_dpipe_match_value_parse(struct ynl_parse_arg *yarg,
+				       const struct nlattr *nested)
 {
-	struct devlink_dl_reload_stats_entry *dst = yarg->data;
+	struct devlink_dl_dpipe_match_value *dst = yarg->data;
+	unsigned int n_dpipe_match = 0;
 	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_match)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-match-value.dpipe-match)");
 
 	mnl_attr_for_each_nested(attr, nested) {
 		unsigned int type = mnl_attr_get_type(attr);
 
-		if (type == DEVLINK_ATTR_RELOAD_STATS_LIMIT) {
+		if (type == DEVLINK_ATTR_DPIPE_MATCH) {
+			n_dpipe_match++;
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.reload_stats_limit = 1;
-			dst->reload_stats_limit = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RELOAD_STATS_VALUE) {
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.dpipe_value_len = len;
+			dst->dpipe_value = malloc(len);
+			memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len);
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.reload_stats_value = 1;
-			dst->reload_stats_value = mnl_attr_get_u32(attr);
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.dpipe_value_mask_len = len;
+			dst->dpipe_value_mask = malloc(len);
+			memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len);
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_value_mapping = 1;
+			dst->dpipe_value_mapping = mnl_attr_get_u32(attr);
+		}
+	}
+
+	if (n_dpipe_match) {
+		dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match));
+		dst->n_dpipe_match = n_dpipe_match;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_match_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) {
+				parg.data = &dst->dpipe_match[i];
+				if (devlink_dl_dpipe_match_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
 		}
 	}
 
 	return 0;
 }
 
-void devlink_dl_reload_act_stats_free(struct devlink_dl_reload_act_stats *obj)
+void devlink_dl_dpipe_action_free(struct devlink_dl_dpipe_action *obj)
+{
+}
+
+int devlink_dl_dpipe_action_parse(struct ynl_parse_arg *yarg,
+				  const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_action *dst = yarg->data;
+	const struct nlattr *attr;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_ACTION_TYPE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_action_type = 1;
+			dst->dpipe_action_type = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_id = 1;
+			dst->dpipe_header_id = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_global = 1;
+			dst->dpipe_header_global = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_index = 1;
+			dst->dpipe_header_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_field_id = 1;
+			dst->dpipe_field_id = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_action_value_free(struct devlink_dl_dpipe_action_value *obj)
 {
 	unsigned int i;
 
-	for (i = 0; i < obj->n_reload_stats_entry; i++)
-		devlink_dl_reload_stats_entry_free(&obj->reload_stats_entry[i]);
-	free(obj->reload_stats_entry);
+	for (i = 0; i < obj->n_dpipe_action; i++)
+		devlink_dl_dpipe_action_free(&obj->dpipe_action[i]);
+	free(obj->dpipe_action);
+	free(obj->dpipe_value);
+	free(obj->dpipe_value_mask);
 }
 
-int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg,
-				      const struct nlattr *nested)
+int devlink_dl_dpipe_action_value_parse(struct ynl_parse_arg *yarg,
+					const struct nlattr *nested)
 {
-	struct devlink_dl_reload_act_stats *dst = yarg->data;
-	unsigned int n_reload_stats_entry = 0;
+	struct devlink_dl_dpipe_action_value *dst = yarg->data;
+	unsigned int n_dpipe_action = 0;
 	const struct nlattr *attr;
 	struct ynl_parse_arg parg;
 	int i;
 
 	parg.ys = yarg->ys;
 
-	if (dst->reload_stats_entry)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-stats.reload-stats-entry)");
+	if (dst->dpipe_action)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-action-value.dpipe-action)");
 
 	mnl_attr_for_each_nested(attr, nested) {
 		unsigned int type = mnl_attr_get_type(attr);
 
-		if (type == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
-			n_reload_stats_entry++;
+		if (type == DEVLINK_ATTR_DPIPE_ACTION) {
+			n_dpipe_action++;
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.dpipe_value_len = len;
+			dst->dpipe_value = malloc(len);
+			memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len);
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.dpipe_value_mask_len = len;
+			dst->dpipe_value_mask = malloc(len);
+			memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len);
+		} else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_value_mapping = 1;
+			dst->dpipe_value_mapping = mnl_attr_get_u32(attr);
 		}
 	}
 
-	if (n_reload_stats_entry) {
-		dst->reload_stats_entry = calloc(n_reload_stats_entry, sizeof(*dst->reload_stats_entry));
-		dst->n_reload_stats_entry = n_reload_stats_entry;
+	if (n_dpipe_action) {
+		dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action));
+		dst->n_dpipe_action = n_dpipe_action;
 		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_stats_entry_nest;
+		parg.rsp_policy = &devlink_dl_dpipe_action_nest;
 		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
-				parg.data = &dst->reload_stats_entry[i];
-				if (devlink_dl_reload_stats_entry_parse(&parg, attr))
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) {
+				parg.data = &dst->dpipe_action[i];
+				if (devlink_dl_dpipe_action_parse(&parg, attr))
 					return MNL_CB_ERROR;
 				i++;
 			}
@@ -273,172 +949,2645 @@ int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg,
 	return 0;
 }
 
-void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj)
+void devlink_dl_dpipe_field_free(struct devlink_dl_dpipe_field *obj)
 {
-	unsigned int i;
-
-	for (i = 0; i < obj->n_reload_action_stats; i++)
-		devlink_dl_reload_act_stats_free(&obj->reload_action_stats[i]);
-	free(obj->reload_action_stats);
+	free(obj->dpipe_field_name);
 }
 
-int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg,
-				     const struct nlattr *nested)
+int devlink_dl_dpipe_field_parse(struct ynl_parse_arg *yarg,
+				 const struct nlattr *nested)
 {
-	struct devlink_dl_reload_act_info *dst = yarg->data;
-	unsigned int n_reload_action_stats = 0;
+	struct devlink_dl_dpipe_field *dst = yarg->data;
 	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
-
-	parg.ys = yarg->ys;
-
-	if (dst->reload_action_stats)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-info.reload-action-stats)");
 
 	mnl_attr_for_each_nested(attr, nested) {
 		unsigned int type = mnl_attr_get_type(attr);
 
-		if (type == DEVLINK_ATTR_RELOAD_ACTION) {
+		if (type == DEVLINK_ATTR_DPIPE_FIELD_NAME) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.reload_action = 1;
-			dst->reload_action = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
-			n_reload_action_stats++;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dpipe_field_name_len = len;
+			dst->dpipe_field_name = malloc(len + 1);
+			memcpy(dst->dpipe_field_name, mnl_attr_get_str(attr), len);
+			dst->dpipe_field_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_field_id = 1;
+			dst->dpipe_field_id = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_field_bitwidth = 1;
+			dst->dpipe_field_bitwidth = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_field_mapping_type = 1;
+			dst->dpipe_field_mapping_type = mnl_attr_get_u32(attr);
 		}
 	}
 
-	if (n_reload_action_stats) {
-		dst->reload_action_stats = calloc(n_reload_action_stats, sizeof(*dst->reload_action_stats));
-		dst->n_reload_action_stats = n_reload_action_stats;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_act_stats_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
-				parg.data = &dst->reload_action_stats[i];
-				if (devlink_dl_reload_act_stats_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
+	return 0;
+}
+
+void devlink_dl_resource_free(struct devlink_dl_resource *obj)
+{
+	free(obj->resource_name);
+}
+
+int devlink_dl_resource_parse(struct ynl_parse_arg *yarg,
+			      const struct nlattr *nested)
+{
+	struct devlink_dl_resource *dst = yarg->data;
+	const struct nlattr *attr;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RESOURCE_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.resource_name_len = len;
+			dst->resource_name = malloc(len + 1);
+			memcpy(dst->resource_name, mnl_attr_get_str(attr), len);
+			dst->resource_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_RESOURCE_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_id = 1;
+			dst->resource_id = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size = 1;
+			dst->resource_size = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_NEW) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size_new = 1;
+			dst->resource_size_new = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_VALID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size_valid = 1;
+			dst->resource_size_valid = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MIN) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size_min = 1;
+			dst->resource_size_min = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MAX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size_max = 1;
+			dst->resource_size_max = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_SIZE_GRAN) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_size_gran = 1;
+			dst->resource_size_gran = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_UNIT) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_unit = 1;
+			dst->resource_unit = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_RESOURCE_OCC) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.resource_occ = 1;
+			dst->resource_occ = mnl_attr_get_u64(attr);
 		}
 	}
 
 	return 0;
 }
 
-void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj)
+void devlink_dl_info_version_free(struct devlink_dl_info_version *obj)
 {
-	unsigned int i;
-
-	for (i = 0; i < obj->n_reload_action_info; i++)
-		devlink_dl_reload_act_info_free(&obj->reload_action_info[i]);
-	free(obj->reload_action_info);
+	free(obj->info_version_name);
+	free(obj->info_version_value);
 }
 
-int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg,
+int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg,
 				  const struct nlattr *nested)
 {
-	struct devlink_dl_reload_stats *dst = yarg->data;
-	unsigned int n_reload_action_info = 0;
+	struct devlink_dl_info_version *dst = yarg->data;
 	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
-	int i;
 
-	parg.ys = yarg->ys;
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
 
-	if (dst->reload_action_info)
-		return ynl_error_parse(yarg, "attribute already present (dl-reload-stats.reload-action-info)");
+		if (type == DEVLINK_ATTR_INFO_VERSION_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.info_version_name_len = len;
+			dst->info_version_name = malloc(len + 1);
+			memcpy(dst->info_version_name, mnl_attr_get_str(attr), len);
+			dst->info_version_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_INFO_VERSION_VALUE) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.info_version_value_len = len;
+			dst->info_version_value = malloc(len + 1);
+			memcpy(dst->info_version_value, mnl_attr_get_str(attr), len);
+			dst->info_version_value[len] = 0;
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_fmsg_free(struct devlink_dl_fmsg *obj)
+{
+	free(obj->fmsg_obj_name);
+}
+
+int devlink_dl_fmsg_parse(struct ynl_parse_arg *yarg,
+			  const struct nlattr *nested)
+{
+	struct devlink_dl_fmsg *dst = yarg->data;
+	const struct nlattr *attr;
 
 	mnl_attr_for_each_nested(attr, nested) {
 		unsigned int type = mnl_attr_get_type(attr);
 
-		if (type == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
-			n_reload_action_info++;
+		if (type == DEVLINK_ATTR_FMSG_OBJ_NEST_START) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.fmsg_obj_nest_start = 1;
+		} else if (type == DEVLINK_ATTR_FMSG_PAIR_NEST_START) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.fmsg_pair_nest_start = 1;
+		} else if (type == DEVLINK_ATTR_FMSG_ARR_NEST_START) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.fmsg_arr_nest_start = 1;
+		} else if (type == DEVLINK_ATTR_FMSG_NEST_END) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.fmsg_nest_end = 1;
+		} else if (type == DEVLINK_ATTR_FMSG_OBJ_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.fmsg_obj_name_len = len;
+			dst->fmsg_obj_name = malloc(len + 1);
+			memcpy(dst->fmsg_obj_name, mnl_attr_get_str(attr), len);
+			dst->fmsg_obj_name[len] = 0;
 		}
 	}
 
-	if (n_reload_action_info) {
-		dst->reload_action_info = calloc(n_reload_action_info, sizeof(*dst->reload_action_info));
-		dst->n_reload_action_info = n_reload_action_info;
-		i = 0;
-		parg.rsp_policy = &devlink_dl_reload_act_info_nest;
-		mnl_attr_for_each_nested(attr, nested) {
-			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
-				parg.data = &dst->reload_action_info[i];
-				if (devlink_dl_reload_act_info_parse(&parg, attr))
-					return MNL_CB_ERROR;
-				i++;
-			}
+	return 0;
+}
+
+void devlink_dl_port_function_free(struct devlink_dl_port_function *obj)
+{
+	free(obj->hw_addr);
+}
+
+int devlink_dl_port_function_put(struct nlmsghdr *nlh, unsigned int attr_type,
+				 struct devlink_dl_port_function *obj)
+{
+	struct nlattr *nest;
+
+	nest = mnl_attr_nest_start(nlh, attr_type);
+	if (obj->_present.hw_addr_len)
+		mnl_attr_put(nlh, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, obj->_present.hw_addr_len, obj->hw_addr);
+	if (obj->_present.state)
+		mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_STATE, obj->state);
+	if (obj->_present.opstate)
+		mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_OPSTATE, obj->opstate);
+	if (obj->_present.caps)
+		mnl_attr_put(nlh, DEVLINK_PORT_FN_ATTR_CAPS, sizeof(struct nla_bitfield32), &obj->caps);
+	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
+}
+
+void
+devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj)
+{
+}
+
+int devlink_dl_reload_stats_entry_parse(struct ynl_parse_arg *yarg,
+					const struct nlattr *nested)
+{
+	struct devlink_dl_reload_stats_entry *dst = yarg->data;
+	const struct nlattr *attr;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RELOAD_STATS_LIMIT) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.reload_stats_limit = 1;
+			dst->reload_stats_limit = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_RELOAD_STATS_VALUE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.reload_stats_value = 1;
+			dst->reload_stats_value = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_reload_act_stats_free(struct devlink_dl_reload_act_stats *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_reload_stats_entry; i++)
+		devlink_dl_reload_stats_entry_free(&obj->reload_stats_entry[i]);
+	free(obj->reload_stats_entry);
+}
+
+int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg,
+				      const struct nlattr *nested)
+{
+	struct devlink_dl_reload_act_stats *dst = yarg->data;
+	unsigned int n_reload_stats_entry = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->reload_stats_entry)
+		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-stats.reload-stats-entry)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
+			n_reload_stats_entry++;
+		}
+	}
+
+	if (n_reload_stats_entry) {
+		dst->reload_stats_entry = calloc(n_reload_stats_entry, sizeof(*dst->reload_stats_entry));
+		dst->n_reload_stats_entry = n_reload_stats_entry;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_reload_stats_entry_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_STATS_ENTRY) {
+				parg.data = &dst->reload_stats_entry[i];
+				if (devlink_dl_reload_stats_entry_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_selftest_id_free(struct devlink_dl_selftest_id *obj)
+{
+}
+
+int devlink_dl_selftest_id_put(struct nlmsghdr *nlh, unsigned int attr_type,
+			       struct devlink_dl_selftest_id *obj)
+{
+	struct nlattr *nest;
+
+	nest = mnl_attr_nest_start(nlh, attr_type);
+	if (obj->_present.flash)
+		mnl_attr_put(nlh, DEVLINK_ATTR_SELFTEST_ID_FLASH, 0, NULL);
+	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_table_matches_free(struct devlink_dl_dpipe_table_matches *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_match; i++)
+		devlink_dl_dpipe_match_free(&obj->dpipe_match[i]);
+	free(obj->dpipe_match);
+}
+
+int devlink_dl_dpipe_table_matches_parse(struct ynl_parse_arg *yarg,
+					 const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_table_matches *dst = yarg->data;
+	unsigned int n_dpipe_match = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_match)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-matches.dpipe-match)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_MATCH) {
+			n_dpipe_match++;
+		}
+	}
+
+	if (n_dpipe_match) {
+		dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match));
+		dst->n_dpipe_match = n_dpipe_match;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_match_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) {
+				parg.data = &dst->dpipe_match[i];
+				if (devlink_dl_dpipe_match_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_table_actions_free(struct devlink_dl_dpipe_table_actions *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_action; i++)
+		devlink_dl_dpipe_action_free(&obj->dpipe_action[i]);
+	free(obj->dpipe_action);
+}
+
+int devlink_dl_dpipe_table_actions_parse(struct ynl_parse_arg *yarg,
+					 const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_table_actions *dst = yarg->data;
+	unsigned int n_dpipe_action = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_action)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-actions.dpipe-action)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_ACTION) {
+			n_dpipe_action++;
+		}
+	}
+
+	if (n_dpipe_action) {
+		dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action));
+		dst->n_dpipe_action = n_dpipe_action;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_action_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) {
+				parg.data = &dst->dpipe_action[i];
+				if (devlink_dl_dpipe_action_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_entry_match_values_free(struct devlink_dl_dpipe_entry_match_values *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_match_value; i++)
+		devlink_dl_dpipe_match_value_free(&obj->dpipe_match_value[i]);
+	free(obj->dpipe_match_value);
+}
+
+int devlink_dl_dpipe_entry_match_values_parse(struct ynl_parse_arg *yarg,
+					      const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_entry_match_values *dst = yarg->data;
+	unsigned int n_dpipe_match_value = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_match_value)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-match-values.dpipe-match-value)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_MATCH_VALUE) {
+			n_dpipe_match_value++;
+		}
+	}
+
+	if (n_dpipe_match_value) {
+		dst->dpipe_match_value = calloc(n_dpipe_match_value, sizeof(*dst->dpipe_match_value));
+		dst->n_dpipe_match_value = n_dpipe_match_value;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_match_value_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH_VALUE) {
+				parg.data = &dst->dpipe_match_value[i];
+				if (devlink_dl_dpipe_match_value_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_entry_action_values_free(struct devlink_dl_dpipe_entry_action_values *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_action_value; i++)
+		devlink_dl_dpipe_action_value_free(&obj->dpipe_action_value[i]);
+	free(obj->dpipe_action_value);
+}
+
+int devlink_dl_dpipe_entry_action_values_parse(struct ynl_parse_arg *yarg,
+					       const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_entry_action_values *dst = yarg->data;
+	unsigned int n_dpipe_action_value = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_action_value)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-action-values.dpipe-action-value)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_ACTION_VALUE) {
+			n_dpipe_action_value++;
+		}
+	}
+
+	if (n_dpipe_action_value) {
+		dst->dpipe_action_value = calloc(n_dpipe_action_value, sizeof(*dst->dpipe_action_value));
+		dst->n_dpipe_action_value = n_dpipe_action_value;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_action_value_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION_VALUE) {
+				parg.data = &dst->dpipe_action_value[i];
+				if (devlink_dl_dpipe_action_value_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void
+devlink_dl_dpipe_header_fields_free(struct devlink_dl_dpipe_header_fields *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_field; i++)
+		devlink_dl_dpipe_field_free(&obj->dpipe_field[i]);
+	free(obj->dpipe_field);
+}
+
+int devlink_dl_dpipe_header_fields_parse(struct ynl_parse_arg *yarg,
+					 const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_header_fields *dst = yarg->data;
+	unsigned int n_dpipe_field = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_field)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-header-fields.dpipe-field)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_FIELD) {
+			n_dpipe_field++;
+		}
+	}
+
+	if (n_dpipe_field) {
+		dst->dpipe_field = calloc(n_dpipe_field, sizeof(*dst->dpipe_field));
+		dst->n_dpipe_field = n_dpipe_field;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_field_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_FIELD) {
+				parg.data = &dst->dpipe_field[i];
+				if (devlink_dl_dpipe_field_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_resource_list_free(struct devlink_dl_resource_list *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_resource; i++)
+		devlink_dl_resource_free(&obj->resource[i]);
+	free(obj->resource);
+}
+
+int devlink_dl_resource_list_parse(struct ynl_parse_arg *yarg,
+				   const struct nlattr *nested)
+{
+	struct devlink_dl_resource_list *dst = yarg->data;
+	unsigned int n_resource = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->resource)
+		return ynl_error_parse(yarg, "attribute already present (dl-resource-list.resource)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RESOURCE) {
+			n_resource++;
+		}
+	}
+
+	if (n_resource) {
+		dst->resource = calloc(n_resource, sizeof(*dst->resource));
+		dst->n_resource = n_resource;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_resource_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RESOURCE) {
+				parg.data = &dst->resource[i];
+				if (devlink_dl_resource_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_reload_action_stats; i++)
+		devlink_dl_reload_act_stats_free(&obj->reload_action_stats[i]);
+	free(obj->reload_action_stats);
+}
+
+int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg,
+				     const struct nlattr *nested)
+{
+	struct devlink_dl_reload_act_info *dst = yarg->data;
+	unsigned int n_reload_action_stats = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->reload_action_stats)
+		return ynl_error_parse(yarg, "attribute already present (dl-reload-act-info.reload-action-stats)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RELOAD_ACTION) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.reload_action = 1;
+			dst->reload_action = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
+			n_reload_action_stats++;
+		}
+	}
+
+	if (n_reload_action_stats) {
+		dst->reload_action_stats = calloc(n_reload_action_stats, sizeof(*dst->reload_action_stats));
+		dst->n_reload_action_stats = n_reload_action_stats;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_reload_act_stats_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_STATS) {
+				parg.data = &dst->reload_action_stats[i];
+				if (devlink_dl_reload_act_stats_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_table_free(struct devlink_dl_dpipe_table *obj)
+{
+	free(obj->dpipe_table_name);
+	devlink_dl_dpipe_table_matches_free(&obj->dpipe_table_matches);
+	devlink_dl_dpipe_table_actions_free(&obj->dpipe_table_actions);
+}
+
+int devlink_dl_dpipe_table_parse(struct ynl_parse_arg *yarg,
+				 const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_table *dst = yarg->data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_TABLE_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dpipe_table_name_len = len;
+			dst->dpipe_table_name = malloc(len + 1);
+			memcpy(dst->dpipe_table_name, mnl_attr_get_str(attr), len);
+			dst->dpipe_table_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_SIZE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_size = 1;
+			dst->dpipe_table_size = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_MATCHES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_matches = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_table_matches_nest;
+			parg.data = &dst->dpipe_table_matches;
+			if (devlink_dl_dpipe_table_matches_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_ACTIONS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_actions = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_table_actions_nest;
+			parg.data = &dst->dpipe_table_actions;
+			if (devlink_dl_dpipe_table_actions_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_counters_enabled = 1;
+			dst->dpipe_table_counters_enabled = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_resource_id = 1;
+			dst->dpipe_table_resource_id = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_table_resource_units = 1;
+			dst->dpipe_table_resource_units = mnl_attr_get_u64(attr);
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_entry_free(struct devlink_dl_dpipe_entry *obj)
+{
+	devlink_dl_dpipe_entry_match_values_free(&obj->dpipe_entry_match_values);
+	devlink_dl_dpipe_entry_action_values_free(&obj->dpipe_entry_action_values);
+}
+
+int devlink_dl_dpipe_entry_parse(struct ynl_parse_arg *yarg,
+				 const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_entry *dst = yarg->data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_ENTRY_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_entry_index = 1;
+			dst->dpipe_entry_index = mnl_attr_get_u64(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_entry_match_values = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_entry_match_values_nest;
+			parg.data = &dst->dpipe_entry_match_values;
+			if (devlink_dl_dpipe_entry_match_values_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_entry_action_values = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_entry_action_values_nest;
+			parg.data = &dst->dpipe_entry_action_values;
+			if (devlink_dl_dpipe_entry_action_values_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		} else if (type == DEVLINK_ATTR_DPIPE_ENTRY_COUNTER) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_entry_counter = 1;
+			dst->dpipe_entry_counter = mnl_attr_get_u64(attr);
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_header_free(struct devlink_dl_dpipe_header *obj)
+{
+	free(obj->dpipe_header_name);
+	devlink_dl_dpipe_header_fields_free(&obj->dpipe_header_fields);
+}
+
+int devlink_dl_dpipe_header_parse(struct ynl_parse_arg *yarg,
+				  const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_header *dst = yarg->data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_HEADER_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dpipe_header_name_len = len;
+			dst->dpipe_header_name = malloc(len + 1);
+			memcpy(dst->dpipe_header_name, mnl_attr_get_str(attr), len);
+			dst->dpipe_header_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_id = 1;
+			dst->dpipe_header_id = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_global = 1;
+			dst->dpipe_header_global = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADER_FIELDS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_header_fields = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_header_fields_nest;
+			parg.data = &dst->dpipe_header_fields;
+			if (devlink_dl_dpipe_header_fields_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_reload_action_info; i++)
+		devlink_dl_reload_act_info_free(&obj->reload_action_info[i]);
+	free(obj->reload_action_info);
+}
+
+int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg,
+				  const struct nlattr *nested)
+{
+	struct devlink_dl_reload_stats *dst = yarg->data;
+	unsigned int n_reload_action_info = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->reload_action_info)
+		return ynl_error_parse(yarg, "attribute already present (dl-reload-stats.reload-action-info)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
+			n_reload_action_info++;
+		}
+	}
+
+	if (n_reload_action_info) {
+		dst->reload_action_info = calloc(n_reload_action_info, sizeof(*dst->reload_action_info));
+		dst->n_reload_action_info = n_reload_action_info;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_reload_act_info_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_INFO) {
+				parg.data = &dst->reload_action_info[i];
+				if (devlink_dl_reload_act_info_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_tables_free(struct devlink_dl_dpipe_tables *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_table; i++)
+		devlink_dl_dpipe_table_free(&obj->dpipe_table[i]);
+	free(obj->dpipe_table);
+}
+
+int devlink_dl_dpipe_tables_parse(struct ynl_parse_arg *yarg,
+				  const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_tables *dst = yarg->data;
+	unsigned int n_dpipe_table = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_table)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-tables.dpipe-table)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_TABLE) {
+			n_dpipe_table++;
+		}
+	}
+
+	if (n_dpipe_table) {
+		dst->dpipe_table = calloc(n_dpipe_table, sizeof(*dst->dpipe_table));
+		dst->n_dpipe_table = n_dpipe_table;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_table_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_TABLE) {
+				parg.data = &dst->dpipe_table[i];
+				if (devlink_dl_dpipe_table_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_entries_free(struct devlink_dl_dpipe_entries *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_entry; i++)
+		devlink_dl_dpipe_entry_free(&obj->dpipe_entry[i]);
+	free(obj->dpipe_entry);
+}
+
+int devlink_dl_dpipe_entries_parse(struct ynl_parse_arg *yarg,
+				   const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_entries *dst = yarg->data;
+	unsigned int n_dpipe_entry = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_entry)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entries.dpipe-entry)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_ENTRY) {
+			n_dpipe_entry++;
+		}
+	}
+
+	if (n_dpipe_entry) {
+		dst->dpipe_entry = calloc(n_dpipe_entry, sizeof(*dst->dpipe_entry));
+		dst->n_dpipe_entry = n_dpipe_entry;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_entry_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ENTRY) {
+				parg.data = &dst->dpipe_entry[i];
+				if (devlink_dl_dpipe_entry_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dpipe_headers_free(struct devlink_dl_dpipe_headers *obj)
+{
+	unsigned int i;
+
+	for (i = 0; i < obj->n_dpipe_header; i++)
+		devlink_dl_dpipe_header_free(&obj->dpipe_header[i]);
+	free(obj->dpipe_header);
+}
+
+int devlink_dl_dpipe_headers_parse(struct ynl_parse_arg *yarg,
+				   const struct nlattr *nested)
+{
+	struct devlink_dl_dpipe_headers *dst = yarg->data;
+	unsigned int n_dpipe_header = 0;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+	int i;
+
+	parg.ys = yarg->ys;
+
+	if (dst->dpipe_header)
+		return ynl_error_parse(yarg, "attribute already present (dl-dpipe-headers.dpipe-header)");
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_DPIPE_HEADER) {
+			n_dpipe_header++;
+		}
+	}
+
+	if (n_dpipe_header) {
+		dst->dpipe_header = calloc(n_dpipe_header, sizeof(*dst->dpipe_header));
+		dst->n_dpipe_header = n_dpipe_header;
+		i = 0;
+		parg.rsp_policy = &devlink_dl_dpipe_header_nest;
+		mnl_attr_for_each_nested(attr, nested) {
+			if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_HEADER) {
+				parg.data = &dst->dpipe_header[i];
+				if (devlink_dl_dpipe_header_parse(&parg, attr))
+					return MNL_CB_ERROR;
+				i++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj)
+{
+	devlink_dl_reload_stats_free(&obj->reload_stats);
+	devlink_dl_reload_stats_free(&obj->remote_reload_stats);
+}
+
+int devlink_dl_dev_stats_parse(struct ynl_parse_arg *yarg,
+			       const struct nlattr *nested)
+{
+	struct devlink_dl_dev_stats *dst = yarg->data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each_nested(attr, nested) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_RELOAD_STATS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.reload_stats = 1;
+
+			parg.rsp_policy = &devlink_dl_reload_stats_nest;
+			parg.data = &dst->reload_stats;
+			if (devlink_dl_reload_stats_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		} else if (type == DEVLINK_ATTR_REMOTE_RELOAD_STATS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.remote_reload_stats = 1;
+
+			parg.rsp_policy = &devlink_dl_reload_stats_nest;
+			parg.data = &dst->remote_reload_stats;
+			if (devlink_dl_reload_stats_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		}
+	}
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_GET ============== */
+/* DEVLINK_CMD_GET - do */
+void devlink_get_req_free(struct devlink_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_get_rsp_free(struct devlink_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	devlink_dl_dev_stats_free(&rsp->dev_stats);
+	free(rsp);
+}
+
+int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_get_rsp *dst;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	dst = yarg->data;
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_RELOAD_FAILED) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.reload_failed = 1;
+			dst->reload_failed = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_DEV_STATS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dev_stats = 1;
+
+			parg.rsp_policy = &devlink_dl_dev_stats_nest;
+			parg.data = &dst->dev_stats;
+			if (devlink_dl_dev_stats_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_get_rsp *
+devlink_get(struct ynl_sock *ys, struct devlink_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_get_rsp_parse;
+	yrs.rsp_cmd = 3;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_GET - dump */
+void devlink_get_list_free(struct devlink_get_list *rsp)
+{
+	struct devlink_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		devlink_dl_dev_stats_free(&rsp->obj.dev_stats);
+		free(rsp);
+	}
+}
+
+struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_get_list);
+	yds.cb = devlink_get_rsp_parse;
+	yds.rsp_cmd = 3;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_GET, 1);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_PORT_GET ============== */
+/* DEVLINK_CMD_PORT_GET - do */
+void devlink_port_get_req_free(struct devlink_port_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_port_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_port_get_rsp *
+devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_port_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_port_get_rsp_parse;
+	yrs.rsp_cmd = 7;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_port_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_PORT_GET - dump */
+int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_port_get_rsp_dump *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp)
+{
+	struct devlink_port_get_rsp_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_port_get_rsp_list *
+devlink_port_get_dump(struct ynl_sock *ys,
+		      struct devlink_port_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list);
+	yds.cb = devlink_port_get_rsp_dump_parse;
+	yds.rsp_cmd = 7;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_port_get_rsp_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_PORT_SET ============== */
+/* DEVLINK_CMD_PORT_SET - do */
+void devlink_port_set_req_free(struct devlink_port_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	devlink_dl_port_function_free(&req->port_function);
+	free(req);
+}
+
+int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.port_type)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_TYPE, req->port_type);
+	if (req->_present.port_function)
+		devlink_dl_port_function_put(nlh, DEVLINK_ATTR_PORT_FUNCTION, &req->port_function);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_PORT_NEW ============== */
+/* DEVLINK_CMD_PORT_NEW - do */
+void devlink_port_new_req_free(struct devlink_port_new_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_port_new_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_port_new_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_port_new_rsp *
+devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_port_new_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_NEW, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.port_flavour)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_FLAVOUR, req->port_flavour);
+	if (req->_present.port_pci_pf_number)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, req->port_pci_pf_number);
+	if (req->_present.port_pci_sf_number)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, req->port_pci_sf_number);
+	if (req->_present.port_controller_number)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, req->port_controller_number);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_port_new_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_PORT_NEW;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_port_new_rsp_free(rsp);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_PORT_DEL ============== */
+/* DEVLINK_CMD_PORT_DEL - do */
+void devlink_port_del_req_free(struct devlink_port_del_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_DEL, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_PORT_SPLIT ============== */
+/* DEVLINK_CMD_PORT_SPLIT - do */
+void devlink_port_split_req_free(struct devlink_port_split_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SPLIT, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.port_split_count)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_SPLIT_COUNT, req->port_split_count);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */
+/* DEVLINK_CMD_PORT_UNSPLIT - do */
+void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_port_unsplit(struct ynl_sock *ys,
+			 struct devlink_port_unsplit_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_UNSPLIT, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_SB_GET ============== */
+/* DEVLINK_CMD_SB_GET - do */
+void devlink_sb_get_req_free(struct devlink_sb_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct devlink_sb_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_get_rsp *
+devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_get_rsp_parse;
+	yrs.rsp_cmd = 13;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_GET - dump */
+void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp)
+{
+	struct devlink_sb_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_get_list *
+devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_get_list);
+	yds.cb = devlink_sb_get_rsp_parse;
+	yds.rsp_cmd = 13;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
+/* DEVLINK_CMD_SB_POOL_GET - do */
+void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_sb_pool_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_index = 1;
+			dst->sb_pool_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_pool_get_rsp *
+devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_pool_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_pool_get_rsp_parse;
+	yrs.rsp_cmd = 17;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_pool_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_POOL_GET - dump */
+void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
+{
+	struct devlink_sb_pool_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_pool_get_list *
+devlink_sb_pool_get_dump(struct ynl_sock *ys,
+			 struct devlink_sb_pool_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list);
+	yds.cb = devlink_sb_pool_get_rsp_parse;
+	yds.rsp_cmd = 17;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_pool_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_POOL_SET ============== */
+/* DEVLINK_CMD_SB_POOL_SET - do */
+void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_sb_pool_set(struct ynl_sock *ys,
+			struct devlink_sb_pool_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+	if (req->_present.sb_pool_threshold_type)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, req->sb_pool_threshold_type);
+	if (req->_present.sb_pool_size)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_POOL_SIZE, req->sb_pool_size);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
+void
+devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void
+devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_sb_port_pool_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_index = 1;
+			dst->sb_pool_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_port_pool_get_rsp *
+devlink_sb_port_pool_get(struct ynl_sock *ys,
+			 struct devlink_sb_port_pool_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_port_pool_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_port_pool_get_rsp_parse;
+	yrs.rsp_cmd = 21;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_port_pool_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+void
+devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
+{
+	struct devlink_sb_port_pool_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_port_pool_get_list *
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
+			      struct devlink_sb_port_pool_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list);
+	yds.cb = devlink_sb_port_pool_get_rsp_parse;
+	yds.rsp_cmd = 21;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_port_pool_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_SET - do */
+void
+devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_sb_port_pool_set(struct ynl_sock *ys,
+			     struct devlink_sb_port_pool_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+	if (req->_present.sb_threshold)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
+void
+devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void
+devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh,
+					  void *data)
+{
+	struct devlink_sb_tc_pool_bind_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_index = 1;
+			dst->sb_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_SB_POOL_TYPE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_pool_type = 1;
+			dst->sb_pool_type = mnl_attr_get_u8(attr);
+		} else if (type == DEVLINK_ATTR_SB_TC_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sb_tc_index = 1;
+			dst->sb_tc_index = mnl_attr_get_u16(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct devlink_sb_tc_pool_bind_get_rsp *
+devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
+			    struct devlink_sb_tc_pool_bind_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_sb_tc_pool_bind_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_type)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
+	if (req->_present.sb_tc_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
+	yrs.rsp_cmd = 25;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_sb_tc_pool_bind_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+void
+devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp)
+{
+	struct devlink_sb_tc_pool_bind_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp);
+	}
+}
+
+struct devlink_sb_tc_pool_bind_get_list *
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
+				 struct devlink_sb_tc_pool_bind_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list);
+	yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
+	yds.rsp_cmd = 25;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_sb_tc_pool_bind_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */
+void
+devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
+				struct devlink_sb_tc_pool_bind_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.sb_pool_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+	if (req->_present.sb_pool_type)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
+	if (req->_present.sb_tc_index)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
+	if (req->_present.sb_threshold)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */
+/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */
+void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_sb_occ_snapshot(struct ynl_sock *ys,
+			    struct devlink_sb_occ_snapshot_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_SNAPSHOT, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */
+/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */
+void
+devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_sb_occ_max_clear(struct ynl_sock *ys,
+			     struct devlink_sb_occ_max_clear_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_MAX_CLEAR, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.sb_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_ESWITCH_GET ============== */
+/* DEVLINK_CMD_ESWITCH_GET - do */
+void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	free(rsp);
+}
+
+int devlink_eswitch_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_eswitch_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_ESWITCH_MODE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.eswitch_mode = 1;
+			dst->eswitch_mode = mnl_attr_get_u16(attr);
+		} else if (type == DEVLINK_ATTR_ESWITCH_INLINE_MODE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.eswitch_inline_mode = 1;
+			dst->eswitch_inline_mode = mnl_attr_get_u16(attr);
+		} else if (type == DEVLINK_ATTR_ESWITCH_ENCAP_MODE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.eswitch_encap_mode = 1;
+			dst->eswitch_encap_mode = mnl_attr_get_u8(attr);
 		}
 	}
 
-	return 0;
+	return MNL_CB_OK;
 }
 
-void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj)
+struct devlink_eswitch_get_rsp *
+devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req)
 {
-	devlink_dl_reload_stats_free(&obj->reload_stats);
-	devlink_dl_reload_stats_free(&obj->remote_reload_stats);
-}
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_eswitch_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
 
-int devlink_dl_dev_stats_parse(struct ynl_parse_arg *yarg,
-			       const struct nlattr *nested)
-{
-	struct devlink_dl_dev_stats *dst = yarg->data;
-	const struct nlattr *attr;
-	struct ynl_parse_arg parg;
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
 
-	parg.ys = yarg->ys;
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
-	mnl_attr_for_each_nested(attr, nested) {
-		unsigned int type = mnl_attr_get_type(attr);
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_eswitch_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_ESWITCH_GET;
 
-		if (type == DEVLINK_ATTR_RELOAD_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.reload_stats = 1;
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
 
-			parg.rsp_policy = &devlink_dl_reload_stats_nest;
-			parg.data = &dst->reload_stats;
-			if (devlink_dl_reload_stats_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		} else if (type == DEVLINK_ATTR_REMOTE_RELOAD_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.remote_reload_stats = 1;
+	return rsp;
 
-			parg.rsp_policy = &devlink_dl_reload_stats_nest;
-			parg.data = &dst->remote_reload_stats;
-			if (devlink_dl_reload_stats_parse(&parg, attr))
-				return MNL_CB_ERROR;
-		}
-	}
+err_free:
+	devlink_eswitch_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_ESWITCH_SET ============== */
+/* DEVLINK_CMD_ESWITCH_SET - do */
+void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_eswitch_set(struct ynl_sock *ys,
+			struct devlink_eswitch_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.eswitch_mode)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_MODE, req->eswitch_mode);
+	if (req->_present.eswitch_inline_mode)
+		mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_INLINE_MODE, req->eswitch_inline_mode);
+	if (req->_present.eswitch_encap_mode)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, req->eswitch_encap_mode);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
 
 	return 0;
 }
 
-/* ============== DEVLINK_CMD_GET ============== */
-/* DEVLINK_CMD_GET - do */
-void devlink_get_req_free(struct devlink_get_req *req)
+/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */
+/* DEVLINK_CMD_DPIPE_TABLE_GET - do */
+void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
+	free(req->dpipe_table_name);
 	free(req);
 }
 
-void devlink_get_rsp_free(struct devlink_get_rsp *rsp)
+void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
-	devlink_dl_dev_stats_free(&rsp->dev_stats);
+	devlink_dl_dpipe_tables_free(&rsp->dpipe_tables);
 	free(rsp);
 }
 
-int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_dpipe_table_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
+	struct devlink_dpipe_table_get_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
-	struct devlink_get_rsp *dst;
 	const struct nlattr *attr;
 	struct ynl_parse_arg parg;
 
@@ -470,19 +3619,14 @@ int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_RELOAD_FAILED) {
+		} else if (type == DEVLINK_ATTR_DPIPE_TABLES) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.reload_failed = 1;
-			dst->reload_failed = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_DEV_STATS) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.dev_stats = 1;
+			dst->_present.dpipe_tables = 1;
 
-			parg.rsp_policy = &devlink_dl_dev_stats_nest;
-			parg.data = &dst->dev_stats;
-			if (devlink_dl_dev_stats_parse(&parg, attr))
+			parg.rsp_policy = &devlink_dl_dpipe_tables_nest;
+			parg.data = &dst->dpipe_tables;
+			if (devlink_dl_dpipe_tables_parse(&parg, attr))
 				return MNL_CB_ERROR;
 		}
 	}
@@ -490,15 +3634,16 @@ int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-struct devlink_get_rsp *
-devlink_get(struct ynl_sock *ys, struct devlink_get_req *req)
+struct devlink_dpipe_table_get_rsp *
+devlink_dpipe_table_get(struct ynl_sock *ys,
+			struct devlink_dpipe_table_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_get_rsp *rsp;
+	struct devlink_dpipe_table_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -506,11 +3651,13 @@ devlink_get(struct ynl_sock *ys, struct devlink_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.dpipe_table_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_get_rsp_parse;
-	yrs.rsp_cmd = 3;
+	yrs.cb = devlink_dpipe_table_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_TABLE_GET;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -519,74 +3666,144 @@ devlink_get(struct ynl_sock *ys, struct devlink_get_req *req)
 	return rsp;
 
 err_free:
-	devlink_get_rsp_free(rsp);
+	devlink_dpipe_table_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_GET - dump */
-void devlink_get_list_free(struct devlink_get_list *rsp)
+/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */
+/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */
+void
+devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req)
 {
-	struct devlink_get_list *next = rsp;
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->dpipe_table_name);
+	free(req);
+}
 
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
+void
+devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp)
+{
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	devlink_dl_dpipe_entries_free(&rsp->dpipe_entries);
+	free(rsp);
+}
 
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		devlink_dl_dev_stats_free(&rsp->obj.dev_stats);
-		free(rsp);
+int devlink_dpipe_entries_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_dpipe_entries_get_rsp *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	dst = yarg->data;
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_BUS_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.bus_name_len = len;
+			dst->bus_name = malloc(len + 1);
+			memcpy(dst->bus_name, mnl_attr_get_str(attr), len);
+			dst->bus_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DEV_NAME) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.dev_name_len = len;
+			dst->dev_name = malloc(len + 1);
+			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
+			dst->dev_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_DPIPE_ENTRIES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dpipe_entries = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_entries_nest;
+			parg.data = &dst->dpipe_entries;
+			if (devlink_dl_dpipe_entries_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		}
 	}
+
+	return MNL_CB_OK;
 }
 
-struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys)
+struct devlink_dpipe_entries_get_rsp *
+devlink_dpipe_entries_get(struct ynl_sock *ys,
+			  struct devlink_dpipe_entries_get_req *req)
 {
-	struct ynl_dump_state yds = {};
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_dpipe_entries_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_get_list);
-	yds.cb = devlink_get_rsp_parse;
-	yds.rsp_cmd = 3;
-	yds.rsp_policy = &devlink_nest;
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_ENTRIES_GET, 1);
+	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_GET, 1);
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.dpipe_table_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
 
-	err = ynl_exec_dump(ys, nlh, &yds);
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_dpipe_entries_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
-		goto free_list;
+		goto err_free;
 
-	return yds.first;
+	return rsp;
 
-free_list:
-	devlink_get_list_free(yds.first);
+err_free:
+	devlink_dpipe_entries_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_PORT_GET ============== */
-/* DEVLINK_CMD_PORT_GET - do */
-void devlink_port_get_req_free(struct devlink_port_get_req *req)
+/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */
+/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */
+void
+devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
 	free(req);
 }
 
-void devlink_port_get_rsp_free(struct devlink_port_get_rsp *rsp)
+void
+devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
+	devlink_dl_dpipe_headers_free(&rsp->dpipe_headers);
 	free(rsp);
 }
 
-int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_dpipe_headers_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
+	struct devlink_dpipe_headers_get_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
-	struct devlink_port_get_rsp *dst;
 	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
 
 	dst = yarg->data;
+	parg.ys = yarg->ys;
 
 	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
 		unsigned int type = mnl_attr_get_type(attr);
@@ -613,26 +3830,31 @@ int devlink_port_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+		} else if (type == DEVLINK_ATTR_DPIPE_HEADERS) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
+			dst->_present.dpipe_headers = 1;
+
+			parg.rsp_policy = &devlink_dl_dpipe_headers_nest;
+			parg.data = &dst->dpipe_headers;
+			if (devlink_dl_dpipe_headers_parse(&parg, attr))
+				return MNL_CB_ERROR;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_port_get_rsp *
-devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req)
+struct devlink_dpipe_headers_get_rsp *
+devlink_dpipe_headers_get(struct ynl_sock *ys,
+			  struct devlink_dpipe_headers_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_port_get_rsp *rsp;
+	struct devlink_dpipe_headers_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_HEADERS_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -640,33 +3862,119 @@ devlink_port_get(struct ynl_sock *ys, struct devlink_port_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_port_get_rsp_parse;
-	yrs.rsp_cmd = 7;
+	yrs.cb = devlink_dpipe_headers_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_DPIPE_HEADERS_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	devlink_dpipe_headers_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */
+/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */
+void
+devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->dpipe_table_name);
+	free(req);
+}
+
+int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
+				     struct devlink_dpipe_table_counters_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.dpipe_table_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name);
+	if (req->_present.dpipe_table_counters_enabled)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, req->dpipe_table_counters_enabled);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_RESOURCE_SET ============== */
+/* DEVLINK_CMD_RESOURCE_SET - do */
+void devlink_resource_set_req_free(struct devlink_resource_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_resource_set(struct ynl_sock *ys,
+			 struct devlink_resource_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.resource_id)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_ID, req->resource_id);
+	if (req->_present.resource_size)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_SIZE, req->resource_size);
 
-	err = ynl_exec(ys, nlh, &yrs);
+	err = ynl_exec(ys, nlh, NULL);
 	if (err < 0)
-		goto err_free;
+		return -1;
 
-	return rsp;
+	return 0;
+}
 
-err_free:
-	devlink_port_get_rsp_free(rsp);
-	return NULL;
+/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */
+/* DEVLINK_CMD_RESOURCE_DUMP - do */
+void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
 }
 
-/* DEVLINK_CMD_PORT_GET - dump */
-int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
+void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp)
 {
-	struct devlink_port_get_rsp_dump *dst;
+	free(rsp->bus_name);
+	free(rsp->dev_name);
+	devlink_dl_resource_list_free(&rsp->resource_list);
+	free(rsp);
+}
+
+int devlink_resource_dump_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct devlink_resource_dump_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
 
 	dst = yarg->data;
+	parg.ys = yarg->ys;
 
 	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
 		unsigned int type = mnl_attr_get_type(attr);
@@ -693,84 +4001,75 @@ int devlink_port_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+		} else if (type == DEVLINK_ATTR_RESOURCE_LIST) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.port_index = 1;
-			dst->port_index = mnl_attr_get_u32(attr);
+			dst->_present.resource_list = 1;
+
+			parg.rsp_policy = &devlink_dl_resource_list_nest;
+			parg.data = &dst->resource_list;
+			if (devlink_dl_resource_list_parse(&parg, attr))
+				return MNL_CB_ERROR;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp)
-{
-	struct devlink_port_get_rsp_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_port_get_rsp_list *
-devlink_port_get_dump(struct ynl_sock *ys,
-		      struct devlink_port_get_req_dump *req)
+struct devlink_resource_dump_rsp *
+devlink_resource_dump(struct ynl_sock *ys,
+		      struct devlink_resource_dump_req *req)
 {
-	struct ynl_dump_state yds = {};
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct devlink_resource_dump_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_port_get_rsp_list);
-	yds.cb = devlink_port_get_rsp_dump_parse;
-	yds.rsp_cmd = 7;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_DUMP, 1);
 	ys->req_policy = &devlink_nest;
+	yrs.yarg.rsp_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 
-	err = ynl_exec_dump(ys, nlh, &yds);
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = devlink_resource_dump_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_RESOURCE_DUMP;
+
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
-		goto free_list;
+		goto err_free;
 
-	return yds.first;
+	return rsp;
 
-free_list:
-	devlink_port_get_rsp_list_free(yds.first);
+err_free:
+	devlink_resource_dump_rsp_free(rsp);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_SB_GET ============== */
-/* DEVLINK_CMD_SB_GET - do */
-void devlink_sb_get_req_free(struct devlink_sb_get_req *req)
+/* ============== DEVLINK_CMD_RELOAD ============== */
+/* DEVLINK_CMD_RELOAD - do */
+void devlink_reload_req_free(struct devlink_reload_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
 	free(req);
 }
 
-void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp)
+void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
 	free(rsp);
 }
 
-int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_reload_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
 	struct ynl_parse_arg *yarg = data;
-	struct devlink_sb_get_rsp *dst;
+	struct devlink_reload_rsp *dst;
 	const struct nlattr *attr;
 
 	dst = yarg->data;
@@ -800,26 +4099,26 @@ int devlink_sb_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
+		} else if (type == DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
+			dst->_present.reload_actions_performed = 1;
+			memcpy(&dst->reload_actions_performed, mnl_attr_get_payload(attr), sizeof(struct nla_bitfield32));
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_sb_get_rsp *
-devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
+struct devlink_reload_rsp *
+devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_get_rsp *rsp;
+	struct devlink_reload_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RELOAD, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -827,13 +4126,21 @@ devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
+	if (req->_present.reload_action)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_RELOAD_ACTION, req->reload_action);
+	if (req->_present.reload_limits)
+		mnl_attr_put(nlh, DEVLINK_ATTR_RELOAD_LIMITS, sizeof(struct nla_bitfield32), &req->reload_limits);
+	if (req->_present.netns_pid)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_PID, req->netns_pid);
+	if (req->_present.netns_fd)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_FD, req->netns_fd);
+	if (req->_present.netns_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_ID, req->netns_id);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_get_rsp_parse;
-	yrs.rsp_cmd = 13;
+	yrs.cb = devlink_reload_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_RELOAD;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -842,76 +4149,31 @@ devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
 	return rsp;
 
 err_free:
-	devlink_sb_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_SB_GET - dump */
-void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp)
-{
-	struct devlink_sb_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
-}
-
-struct devlink_sb_get_list *
-devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req)
-{
-	struct ynl_dump_state yds = {};
-	struct nlmsghdr *nlh;
-	int err;
-
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_get_list);
-	yds.cb = devlink_sb_get_rsp_parse;
-	yds.rsp_cmd = 13;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
-	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_get_list_free(yds.first);
+	devlink_reload_rsp_free(rsp);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
-/* DEVLINK_CMD_SB_POOL_GET - do */
-void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req)
+/* ============== DEVLINK_CMD_PARAM_GET ============== */
+/* DEVLINK_CMD_PARAM_GET - do */
+void devlink_param_get_req_free(struct devlink_param_get_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
+	free(req->param_name);
 	free(req);
 }
 
-void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp)
+void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
+	free(rsp->param_name);
 	free(rsp);
 }
 
-int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct devlink_sb_pool_get_rsp *dst;
+	struct devlink_param_get_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
 
@@ -942,31 +4204,32 @@ int devlink_sb_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+		} else if (type == DEVLINK_ATTR_PARAM_NAME) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.sb_pool_index = 1;
-			dst->sb_pool_index = mnl_attr_get_u16(attr);
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.param_name_len = len;
+			dst->param_name = malloc(len + 1);
+			memcpy(dst->param_name, mnl_attr_get_str(attr), len);
+			dst->param_name[len] = 0;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_sb_pool_get_rsp *
-devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
+struct devlink_param_get_rsp *
+devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_pool_get_rsp *rsp;
+	struct devlink_param_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -974,15 +4237,13 @@ devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+	if (req->_present.param_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_pool_get_rsp_parse;
-	yrs.rsp_cmd = 17;
+	yrs.cb = devlink_param_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -991,14 +4252,14 @@ devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
 	return rsp;
 
 err_free:
-	devlink_sb_pool_get_rsp_free(rsp);
+	devlink_param_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_SB_POOL_GET - dump */
-void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
+/* DEVLINK_CMD_PARAM_GET - dump */
+void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
 {
-	struct devlink_sb_pool_get_list *next = rsp;
+	struct devlink_param_get_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
 		rsp = next;
@@ -1006,25 +4267,26 @@ void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp)
 
 		free(rsp->obj.bus_name);
 		free(rsp->obj.dev_name);
+		free(rsp->obj.param_name);
 		free(rsp);
 	}
 }
 
-struct devlink_sb_pool_get_list *
-devlink_sb_pool_get_dump(struct ynl_sock *ys,
-			 struct devlink_sb_pool_get_req_dump *req)
+struct devlink_param_get_list *
+devlink_param_get_dump(struct ynl_sock *ys,
+		       struct devlink_param_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list);
-	yds.cb = devlink_sb_pool_get_rsp_parse;
-	yds.rsp_cmd = 17;
+	yds.alloc_sz = sizeof(struct devlink_param_get_list);
+	yds.cb = devlink_param_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_PARAM_GET;
 	yds.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
 	ys->req_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
@@ -1039,31 +4301,67 @@ devlink_sb_pool_get_dump(struct ynl_sock *ys,
 	return yds.first;
 
 free_list:
-	devlink_sb_pool_get_list_free(yds.first);
+	devlink_param_get_list_free(yds.first);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
-void
-devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req)
+/* ============== DEVLINK_CMD_PARAM_SET ============== */
+/* DEVLINK_CMD_PARAM_SET - do */
+void devlink_param_set_req_free(struct devlink_param_set_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
+	free(req->param_name);
 	free(req);
 }
 
-void
-devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp)
+int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.param_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
+	if (req->_present.param_type)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_TYPE, req->param_type);
+	if (req->_present.param_value_cmode)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_VALUE_CMODE, req->param_value_cmode);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_REGION_GET ============== */
+/* DEVLINK_CMD_REGION_GET - do */
+void devlink_region_get_req_free(struct devlink_region_get_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->region_name);
+	free(req);
+}
+
+void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
+	free(rsp->region_name);
 	free(rsp);
 }
 
-int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct devlink_sb_port_pool_get_rsp *dst;
+	struct devlink_region_get_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
 
@@ -1099,32 +4397,32 @@ int devlink_sb_port_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.port_index = 1;
 			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_INDEX) {
+		} else if (type == DEVLINK_ATTR_REGION_NAME) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.sb_pool_index = 1;
-			dst->sb_pool_index = mnl_attr_get_u16(attr);
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.region_name_len = len;
+			dst->region_name = malloc(len + 1);
+			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
+			dst->region_name[len] = 0;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_sb_port_pool_get_rsp *
-devlink_sb_port_pool_get(struct ynl_sock *ys,
-			 struct devlink_sb_port_pool_get_req *req)
+struct devlink_region_get_rsp *
+devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_port_pool_get_rsp *rsp;
+	struct devlink_region_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -1134,15 +4432,13 @@ devlink_sb_port_pool_get(struct ynl_sock *ys,
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index);
+	if (req->_present.region_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_port_pool_get_rsp_parse;
-	yrs.rsp_cmd = 21;
+	yrs.cb = devlink_region_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_REGION_GET;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -1151,15 +4447,14 @@ devlink_sb_port_pool_get(struct ynl_sock *ys,
 	return rsp;
 
 err_free:
-	devlink_sb_port_pool_get_rsp_free(rsp);
+	devlink_region_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
-void
-devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
+/* DEVLINK_CMD_REGION_GET - dump */
+void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
 {
-	struct devlink_sb_port_pool_get_list *next = rsp;
+	struct devlink_region_get_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
 		rsp = next;
@@ -1167,25 +4462,26 @@ devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp)
 
 		free(rsp->obj.bus_name);
 		free(rsp->obj.dev_name);
+		free(rsp->obj.region_name);
 		free(rsp);
 	}
 }
 
-struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
-			      struct devlink_sb_port_pool_get_req_dump *req)
+struct devlink_region_get_list *
+devlink_region_get_dump(struct ynl_sock *ys,
+			struct devlink_region_get_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list);
-	yds.cb = devlink_sb_port_pool_get_rsp_parse;
-	yds.rsp_cmd = 21;
+	yds.alloc_sz = sizeof(struct devlink_region_get_list);
+	yds.cb = devlink_region_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_REGION_GET;
 	yds.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
 	ys->req_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
@@ -1200,32 +4496,31 @@ devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
 	return yds.first;
 
 free_list:
-	devlink_sb_port_pool_get_list_free(yds.first);
+	devlink_region_get_list_free(yds.first);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
-void
-devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req)
+/* ============== DEVLINK_CMD_REGION_NEW ============== */
+/* DEVLINK_CMD_REGION_NEW - do */
+void devlink_region_new_req_free(struct devlink_region_new_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
+	free(req->region_name);
 	free(req);
 }
 
-void
-devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp)
+void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
+	free(rsp->region_name);
 	free(rsp);
 }
 
-int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh,
-					  void *data)
+int devlink_region_new_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct devlink_sb_tc_pool_bind_get_rsp *dst;
+	struct devlink_region_new_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
 
@@ -1261,37 +4556,37 @@ int devlink_sb_tc_pool_bind_get_rsp_parse(const struct nlmsghdr *nlh,
 				return MNL_CB_ERROR;
 			dst->_present.port_index = 1;
 			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_INDEX) {
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-			dst->_present.sb_index = 1;
-			dst->sb_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_SB_POOL_TYPE) {
+		} else if (type == DEVLINK_ATTR_REGION_NAME) {
+			unsigned int len;
+
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.sb_pool_type = 1;
-			dst->sb_pool_type = mnl_attr_get_u8(attr);
-		} else if (type == DEVLINK_ATTR_SB_TC_INDEX) {
+
+			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
+			dst->_present.region_name_len = len;
+			dst->region_name = malloc(len + 1);
+			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
+			dst->region_name[len] = 0;
+		} else if (type == DEVLINK_ATTR_REGION_SNAPSHOT_ID) {
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
-			dst->_present.sb_tc_index = 1;
-			dst->sb_tc_index = mnl_attr_get_u16(attr);
+			dst->_present.region_snapshot_id = 1;
+			dst->region_snapshot_id = mnl_attr_get_u32(attr);
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_sb_tc_pool_bind_get_rsp *
-devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
-			    struct devlink_sb_tc_pool_bind_get_req *req)
+struct devlink_region_new_rsp *
+devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_sb_tc_pool_bind_get_rsp *rsp;
+	struct devlink_region_new_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_NEW, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -1301,17 +4596,15 @@ devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.sb_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
-	if (req->_present.sb_pool_type)
-		mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type);
-	if (req->_present.sb_tc_index)
-		mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index);
+	if (req->_present.region_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
+	if (req->_present.region_snapshot_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
-	yrs.rsp_cmd = 25;
+	yrs.cb = devlink_region_new_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_REGION_NEW;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -1320,80 +4613,51 @@ devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
 	return rsp;
 
 err_free:
-	devlink_sb_tc_pool_bind_get_rsp_free(rsp);
+	devlink_region_new_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
-void
-devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp)
+/* ============== DEVLINK_CMD_REGION_DEL ============== */
+/* DEVLINK_CMD_REGION_DEL - do */
+void devlink_region_del_req_free(struct devlink_region_del_req *req)
 {
-	struct devlink_sb_tc_pool_bind_get_list *next = rsp;
-
-	while ((void *)next != YNL_LIST_END) {
-		rsp = next;
-		next = rsp->next;
-
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp);
-	}
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->region_name);
+	free(req);
 }
 
-struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
-				 struct devlink_sb_tc_pool_bind_get_req_dump *req)
+int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req)
 {
-	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list);
-	yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
-	yds.rsp_cmd = 25;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_DEL, 1);
 	ys->req_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.region_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
+	if (req->_present.region_snapshot_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
 
-	err = ynl_exec_dump(ys, nlh, &yds);
+	err = ynl_exec(ys, nlh, NULL);
 	if (err < 0)
-		goto free_list;
-
-	return yds.first;
-
-free_list:
-	devlink_sb_tc_pool_bind_get_list_free(yds.first);
-	return NULL;
-}
-
-/* ============== DEVLINK_CMD_PARAM_GET ============== */
-/* DEVLINK_CMD_PARAM_GET - do */
-void devlink_param_get_req_free(struct devlink_param_get_req *req)
-{
-	free(req->bus_name);
-	free(req->dev_name);
-	free(req->param_name);
-	free(req);
-}
+		return -1;
 
-void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp)
-{
-	free(rsp->bus_name);
-	free(rsp->dev_name);
-	free(rsp->param_name);
-	free(rsp);
+	return 0;
 }
 
-int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+/* ============== DEVLINK_CMD_REGION_READ ============== */
+/* DEVLINK_CMD_REGION_READ - dump */
+int devlink_region_read_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct devlink_param_get_rsp *dst;
+	struct devlink_region_read_rsp_dump *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
 
@@ -1424,62 +4688,32 @@ int devlink_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 			dst->dev_name = malloc(len + 1);
 			memcpy(dst->dev_name, mnl_attr_get_str(attr), len);
 			dst->dev_name[len] = 0;
-		} else if (type == DEVLINK_ATTR_PARAM_NAME) {
+		} else if (type == DEVLINK_ATTR_PORT_INDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.port_index = 1;
+			dst->port_index = mnl_attr_get_u32(attr);
+		} else if (type == DEVLINK_ATTR_REGION_NAME) {
 			unsigned int len;
 
 			if (ynl_attr_validate(yarg, attr))
 				return MNL_CB_ERROR;
 
 			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.param_name_len = len;
-			dst->param_name = malloc(len + 1);
-			memcpy(dst->param_name, mnl_attr_get_str(attr), len);
-			dst->param_name[len] = 0;
+			dst->_present.region_name_len = len;
+			dst->region_name = malloc(len + 1);
+			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
+			dst->region_name[len] = 0;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_param_get_rsp *
-devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req)
-{
-	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_param_get_rsp *rsp;
-	struct nlmsghdr *nlh;
-	int err;
-
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
-	ys->req_policy = &devlink_nest;
-	yrs.yarg.rsp_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.param_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name);
-
-	rsp = calloc(1, sizeof(*rsp));
-	yrs.yarg.data = rsp;
-	yrs.cb = devlink_param_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_PARAM_GET;
-
-	err = ynl_exec(ys, nlh, &yrs);
-	if (err < 0)
-		goto err_free;
-
-	return rsp;
-
-err_free:
-	devlink_param_get_rsp_free(rsp);
-	return NULL;
-}
-
-/* DEVLINK_CMD_PARAM_GET - dump */
-void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
+void
+devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp)
 {
-	struct devlink_param_get_list *next = rsp;
+	struct devlink_region_read_rsp_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
 		rsp = next;
@@ -1487,32 +4721,44 @@ void devlink_param_get_list_free(struct devlink_param_get_list *rsp)
 
 		free(rsp->obj.bus_name);
 		free(rsp->obj.dev_name);
-		free(rsp->obj.param_name);
+		free(rsp->obj.region_name);
 		free(rsp);
 	}
 }
 
-struct devlink_param_get_list *
-devlink_param_get_dump(struct ynl_sock *ys,
-		       struct devlink_param_get_req_dump *req)
+struct devlink_region_read_rsp_list *
+devlink_region_read_dump(struct ynl_sock *ys,
+			 struct devlink_region_read_req_dump *req)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_param_get_list);
-	yds.cb = devlink_param_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_PARAM_GET;
+	yds.alloc_sz = sizeof(struct devlink_region_read_rsp_list);
+	yds.cb = devlink_region_read_rsp_dump_parse;
+	yds.rsp_cmd = DEVLINK_CMD_REGION_READ;
 	yds.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PARAM_GET, 1);
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_READ, 1);
 	ys->req_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.region_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
+	if (req->_present.region_snapshot_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
+	if (req->_present.region_direct)
+		mnl_attr_put(nlh, DEVLINK_ATTR_REGION_DIRECT, 0, NULL);
+	if (req->_present.region_chunk_addr)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_ADDR, req->region_chunk_addr);
+	if (req->_present.region_chunk_len)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN, req->region_chunk_len);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1521,31 +4767,29 @@ devlink_param_get_dump(struct ynl_sock *ys,
 	return yds.first;
 
 free_list:
-	devlink_param_get_list_free(yds.first);
+	devlink_region_read_rsp_list_free(yds.first);
 	return NULL;
 }
 
-/* ============== DEVLINK_CMD_REGION_GET ============== */
-/* DEVLINK_CMD_REGION_GET - do */
-void devlink_region_get_req_free(struct devlink_region_get_req *req)
+/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */
+/* DEVLINK_CMD_PORT_PARAM_GET - do */
+void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req)
 {
 	free(req->bus_name);
 	free(req->dev_name);
-	free(req->region_name);
 	free(req);
 }
 
-void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp)
+void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp)
 {
 	free(rsp->bus_name);
 	free(rsp->dev_name);
-	free(rsp->region_name);
 	free(rsp);
 }
 
-int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+int devlink_port_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct devlink_region_get_rsp *dst;
+	struct devlink_port_param_get_rsp *dst;
 	struct ynl_parse_arg *yarg = data;
 	const struct nlattr *attr;
 
@@ -1581,32 +4825,22 @@ int devlink_region_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.port_index = 1;
 			dst->port_index = mnl_attr_get_u32(attr);
-		} else if (type == DEVLINK_ATTR_REGION_NAME) {
-			unsigned int len;
-
-			if (ynl_attr_validate(yarg, attr))
-				return MNL_CB_ERROR;
-
-			len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));
-			dst->_present.region_name_len = len;
-			dst->region_name = malloc(len + 1);
-			memcpy(dst->region_name, mnl_attr_get_str(attr), len);
-			dst->region_name[len] = 0;
 		}
 	}
 
 	return MNL_CB_OK;
 }
 
-struct devlink_region_get_rsp *
-devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
+struct devlink_port_param_get_rsp *
+devlink_port_param_get(struct ynl_sock *ys,
+		       struct devlink_port_param_get_req *req)
 {
 	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
-	struct devlink_region_get_rsp *rsp;
+	struct devlink_port_param_get_rsp *rsp;
 	struct nlmsghdr *nlh;
 	int err;
 
-	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1);
 	ys->req_policy = &devlink_nest;
 	yrs.yarg.rsp_policy = &devlink_nest;
 
@@ -1616,13 +4850,11 @@ devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-	if (req->_present.region_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name);
 
 	rsp = calloc(1, sizeof(*rsp));
 	yrs.yarg.data = rsp;
-	yrs.cb = devlink_region_get_rsp_parse;
-	yrs.rsp_cmd = DEVLINK_CMD_REGION_GET;
+	yrs.cb = devlink_port_param_get_rsp_parse;
+	yrs.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET;
 
 	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
@@ -1631,14 +4863,14 @@ devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req)
 	return rsp;
 
 err_free:
-	devlink_region_get_rsp_free(rsp);
+	devlink_port_param_get_rsp_free(rsp);
 	return NULL;
 }
 
-/* DEVLINK_CMD_REGION_GET - dump */
-void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
+/* DEVLINK_CMD_PORT_PARAM_GET - dump */
+void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp)
 {
-	struct devlink_region_get_list *next = rsp;
+	struct devlink_port_param_get_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
 		rsp = next;
@@ -1646,32 +4878,24 @@ void devlink_region_get_list_free(struct devlink_region_get_list *rsp)
 
 		free(rsp->obj.bus_name);
 		free(rsp->obj.dev_name);
-		free(rsp->obj.region_name);
 		free(rsp);
 	}
 }
 
-struct devlink_region_get_list *
-devlink_region_get_dump(struct ynl_sock *ys,
-			struct devlink_region_get_req_dump *req)
+struct devlink_port_param_get_list *
+devlink_port_param_get_dump(struct ynl_sock *ys)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_region_get_list);
-	yds.cb = devlink_region_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_REGION_GET;
+	yds.alloc_sz = sizeof(struct devlink_port_param_get_list);
+	yds.cb = devlink_port_param_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET;
 	yds.rsp_policy = &devlink_nest;
 
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_GET, 1);
-	ys->req_policy = &devlink_nest;
-
-	if (req->_present.bus_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
-	if (req->_present.dev_name_len)
-		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1);
 
 	err = ynl_exec_dump(ys, nlh, &yds);
 	if (err < 0)
@@ -1680,10 +4904,42 @@ devlink_region_get_dump(struct ynl_sock *ys,
 	return yds.first;
 
 free_list:
-	devlink_region_get_list_free(yds.first);
+	devlink_port_param_get_list_free(yds.first);
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */
+/* DEVLINK_CMD_PORT_PARAM_SET - do */
+void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_port_param_set(struct ynl_sock *ys,
+			   struct devlink_port_param_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_INFO_GET ============== */
 /* DEVLINK_CMD_INFO_GET - do */
 void devlink_info_get_req_free(struct devlink_info_get_req *req)
@@ -2046,46 +5302,316 @@ devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *r
 		rsp = next;
 		next = rsp->next;
 
-		free(rsp->obj.bus_name);
-		free(rsp->obj.dev_name);
-		free(rsp->obj.health_reporter_name);
-		free(rsp);
-	}
+		free(rsp->obj.bus_name);
+		free(rsp->obj.dev_name);
+		free(rsp->obj.health_reporter_name);
+		free(rsp);
+	}
+}
+
+struct devlink_health_reporter_get_list *
+devlink_health_reporter_get_dump(struct ynl_sock *ys,
+				 struct devlink_health_reporter_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list);
+	yds.cb = devlink_health_reporter_get_rsp_parse;
+	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_health_reporter_get_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */
+void
+devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+int devlink_health_reporter_set(struct ynl_sock *ys,
+				struct devlink_health_reporter_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+	if (req->_present.health_reporter_graceful_period)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, req->health_reporter_graceful_period);
+	if (req->_present.health_reporter_auto_recover)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, req->health_reporter_auto_recover);
+	if (req->_present.health_reporter_auto_dump)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, req->health_reporter_auto_dump);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */
+void
+devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+int devlink_health_reporter_recover(struct ynl_sock *ys,
+				    struct devlink_health_reporter_recover_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_RECOVER, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */
+void
+devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+int devlink_health_reporter_diagnose(struct ynl_sock *ys,
+				     struct devlink_health_reporter_diagnose_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */
+int devlink_health_reporter_dump_get_rsp_dump_parse(const struct nlmsghdr *nlh,
+						    void *data)
+{
+	struct devlink_health_reporter_dump_get_rsp_dump *dst;
+	struct ynl_parse_arg *yarg = data;
+	const struct nlattr *attr;
+	struct ynl_parse_arg parg;
+
+	dst = yarg->data;
+	parg.ys = yarg->ys;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == DEVLINK_ATTR_FMSG) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.fmsg = 1;
+
+			parg.rsp_policy = &devlink_dl_fmsg_nest;
+			parg.data = &dst->fmsg;
+			if (devlink_dl_fmsg_parse(&parg, attr))
+				return MNL_CB_ERROR;
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+void
+devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp)
+{
+	struct devlink_health_reporter_dump_get_rsp_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		devlink_dl_fmsg_free(&rsp->obj.fmsg);
+		free(rsp);
+	}
+}
+
+struct devlink_health_reporter_dump_get_rsp_list *
+devlink_health_reporter_dump_get_dump(struct ynl_sock *ys,
+				      struct devlink_health_reporter_dump_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct devlink_health_reporter_dump_get_rsp_list);
+	yds.cb = devlink_health_reporter_dump_get_rsp_dump_parse;
+	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET;
+	yds.rsp_policy = &devlink_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	devlink_health_reporter_dump_get_rsp_list_free(yds.first);
+	return NULL;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */
+void
+devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
+				       struct devlink_health_reporter_dump_clear_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */
+/* DEVLINK_CMD_FLASH_UPDATE - do */
+void devlink_flash_update_req_free(struct devlink_flash_update_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->flash_update_file_name);
+	free(req->flash_update_component);
+	free(req);
 }
 
-struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys,
-				 struct devlink_health_reporter_get_req_dump *req)
+int devlink_flash_update(struct ynl_sock *ys,
+			 struct devlink_flash_update_req *req)
 {
-	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
-	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct devlink_health_reporter_get_list);
-	yds.cb = devlink_health_reporter_get_rsp_parse;
-	yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_GET;
-	yds.rsp_policy = &devlink_nest;
-
-	nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_GET, 1);
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_FLASH_UPDATE, 1);
 	ys->req_policy = &devlink_nest;
 
 	if (req->_present.bus_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
 	if (req->_present.dev_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
-	if (req->_present.port_index)
-		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
-
-	err = ynl_exec_dump(ys, nlh, &yds);
+	if (req->_present.flash_update_file_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, req->flash_update_file_name);
+	if (req->_present.flash_update_component_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, req->flash_update_component);
+	if (req->_present.flash_update_overwrite_mask)
+		mnl_attr_put(nlh, DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, sizeof(struct nla_bitfield32), &req->flash_update_overwrite_mask);
+
+	err = ynl_exec(ys, nlh, NULL);
 	if (err < 0)
-		goto free_list;
-
-	return yds.first;
+		return -1;
 
-free_list:
-	devlink_health_reporter_get_list_free(yds.first);
-	return NULL;
+	return 0;
 }
 
 /* ============== DEVLINK_CMD_TRAP_GET ============== */
@@ -2240,6 +5766,40 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_TRAP_SET ============== */
+/* DEVLINK_CMD_TRAP_SET - do */
+void devlink_trap_set_req_free(struct devlink_trap_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->trap_name);
+	free(req);
+}
+
+int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name);
+	if (req->_present.trap_action)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
 /* DEVLINK_CMD_TRAP_GROUP_GET - do */
 void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req)
@@ -2393,6 +5953,43 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */
+/* DEVLINK_CMD_TRAP_GROUP_SET - do */
+void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->trap_group_name);
+	free(req);
+}
+
+int devlink_trap_group_set(struct ynl_sock *ys,
+			   struct devlink_trap_group_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_group_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name);
+	if (req->_present.trap_action)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action);
+	if (req->_present.trap_policer_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
 /* DEVLINK_CMD_TRAP_POLICER_GET - do */
 void
@@ -2540,6 +6137,79 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */
+/* DEVLINK_CMD_TRAP_POLICER_SET - do */
+void
+devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req);
+}
+
+int devlink_trap_policer_set(struct ynl_sock *ys,
+			     struct devlink_trap_policer_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.trap_policer_id)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
+	if (req->_present.trap_policer_rate)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_RATE, req->trap_policer_rate);
+	if (req->_present.trap_policer_burst)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_BURST, req->trap_policer_burst);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */
+void
+devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->health_reporter_name);
+	free(req);
+}
+
+int devlink_health_reporter_test(struct ynl_sock *ys,
+				 struct devlink_health_reporter_test_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_TEST, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.port_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
+	if (req->_present.health_reporter_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_RATE_GET ============== */
 /* DEVLINK_CMD_RATE_GET - do */
 void devlink_rate_get_req_free(struct devlink_rate_get_req *req)
@@ -2699,6 +6369,124 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_RATE_SET ============== */
+/* DEVLINK_CMD_RATE_SET - do */
+void devlink_rate_set_req_free(struct devlink_rate_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->rate_node_name);
+	free(req->rate_parent_node_name);
+	free(req);
+}
+
+int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.rate_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
+	if (req->_present.rate_tx_share)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share);
+	if (req->_present.rate_tx_max)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max);
+	if (req->_present.rate_tx_priority)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority);
+	if (req->_present.rate_tx_weight)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight);
+	if (req->_present.rate_parent_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_RATE_NEW ============== */
+/* DEVLINK_CMD_RATE_NEW - do */
+void devlink_rate_new_req_free(struct devlink_rate_new_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->rate_node_name);
+	free(req->rate_parent_node_name);
+	free(req);
+}
+
+int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_NEW, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.rate_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
+	if (req->_present.rate_tx_share)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share);
+	if (req->_present.rate_tx_max)
+		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max);
+	if (req->_present.rate_tx_priority)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority);
+	if (req->_present.rate_tx_weight)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight);
+	if (req->_present.rate_parent_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
+/* ============== DEVLINK_CMD_RATE_DEL ============== */
+/* DEVLINK_CMD_RATE_DEL - do */
+void devlink_rate_del_req_free(struct devlink_rate_del_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->rate_node_name);
+	free(req);
+}
+
+int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_DEL, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.rate_node_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_LINECARD_GET ============== */
 /* DEVLINK_CMD_LINECARD_GET - do */
 void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req)
@@ -2842,6 +6630,41 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_LINECARD_SET ============== */
+/* DEVLINK_CMD_LINECARD_SET - do */
+void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	free(req->linecard_type);
+	free(req);
+}
+
+int devlink_linecard_set(struct ynl_sock *ys,
+			 struct devlink_linecard_set_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_SET, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.linecard_index)
+		mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index);
+	if (req->_present.linecard_type_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_LINECARD_TYPE, req->linecard_type);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 /* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
 /* DEVLINK_CMD_SELFTESTS_GET - do */
 void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req)
@@ -2972,6 +6795,39 @@ free_list:
 	return NULL;
 }
 
+/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */
+/* DEVLINK_CMD_SELFTESTS_RUN - do */
+void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req)
+{
+	free(req->bus_name);
+	free(req->dev_name);
+	devlink_dl_selftest_id_free(&req->selftests);
+	free(req);
+}
+
+int devlink_selftests_run(struct ynl_sock *ys,
+			  struct devlink_selftests_run_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_RUN, 1);
+	ys->req_policy = &devlink_nest;
+
+	if (req->_present.bus_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name);
+	if (req->_present.dev_name_len)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name);
+	if (req->_present.selftests)
+		devlink_dl_selftest_id_put(nlh, DEVLINK_ATTR_SELFTESTS, &req->selftests);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 const struct ynl_family ynl_devlink_family =  {
 	.name		= "devlink",
 };
diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h
index d00bcf79fa0d..9f45cc0d854c 100644
--- a/tools/net/ynl/generated/devlink-user.h
+++ b/tools/net/ynl/generated/devlink-user.h
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <linux/types.h>
+#include <linux/netlink.h>
 #include <linux/devlink.h>
 
 struct ynl_sock;
@@ -18,8 +19,130 @@ extern const struct ynl_family ynl_devlink_family;
 /* Enums */
 const char *devlink_op_str(int op);
 const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value);
+const char *devlink_port_type_str(enum devlink_port_type value);
+const char *devlink_port_flavour_str(enum devlink_port_flavour value);
+const char *devlink_port_fn_state_str(enum devlink_port_fn_state value);
+const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value);
+const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value);
+const char *
+devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value);
+const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value);
+const char *
+devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value);
+const char *
+devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value);
+const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value);
+const char *
+devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value);
+const char *
+devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value);
+const char *devlink_resource_unit_str(enum devlink_resource_unit value);
+const char *devlink_reload_action_str(enum devlink_reload_action value);
+const char *devlink_param_cmode_str(enum devlink_param_cmode value);
+const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value);
+const char *devlink_trap_action_str(enum devlink_trap_action value);
 
 /* Common nested types */
+struct devlink_dl_dpipe_match {
+	struct {
+		__u32 dpipe_match_type:1;
+		__u32 dpipe_header_id:1;
+		__u32 dpipe_header_global:1;
+		__u32 dpipe_header_index:1;
+		__u32 dpipe_field_id:1;
+	} _present;
+
+	enum devlink_dpipe_match_type dpipe_match_type;
+	__u32 dpipe_header_id;
+	__u8 dpipe_header_global;
+	__u32 dpipe_header_index;
+	__u32 dpipe_field_id;
+};
+
+struct devlink_dl_dpipe_match_value {
+	struct {
+		__u32 dpipe_value_len;
+		__u32 dpipe_value_mask_len;
+		__u32 dpipe_value_mapping:1;
+	} _present;
+
+	unsigned int n_dpipe_match;
+	struct devlink_dl_dpipe_match *dpipe_match;
+	void *dpipe_value;
+	void *dpipe_value_mask;
+	__u32 dpipe_value_mapping;
+};
+
+struct devlink_dl_dpipe_action {
+	struct {
+		__u32 dpipe_action_type:1;
+		__u32 dpipe_header_id:1;
+		__u32 dpipe_header_global:1;
+		__u32 dpipe_header_index:1;
+		__u32 dpipe_field_id:1;
+	} _present;
+
+	enum devlink_dpipe_action_type dpipe_action_type;
+	__u32 dpipe_header_id;
+	__u8 dpipe_header_global;
+	__u32 dpipe_header_index;
+	__u32 dpipe_field_id;
+};
+
+struct devlink_dl_dpipe_action_value {
+	struct {
+		__u32 dpipe_value_len;
+		__u32 dpipe_value_mask_len;
+		__u32 dpipe_value_mapping:1;
+	} _present;
+
+	unsigned int n_dpipe_action;
+	struct devlink_dl_dpipe_action *dpipe_action;
+	void *dpipe_value;
+	void *dpipe_value_mask;
+	__u32 dpipe_value_mapping;
+};
+
+struct devlink_dl_dpipe_field {
+	struct {
+		__u32 dpipe_field_name_len;
+		__u32 dpipe_field_id:1;
+		__u32 dpipe_field_bitwidth:1;
+		__u32 dpipe_field_mapping_type:1;
+	} _present;
+
+	char *dpipe_field_name;
+	__u32 dpipe_field_id;
+	__u32 dpipe_field_bitwidth;
+	enum devlink_dpipe_field_mapping_type dpipe_field_mapping_type;
+};
+
+struct devlink_dl_resource {
+	struct {
+		__u32 resource_name_len;
+		__u32 resource_id:1;
+		__u32 resource_size:1;
+		__u32 resource_size_new:1;
+		__u32 resource_size_valid:1;
+		__u32 resource_size_min:1;
+		__u32 resource_size_max:1;
+		__u32 resource_size_gran:1;
+		__u32 resource_unit:1;
+		__u32 resource_occ:1;
+	} _present;
+
+	char *resource_name;
+	__u64 resource_id;
+	__u64 resource_size;
+	__u64 resource_size_new;
+	__u8 resource_size_valid;
+	__u64 resource_size_min;
+	__u64 resource_size_max;
+	__u64 resource_size_gran;
+	enum devlink_resource_unit resource_unit;
+	__u64 resource_occ;
+};
+
 struct devlink_dl_info_version {
 	struct {
 		__u32 info_version_name_len;
@@ -30,6 +153,32 @@ struct devlink_dl_info_version {
 	char *info_version_value;
 };
 
+struct devlink_dl_fmsg {
+	struct {
+		__u32 fmsg_obj_nest_start:1;
+		__u32 fmsg_pair_nest_start:1;
+		__u32 fmsg_arr_nest_start:1;
+		__u32 fmsg_nest_end:1;
+		__u32 fmsg_obj_name_len;
+	} _present;
+
+	char *fmsg_obj_name;
+};
+
+struct devlink_dl_port_function {
+	struct {
+		__u32 hw_addr_len;
+		__u32 state:1;
+		__u32 opstate:1;
+		__u32 caps:1;
+	} _present;
+
+	void *hw_addr;
+	enum devlink_port_fn_state state;
+	enum devlink_port_fn_opstate opstate;
+	struct nla_bitfield32 caps;
+};
+
 struct devlink_dl_reload_stats_entry {
 	struct {
 		__u32 reload_stats_limit:1;
@@ -45,21 +194,120 @@ struct devlink_dl_reload_act_stats {
 	struct devlink_dl_reload_stats_entry *reload_stats_entry;
 };
 
+struct devlink_dl_selftest_id {
+	struct {
+		__u32 flash:1;
+	} _present;
+};
+
+struct devlink_dl_dpipe_table_matches {
+	unsigned int n_dpipe_match;
+	struct devlink_dl_dpipe_match *dpipe_match;
+};
+
+struct devlink_dl_dpipe_table_actions {
+	unsigned int n_dpipe_action;
+	struct devlink_dl_dpipe_action *dpipe_action;
+};
+
+struct devlink_dl_dpipe_entry_match_values {
+	unsigned int n_dpipe_match_value;
+	struct devlink_dl_dpipe_match_value *dpipe_match_value;
+};
+
+struct devlink_dl_dpipe_entry_action_values {
+	unsigned int n_dpipe_action_value;
+	struct devlink_dl_dpipe_action_value *dpipe_action_value;
+};
+
+struct devlink_dl_dpipe_header_fields {
+	unsigned int n_dpipe_field;
+	struct devlink_dl_dpipe_field *dpipe_field;
+};
+
+struct devlink_dl_resource_list {
+	unsigned int n_resource;
+	struct devlink_dl_resource *resource;
+};
+
 struct devlink_dl_reload_act_info {
 	struct {
 		__u32 reload_action:1;
 	} _present;
 
-	__u8 reload_action;
+	enum devlink_reload_action reload_action;
 	unsigned int n_reload_action_stats;
 	struct devlink_dl_reload_act_stats *reload_action_stats;
 };
 
+struct devlink_dl_dpipe_table {
+	struct {
+		__u32 dpipe_table_name_len;
+		__u32 dpipe_table_size:1;
+		__u32 dpipe_table_matches:1;
+		__u32 dpipe_table_actions:1;
+		__u32 dpipe_table_counters_enabled:1;
+		__u32 dpipe_table_resource_id:1;
+		__u32 dpipe_table_resource_units:1;
+	} _present;
+
+	char *dpipe_table_name;
+	__u64 dpipe_table_size;
+	struct devlink_dl_dpipe_table_matches dpipe_table_matches;
+	struct devlink_dl_dpipe_table_actions dpipe_table_actions;
+	__u8 dpipe_table_counters_enabled;
+	__u64 dpipe_table_resource_id;
+	__u64 dpipe_table_resource_units;
+};
+
+struct devlink_dl_dpipe_entry {
+	struct {
+		__u32 dpipe_entry_index:1;
+		__u32 dpipe_entry_match_values:1;
+		__u32 dpipe_entry_action_values:1;
+		__u32 dpipe_entry_counter:1;
+	} _present;
+
+	__u64 dpipe_entry_index;
+	struct devlink_dl_dpipe_entry_match_values dpipe_entry_match_values;
+	struct devlink_dl_dpipe_entry_action_values dpipe_entry_action_values;
+	__u64 dpipe_entry_counter;
+};
+
+struct devlink_dl_dpipe_header {
+	struct {
+		__u32 dpipe_header_name_len;
+		__u32 dpipe_header_id:1;
+		__u32 dpipe_header_global:1;
+		__u32 dpipe_header_fields:1;
+	} _present;
+
+	char *dpipe_header_name;
+	__u32 dpipe_header_id;
+	__u8 dpipe_header_global;
+	struct devlink_dl_dpipe_header_fields dpipe_header_fields;
+};
+
 struct devlink_dl_reload_stats {
 	unsigned int n_reload_action_info;
 	struct devlink_dl_reload_act_info *reload_action_info;
 };
 
+struct devlink_dl_dpipe_tables {
+	unsigned int n_dpipe_table;
+	struct devlink_dl_dpipe_table *dpipe_table;
+};
+
+struct devlink_dl_dpipe_entries {
+	unsigned int n_dpipe_entry;
+	struct devlink_dl_dpipe_entry *dpipe_entry;
+};
+
+struct devlink_dl_dpipe_headers {
+	unsigned int n_dpipe_header;
+	struct devlink_dl_dpipe_header *dpipe_header;
+};
+
 struct devlink_dl_dev_stats {
 	struct {
 		__u32 reload_stats:1;
@@ -269,29 +517,33 @@ struct devlink_port_get_rsp_list *
 devlink_port_get_dump(struct ynl_sock *ys,
 		      struct devlink_port_get_req_dump *req);
 
-/* ============== DEVLINK_CMD_SB_GET ============== */
-/* DEVLINK_CMD_SB_GET - do */
-struct devlink_sb_get_req {
+/* ============== DEVLINK_CMD_PORT_SET ============== */
+/* DEVLINK_CMD_PORT_SET - do */
+struct devlink_port_set_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 sb_index:1;
+		__u32 port_index:1;
+		__u32 port_type:1;
+		__u32 port_function:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	__u32 sb_index;
+	__u32 port_index;
+	enum devlink_port_type port_type;
+	struct devlink_dl_port_function port_function;
 };
 
-static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void)
+static inline struct devlink_port_set_req *devlink_port_set_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_get_req));
+	return calloc(1, sizeof(struct devlink_port_set_req));
 }
-void devlink_sb_get_req_free(struct devlink_sb_get_req *req);
+void devlink_port_set_req_free(struct devlink_port_set_req *req);
 
 static inline void
-devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req,
-				const char *bus_name)
+devlink_port_set_req_set_bus_name(struct devlink_port_set_req *req,
+				  const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -300,8 +552,8 @@ devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req,
-				const char *dev_name)
+devlink_port_set_req_set_dev_name(struct devlink_port_set_req *req,
+				  const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -310,53 +562,89 @@ devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req,
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index)
+devlink_port_set_req_set_port_index(struct devlink_port_set_req *req,
+				    __u32 port_index)
 {
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_port_set_req_set_port_type(struct devlink_port_set_req *req,
+				   enum devlink_port_type port_type)
+{
+	req->_present.port_type = 1;
+	req->port_type = port_type;
+}
+static inline void
+devlink_port_set_req_set_port_function_hw_addr(struct devlink_port_set_req *req,
+					       const void *hw_addr, size_t len)
+{
+	free(req->port_function.hw_addr);
+	req->port_function._present.hw_addr_len = len;
+	req->port_function.hw_addr = malloc(req->port_function._present.hw_addr_len);
+	memcpy(req->port_function.hw_addr, hw_addr, req->port_function._present.hw_addr_len);
+}
+static inline void
+devlink_port_set_req_set_port_function_state(struct devlink_port_set_req *req,
+					     enum devlink_port_fn_state state)
+{
+	req->_present.port_function = 1;
+	req->port_function._present.state = 1;
+	req->port_function.state = state;
+}
+static inline void
+devlink_port_set_req_set_port_function_opstate(struct devlink_port_set_req *req,
+					       enum devlink_port_fn_opstate opstate)
+{
+	req->_present.port_function = 1;
+	req->port_function._present.opstate = 1;
+	req->port_function.opstate = opstate;
+}
+static inline void
+devlink_port_set_req_set_port_function_caps(struct devlink_port_set_req *req,
+					    struct nla_bitfield32 *caps)
+{
+	req->_present.port_function = 1;
+	req->port_function._present.caps = 1;
+	memcpy(&req->port_function.caps, caps, sizeof(struct nla_bitfield32));
 }
-
-struct devlink_sb_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-};
-
-void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp);
 
 /*
- * Get shared buffer instances.
+ * Set devlink port instances.
  */
-struct devlink_sb_get_rsp *
-devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req);
+int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req);
 
-/* DEVLINK_CMD_SB_GET - dump */
-struct devlink_sb_get_req_dump {
+/* ============== DEVLINK_CMD_PORT_NEW ============== */
+/* DEVLINK_CMD_PORT_NEW - do */
+struct devlink_port_new_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 port_flavour:1;
+		__u32 port_pci_pf_number:1;
+		__u32 port_pci_sf_number:1;
+		__u32 port_controller_number:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
+	enum devlink_port_flavour port_flavour;
+	__u16 port_pci_pf_number;
+	__u32 port_pci_sf_number;
+	__u32 port_controller_number;
 };
 
-static inline struct devlink_sb_get_req_dump *
-devlink_sb_get_req_dump_alloc(void)
+static inline struct devlink_port_new_req *devlink_port_new_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_get_req_dump));
+	return calloc(1, sizeof(struct devlink_port_new_req));
 }
-void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req);
+void devlink_port_new_req_free(struct devlink_port_new_req *req);
 
 static inline void
-devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req,
-				     const char *bus_name)
+devlink_port_new_req_set_bus_name(struct devlink_port_new_req *req,
+				  const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -365,8 +653,8 @@ devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
-				     const char *dev_name)
+devlink_port_new_req_set_dev_name(struct devlink_port_new_req *req,
+				  const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -374,119 +662,85 @@ devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
-
-struct devlink_sb_get_list {
-	struct devlink_sb_get_list *next;
-	struct devlink_sb_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
-
-struct devlink_sb_get_list *
-devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req);
-
-/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
-/* DEVLINK_CMD_SB_POOL_GET - do */
-struct devlink_sb_pool_get_req {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-static inline struct devlink_sb_pool_get_req *
-devlink_sb_pool_get_req_alloc(void)
+static inline void
+devlink_port_new_req_set_port_index(struct devlink_port_new_req *req,
+				    __u32 port_index)
 {
-	return calloc(1, sizeof(struct devlink_sb_pool_get_req));
+	req->_present.port_index = 1;
+	req->port_index = port_index;
 }
-void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req);
-
 static inline void
-devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req,
-				     const char *bus_name)
+devlink_port_new_req_set_port_flavour(struct devlink_port_new_req *req,
+				      enum devlink_port_flavour port_flavour)
 {
-	free(req->bus_name);
-	req->_present.bus_name_len = strlen(bus_name);
-	req->bus_name = malloc(req->_present.bus_name_len + 1);
-	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
-	req->bus_name[req->_present.bus_name_len] = 0;
+	req->_present.port_flavour = 1;
+	req->port_flavour = port_flavour;
 }
 static inline void
-devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req,
-				     const char *dev_name)
+devlink_port_new_req_set_port_pci_pf_number(struct devlink_port_new_req *req,
+					    __u16 port_pci_pf_number)
 {
-	free(req->dev_name);
-	req->_present.dev_name_len = strlen(dev_name);
-	req->dev_name = malloc(req->_present.dev_name_len + 1);
-	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
-	req->dev_name[req->_present.dev_name_len] = 0;
+	req->_present.port_pci_pf_number = 1;
+	req->port_pci_pf_number = port_pci_pf_number;
 }
 static inline void
-devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req,
-				     __u32 sb_index)
+devlink_port_new_req_set_port_pci_sf_number(struct devlink_port_new_req *req,
+					    __u32 port_pci_sf_number)
 {
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
+	req->_present.port_pci_sf_number = 1;
+	req->port_pci_sf_number = port_pci_sf_number;
 }
 static inline void
-devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req,
-					  __u16 sb_pool_index)
+devlink_port_new_req_set_port_controller_number(struct devlink_port_new_req *req,
+						__u32 port_controller_number)
 {
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
+	req->_present.port_controller_number = 1;
+	req->port_controller_number = port_controller_number;
 }
 
-struct devlink_sb_pool_get_rsp {
+struct devlink_port_new_rsp {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
+		__u32 port_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	__u32 sb_index;
-	__u16 sb_pool_index;
+	__u32 port_index;
 };
 
-void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp);
+void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp);
 
 /*
- * Get shared buffer pool instances.
+ * Create devlink port instances.
  */
-struct devlink_sb_pool_get_rsp *
-devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req);
+struct devlink_port_new_rsp *
+devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req);
 
-/* DEVLINK_CMD_SB_POOL_GET - dump */
-struct devlink_sb_pool_get_req_dump {
+/* ============== DEVLINK_CMD_PORT_DEL ============== */
+/* DEVLINK_CMD_PORT_DEL - do */
+struct devlink_port_del_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
 };
 
-static inline struct devlink_sb_pool_get_req_dump *
-devlink_sb_pool_get_req_dump_alloc(void)
+static inline struct devlink_port_del_req *devlink_port_del_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump));
+	return calloc(1, sizeof(struct devlink_port_del_req));
 }
-void
-devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req);
+void devlink_port_del_req_free(struct devlink_port_del_req *req);
 
 static inline void
-devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req,
-					  const char *bus_name)
+devlink_port_del_req_set_bus_name(struct devlink_port_del_req *req,
+				  const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -495,8 +749,8 @@ devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *r
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req,
-					  const char *dev_name)
+devlink_port_del_req_set_dev_name(struct devlink_port_del_req *req,
+				  const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -504,47 +758,44 @@ devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *r
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_port_del_req_set_port_index(struct devlink_port_del_req *req,
+				    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
 
-struct devlink_sb_pool_get_list {
-	struct devlink_sb_pool_get_list *next;
-	struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
-
-struct devlink_sb_pool_get_list *
-devlink_sb_pool_get_dump(struct ynl_sock *ys,
-			 struct devlink_sb_pool_get_req_dump *req);
+/*
+ * Delete devlink port instances.
+ */
+int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req);
 
-/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
-/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
-struct devlink_sb_port_pool_get_req {
+/* ============== DEVLINK_CMD_PORT_SPLIT ============== */
+/* DEVLINK_CMD_PORT_SPLIT - do */
+struct devlink_port_split_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
 		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
+		__u32 port_split_count:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
 	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
+	__u32 port_split_count;
 };
 
-static inline struct devlink_sb_port_pool_get_req *
-devlink_sb_port_pool_get_req_alloc(void)
+static inline struct devlink_port_split_req *devlink_port_split_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req));
+	return calloc(1, sizeof(struct devlink_port_split_req));
 }
-void
-devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req);
+void devlink_port_split_req_free(struct devlink_port_split_req *req);
 
 static inline void
-devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req,
-					  const char *bus_name)
+devlink_port_split_req_set_bus_name(struct devlink_port_split_req *req,
+				    const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -553,8 +804,8 @@ devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *r
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req,
-					  const char *dev_name)
+devlink_port_split_req_set_dev_name(struct devlink_port_split_req *req,
+				    const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -563,75 +814,49 @@ devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *r
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req,
-					    __u32 port_index)
+devlink_port_split_req_set_port_index(struct devlink_port_split_req *req,
+				      __u32 port_index)
 {
 	req->_present.port_index = 1;
 	req->port_index = port_index;
 }
 static inline void
-devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req,
-					  __u32 sb_index)
-{
-	req->_present.sb_index = 1;
-	req->sb_index = sb_index;
-}
-static inline void
-devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req,
-					       __u16 sb_pool_index)
+devlink_port_split_req_set_port_split_count(struct devlink_port_split_req *req,
+					    __u32 port_split_count)
 {
-	req->_present.sb_pool_index = 1;
-	req->sb_pool_index = sb_pool_index;
+	req->_present.port_split_count = 1;
+	req->port_split_count = port_split_count;
 }
 
-struct devlink_sb_port_pool_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 sb_index:1;
-		__u32 sb_pool_index:1;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	__u32 sb_index;
-	__u16 sb_pool_index;
-};
-
-void
-devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp);
-
 /*
- * Get shared buffer port-pool combinations and threshold.
+ * Split devlink port instances.
  */
-struct devlink_sb_port_pool_get_rsp *
-devlink_sb_port_pool_get(struct ynl_sock *ys,
-			 struct devlink_sb_port_pool_get_req *req);
+int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req);
 
-/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
-struct devlink_sb_port_pool_get_req_dump {
+/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */
+/* DEVLINK_CMD_PORT_UNSPLIT - do */
+struct devlink_port_unsplit_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
 };
 
-static inline struct devlink_sb_port_pool_get_req_dump *
-devlink_sb_port_pool_get_req_dump_alloc(void)
+static inline struct devlink_port_unsplit_req *
+devlink_port_unsplit_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump));
+	return calloc(1, sizeof(struct devlink_port_unsplit_req));
 }
-void
-devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req);
+void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req);
 
 static inline void
-devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req,
-					       const char *bus_name)
+devlink_port_unsplit_req_set_bus_name(struct devlink_port_unsplit_req *req,
+				      const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -640,8 +865,8 @@ devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_r
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req,
-					       const char *dev_name)
+devlink_port_unsplit_req_set_dev_name(struct devlink_port_unsplit_req *req,
+				      const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -649,50 +874,43 @@ devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_r
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_port_unsplit_req_set_port_index(struct devlink_port_unsplit_req *req,
+					__u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
 
-struct devlink_sb_port_pool_get_list {
-	struct devlink_sb_port_pool_get_list *next;
-	struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void
-devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp);
-
-struct devlink_sb_port_pool_get_list *
-devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
-			      struct devlink_sb_port_pool_get_req_dump *req);
+/*
+ * Unplit devlink port instances.
+ */
+int devlink_port_unsplit(struct ynl_sock *ys,
+			 struct devlink_port_unsplit_req *req);
 
-/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
-struct devlink_sb_tc_pool_bind_get_req {
+/* ============== DEVLINK_CMD_SB_GET ============== */
+/* DEVLINK_CMD_SB_GET - do */
+struct devlink_sb_get_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 port_index:1;
 		__u32 sb_index:1;
-		__u32 sb_pool_type:1;
-		__u32 sb_tc_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	__u32 port_index;
 	__u32 sb_index;
-	enum devlink_sb_pool_type sb_pool_type;
-	__u16 sb_tc_index;
 };
 
-static inline struct devlink_sb_tc_pool_bind_get_req *
-devlink_sb_tc_pool_bind_get_req_alloc(void)
+static inline struct devlink_sb_get_req *devlink_sb_get_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req));
+	return calloc(1, sizeof(struct devlink_sb_get_req));
 }
-void
-devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req);
+void devlink_sb_get_req_free(struct devlink_sb_get_req *req);
 
 static inline void
-devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req,
-					     const char *bus_name)
+devlink_sb_get_req_set_bus_name(struct devlink_sb_get_req *req,
+				const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -701,8 +919,8 @@ devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req,
-					     const char *dev_name)
+devlink_sb_get_req_set_dev_name(struct devlink_sb_get_req *req,
+				const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -711,64 +929,34 @@ devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req,
-					       __u32 port_index)
-{
-	req->_present.port_index = 1;
-	req->port_index = port_index;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req,
-					     __u32 sb_index)
+devlink_sb_get_req_set_sb_index(struct devlink_sb_get_req *req, __u32 sb_index)
 {
 	req->_present.sb_index = 1;
 	req->sb_index = sb_index;
 }
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req,
-						 enum devlink_sb_pool_type sb_pool_type)
-{
-	req->_present.sb_pool_type = 1;
-	req->sb_pool_type = sb_pool_type;
-}
-static inline void
-devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req,
-						__u16 sb_tc_index)
-{
-	req->_present.sb_tc_index = 1;
-	req->sb_tc_index = sb_tc_index;
-}
 
-struct devlink_sb_tc_pool_bind_get_rsp {
+struct devlink_sb_get_rsp {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 port_index:1;
 		__u32 sb_index:1;
-		__u32 sb_pool_type:1;
-		__u32 sb_tc_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	__u32 port_index;
 	__u32 sb_index;
-	enum devlink_sb_pool_type sb_pool_type;
-	__u16 sb_tc_index;
 };
 
-void
-devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp);
+void devlink_sb_get_rsp_free(struct devlink_sb_get_rsp *rsp);
 
 /*
- * Get shared buffer port-TC to pool bindings and threshold.
+ * Get shared buffer instances.
  */
-struct devlink_sb_tc_pool_bind_get_rsp *
-devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
-			    struct devlink_sb_tc_pool_bind_get_req *req);
+struct devlink_sb_get_rsp *
+devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req);
 
-/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
-struct devlink_sb_tc_pool_bind_get_req_dump {
+/* DEVLINK_CMD_SB_GET - dump */
+struct devlink_sb_get_req_dump {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
@@ -778,17 +966,16 @@ struct devlink_sb_tc_pool_bind_get_req_dump {
 	char *dev_name;
 };
 
-static inline struct devlink_sb_tc_pool_bind_get_req_dump *
-devlink_sb_tc_pool_bind_get_req_dump_alloc(void)
+static inline struct devlink_sb_get_req_dump *
+devlink_sb_get_req_dump_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump));
+	return calloc(1, sizeof(struct devlink_sb_get_req_dump));
 }
-void
-devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req);
+void devlink_sb_get_req_dump_free(struct devlink_sb_get_req_dump *req);
 
 static inline void
-devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
-						  const char *bus_name)
+devlink_sb_get_req_dump_set_bus_name(struct devlink_sb_get_req_dump *req,
+				     const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -797,8 +984,8 @@ devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
-						  const char *dev_name)
+devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req,
+				     const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -807,41 +994,42 @@ devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 
-struct devlink_sb_tc_pool_bind_get_list {
-	struct devlink_sb_tc_pool_bind_get_list *next;
-	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8)));
+struct devlink_sb_get_list {
+	struct devlink_sb_get_list *next;
+	struct devlink_sb_get_rsp obj __attribute__ ((aligned (8)));
 };
 
-void
-devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp);
+void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp);
 
-struct devlink_sb_tc_pool_bind_get_list *
-devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
-				 struct devlink_sb_tc_pool_bind_get_req_dump *req);
+struct devlink_sb_get_list *
+devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req);
 
-/* ============== DEVLINK_CMD_PARAM_GET ============== */
-/* DEVLINK_CMD_PARAM_GET - do */
-struct devlink_param_get_req {
+/* ============== DEVLINK_CMD_SB_POOL_GET ============== */
+/* DEVLINK_CMD_SB_POOL_GET - do */
+struct devlink_sb_pool_get_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 param_name_len;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	char *param_name;
+	__u32 sb_index;
+	__u16 sb_pool_index;
 };
 
-static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void)
+static inline struct devlink_sb_pool_get_req *
+devlink_sb_pool_get_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_param_get_req));
+	return calloc(1, sizeof(struct devlink_sb_pool_get_req));
 }
-void devlink_param_get_req_free(struct devlink_param_get_req *req);
+void devlink_sb_pool_get_req_free(struct devlink_sb_pool_get_req *req);
 
 static inline void
-devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req,
-				   const char *bus_name)
+devlink_sb_pool_get_req_set_bus_name(struct devlink_sb_pool_get_req *req,
+				     const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -850,8 +1038,8 @@ devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req,
-				   const char *dev_name)
+devlink_sb_pool_get_req_set_dev_name(struct devlink_sb_pool_get_req *req,
+				     const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -860,38 +1048,44 @@ devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req,
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_param_get_req_set_param_name(struct devlink_param_get_req *req,
-				     const char *param_name)
+devlink_sb_pool_get_req_set_sb_index(struct devlink_sb_pool_get_req *req,
+				     __u32 sb_index)
 {
-	free(req->param_name);
-	req->_present.param_name_len = strlen(param_name);
-	req->param_name = malloc(req->_present.param_name_len + 1);
-	memcpy(req->param_name, param_name, req->_present.param_name_len);
-	req->param_name[req->_present.param_name_len] = 0;
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_pool_get_req_set_sb_pool_index(struct devlink_sb_pool_get_req *req,
+					  __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
 }
 
-struct devlink_param_get_rsp {
+struct devlink_sb_pool_get_rsp {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 param_name_len;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	char *param_name;
+	__u32 sb_index;
+	__u16 sb_pool_index;
 };
 
-void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp);
+void devlink_sb_pool_get_rsp_free(struct devlink_sb_pool_get_rsp *rsp);
 
 /*
- * Get param instances.
+ * Get shared buffer pool instances.
  */
-struct devlink_param_get_rsp *
-devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req);
+struct devlink_sb_pool_get_rsp *
+devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req);
 
-/* DEVLINK_CMD_PARAM_GET - dump */
-struct devlink_param_get_req_dump {
+/* DEVLINK_CMD_SB_POOL_GET - dump */
+struct devlink_sb_pool_get_req_dump {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
@@ -901,16 +1095,2307 @@ struct devlink_param_get_req_dump {
 	char *dev_name;
 };
 
-static inline struct devlink_param_get_req_dump *
-devlink_param_get_req_dump_alloc(void)
+static inline struct devlink_sb_pool_get_req_dump *
+devlink_sb_pool_get_req_dump_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_param_get_req_dump));
+	return calloc(1, sizeof(struct devlink_sb_pool_get_req_dump));
 }
-void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req);
+void
+devlink_sb_pool_get_req_dump_free(struct devlink_sb_pool_get_req_dump *req);
+
+static inline void
+devlink_sb_pool_get_req_dump_set_bus_name(struct devlink_sb_pool_get_req_dump *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_sb_pool_get_list {
+	struct devlink_sb_pool_get_list *next;
+	struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp);
+
+struct devlink_sb_pool_get_list *
+devlink_sb_pool_get_dump(struct ynl_sock *ys,
+			 struct devlink_sb_pool_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_SB_POOL_SET ============== */
+/* DEVLINK_CMD_SB_POOL_SET - do */
+struct devlink_sb_pool_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+		__u32 sb_pool_threshold_type:1;
+		__u32 sb_pool_size:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+	enum devlink_sb_threshold_type sb_pool_threshold_type;
+	__u32 sb_pool_size;
+};
+
+static inline struct devlink_sb_pool_set_req *
+devlink_sb_pool_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_pool_set_req));
+}
+void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req);
+
+static inline void
+devlink_sb_pool_set_req_set_bus_name(struct devlink_sb_pool_set_req *req,
+				     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_set_req_set_dev_name(struct devlink_sb_pool_set_req *req,
+				     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_pool_set_req_set_sb_index(struct devlink_sb_pool_set_req *req,
+				     __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_pool_set_req_set_sb_pool_index(struct devlink_sb_pool_set_req *req,
+					  __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+static inline void
+devlink_sb_pool_set_req_set_sb_pool_threshold_type(struct devlink_sb_pool_set_req *req,
+						   enum devlink_sb_threshold_type sb_pool_threshold_type)
+{
+	req->_present.sb_pool_threshold_type = 1;
+	req->sb_pool_threshold_type = sb_pool_threshold_type;
+}
+static inline void
+devlink_sb_pool_set_req_set_sb_pool_size(struct devlink_sb_pool_set_req *req,
+					 __u32 sb_pool_size)
+{
+	req->_present.sb_pool_size = 1;
+	req->sb_pool_size = sb_pool_size;
+}
+
+/*
+ * Set shared buffer pool instances.
+ */
+int devlink_sb_pool_set(struct ynl_sock *ys,
+			struct devlink_sb_pool_set_req *req);
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_GET - do */
+struct devlink_sb_port_pool_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+static inline struct devlink_sb_port_pool_get_req *
+devlink_sb_port_pool_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req));
+}
+void
+devlink_sb_port_pool_get_req_free(struct devlink_sb_port_pool_get_req *req);
+
+static inline void
+devlink_sb_port_pool_get_req_set_bus_name(struct devlink_sb_port_pool_get_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_dev_name(struct devlink_sb_port_pool_get_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_port_index(struct devlink_sb_port_pool_get_req *req,
+					    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_sb_index(struct devlink_sb_port_pool_get_req *req,
+					  __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_port_pool_get_req_set_sb_pool_index(struct devlink_sb_port_pool_get_req *req,
+					       __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+
+struct devlink_sb_port_pool_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+};
+
+void
+devlink_sb_port_pool_get_rsp_free(struct devlink_sb_port_pool_get_rsp *rsp);
+
+/*
+ * Get shared buffer port-pool combinations and threshold.
+ */
+struct devlink_sb_port_pool_get_rsp *
+devlink_sb_port_pool_get(struct ynl_sock *ys,
+			 struct devlink_sb_port_pool_get_req *req);
+
+/* DEVLINK_CMD_SB_PORT_POOL_GET - dump */
+struct devlink_sb_port_pool_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_port_pool_get_req_dump *
+devlink_sb_port_pool_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_port_pool_get_req_dump));
+}
+void
+devlink_sb_port_pool_get_req_dump_free(struct devlink_sb_port_pool_get_req_dump *req);
+
+static inline void
+devlink_sb_port_pool_get_req_dump_set_bus_name(struct devlink_sb_port_pool_get_req_dump *req,
+					       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_req_dump *req,
+					       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_sb_port_pool_get_list {
+	struct devlink_sb_port_pool_get_list *next;
+	struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_sb_port_pool_get_list_free(struct devlink_sb_port_pool_get_list *rsp);
+
+struct devlink_sb_port_pool_get_list *
+devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
+			      struct devlink_sb_port_pool_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */
+/* DEVLINK_CMD_SB_PORT_POOL_SET - do */
+struct devlink_sb_port_pool_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+		__u32 sb_threshold:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+	__u32 sb_threshold;
+};
+
+static inline struct devlink_sb_port_pool_set_req *
+devlink_sb_port_pool_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_port_pool_set_req));
+}
+void
+devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req);
+
+static inline void
+devlink_sb_port_pool_set_req_set_bus_name(struct devlink_sb_port_pool_set_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_set_req_set_dev_name(struct devlink_sb_port_pool_set_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_port_pool_set_req_set_port_index(struct devlink_sb_port_pool_set_req *req,
+					    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_port_pool_set_req_set_sb_index(struct devlink_sb_port_pool_set_req *req,
+					  __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_port_pool_set_req_set_sb_pool_index(struct devlink_sb_port_pool_set_req *req,
+					       __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+static inline void
+devlink_sb_port_pool_set_req_set_sb_threshold(struct devlink_sb_port_pool_set_req *req,
+					      __u32 sb_threshold)
+{
+	req->_present.sb_threshold = 1;
+	req->sb_threshold = sb_threshold;
+}
+
+/*
+ * Set shared buffer port-pool combinations and threshold.
+ */
+int devlink_sb_port_pool_set(struct ynl_sock *ys,
+			     struct devlink_sb_port_pool_set_req *req);
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */
+struct devlink_sb_tc_pool_bind_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_type:1;
+		__u32 sb_tc_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	enum devlink_sb_pool_type sb_pool_type;
+	__u16 sb_tc_index;
+};
+
+static inline struct devlink_sb_tc_pool_bind_get_req *
+devlink_sb_tc_pool_bind_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req));
+}
+void
+devlink_sb_tc_pool_bind_get_req_free(struct devlink_sb_tc_pool_bind_get_req *req);
+
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_bus_name(struct devlink_sb_tc_pool_bind_get_req *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_dev_name(struct devlink_sb_tc_pool_bind_get_req *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_port_index(struct devlink_sb_tc_pool_bind_get_req *req,
+					       __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_index(struct devlink_sb_tc_pool_bind_get_req *req,
+					     __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_get_req *req,
+						 enum devlink_sb_pool_type sb_pool_type)
+{
+	req->_present.sb_pool_type = 1;
+	req->sb_pool_type = sb_pool_type;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_get_req *req,
+						__u16 sb_tc_index)
+{
+	req->_present.sb_tc_index = 1;
+	req->sb_tc_index = sb_tc_index;
+}
+
+struct devlink_sb_tc_pool_bind_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_type:1;
+		__u32 sb_tc_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	enum devlink_sb_pool_type sb_pool_type;
+	__u16 sb_tc_index;
+};
+
+void
+devlink_sb_tc_pool_bind_get_rsp_free(struct devlink_sb_tc_pool_bind_get_rsp *rsp);
+
+/*
+ * Get shared buffer port-TC to pool bindings and threshold.
+ */
+struct devlink_sb_tc_pool_bind_get_rsp *
+devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
+			    struct devlink_sb_tc_pool_bind_get_req *req);
+
+/* DEVLINK_CMD_SB_TC_POOL_BIND_GET - dump */
+struct devlink_sb_tc_pool_bind_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_sb_tc_pool_bind_get_req_dump *
+devlink_sb_tc_pool_bind_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_get_req_dump));
+}
+void
+devlink_sb_tc_pool_bind_get_req_dump_free(struct devlink_sb_tc_pool_bind_get_req_dump *req);
+
+static inline void
+devlink_sb_tc_pool_bind_get_req_dump_set_bus_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
+						  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind_get_req_dump *req,
+						  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_sb_tc_pool_bind_get_list {
+	struct devlink_sb_tc_pool_bind_get_list *next;
+	struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void
+devlink_sb_tc_pool_bind_get_list_free(struct devlink_sb_tc_pool_bind_get_list *rsp);
+
+struct devlink_sb_tc_pool_bind_get_list *
+devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
+				 struct devlink_sb_tc_pool_bind_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */
+/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */
+struct devlink_sb_tc_pool_bind_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 sb_index:1;
+		__u32 sb_pool_index:1;
+		__u32 sb_pool_type:1;
+		__u32 sb_tc_index:1;
+		__u32 sb_threshold:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	__u32 sb_index;
+	__u16 sb_pool_index;
+	enum devlink_sb_pool_type sb_pool_type;
+	__u16 sb_tc_index;
+	__u32 sb_threshold;
+};
+
+static inline struct devlink_sb_tc_pool_bind_set_req *
+devlink_sb_tc_pool_bind_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_set_req));
+}
+void
+devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req);
+
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_bus_name(struct devlink_sb_tc_pool_bind_set_req *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_dev_name(struct devlink_sb_tc_pool_bind_set_req *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_port_index(struct devlink_sb_tc_pool_bind_set_req *req,
+					       __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_sb_index(struct devlink_sb_tc_pool_bind_set_req *req,
+					     __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_sb_pool_index(struct devlink_sb_tc_pool_bind_set_req *req,
+						  __u16 sb_pool_index)
+{
+	req->_present.sb_pool_index = 1;
+	req->sb_pool_index = sb_pool_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_set_req *req,
+						 enum devlink_sb_pool_type sb_pool_type)
+{
+	req->_present.sb_pool_type = 1;
+	req->sb_pool_type = sb_pool_type;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_set_req *req,
+						__u16 sb_tc_index)
+{
+	req->_present.sb_tc_index = 1;
+	req->sb_tc_index = sb_tc_index;
+}
+static inline void
+devlink_sb_tc_pool_bind_set_req_set_sb_threshold(struct devlink_sb_tc_pool_bind_set_req *req,
+						 __u32 sb_threshold)
+{
+	req->_present.sb_threshold = 1;
+	req->sb_threshold = sb_threshold;
+}
+
+/*
+ * Set shared buffer port-TC to pool bindings and threshold.
+ */
+int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
+				struct devlink_sb_tc_pool_bind_set_req *req);
+
+/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */
+/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */
+struct devlink_sb_occ_snapshot_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+};
+
+static inline struct devlink_sb_occ_snapshot_req *
+devlink_sb_occ_snapshot_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_occ_snapshot_req));
+}
+void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req);
+
+static inline void
+devlink_sb_occ_snapshot_req_set_bus_name(struct devlink_sb_occ_snapshot_req *req,
+					 const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_occ_snapshot_req_set_dev_name(struct devlink_sb_occ_snapshot_req *req,
+					 const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_occ_snapshot_req_set_sb_index(struct devlink_sb_occ_snapshot_req *req,
+					 __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+
+/*
+ * Take occupancy snapshot of shared buffer.
+ */
+int devlink_sb_occ_snapshot(struct ynl_sock *ys,
+			    struct devlink_sb_occ_snapshot_req *req);
+
+/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */
+/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */
+struct devlink_sb_occ_max_clear_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 sb_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 sb_index;
+};
+
+static inline struct devlink_sb_occ_max_clear_req *
+devlink_sb_occ_max_clear_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_sb_occ_max_clear_req));
+}
+void
+devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req);
+
+static inline void
+devlink_sb_occ_max_clear_req_set_bus_name(struct devlink_sb_occ_max_clear_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_sb_occ_max_clear_req_set_dev_name(struct devlink_sb_occ_max_clear_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_sb_occ_max_clear_req_set_sb_index(struct devlink_sb_occ_max_clear_req *req,
+					  __u32 sb_index)
+{
+	req->_present.sb_index = 1;
+	req->sb_index = sb_index;
+}
+
+/*
+ * Clear occupancy watermarks of shared buffer.
+ */
+int devlink_sb_occ_max_clear(struct ynl_sock *ys,
+			     struct devlink_sb_occ_max_clear_req *req);
+
+/* ============== DEVLINK_CMD_ESWITCH_GET ============== */
+/* DEVLINK_CMD_ESWITCH_GET - do */
+struct devlink_eswitch_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_eswitch_get_req *
+devlink_eswitch_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_eswitch_get_req));
+}
+void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req);
+
+static inline void
+devlink_eswitch_get_req_set_bus_name(struct devlink_eswitch_get_req *req,
+				     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_eswitch_get_req_set_dev_name(struct devlink_eswitch_get_req *req,
+				     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_eswitch_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 eswitch_mode:1;
+		__u32 eswitch_inline_mode:1;
+		__u32 eswitch_encap_mode:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	enum devlink_eswitch_mode eswitch_mode;
+	enum devlink_eswitch_inline_mode eswitch_inline_mode;
+	enum devlink_eswitch_encap_mode eswitch_encap_mode;
+};
+
+void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp);
+
+/*
+ * Get eswitch attributes.
+ */
+struct devlink_eswitch_get_rsp *
+devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req);
+
+/* ============== DEVLINK_CMD_ESWITCH_SET ============== */
+/* DEVLINK_CMD_ESWITCH_SET - do */
+struct devlink_eswitch_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 eswitch_mode:1;
+		__u32 eswitch_inline_mode:1;
+		__u32 eswitch_encap_mode:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	enum devlink_eswitch_mode eswitch_mode;
+	enum devlink_eswitch_inline_mode eswitch_inline_mode;
+	enum devlink_eswitch_encap_mode eswitch_encap_mode;
+};
+
+static inline struct devlink_eswitch_set_req *
+devlink_eswitch_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_eswitch_set_req));
+}
+void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req);
+
+static inline void
+devlink_eswitch_set_req_set_bus_name(struct devlink_eswitch_set_req *req,
+				     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_eswitch_set_req_set_dev_name(struct devlink_eswitch_set_req *req,
+				     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_eswitch_set_req_set_eswitch_mode(struct devlink_eswitch_set_req *req,
+					 enum devlink_eswitch_mode eswitch_mode)
+{
+	req->_present.eswitch_mode = 1;
+	req->eswitch_mode = eswitch_mode;
+}
+static inline void
+devlink_eswitch_set_req_set_eswitch_inline_mode(struct devlink_eswitch_set_req *req,
+						enum devlink_eswitch_inline_mode eswitch_inline_mode)
+{
+	req->_present.eswitch_inline_mode = 1;
+	req->eswitch_inline_mode = eswitch_inline_mode;
+}
+static inline void
+devlink_eswitch_set_req_set_eswitch_encap_mode(struct devlink_eswitch_set_req *req,
+					       enum devlink_eswitch_encap_mode eswitch_encap_mode)
+{
+	req->_present.eswitch_encap_mode = 1;
+	req->eswitch_encap_mode = eswitch_encap_mode;
+}
+
+/*
+ * Set eswitch attributes.
+ */
+int devlink_eswitch_set(struct ynl_sock *ys,
+			struct devlink_eswitch_set_req *req);
+
+/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */
+/* DEVLINK_CMD_DPIPE_TABLE_GET - do */
+struct devlink_dpipe_table_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_table_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *dpipe_table_name;
+};
+
+static inline struct devlink_dpipe_table_get_req *
+devlink_dpipe_table_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_dpipe_table_get_req));
+}
+void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req);
+
+static inline void
+devlink_dpipe_table_get_req_set_bus_name(struct devlink_dpipe_table_get_req *req,
+					 const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_dpipe_table_get_req_set_dev_name(struct devlink_dpipe_table_get_req *req,
+					 const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_dpipe_table_get_req_set_dpipe_table_name(struct devlink_dpipe_table_get_req *req,
+						 const char *dpipe_table_name)
+{
+	free(req->dpipe_table_name);
+	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
+	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
+	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
+	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
+}
+
+struct devlink_dpipe_table_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_tables:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct devlink_dl_dpipe_tables dpipe_tables;
+};
+
+void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp);
+
+/*
+ * Get dpipe table attributes.
+ */
+struct devlink_dpipe_table_get_rsp *
+devlink_dpipe_table_get(struct ynl_sock *ys,
+			struct devlink_dpipe_table_get_req *req);
+
+/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */
+/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */
+struct devlink_dpipe_entries_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_table_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *dpipe_table_name;
+};
+
+static inline struct devlink_dpipe_entries_get_req *
+devlink_dpipe_entries_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_dpipe_entries_get_req));
+}
+void
+devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req);
+
+static inline void
+devlink_dpipe_entries_get_req_set_bus_name(struct devlink_dpipe_entries_get_req *req,
+					   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_dpipe_entries_get_req_set_dev_name(struct devlink_dpipe_entries_get_req *req,
+					   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_dpipe_entries_get_req_set_dpipe_table_name(struct devlink_dpipe_entries_get_req *req,
+						   const char *dpipe_table_name)
+{
+	free(req->dpipe_table_name);
+	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
+	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
+	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
+	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
+}
+
+struct devlink_dpipe_entries_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_entries:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct devlink_dl_dpipe_entries dpipe_entries;
+};
+
+void
+devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp);
+
+/*
+ * Get dpipe entries attributes.
+ */
+struct devlink_dpipe_entries_get_rsp *
+devlink_dpipe_entries_get(struct ynl_sock *ys,
+			  struct devlink_dpipe_entries_get_req *req);
+
+/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */
+/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */
+struct devlink_dpipe_headers_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_dpipe_headers_get_req *
+devlink_dpipe_headers_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_dpipe_headers_get_req));
+}
+void
+devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req);
+
+static inline void
+devlink_dpipe_headers_get_req_set_bus_name(struct devlink_dpipe_headers_get_req *req,
+					   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_dpipe_headers_get_req_set_dev_name(struct devlink_dpipe_headers_get_req *req,
+					   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_dpipe_headers_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_headers:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct devlink_dl_dpipe_headers dpipe_headers;
+};
+
+void
+devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp);
+
+/*
+ * Get dpipe headers attributes.
+ */
+struct devlink_dpipe_headers_get_rsp *
+devlink_dpipe_headers_get(struct ynl_sock *ys,
+			  struct devlink_dpipe_headers_get_req *req);
+
+/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */
+/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */
+struct devlink_dpipe_table_counters_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 dpipe_table_name_len;
+		__u32 dpipe_table_counters_enabled:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *dpipe_table_name;
+	__u8 dpipe_table_counters_enabled;
+};
+
+static inline struct devlink_dpipe_table_counters_set_req *
+devlink_dpipe_table_counters_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_dpipe_table_counters_set_req));
+}
+void
+devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req);
+
+static inline void
+devlink_dpipe_table_counters_set_req_set_bus_name(struct devlink_dpipe_table_counters_set_req *req,
+						  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_dpipe_table_counters_set_req_set_dev_name(struct devlink_dpipe_table_counters_set_req *req,
+						  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_dpipe_table_counters_set_req_set_dpipe_table_name(struct devlink_dpipe_table_counters_set_req *req,
+							  const char *dpipe_table_name)
+{
+	free(req->dpipe_table_name);
+	req->_present.dpipe_table_name_len = strlen(dpipe_table_name);
+	req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1);
+	memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len);
+	req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0;
+}
+static inline void
+devlink_dpipe_table_counters_set_req_set_dpipe_table_counters_enabled(struct devlink_dpipe_table_counters_set_req *req,
+								      __u8 dpipe_table_counters_enabled)
+{
+	req->_present.dpipe_table_counters_enabled = 1;
+	req->dpipe_table_counters_enabled = dpipe_table_counters_enabled;
+}
+
+/*
+ * Set dpipe counter attributes.
+ */
+int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
+				     struct devlink_dpipe_table_counters_set_req *req);
+
+/* ============== DEVLINK_CMD_RESOURCE_SET ============== */
+/* DEVLINK_CMD_RESOURCE_SET - do */
+struct devlink_resource_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 resource_id:1;
+		__u32 resource_size:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u64 resource_id;
+	__u64 resource_size;
+};
+
+static inline struct devlink_resource_set_req *
+devlink_resource_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_resource_set_req));
+}
+void devlink_resource_set_req_free(struct devlink_resource_set_req *req);
+
+static inline void
+devlink_resource_set_req_set_bus_name(struct devlink_resource_set_req *req,
+				      const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_resource_set_req_set_dev_name(struct devlink_resource_set_req *req,
+				      const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_resource_set_req_set_resource_id(struct devlink_resource_set_req *req,
+					 __u64 resource_id)
+{
+	req->_present.resource_id = 1;
+	req->resource_id = resource_id;
+}
+static inline void
+devlink_resource_set_req_set_resource_size(struct devlink_resource_set_req *req,
+					   __u64 resource_size)
+{
+	req->_present.resource_size = 1;
+	req->resource_size = resource_size;
+}
+
+/*
+ * Set resource attributes.
+ */
+int devlink_resource_set(struct ynl_sock *ys,
+			 struct devlink_resource_set_req *req);
+
+/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */
+/* DEVLINK_CMD_RESOURCE_DUMP - do */
+struct devlink_resource_dump_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_resource_dump_req *
+devlink_resource_dump_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_resource_dump_req));
+}
+void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req);
+
+static inline void
+devlink_resource_dump_req_set_bus_name(struct devlink_resource_dump_req *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_resource_dump_req_set_dev_name(struct devlink_resource_dump_req *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_resource_dump_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 resource_list:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct devlink_dl_resource_list resource_list;
+};
+
+void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp);
+
+/*
+ * Get resource attributes.
+ */
+struct devlink_resource_dump_rsp *
+devlink_resource_dump(struct ynl_sock *ys,
+		      struct devlink_resource_dump_req *req);
+
+/* ============== DEVLINK_CMD_RELOAD ============== */
+/* DEVLINK_CMD_RELOAD - do */
+struct devlink_reload_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 reload_action:1;
+		__u32 reload_limits:1;
+		__u32 netns_pid:1;
+		__u32 netns_fd:1;
+		__u32 netns_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	enum devlink_reload_action reload_action;
+	struct nla_bitfield32 reload_limits;
+	__u32 netns_pid;
+	__u32 netns_fd;
+	__u32 netns_id;
+};
+
+static inline struct devlink_reload_req *devlink_reload_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_reload_req));
+}
+void devlink_reload_req_free(struct devlink_reload_req *req);
+
+static inline void
+devlink_reload_req_set_bus_name(struct devlink_reload_req *req,
+				const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_reload_req_set_dev_name(struct devlink_reload_req *req,
+				const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_reload_req_set_reload_action(struct devlink_reload_req *req,
+				     enum devlink_reload_action reload_action)
+{
+	req->_present.reload_action = 1;
+	req->reload_action = reload_action;
+}
+static inline void
+devlink_reload_req_set_reload_limits(struct devlink_reload_req *req,
+				     struct nla_bitfield32 *reload_limits)
+{
+	req->_present.reload_limits = 1;
+	memcpy(&req->reload_limits, reload_limits, sizeof(struct nla_bitfield32));
+}
+static inline void
+devlink_reload_req_set_netns_pid(struct devlink_reload_req *req,
+				 __u32 netns_pid)
+{
+	req->_present.netns_pid = 1;
+	req->netns_pid = netns_pid;
+}
+static inline void
+devlink_reload_req_set_netns_fd(struct devlink_reload_req *req, __u32 netns_fd)
+{
+	req->_present.netns_fd = 1;
+	req->netns_fd = netns_fd;
+}
+static inline void
+devlink_reload_req_set_netns_id(struct devlink_reload_req *req, __u32 netns_id)
+{
+	req->_present.netns_id = 1;
+	req->netns_id = netns_id;
+}
+
+struct devlink_reload_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 reload_actions_performed:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct nla_bitfield32 reload_actions_performed;
+};
+
+void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp);
+
+/*
+ * Reload devlink.
+ */
+struct devlink_reload_rsp *
+devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req);
+
+/* ============== DEVLINK_CMD_PARAM_GET ============== */
+/* DEVLINK_CMD_PARAM_GET - do */
+struct devlink_param_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 param_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *param_name;
+};
+
+static inline struct devlink_param_get_req *devlink_param_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_param_get_req));
+}
+void devlink_param_get_req_free(struct devlink_param_get_req *req);
+
+static inline void
+devlink_param_get_req_set_bus_name(struct devlink_param_get_req *req,
+				   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_set_dev_name(struct devlink_param_get_req *req,
+				   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_set_param_name(struct devlink_param_get_req *req,
+				     const char *param_name)
+{
+	free(req->param_name);
+	req->_present.param_name_len = strlen(param_name);
+	req->param_name = malloc(req->_present.param_name_len + 1);
+	memcpy(req->param_name, param_name, req->_present.param_name_len);
+	req->param_name[req->_present.param_name_len] = 0;
+}
+
+struct devlink_param_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 param_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *param_name;
+};
+
+void devlink_param_get_rsp_free(struct devlink_param_get_rsp *rsp);
+
+/*
+ * Get param instances.
+ */
+struct devlink_param_get_rsp *
+devlink_param_get(struct ynl_sock *ys, struct devlink_param_get_req *req);
+
+/* DEVLINK_CMD_PARAM_GET - dump */
+struct devlink_param_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_param_get_req_dump *
+devlink_param_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_param_get_req_dump));
+}
+void devlink_param_get_req_dump_free(struct devlink_param_get_req_dump *req);
+
+static inline void
+devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_param_get_list {
+	struct devlink_param_get_list *next;
+	struct devlink_param_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
+
+struct devlink_param_get_list *
+devlink_param_get_dump(struct ynl_sock *ys,
+		       struct devlink_param_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_PARAM_SET ============== */
+/* DEVLINK_CMD_PARAM_SET - do */
+struct devlink_param_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 param_name_len;
+		__u32 param_type:1;
+		__u32 param_value_cmode:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *param_name;
+	__u8 param_type;
+	enum devlink_param_cmode param_value_cmode;
+};
+
+static inline struct devlink_param_set_req *devlink_param_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_param_set_req));
+}
+void devlink_param_set_req_free(struct devlink_param_set_req *req);
+
+static inline void
+devlink_param_set_req_set_bus_name(struct devlink_param_set_req *req,
+				   const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_param_set_req_set_dev_name(struct devlink_param_set_req *req,
+				   const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_param_set_req_set_param_name(struct devlink_param_set_req *req,
+				     const char *param_name)
+{
+	free(req->param_name);
+	req->_present.param_name_len = strlen(param_name);
+	req->param_name = malloc(req->_present.param_name_len + 1);
+	memcpy(req->param_name, param_name, req->_present.param_name_len);
+	req->param_name[req->_present.param_name_len] = 0;
+}
+static inline void
+devlink_param_set_req_set_param_type(struct devlink_param_set_req *req,
+				     __u8 param_type)
+{
+	req->_present.param_type = 1;
+	req->param_type = param_type;
+}
+static inline void
+devlink_param_set_req_set_param_value_cmode(struct devlink_param_set_req *req,
+					    enum devlink_param_cmode param_value_cmode)
+{
+	req->_present.param_value_cmode = 1;
+	req->param_value_cmode = param_value_cmode;
+}
+
+/*
+ * Set param instances.
+ */
+int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req);
+
+/* ============== DEVLINK_CMD_REGION_GET ============== */
+/* DEVLINK_CMD_REGION_GET - do */
+struct devlink_region_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+};
+
+static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_get_req));
+}
+void devlink_region_get_req_free(struct devlink_region_get_req *req);
+
+static inline void
+devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req,
+				    const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req,
+				    const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_set_port_index(struct devlink_region_get_req *req,
+				      __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_region_get_req_set_region_name(struct devlink_region_get_req *req,
+				       const char *region_name)
+{
+	free(req->region_name);
+	req->_present.region_name_len = strlen(region_name);
+	req->region_name = malloc(req->_present.region_name_len + 1);
+	memcpy(req->region_name, region_name, req->_present.region_name_len);
+	req->region_name[req->_present.region_name_len] = 0;
+}
+
+struct devlink_region_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+};
+
+void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp);
+
+/*
+ * Get region instances.
+ */
+struct devlink_region_get_rsp *
+devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req);
+
+/* DEVLINK_CMD_REGION_GET - dump */
+struct devlink_region_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_region_get_req_dump *
+devlink_region_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_get_req_dump));
+}
+void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req);
+
+static inline void
+devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req,
+					 const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req,
+					 const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_region_get_list {
+	struct devlink_region_get_list *next;
+	struct devlink_region_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
+
+struct devlink_region_get_list *
+devlink_region_get_dump(struct ynl_sock *ys,
+			struct devlink_region_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_REGION_NEW ============== */
+/* DEVLINK_CMD_REGION_NEW - do */
+struct devlink_region_new_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+		__u32 region_snapshot_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+	__u32 region_snapshot_id;
+};
+
+static inline struct devlink_region_new_req *devlink_region_new_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_new_req));
+}
+void devlink_region_new_req_free(struct devlink_region_new_req *req);
+
+static inline void
+devlink_region_new_req_set_bus_name(struct devlink_region_new_req *req,
+				    const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_new_req_set_dev_name(struct devlink_region_new_req *req,
+				    const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_region_new_req_set_port_index(struct devlink_region_new_req *req,
+				      __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_region_new_req_set_region_name(struct devlink_region_new_req *req,
+				       const char *region_name)
+{
+	free(req->region_name);
+	req->_present.region_name_len = strlen(region_name);
+	req->region_name = malloc(req->_present.region_name_len + 1);
+	memcpy(req->region_name, region_name, req->_present.region_name_len);
+	req->region_name[req->_present.region_name_len] = 0;
+}
+static inline void
+devlink_region_new_req_set_region_snapshot_id(struct devlink_region_new_req *req,
+					      __u32 region_snapshot_id)
+{
+	req->_present.region_snapshot_id = 1;
+	req->region_snapshot_id = region_snapshot_id;
+}
+
+struct devlink_region_new_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+		__u32 region_snapshot_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+	__u32 region_snapshot_id;
+};
+
+void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp);
+
+/*
+ * Create region snapshot.
+ */
+struct devlink_region_new_rsp *
+devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req);
+
+/* ============== DEVLINK_CMD_REGION_DEL ============== */
+/* DEVLINK_CMD_REGION_DEL - do */
+struct devlink_region_del_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+		__u32 region_snapshot_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+	__u32 region_snapshot_id;
+};
+
+static inline struct devlink_region_del_req *devlink_region_del_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_del_req));
+}
+void devlink_region_del_req_free(struct devlink_region_del_req *req);
+
+static inline void
+devlink_region_del_req_set_bus_name(struct devlink_region_del_req *req,
+				    const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_del_req_set_dev_name(struct devlink_region_del_req *req,
+				    const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_region_del_req_set_port_index(struct devlink_region_del_req *req,
+				      __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_region_del_req_set_region_name(struct devlink_region_del_req *req,
+				       const char *region_name)
+{
+	free(req->region_name);
+	req->_present.region_name_len = strlen(region_name);
+	req->region_name = malloc(req->_present.region_name_len + 1);
+	memcpy(req->region_name, region_name, req->_present.region_name_len);
+	req->region_name[req->_present.region_name_len] = 0;
+}
+static inline void
+devlink_region_del_req_set_region_snapshot_id(struct devlink_region_del_req *req,
+					      __u32 region_snapshot_id)
+{
+	req->_present.region_snapshot_id = 1;
+	req->region_snapshot_id = region_snapshot_id;
+}
+
+/*
+ * Delete region snapshot.
+ */
+int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req);
+
+/* ============== DEVLINK_CMD_REGION_READ ============== */
+/* DEVLINK_CMD_REGION_READ - dump */
+struct devlink_region_read_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+		__u32 region_snapshot_id:1;
+		__u32 region_direct:1;
+		__u32 region_chunk_addr:1;
+		__u32 region_chunk_len:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+	__u32 region_snapshot_id;
+	__u64 region_chunk_addr;
+	__u64 region_chunk_len;
+};
+
+static inline struct devlink_region_read_req_dump *
+devlink_region_read_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_region_read_req_dump));
+}
+void
+devlink_region_read_req_dump_free(struct devlink_region_read_req_dump *req);
+
+static inline void
+devlink_region_read_req_dump_set_bus_name(struct devlink_region_read_req_dump *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_region_read_req_dump_set_dev_name(struct devlink_region_read_req_dump *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_region_read_req_dump_set_port_index(struct devlink_region_read_req_dump *req,
+					    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_region_read_req_dump_set_region_name(struct devlink_region_read_req_dump *req,
+					     const char *region_name)
+{
+	free(req->region_name);
+	req->_present.region_name_len = strlen(region_name);
+	req->region_name = malloc(req->_present.region_name_len + 1);
+	memcpy(req->region_name, region_name, req->_present.region_name_len);
+	req->region_name[req->_present.region_name_len] = 0;
+}
+static inline void
+devlink_region_read_req_dump_set_region_snapshot_id(struct devlink_region_read_req_dump *req,
+						    __u32 region_snapshot_id)
+{
+	req->_present.region_snapshot_id = 1;
+	req->region_snapshot_id = region_snapshot_id;
+}
+static inline void
+devlink_region_read_req_dump_set_region_direct(struct devlink_region_read_req_dump *req)
+{
+	req->_present.region_direct = 1;
+}
+static inline void
+devlink_region_read_req_dump_set_region_chunk_addr(struct devlink_region_read_req_dump *req,
+						   __u64 region_chunk_addr)
+{
+	req->_present.region_chunk_addr = 1;
+	req->region_chunk_addr = region_chunk_addr;
+}
+static inline void
+devlink_region_read_req_dump_set_region_chunk_len(struct devlink_region_read_req_dump *req,
+						  __u64 region_chunk_len)
+{
+	req->_present.region_chunk_len = 1;
+	req->region_chunk_len = region_chunk_len;
+}
+
+struct devlink_region_read_rsp_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 region_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *region_name;
+};
+
+struct devlink_region_read_rsp_list {
+	struct devlink_region_read_rsp_list *next;
+	struct devlink_region_read_rsp_dump obj __attribute__((aligned(8)));
+};
+
+void
+devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp);
+
+struct devlink_region_read_rsp_list *
+devlink_region_read_dump(struct ynl_sock *ys,
+			 struct devlink_region_read_req_dump *req);
+
+/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */
+/* DEVLINK_CMD_PORT_PARAM_GET - do */
+struct devlink_port_param_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+static inline struct devlink_port_param_get_req *
+devlink_port_param_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_port_param_get_req));
+}
+void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req);
+
+static inline void
+devlink_port_param_get_req_set_bus_name(struct devlink_port_param_get_req *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_port_param_get_req_set_dev_name(struct devlink_port_param_get_req *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_port_param_get_req_set_port_index(struct devlink_port_param_get_req *req,
+					  __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+
+struct devlink_port_param_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp);
+
+/*
+ * Get port param instances.
+ */
+struct devlink_port_param_get_rsp *
+devlink_port_param_get(struct ynl_sock *ys,
+		       struct devlink_port_param_get_req *req);
+
+/* DEVLINK_CMD_PORT_PARAM_GET - dump */
+struct devlink_port_param_get_list {
+	struct devlink_port_param_get_list *next;
+	struct devlink_port_param_get_rsp obj __attribute__((aligned(8)));
+};
+
+void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp);
+
+struct devlink_port_param_get_list *
+devlink_port_param_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */
+/* DEVLINK_CMD_PORT_PARAM_SET - do */
+struct devlink_port_param_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+static inline struct devlink_port_param_set_req *
+devlink_port_param_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_port_param_set_req));
+}
+void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req);
+
+static inline void
+devlink_port_param_set_req_set_bus_name(struct devlink_port_param_set_req *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_port_param_set_req_set_dev_name(struct devlink_port_param_set_req *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_port_param_set_req_set_port_index(struct devlink_port_param_set_req *req,
+					  __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+
+/*
+ * Set port param instances.
+ */
+int devlink_port_param_set(struct ynl_sock *ys,
+			   struct devlink_port_param_set_req *req);
+
+/* ============== DEVLINK_CMD_INFO_GET ============== */
+/* DEVLINK_CMD_INFO_GET - do */
+struct devlink_info_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+};
+
+static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_info_get_req));
+}
+void devlink_info_get_req_free(struct devlink_info_get_req *req);
+
+static inline void
+devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+
+struct devlink_info_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 info_driver_name_len;
+		__u32 info_serial_number_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *info_driver_name;
+	char *info_serial_number;
+	unsigned int n_info_version_fixed;
+	struct devlink_dl_info_version *info_version_fixed;
+	unsigned int n_info_version_running;
+	struct devlink_dl_info_version *info_version_running;
+	unsigned int n_info_version_stored;
+	struct devlink_dl_info_version *info_version_stored;
+};
+
+void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
+
+/*
+ * Get device information, like driver name, hardware and firmware versions etc.
+ */
+struct devlink_info_get_rsp *
+devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
+
+/* DEVLINK_CMD_INFO_GET - dump */
+struct devlink_info_get_list {
+	struct devlink_info_get_list *next;
+	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
+};
+
+void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
+
+struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
+struct devlink_health_reporter_get_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
+};
+
+static inline struct devlink_health_reporter_get_req *
+devlink_health_reporter_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_get_req));
+}
+void
+devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req);
+
+static inline void
+devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req,
+					     const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req,
+					     const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req,
+					       __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req,
+							 const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
+
+struct devlink_health_reporter_get_rsp {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
+};
+
+void
+devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp);
+
+/*
+ * Get health reporter instances.
+ */
+struct devlink_health_reporter_get_rsp *
+devlink_health_reporter_get(struct ynl_sock *ys,
+			    struct devlink_health_reporter_get_req *req);
+
+/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
+struct devlink_health_reporter_get_req_dump {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+};
+
+static inline struct devlink_health_reporter_get_req_dump *
+devlink_health_reporter_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump));
+}
+void
+devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req);
 
 static inline void
-devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req,
-					const char *bus_name)
+devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req,
+						  const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -919,8 +3404,8 @@ devlink_param_get_req_dump_set_bus_name(struct devlink_param_get_req_dump *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
-					const char *dev_name)
+devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req,
+						  const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -928,43 +3413,59 @@ devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req,
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req,
+						    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
 
-struct devlink_param_get_list {
-	struct devlink_param_get_list *next;
-	struct devlink_param_get_rsp obj __attribute__ ((aligned (8)));
+struct devlink_health_reporter_get_list {
+	struct devlink_health_reporter_get_list *next;
+	struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8)));
 };
 
-void devlink_param_get_list_free(struct devlink_param_get_list *rsp);
+void
+devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp);
 
-struct devlink_param_get_list *
-devlink_param_get_dump(struct ynl_sock *ys,
-		       struct devlink_param_get_req_dump *req);
+struct devlink_health_reporter_get_list *
+devlink_health_reporter_get_dump(struct ynl_sock *ys,
+				 struct devlink_health_reporter_get_req_dump *req);
 
-/* ============== DEVLINK_CMD_REGION_GET ============== */
-/* DEVLINK_CMD_REGION_GET - do */
-struct devlink_region_get_req {
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */
+struct devlink_health_reporter_set_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
 		__u32 port_index:1;
-		__u32 region_name_len;
+		__u32 health_reporter_name_len;
+		__u32 health_reporter_graceful_period:1;
+		__u32 health_reporter_auto_recover:1;
+		__u32 health_reporter_auto_dump:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
 	__u32 port_index;
-	char *region_name;
+	char *health_reporter_name;
+	__u64 health_reporter_graceful_period;
+	__u8 health_reporter_auto_recover;
+	__u8 health_reporter_auto_dump;
 };
 
-static inline struct devlink_region_get_req *devlink_region_get_req_alloc(void)
+static inline struct devlink_health_reporter_set_req *
+devlink_health_reporter_set_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_region_get_req));
+	return calloc(1, sizeof(struct devlink_health_reporter_set_req));
 }
-void devlink_region_get_req_free(struct devlink_region_get_req *req);
+void
+devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req);
 
 static inline void
-devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req,
-				    const char *bus_name)
+devlink_health_reporter_set_req_set_bus_name(struct devlink_health_reporter_set_req *req,
+					     const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -973,8 +3474,8 @@ devlink_region_get_req_set_bus_name(struct devlink_region_get_req *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req,
-				    const char *dev_name)
+devlink_health_reporter_set_req_set_dev_name(struct devlink_health_reporter_set_req *req,
+					     const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -983,66 +3484,77 @@ devlink_region_get_req_set_dev_name(struct devlink_region_get_req *req,
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_region_get_req_set_port_index(struct devlink_region_get_req *req,
-				      __u32 port_index)
+devlink_health_reporter_set_req_set_port_index(struct devlink_health_reporter_set_req *req,
+					       __u32 port_index)
 {
 	req->_present.port_index = 1;
 	req->port_index = port_index;
 }
 static inline void
-devlink_region_get_req_set_region_name(struct devlink_region_get_req *req,
-				       const char *region_name)
+devlink_health_reporter_set_req_set_health_reporter_name(struct devlink_health_reporter_set_req *req,
+							 const char *health_reporter_name)
 {
-	free(req->region_name);
-	req->_present.region_name_len = strlen(region_name);
-	req->region_name = malloc(req->_present.region_name_len + 1);
-	memcpy(req->region_name, region_name, req->_present.region_name_len);
-	req->region_name[req->_present.region_name_len] = 0;
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_set_req_set_health_reporter_graceful_period(struct devlink_health_reporter_set_req *req,
+								    __u64 health_reporter_graceful_period)
+{
+	req->_present.health_reporter_graceful_period = 1;
+	req->health_reporter_graceful_period = health_reporter_graceful_period;
+}
+static inline void
+devlink_health_reporter_set_req_set_health_reporter_auto_recover(struct devlink_health_reporter_set_req *req,
+								 __u8 health_reporter_auto_recover)
+{
+	req->_present.health_reporter_auto_recover = 1;
+	req->health_reporter_auto_recover = health_reporter_auto_recover;
+}
+static inline void
+devlink_health_reporter_set_req_set_health_reporter_auto_dump(struct devlink_health_reporter_set_req *req,
+							      __u8 health_reporter_auto_dump)
+{
+	req->_present.health_reporter_auto_dump = 1;
+	req->health_reporter_auto_dump = health_reporter_auto_dump;
 }
-
-struct devlink_region_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 port_index:1;
-		__u32 region_name_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	__u32 port_index;
-	char *region_name;
-};
-
-void devlink_region_get_rsp_free(struct devlink_region_get_rsp *rsp);
 
 /*
- * Get region instances.
+ * Set health reporter instances.
  */
-struct devlink_region_get_rsp *
-devlink_region_get(struct ynl_sock *ys, struct devlink_region_get_req *req);
+int devlink_health_reporter_set(struct ynl_sock *ys,
+				struct devlink_health_reporter_set_req *req);
 
-/* DEVLINK_CMD_REGION_GET - dump */
-struct devlink_region_get_req_dump {
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */
+struct devlink_health_reporter_recover_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
 };
 
-static inline struct devlink_region_get_req_dump *
-devlink_region_get_req_dump_alloc(void)
+static inline struct devlink_health_reporter_recover_req *
+devlink_health_reporter_recover_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_region_get_req_dump));
+	return calloc(1, sizeof(struct devlink_health_reporter_recover_req));
 }
-void devlink_region_get_req_dump_free(struct devlink_region_get_req_dump *req);
+void
+devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req);
 
 static inline void
-devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req,
-					 const char *bus_name)
+devlink_health_reporter_recover_req_set_bus_name(struct devlink_health_reporter_recover_req *req,
+						 const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -1051,8 +3563,8 @@ devlink_region_get_req_dump_set_bus_name(struct devlink_region_get_req_dump *req
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req,
-					 const char *dev_name)
+devlink_health_reporter_recover_req_set_dev_name(struct devlink_health_reporter_recover_req *req,
+						 const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -1060,39 +3572,57 @@ devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
+static inline void
+devlink_health_reporter_recover_req_set_port_index(struct devlink_health_reporter_recover_req *req,
+						   __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_recover_req_set_health_reporter_name(struct devlink_health_reporter_recover_req *req,
+							     const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
 
-struct devlink_region_get_list {
-	struct devlink_region_get_list *next;
-	struct devlink_region_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void devlink_region_get_list_free(struct devlink_region_get_list *rsp);
-
-struct devlink_region_get_list *
-devlink_region_get_dump(struct ynl_sock *ys,
-			struct devlink_region_get_req_dump *req);
+/*
+ * Recover health reporter instances.
+ */
+int devlink_health_reporter_recover(struct ynl_sock *ys,
+				    struct devlink_health_reporter_recover_req *req);
 
-/* ============== DEVLINK_CMD_INFO_GET ============== */
-/* DEVLINK_CMD_INFO_GET - do */
-struct devlink_info_get_req {
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */
+struct devlink_health_reporter_diagnose_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
 };
 
-static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void)
+static inline struct devlink_health_reporter_diagnose_req *
+devlink_health_reporter_diagnose_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_info_get_req));
+	return calloc(1, sizeof(struct devlink_health_reporter_diagnose_req));
 }
-void devlink_info_get_req_free(struct devlink_info_get_req *req);
+void
+devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req);
 
 static inline void
-devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
-				  const char *bus_name)
+devlink_health_reporter_diagnose_req_set_bus_name(struct devlink_health_reporter_diagnose_req *req,
+						  const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -1101,8 +3631,8 @@ devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req,
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
-				  const char *dev_name)
+devlink_health_reporter_diagnose_req_set_dev_name(struct devlink_health_reporter_diagnose_req *req,
+						  const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -1110,48 +3640,33 @@ devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req,
 	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
-
-struct devlink_info_get_rsp {
-	struct {
-		__u32 bus_name_len;
-		__u32 dev_name_len;
-		__u32 info_driver_name_len;
-		__u32 info_serial_number_len;
-	} _present;
-
-	char *bus_name;
-	char *dev_name;
-	char *info_driver_name;
-	char *info_serial_number;
-	unsigned int n_info_version_fixed;
-	struct devlink_dl_info_version *info_version_fixed;
-	unsigned int n_info_version_running;
-	struct devlink_dl_info_version *info_version_running;
-	unsigned int n_info_version_stored;
-	struct devlink_dl_info_version *info_version_stored;
-};
-
-void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp);
+static inline void
+devlink_health_reporter_diagnose_req_set_port_index(struct devlink_health_reporter_diagnose_req *req,
+						    __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_diagnose_req_set_health_reporter_name(struct devlink_health_reporter_diagnose_req *req,
+							      const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
 
 /*
- * Get device information, like driver name, hardware and firmware versions etc.
+ * Diagnose health reporter instances.
  */
-struct devlink_info_get_rsp *
-devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req);
-
-/* DEVLINK_CMD_INFO_GET - dump */
-struct devlink_info_get_list {
-	struct devlink_info_get_list *next;
-	struct devlink_info_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void devlink_info_get_list_free(struct devlink_info_get_list *rsp);
-
-struct devlink_info_get_list *devlink_info_get_dump(struct ynl_sock *ys);
+int devlink_health_reporter_diagnose(struct ynl_sock *ys,
+				     struct devlink_health_reporter_diagnose_req *req);
 
-/* ============== DEVLINK_CMD_HEALTH_REPORTER_GET ============== */
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - do */
-struct devlink_health_reporter_get_req {
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */
+struct devlink_health_reporter_dump_get_req_dump {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
@@ -1165,17 +3680,17 @@ struct devlink_health_reporter_get_req {
 	char *health_reporter_name;
 };
 
-static inline struct devlink_health_reporter_get_req *
-devlink_health_reporter_get_req_alloc(void)
+static inline struct devlink_health_reporter_dump_get_req_dump *
+devlink_health_reporter_dump_get_req_dump_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_health_reporter_get_req));
+	return calloc(1, sizeof(struct devlink_health_reporter_dump_get_req_dump));
 }
 void
-devlink_health_reporter_get_req_free(struct devlink_health_reporter_get_req *req);
+devlink_health_reporter_dump_get_req_dump_free(struct devlink_health_reporter_dump_get_req_dump *req);
 
 static inline void
-devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_req *req,
-					     const char *bus_name)
+devlink_health_reporter_dump_get_req_dump_set_bus_name(struct devlink_health_reporter_dump_get_req_dump *req,
+						       const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -1184,8 +3699,8 @@ devlink_health_reporter_get_req_set_bus_name(struct devlink_health_reporter_get_
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_req *req,
-					     const char *dev_name)
+devlink_health_reporter_dump_get_req_dump_set_dev_name(struct devlink_health_reporter_dump_get_req_dump *req,
+						       const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -1194,15 +3709,15 @@ devlink_health_reporter_get_req_set_dev_name(struct devlink_health_reporter_get_
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_health_reporter_get_req_set_port_index(struct devlink_health_reporter_get_req *req,
-					       __u32 port_index)
+devlink_health_reporter_dump_get_req_dump_set_port_index(struct devlink_health_reporter_dump_get_req_dump *req,
+							 __u32 port_index)
 {
 	req->_present.port_index = 1;
 	req->port_index = port_index;
 }
 static inline void
-devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_reporter_get_req *req,
-							 const char *health_reporter_name)
+devlink_health_reporter_dump_get_req_dump_set_health_reporter_name(struct devlink_health_reporter_dump_get_req_dump *req,
+								   const char *health_reporter_name)
 {
 	free(req->health_reporter_name);
 	req->_present.health_reporter_name_len = strlen(health_reporter_name);
@@ -1211,7 +3726,29 @@ devlink_health_reporter_get_req_set_health_reporter_name(struct devlink_health_r
 	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
 }
 
-struct devlink_health_reporter_get_rsp {
+struct devlink_health_reporter_dump_get_rsp_dump {
+	struct {
+		__u32 fmsg:1;
+	} _present;
+
+	struct devlink_dl_fmsg fmsg;
+};
+
+struct devlink_health_reporter_dump_get_rsp_list {
+	struct devlink_health_reporter_dump_get_rsp_list *next;
+	struct devlink_health_reporter_dump_get_rsp_dump obj __attribute__((aligned(8)));
+};
+
+void
+devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp);
+
+struct devlink_health_reporter_dump_get_rsp_list *
+devlink_health_reporter_dump_get_dump(struct ynl_sock *ys,
+				      struct devlink_health_reporter_dump_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */
+struct devlink_health_reporter_dump_clear_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
@@ -1225,40 +3762,86 @@ struct devlink_health_reporter_get_rsp {
 	char *health_reporter_name;
 };
 
+static inline struct devlink_health_reporter_dump_clear_req *
+devlink_health_reporter_dump_clear_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_dump_clear_req));
+}
 void
-devlink_health_reporter_get_rsp_free(struct devlink_health_reporter_get_rsp *rsp);
+devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req);
+
+static inline void
+devlink_health_reporter_dump_clear_req_set_bus_name(struct devlink_health_reporter_dump_clear_req *req,
+						    const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_dump_clear_req_set_dev_name(struct devlink_health_reporter_dump_clear_req *req,
+						    const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_dump_clear_req_set_port_index(struct devlink_health_reporter_dump_clear_req *req,
+						      __u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_dump_clear_req_set_health_reporter_name(struct devlink_health_reporter_dump_clear_req *req,
+								const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
 
 /*
- * Get health reporter instances.
+ * Clear dump of health reporter instances.
  */
-struct devlink_health_reporter_get_rsp *
-devlink_health_reporter_get(struct ynl_sock *ys,
-			    struct devlink_health_reporter_get_req *req);
+int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
+				       struct devlink_health_reporter_dump_clear_req *req);
 
-/* DEVLINK_CMD_HEALTH_REPORTER_GET - dump */
-struct devlink_health_reporter_get_req_dump {
+/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */
+/* DEVLINK_CMD_FLASH_UPDATE - do */
+struct devlink_flash_update_req {
 	struct {
 		__u32 bus_name_len;
 		__u32 dev_name_len;
-		__u32 port_index:1;
+		__u32 flash_update_file_name_len;
+		__u32 flash_update_component_len;
+		__u32 flash_update_overwrite_mask:1;
 	} _present;
 
 	char *bus_name;
 	char *dev_name;
-	__u32 port_index;
+	char *flash_update_file_name;
+	char *flash_update_component;
+	struct nla_bitfield32 flash_update_overwrite_mask;
 };
 
-static inline struct devlink_health_reporter_get_req_dump *
-devlink_health_reporter_get_req_dump_alloc(void)
+static inline struct devlink_flash_update_req *
+devlink_flash_update_req_alloc(void)
 {
-	return calloc(1, sizeof(struct devlink_health_reporter_get_req_dump));
+	return calloc(1, sizeof(struct devlink_flash_update_req));
 }
-void
-devlink_health_reporter_get_req_dump_free(struct devlink_health_reporter_get_req_dump *req);
+void devlink_flash_update_req_free(struct devlink_flash_update_req *req);
 
 static inline void
-devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter_get_req_dump *req,
-						  const char *bus_name)
+devlink_flash_update_req_set_bus_name(struct devlink_flash_update_req *req,
+				      const char *bus_name)
 {
 	free(req->bus_name);
 	req->_present.bus_name_len = strlen(bus_name);
@@ -1267,8 +3850,8 @@ devlink_health_reporter_get_req_dump_set_bus_name(struct devlink_health_reporter
 	req->bus_name[req->_present.bus_name_len] = 0;
 }
 static inline void
-devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter_get_req_dump *req,
-						  const char *dev_name)
+devlink_flash_update_req_set_dev_name(struct devlink_flash_update_req *req,
+				      const char *dev_name)
 {
 	free(req->dev_name);
 	req->_present.dev_name_len = strlen(dev_name);
@@ -1277,24 +3860,38 @@ devlink_health_reporter_get_req_dump_set_dev_name(struct devlink_health_reporter
 	req->dev_name[req->_present.dev_name_len] = 0;
 }
 static inline void
-devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_reporter_get_req_dump *req,
-						    __u32 port_index)
+devlink_flash_update_req_set_flash_update_file_name(struct devlink_flash_update_req *req,
+						    const char *flash_update_file_name)
 {
-	req->_present.port_index = 1;
-	req->port_index = port_index;
+	free(req->flash_update_file_name);
+	req->_present.flash_update_file_name_len = strlen(flash_update_file_name);
+	req->flash_update_file_name = malloc(req->_present.flash_update_file_name_len + 1);
+	memcpy(req->flash_update_file_name, flash_update_file_name, req->_present.flash_update_file_name_len);
+	req->flash_update_file_name[req->_present.flash_update_file_name_len] = 0;
+}
+static inline void
+devlink_flash_update_req_set_flash_update_component(struct devlink_flash_update_req *req,
+						    const char *flash_update_component)
+{
+	free(req->flash_update_component);
+	req->_present.flash_update_component_len = strlen(flash_update_component);
+	req->flash_update_component = malloc(req->_present.flash_update_component_len + 1);
+	memcpy(req->flash_update_component, flash_update_component, req->_present.flash_update_component_len);
+	req->flash_update_component[req->_present.flash_update_component_len] = 0;
+}
+static inline void
+devlink_flash_update_req_set_flash_update_overwrite_mask(struct devlink_flash_update_req *req,
+							 struct nla_bitfield32 *flash_update_overwrite_mask)
+{
+	req->_present.flash_update_overwrite_mask = 1;
+	memcpy(&req->flash_update_overwrite_mask, flash_update_overwrite_mask, sizeof(struct nla_bitfield32));
 }
 
-struct devlink_health_reporter_get_list {
-	struct devlink_health_reporter_get_list *next;
-	struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8)));
-};
-
-void
-devlink_health_reporter_get_list_free(struct devlink_health_reporter_get_list *rsp);
-
-struct devlink_health_reporter_get_list *
-devlink_health_reporter_get_dump(struct ynl_sock *ys,
-				 struct devlink_health_reporter_get_req_dump *req);
+/*
+ * Flash update devlink instances.
+ */
+int devlink_flash_update(struct ynl_sock *ys,
+			 struct devlink_flash_update_req *req);
 
 /* ============== DEVLINK_CMD_TRAP_GET ============== */
 /* DEVLINK_CMD_TRAP_GET - do */
@@ -1417,6 +4014,71 @@ struct devlink_trap_get_list *
 devlink_trap_get_dump(struct ynl_sock *ys,
 		      struct devlink_trap_get_req_dump *req);
 
+/* ============== DEVLINK_CMD_TRAP_SET ============== */
+/* DEVLINK_CMD_TRAP_SET - do */
+struct devlink_trap_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_name_len;
+		__u32 trap_action:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_name;
+	enum devlink_trap_action trap_action;
+};
+
+static inline struct devlink_trap_set_req *devlink_trap_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_set_req));
+}
+void devlink_trap_set_req_free(struct devlink_trap_set_req *req);
+
+static inline void
+devlink_trap_set_req_set_bus_name(struct devlink_trap_set_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_set_req_set_dev_name(struct devlink_trap_set_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_set_req_set_trap_name(struct devlink_trap_set_req *req,
+				   const char *trap_name)
+{
+	free(req->trap_name);
+	req->_present.trap_name_len = strlen(trap_name);
+	req->trap_name = malloc(req->_present.trap_name_len + 1);
+	memcpy(req->trap_name, trap_name, req->_present.trap_name_len);
+	req->trap_name[req->_present.trap_name_len] = 0;
+}
+static inline void
+devlink_trap_set_req_set_trap_action(struct devlink_trap_set_req *req,
+				     enum devlink_trap_action trap_action)
+{
+	req->_present.trap_action = 1;
+	req->trap_action = trap_action;
+}
+
+/*
+ * Set trap instances.
+ */
+int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req);
+
 /* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */
 /* DEVLINK_CMD_TRAP_GROUP_GET - do */
 struct devlink_trap_group_get_req {
@@ -1541,6 +4203,82 @@ struct devlink_trap_group_get_list *
 devlink_trap_group_get_dump(struct ynl_sock *ys,
 			    struct devlink_trap_group_get_req_dump *req);
 
+/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */
+/* DEVLINK_CMD_TRAP_GROUP_SET - do */
+struct devlink_trap_group_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_group_name_len;
+		__u32 trap_action:1;
+		__u32 trap_policer_id:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *trap_group_name;
+	enum devlink_trap_action trap_action;
+	__u32 trap_policer_id;
+};
+
+static inline struct devlink_trap_group_set_req *
+devlink_trap_group_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_group_set_req));
+}
+void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req);
+
+static inline void
+devlink_trap_group_set_req_set_bus_name(struct devlink_trap_group_set_req *req,
+					const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_group_set_req_set_dev_name(struct devlink_trap_group_set_req *req,
+					const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_group_set_req_set_trap_group_name(struct devlink_trap_group_set_req *req,
+					       const char *trap_group_name)
+{
+	free(req->trap_group_name);
+	req->_present.trap_group_name_len = strlen(trap_group_name);
+	req->trap_group_name = malloc(req->_present.trap_group_name_len + 1);
+	memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len);
+	req->trap_group_name[req->_present.trap_group_name_len] = 0;
+}
+static inline void
+devlink_trap_group_set_req_set_trap_action(struct devlink_trap_group_set_req *req,
+					   enum devlink_trap_action trap_action)
+{
+	req->_present.trap_action = 1;
+	req->trap_action = trap_action;
+}
+static inline void
+devlink_trap_group_set_req_set_trap_policer_id(struct devlink_trap_group_set_req *req,
+					       __u32 trap_policer_id)
+{
+	req->_present.trap_policer_id = 1;
+	req->trap_policer_id = trap_policer_id;
+}
+
+/*
+ * Set trap group instances.
+ */
+int devlink_trap_group_set(struct ynl_sock *ys,
+			   struct devlink_trap_group_set_req *req);
+
 /* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */
 /* DEVLINK_CMD_TRAP_POLICER_GET - do */
 struct devlink_trap_policer_get_req {
@@ -1661,9 +4399,151 @@ struct devlink_trap_policer_get_list {
 void
 devlink_trap_policer_get_list_free(struct devlink_trap_policer_get_list *rsp);
 
-struct devlink_trap_policer_get_list *
-devlink_trap_policer_get_dump(struct ynl_sock *ys,
-			      struct devlink_trap_policer_get_req_dump *req);
+struct devlink_trap_policer_get_list *
+devlink_trap_policer_get_dump(struct ynl_sock *ys,
+			      struct devlink_trap_policer_get_req_dump *req);
+
+/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */
+/* DEVLINK_CMD_TRAP_POLICER_SET - do */
+struct devlink_trap_policer_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 trap_policer_id:1;
+		__u32 trap_policer_rate:1;
+		__u32 trap_policer_burst:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 trap_policer_id;
+	__u64 trap_policer_rate;
+	__u64 trap_policer_burst;
+};
+
+static inline struct devlink_trap_policer_set_req *
+devlink_trap_policer_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_trap_policer_set_req));
+}
+void
+devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req);
+
+static inline void
+devlink_trap_policer_set_req_set_bus_name(struct devlink_trap_policer_set_req *req,
+					  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_trap_policer_set_req_set_dev_name(struct devlink_trap_policer_set_req *req,
+					  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_trap_policer_set_req_set_trap_policer_id(struct devlink_trap_policer_set_req *req,
+						 __u32 trap_policer_id)
+{
+	req->_present.trap_policer_id = 1;
+	req->trap_policer_id = trap_policer_id;
+}
+static inline void
+devlink_trap_policer_set_req_set_trap_policer_rate(struct devlink_trap_policer_set_req *req,
+						   __u64 trap_policer_rate)
+{
+	req->_present.trap_policer_rate = 1;
+	req->trap_policer_rate = trap_policer_rate;
+}
+static inline void
+devlink_trap_policer_set_req_set_trap_policer_burst(struct devlink_trap_policer_set_req *req,
+						    __u64 trap_policer_burst)
+{
+	req->_present.trap_policer_burst = 1;
+	req->trap_policer_burst = trap_policer_burst;
+}
+
+/*
+ * Get trap policer instances.
+ */
+int devlink_trap_policer_set(struct ynl_sock *ys,
+			     struct devlink_trap_policer_set_req *req);
+
+/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */
+/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */
+struct devlink_health_reporter_test_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 port_index:1;
+		__u32 health_reporter_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 port_index;
+	char *health_reporter_name;
+};
+
+static inline struct devlink_health_reporter_test_req *
+devlink_health_reporter_test_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_health_reporter_test_req));
+}
+void
+devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req);
+
+static inline void
+devlink_health_reporter_test_req_set_bus_name(struct devlink_health_reporter_test_req *req,
+					      const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_test_req_set_dev_name(struct devlink_health_reporter_test_req *req,
+					      const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_health_reporter_test_req_set_port_index(struct devlink_health_reporter_test_req *req,
+						__u32 port_index)
+{
+	req->_present.port_index = 1;
+	req->port_index = port_index;
+}
+static inline void
+devlink_health_reporter_test_req_set_health_reporter_name(struct devlink_health_reporter_test_req *req,
+							  const char *health_reporter_name)
+{
+	free(req->health_reporter_name);
+	req->_present.health_reporter_name_len = strlen(health_reporter_name);
+	req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1);
+	memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len);
+	req->health_reporter_name[req->_present.health_reporter_name_len] = 0;
+}
+
+/*
+ * Test health reporter instances.
+ */
+int devlink_health_reporter_test(struct ynl_sock *ys,
+				 struct devlink_health_reporter_test_req *req);
 
 /* ============== DEVLINK_CMD_RATE_GET ============== */
 /* DEVLINK_CMD_RATE_GET - do */
@@ -1797,6 +4677,270 @@ struct devlink_rate_get_list *
 devlink_rate_get_dump(struct ynl_sock *ys,
 		      struct devlink_rate_get_req_dump *req);
 
+/* ============== DEVLINK_CMD_RATE_SET ============== */
+/* DEVLINK_CMD_RATE_SET - do */
+struct devlink_rate_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 rate_node_name_len;
+		__u32 rate_tx_share:1;
+		__u32 rate_tx_max:1;
+		__u32 rate_tx_priority:1;
+		__u32 rate_tx_weight:1;
+		__u32 rate_parent_node_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *rate_node_name;
+	__u64 rate_tx_share;
+	__u64 rate_tx_max;
+	__u32 rate_tx_priority;
+	__u32 rate_tx_weight;
+	char *rate_parent_node_name;
+};
+
+static inline struct devlink_rate_set_req *devlink_rate_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_rate_set_req));
+}
+void devlink_rate_set_req_free(struct devlink_rate_set_req *req);
+
+static inline void
+devlink_rate_set_req_set_bus_name(struct devlink_rate_set_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_rate_set_req_set_dev_name(struct devlink_rate_set_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_rate_set_req_set_rate_node_name(struct devlink_rate_set_req *req,
+					const char *rate_node_name)
+{
+	free(req->rate_node_name);
+	req->_present.rate_node_name_len = strlen(rate_node_name);
+	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
+	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
+	req->rate_node_name[req->_present.rate_node_name_len] = 0;
+}
+static inline void
+devlink_rate_set_req_set_rate_tx_share(struct devlink_rate_set_req *req,
+				       __u64 rate_tx_share)
+{
+	req->_present.rate_tx_share = 1;
+	req->rate_tx_share = rate_tx_share;
+}
+static inline void
+devlink_rate_set_req_set_rate_tx_max(struct devlink_rate_set_req *req,
+				     __u64 rate_tx_max)
+{
+	req->_present.rate_tx_max = 1;
+	req->rate_tx_max = rate_tx_max;
+}
+static inline void
+devlink_rate_set_req_set_rate_tx_priority(struct devlink_rate_set_req *req,
+					  __u32 rate_tx_priority)
+{
+	req->_present.rate_tx_priority = 1;
+	req->rate_tx_priority = rate_tx_priority;
+}
+static inline void
+devlink_rate_set_req_set_rate_tx_weight(struct devlink_rate_set_req *req,
+					__u32 rate_tx_weight)
+{
+	req->_present.rate_tx_weight = 1;
+	req->rate_tx_weight = rate_tx_weight;
+}
+static inline void
+devlink_rate_set_req_set_rate_parent_node_name(struct devlink_rate_set_req *req,
+					       const char *rate_parent_node_name)
+{
+	free(req->rate_parent_node_name);
+	req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name);
+	req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1);
+	memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len);
+	req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0;
+}
+
+/*
+ * Set rate instances.
+ */
+int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req);
+
+/* ============== DEVLINK_CMD_RATE_NEW ============== */
+/* DEVLINK_CMD_RATE_NEW - do */
+struct devlink_rate_new_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 rate_node_name_len;
+		__u32 rate_tx_share:1;
+		__u32 rate_tx_max:1;
+		__u32 rate_tx_priority:1;
+		__u32 rate_tx_weight:1;
+		__u32 rate_parent_node_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *rate_node_name;
+	__u64 rate_tx_share;
+	__u64 rate_tx_max;
+	__u32 rate_tx_priority;
+	__u32 rate_tx_weight;
+	char *rate_parent_node_name;
+};
+
+static inline struct devlink_rate_new_req *devlink_rate_new_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_rate_new_req));
+}
+void devlink_rate_new_req_free(struct devlink_rate_new_req *req);
+
+static inline void
+devlink_rate_new_req_set_bus_name(struct devlink_rate_new_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_rate_new_req_set_dev_name(struct devlink_rate_new_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_rate_new_req_set_rate_node_name(struct devlink_rate_new_req *req,
+					const char *rate_node_name)
+{
+	free(req->rate_node_name);
+	req->_present.rate_node_name_len = strlen(rate_node_name);
+	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
+	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
+	req->rate_node_name[req->_present.rate_node_name_len] = 0;
+}
+static inline void
+devlink_rate_new_req_set_rate_tx_share(struct devlink_rate_new_req *req,
+				       __u64 rate_tx_share)
+{
+	req->_present.rate_tx_share = 1;
+	req->rate_tx_share = rate_tx_share;
+}
+static inline void
+devlink_rate_new_req_set_rate_tx_max(struct devlink_rate_new_req *req,
+				     __u64 rate_tx_max)
+{
+	req->_present.rate_tx_max = 1;
+	req->rate_tx_max = rate_tx_max;
+}
+static inline void
+devlink_rate_new_req_set_rate_tx_priority(struct devlink_rate_new_req *req,
+					  __u32 rate_tx_priority)
+{
+	req->_present.rate_tx_priority = 1;
+	req->rate_tx_priority = rate_tx_priority;
+}
+static inline void
+devlink_rate_new_req_set_rate_tx_weight(struct devlink_rate_new_req *req,
+					__u32 rate_tx_weight)
+{
+	req->_present.rate_tx_weight = 1;
+	req->rate_tx_weight = rate_tx_weight;
+}
+static inline void
+devlink_rate_new_req_set_rate_parent_node_name(struct devlink_rate_new_req *req,
+					       const char *rate_parent_node_name)
+{
+	free(req->rate_parent_node_name);
+	req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name);
+	req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1);
+	memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len);
+	req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0;
+}
+
+/*
+ * Create rate instances.
+ */
+int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req);
+
+/* ============== DEVLINK_CMD_RATE_DEL ============== */
+/* DEVLINK_CMD_RATE_DEL - do */
+struct devlink_rate_del_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 rate_node_name_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	char *rate_node_name;
+};
+
+static inline struct devlink_rate_del_req *devlink_rate_del_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_rate_del_req));
+}
+void devlink_rate_del_req_free(struct devlink_rate_del_req *req);
+
+static inline void
+devlink_rate_del_req_set_bus_name(struct devlink_rate_del_req *req,
+				  const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_rate_del_req_set_dev_name(struct devlink_rate_del_req *req,
+				  const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_rate_del_req_set_rate_node_name(struct devlink_rate_del_req *req,
+					const char *rate_node_name)
+{
+	free(req->rate_node_name);
+	req->_present.rate_node_name_len = strlen(rate_node_name);
+	req->rate_node_name = malloc(req->_present.rate_node_name_len + 1);
+	memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len);
+	req->rate_node_name[req->_present.rate_node_name_len] = 0;
+}
+
+/*
+ * Delete rate instances.
+ */
+int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req);
+
 /* ============== DEVLINK_CMD_LINECARD_GET ============== */
 /* DEVLINK_CMD_LINECARD_GET - do */
 struct devlink_linecard_get_req {
@@ -1917,6 +5061,73 @@ struct devlink_linecard_get_list *
 devlink_linecard_get_dump(struct ynl_sock *ys,
 			  struct devlink_linecard_get_req_dump *req);
 
+/* ============== DEVLINK_CMD_LINECARD_SET ============== */
+/* DEVLINK_CMD_LINECARD_SET - do */
+struct devlink_linecard_set_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 linecard_index:1;
+		__u32 linecard_type_len;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	__u32 linecard_index;
+	char *linecard_type;
+};
+
+static inline struct devlink_linecard_set_req *
+devlink_linecard_set_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_linecard_set_req));
+}
+void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req);
+
+static inline void
+devlink_linecard_set_req_set_bus_name(struct devlink_linecard_set_req *req,
+				      const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_linecard_set_req_set_dev_name(struct devlink_linecard_set_req *req,
+				      const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_linecard_set_req_set_linecard_index(struct devlink_linecard_set_req *req,
+					    __u32 linecard_index)
+{
+	req->_present.linecard_index = 1;
+	req->linecard_index = linecard_index;
+}
+static inline void
+devlink_linecard_set_req_set_linecard_type(struct devlink_linecard_set_req *req,
+					   const char *linecard_type)
+{
+	free(req->linecard_type);
+	req->_present.linecard_type_len = strlen(linecard_type);
+	req->linecard_type = malloc(req->_present.linecard_type_len + 1);
+	memcpy(req->linecard_type, linecard_type, req->_present.linecard_type_len);
+	req->linecard_type[req->_present.linecard_type_len] = 0;
+}
+
+/*
+ * Set line card instances.
+ */
+int devlink_linecard_set(struct ynl_sock *ys,
+			 struct devlink_linecard_set_req *req);
+
 /* ============== DEVLINK_CMD_SELFTESTS_GET ============== */
 /* DEVLINK_CMD_SELFTESTS_GET - do */
 struct devlink_selftests_get_req {
@@ -1987,4 +5198,58 @@ void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp);
 struct devlink_selftests_get_list *
 devlink_selftests_get_dump(struct ynl_sock *ys);
 
+/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */
+/* DEVLINK_CMD_SELFTESTS_RUN - do */
+struct devlink_selftests_run_req {
+	struct {
+		__u32 bus_name_len;
+		__u32 dev_name_len;
+		__u32 selftests:1;
+	} _present;
+
+	char *bus_name;
+	char *dev_name;
+	struct devlink_dl_selftest_id selftests;
+};
+
+static inline struct devlink_selftests_run_req *
+devlink_selftests_run_req_alloc(void)
+{
+	return calloc(1, sizeof(struct devlink_selftests_run_req));
+}
+void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req);
+
+static inline void
+devlink_selftests_run_req_set_bus_name(struct devlink_selftests_run_req *req,
+				       const char *bus_name)
+{
+	free(req->bus_name);
+	req->_present.bus_name_len = strlen(bus_name);
+	req->bus_name = malloc(req->_present.bus_name_len + 1);
+	memcpy(req->bus_name, bus_name, req->_present.bus_name_len);
+	req->bus_name[req->_present.bus_name_len] = 0;
+}
+static inline void
+devlink_selftests_run_req_set_dev_name(struct devlink_selftests_run_req *req,
+				       const char *dev_name)
+{
+	free(req->dev_name);
+	req->_present.dev_name_len = strlen(dev_name);
+	req->dev_name = malloc(req->_present.dev_name_len + 1);
+	memcpy(req->dev_name, dev_name, req->_present.dev_name_len);
+	req->dev_name[req->_present.dev_name_len] = 0;
+}
+static inline void
+devlink_selftests_run_req_set_selftests_flash(struct devlink_selftests_run_req *req)
+{
+	req->_present.selftests = 1;
+	req->selftests._present.flash = 1;
+}
+
+/*
+ * Run device selftest instances.
+ */
+int devlink_selftests_run(struct ynl_sock *ys,
+			  struct devlink_selftests_run_req *req);
+
 #endif /* _LINUX_DEVLINK_GEN_H */
-- 
cgit v1.2.3


From 2793a8b015f7f1caadb9bce9c63dc659f7522676 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 24 Oct 2023 03:09:13 +0300
Subject: bpf: exact states comparison for iterator convergence checks

Convergence for open coded iterators is computed in is_state_visited()
by examining states with branches count > 1 and using states_equal().
states_equal() computes sub-state relation using read and precision marks.
Read and precision marks are propagated from children states,
thus are not guaranteed to be complete inside a loop when branches
count > 1. This could be demonstrated using the following unsafe program:

     1. r7 = -16
     2. r6 = bpf_get_prandom_u32()
     3. while (bpf_iter_num_next(&fp[-8])) {
     4.   if (r6 != 42) {
     5.     r7 = -32
     6.     r6 = bpf_get_prandom_u32()
     7.     continue
     8.   }
     9.   r0 = r10
    10.   r0 += r7
    11.   r8 = *(u64 *)(r0 + 0)
    12.   r6 = bpf_get_prandom_u32()
    13. }

Here verifier would first visit path 1-3, create a checkpoint at 3
with r7=-16, continue to 4-7,3 with r7=-32.

Because instructions at 9-12 had not been visitied yet existing
checkpoint at 3 does not have read or precision mark for r7.
Thus states_equal() would return true and verifier would discard
current state, thus unsafe memory access at 11 would not be caught.

This commit fixes this loophole by introducing exact state comparisons
for iterator convergence logic:
- registers are compared using regs_exact() regardless of read or
  precision marks;
- stack slots have to have identical type.

Unfortunately, this is too strict even for simple programs like below:

    i = 0;
    while(iter_next(&it))
      i++;

At each iteration step i++ would produce a new distinct state and
eventually instruction processing limit would be reached.

To avoid such behavior speculatively forget (widen) range for
imprecise scalar registers, if those registers were not precise at the
end of the previous iteration and do not match exactly.

This a conservative heuristic that allows to verify wide range of
programs, however it precludes verification of programs that conjure
an imprecise value on the first loop iteration and use it as precise
on the second.

Test case iter_task_vma_for_each() presents one of such cases:

        unsigned int seen = 0;
        ...
        bpf_for_each(task_vma, vma, task, 0) {
                if (seen >= 1000)
                        break;
                ...
                seen++;
        }

Here clang generates the following code:

<LBB0_4>:
      24:       r8 = r6                          ; stash current value of
                ... body ...                       'seen'
      29:       r1 = r10
      30:       r1 += -0x8
      31:       call bpf_iter_task_vma_next
      32:       r6 += 0x1                        ; seen++;
      33:       if r0 == 0x0 goto +0x2 <LBB0_6>  ; exit on next() == NULL
      34:       r7 += 0x10
      35:       if r8 < 0x3e7 goto -0xc <LBB0_4> ; loop on seen < 1000

<LBB0_6>:
      ... exit ...

Note that counter in r6 is copied to r8 and then incremented,
conditional jump is done using r8. Because of this precision mark for
r6 lags one state behind of precision mark on r8 and widening logic
kicks in.

Adding barrier_var(seen) after conditional is sufficient to force
clang use the same register for both counting and conditional jump.

This issue was discussed in the thread [1] which was started by
Andrew Werner <awerner32@gmail.com> demonstrating a similar bug
in callback functions handling. The callbacks would be addressed
in a followup patch.

[1] https://lore.kernel.org/bpf/97a90da09404c65c8e810cf83c94ac703705dc0e.camel@gmail.com/

Co-developed-by: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Co-developed-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231024000917.12153-4-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                       |   1 +
 kernel/bpf/verifier.c                              | 218 ++++++++++++++++++---
 tools/testing/selftests/bpf/progs/iters_task_vma.c |   1 +
 3 files changed, 189 insertions(+), 31 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e67cd45a85be..38b788228594 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -384,6 +384,7 @@ struct bpf_verifier_state {
 	 */
 	struct bpf_idx_pair *jmp_history;
 	u32 jmp_history_cnt;
+	u32 dfs_depth;
 };
 
 #define bpf_get_spilled_reg(slot, frame, mask)				\
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 366029e484a0..6573e8c77329 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1802,6 +1802,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->parent = src->parent;
 	dst_state->first_insn_idx = src->first_insn_idx;
 	dst_state->last_insn_idx = src->last_insn_idx;
+	dst_state->dfs_depth = src->dfs_depth;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
 		if (!dst) {
@@ -7723,6 +7724,81 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 	return 0;
 }
 
+/* Look for a previous loop entry at insn_idx: nearest parent state
+ * stopped at insn_idx with callsites matching those in cur->frame.
+ */
+static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env,
+						  struct bpf_verifier_state *cur,
+						  int insn_idx)
+{
+	struct bpf_verifier_state_list *sl;
+	struct bpf_verifier_state *st;
+
+	/* Explored states are pushed in stack order, most recent states come first */
+	sl = *explored_state(env, insn_idx);
+	for (; sl; sl = sl->next) {
+		/* If st->branches != 0 state is a part of current DFS verification path,
+		 * hence cur & st for a loop.
+		 */
+		st = &sl->state;
+		if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) &&
+		    st->dfs_depth < cur->dfs_depth)
+			return st;
+	}
+
+	return NULL;
+}
+
+static void reset_idmap_scratch(struct bpf_verifier_env *env);
+static bool regs_exact(const struct bpf_reg_state *rold,
+		       const struct bpf_reg_state *rcur,
+		       struct bpf_idmap *idmap);
+
+static void maybe_widen_reg(struct bpf_verifier_env *env,
+			    struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
+			    struct bpf_idmap *idmap)
+{
+	if (rold->type != SCALAR_VALUE)
+		return;
+	if (rold->type != rcur->type)
+		return;
+	if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap))
+		return;
+	__mark_reg_unknown(env, rcur);
+}
+
+static int widen_imprecise_scalars(struct bpf_verifier_env *env,
+				   struct bpf_verifier_state *old,
+				   struct bpf_verifier_state *cur)
+{
+	struct bpf_func_state *fold, *fcur;
+	int i, fr;
+
+	reset_idmap_scratch(env);
+	for (fr = old->curframe; fr >= 0; fr--) {
+		fold = old->frame[fr];
+		fcur = cur->frame[fr];
+
+		for (i = 0; i < MAX_BPF_REG; i++)
+			maybe_widen_reg(env,
+					&fold->regs[i],
+					&fcur->regs[i],
+					&env->idmap_scratch);
+
+		for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) {
+			if (!is_spilled_reg(&fold->stack[i]) ||
+			    !is_spilled_reg(&fcur->stack[i]))
+				continue;
+
+			maybe_widen_reg(env,
+					&fold->stack[i].spilled_ptr,
+					&fcur->stack[i].spilled_ptr,
+					&env->idmap_scratch);
+		}
+	}
+	return 0;
+}
+
 /* process_iter_next_call() is called when verifier gets to iterator's next
  * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer
  * to it as just "iter_next()" in comments below.
@@ -7764,25 +7840,47 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
  * is some statically known limit on number of iterations (e.g., if there is
  * an explicit `if n > 100 then break;` statement somewhere in the loop).
  *
- * One very subtle but very important aspect is that we *always* simulate NULL
- * condition first (as the current state) before we simulate non-NULL case.
- * This has to do with intricacies of scalar precision tracking. By simulating
- * "exit condition" of iter_next() returning NULL first, we make sure all the
- * relevant precision marks *that will be set **after** we exit iterator loop*
- * are propagated backwards to common parent state of NULL and non-NULL
- * branches. Thanks to that, state equivalence checks done later in forked
- * state, when reaching iter_next() for ACTIVE iterator, can assume that
- * precision marks are finalized and won't change. Because simulating another
- * ACTIVE iterator iteration won't change them (because given same input
- * states we'll end up with exactly same output states which we are currently
- * comparing; and verification after the loop already propagated back what
- * needs to be **additionally** tracked as precise). It's subtle, grok
- * precision tracking for more intuitive understanding.
+ * Iteration convergence logic in is_state_visited() relies on exact
+ * states comparison, which ignores read and precision marks.
+ * This is necessary because read and precision marks are not finalized
+ * while in the loop. Exact comparison might preclude convergence for
+ * simple programs like below:
+ *
+ *     i = 0;
+ *     while(iter_next(&it))
+ *       i++;
+ *
+ * At each iteration step i++ would produce a new distinct state and
+ * eventually instruction processing limit would be reached.
+ *
+ * To avoid such behavior speculatively forget (widen) range for
+ * imprecise scalar registers, if those registers were not precise at the
+ * end of the previous iteration and do not match exactly.
+ *
+ * This is a conservative heuristic that allows to verify wide range of programs,
+ * however it precludes verification of programs that conjure an
+ * imprecise value on the first loop iteration and use it as precise on a second.
+ * For example, the following safe program would fail to verify:
+ *
+ *     struct bpf_num_iter it;
+ *     int arr[10];
+ *     int i = 0, a = 0;
+ *     bpf_iter_num_new(&it, 0, 10);
+ *     while (bpf_iter_num_next(&it)) {
+ *       if (a == 0) {
+ *         a = 1;
+ *         i = 7; // Because i changed verifier would forget
+ *                // it's range on second loop entry.
+ *       } else {
+ *         arr[i] = 42; // This would fail to verify.
+ *       }
+ *     }
+ *     bpf_iter_num_destroy(&it);
  */
 static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
 				  struct bpf_kfunc_call_arg_meta *meta)
 {
-	struct bpf_verifier_state *cur_st = env->cur_state, *queued_st;
+	struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st;
 	struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr;
 	struct bpf_reg_state *cur_iter, *queued_iter;
 	int iter_frameno = meta->iter.frameno;
@@ -7800,6 +7898,19 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
 	}
 
 	if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) {
+		/* Because iter_next() call is a checkpoint is_state_visitied()
+		 * should guarantee parent state with same call sites and insn_idx.
+		 */
+		if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx ||
+		    !same_callsites(cur_st->parent, cur_st)) {
+			verbose(env, "bug: bad parent state for iter next call");
+			return -EFAULT;
+		}
+		/* Note cur_st->parent in the call below, it is necessary to skip
+		 * checkpoint created for cur_st by is_state_visited()
+		 * right at this instruction.
+		 */
+		prev_st = find_prev_entry(env, cur_st->parent, insn_idx);
 		/* branch out active iter state */
 		queued_st = push_stack(env, insn_idx + 1, insn_idx, false);
 		if (!queued_st)
@@ -7808,6 +7919,8 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
 		queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr;
 		queued_iter->iter.state = BPF_ITER_STATE_ACTIVE;
 		queued_iter->iter.depth++;
+		if (prev_st)
+			widen_imprecise_scalars(env, prev_st, queued_st);
 
 		queued_fr = queued_st->frame[queued_st->curframe];
 		mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]);
@@ -15948,8 +16061,11 @@ static bool regs_exact(const struct bpf_reg_state *rold,
 
 /* Returns true if (rold safe implies rcur safe) */
 static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
-		    struct bpf_reg_state *rcur, struct bpf_idmap *idmap)
+		    struct bpf_reg_state *rcur, struct bpf_idmap *idmap, bool exact)
 {
+	if (exact)
+		return regs_exact(rold, rcur, idmap);
+
 	if (!(rold->live & REG_LIVE_READ))
 		/* explored state didn't use this */
 		return true;
@@ -16066,7 +16182,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 }
 
 static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
-		      struct bpf_func_state *cur, struct bpf_idmap *idmap)
+		      struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact)
 {
 	int i, spi;
 
@@ -16079,7 +16195,12 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 
 		spi = i / BPF_REG_SIZE;
 
-		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+		if (exact &&
+		    old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+		    cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+			return false;
+
+		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && !exact) {
 			i += BPF_REG_SIZE - 1;
 			/* explored state didn't use this */
 			continue;
@@ -16129,7 +16250,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			 * return false to continue verification of this path
 			 */
 			if (!regsafe(env, &old->stack[spi].spilled_ptr,
-				     &cur->stack[spi].spilled_ptr, idmap))
+				     &cur->stack[spi].spilled_ptr, idmap, exact))
 				return false;
 			break;
 		case STACK_DYNPTR:
@@ -16211,16 +16332,16 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur,
  * the current state will reach 'bpf_exit' instruction safely
  */
 static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
-			      struct bpf_func_state *cur)
+			      struct bpf_func_state *cur, bool exact)
 {
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (!regsafe(env, &old->regs[i], &cur->regs[i],
-			     &env->idmap_scratch))
+			     &env->idmap_scratch, exact))
 			return false;
 
-	if (!stacksafe(env, old, cur, &env->idmap_scratch))
+	if (!stacksafe(env, old, cur, &env->idmap_scratch, exact))
 		return false;
 
 	if (!refsafe(old, cur, &env->idmap_scratch))
@@ -16229,17 +16350,23 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
 	return true;
 }
 
+static void reset_idmap_scratch(struct bpf_verifier_env *env)
+{
+	env->idmap_scratch.tmp_id_gen = env->id_gen;
+	memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+}
+
 static bool states_equal(struct bpf_verifier_env *env,
 			 struct bpf_verifier_state *old,
-			 struct bpf_verifier_state *cur)
+			 struct bpf_verifier_state *cur,
+			 bool exact)
 {
 	int i;
 
 	if (old->curframe != cur->curframe)
 		return false;
 
-	env->idmap_scratch.tmp_id_gen = env->id_gen;
-	memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
+	reset_idmap_scratch(env);
 
 	/* Verification state from speculative execution simulation
 	 * must never prune a non-speculative execution one.
@@ -16269,7 +16396,7 @@ static bool states_equal(struct bpf_verifier_env *env,
 	for (i = 0; i <= old->curframe; i++) {
 		if (old->frame[i]->callsite != cur->frame[i]->callsite)
 			return false;
-		if (!func_states_equal(env, old->frame[i], cur->frame[i]))
+		if (!func_states_equal(env, old->frame[i], cur->frame[i], exact))
 			return false;
 	}
 	return true;
@@ -16524,7 +16651,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	struct bpf_verifier_state_list *new_sl;
 	struct bpf_verifier_state_list *sl, **pprev;
 	struct bpf_verifier_state *cur = env->cur_state, *new;
-	int i, j, err, states_cnt = 0;
+	int i, j, n, err, states_cnt = 0;
 	bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx);
 	bool add_new_state = force_new_state;
 
@@ -16579,9 +16706,33 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 			 * It's safe to assume that iterator loop will finish, taking into
 			 * account iter_next() contract of eventually returning
 			 * sticky NULL result.
+			 *
+			 * Note, that states have to be compared exactly in this case because
+			 * read and precision marks might not be finalized inside the loop.
+			 * E.g. as in the program below:
+			 *
+			 *     1. r7 = -16
+			 *     2. r6 = bpf_get_prandom_u32()
+			 *     3. while (bpf_iter_num_next(&fp[-8])) {
+			 *     4.   if (r6 != 42) {
+			 *     5.     r7 = -32
+			 *     6.     r6 = bpf_get_prandom_u32()
+			 *     7.     continue
+			 *     8.   }
+			 *     9.   r0 = r10
+			 *    10.   r0 += r7
+			 *    11.   r8 = *(u64 *)(r0 + 0)
+			 *    12.   r6 = bpf_get_prandom_u32()
+			 *    13. }
+			 *
+			 * Here verifier would first visit path 1-3, create a checkpoint at 3
+			 * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does
+			 * not have read or precision mark for r7 yet, thus inexact states
+			 * comparison would discard current state with r7=-32
+			 * => unsafe memory access at 11 would not be caught.
 			 */
 			if (is_iter_next_insn(env, insn_idx)) {
-				if (states_equal(env, &sl->state, cur)) {
+				if (states_equal(env, &sl->state, cur, true)) {
 					struct bpf_func_state *cur_frame;
 					struct bpf_reg_state *iter_state, *iter_reg;
 					int spi;
@@ -16604,7 +16755,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 			}
 			/* attempt to detect infinite loop to avoid unnecessary doomed work */
 			if (states_maybe_looping(&sl->state, cur) &&
-			    states_equal(env, &sl->state, cur) &&
+			    states_equal(env, &sl->state, cur, false) &&
 			    !iter_active_depths_differ(&sl->state, cur)) {
 				verbose_linfo(env, insn_idx, "; ");
 				verbose(env, "infinite loop detected at insn %d\n", insn_idx);
@@ -16629,7 +16780,7 @@ skip_inf_loop_check:
 				add_new_state = false;
 			goto miss;
 		}
-		if (states_equal(env, &sl->state, cur)) {
+		if (states_equal(env, &sl->state, cur, false)) {
 hit:
 			sl->hit_cnt++;
 			/* reached equivalent register/stack state,
@@ -16668,8 +16819,12 @@ miss:
 		 * to keep checking from state equivalence point of view.
 		 * Higher numbers increase max_states_per_insn and verification time,
 		 * but do not meaningfully decrease insn_processed.
+		 * 'n' controls how many times state could miss before eviction.
+		 * Use bigger 'n' for checkpoints because evicting checkpoint states
+		 * too early would hinder iterator convergence.
 		 */
-		if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+		n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3;
+		if (sl->miss_cnt > sl->hit_cnt * n + n) {
 			/* the state is unlikely to be useful. Remove it to
 			 * speed up verification
 			 */
@@ -16743,6 +16898,7 @@ next:
 
 	cur->parent = new;
 	cur->first_insn_idx = insn_idx;
+	cur->dfs_depth = new->dfs_depth + 1;
 	clear_jmp_history(cur);
 	new_sl->next = *explored_state(env, insn_idx);
 	*explored_state(env, insn_idx) = new_sl;
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
index 44edecfdfaee..e085a51d153e 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -30,6 +30,7 @@ int iter_task_vma_for_each(const void *ctx)
 	bpf_for_each(task_vma, vma, task, 0) {
 		if (seen >= 1000)
 			break;
+		barrier_var(seen);
 
 		vm_ranges[seen].vm_start = vma->vm_start;
 		vm_ranges[seen].vm_end = vma->vm_end;
-- 
cgit v1.2.3


From 389ede06c2974b2f878a7ebff6b0f4f707f9db74 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 24 Oct 2023 03:09:14 +0300
Subject: selftests/bpf: tests with delayed read/precision makrs in loop body

These test cases try to hide read and precision marks from loop
convergence logic: marks would only be assigned on subsequent loop
iterations or after exploring states pushed to env->head stack first.
Without verifier fix to use exact states comparison logic for
iterators convergence these tests (except 'triple_continue') would be
errorneously marked as safe.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231024000917.12153-5-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/iters.c | 518 ++++++++++++++++++++++++++++++
 1 file changed, 518 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 6b9b3c56f009..764a68420c3e 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -14,6 +14,13 @@ int my_pid;
 int arr[256];
 int small_arr[16] SEC(".data.small_arr");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 10);
+	__type(key, int);
+	__type(value, int);
+} amap SEC(".maps");
+
 #ifdef REAL_TEST
 #define MY_PID_GUARD() if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0
 #else
@@ -716,4 +723,515 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx)
 	return 0;
 }
 
+SEC("?raw_tp")
+__failure
+__msg("R1 type=scalar expected=fp")
+__naked int delayed_read_mark(void)
+{
+	/* This is equivalent to C program below.
+	 * The call to bpf_iter_num_next() is reachable with r7 values &fp[-16] and 0xdead.
+	 * State with r7=&fp[-16] is visited first and follows r6 != 42 ... continue branch.
+	 * At this point iterator next() call is reached with r7 that has no read mark.
+	 * Loop body with r7=0xdead would only be visited if verifier would decide to continue
+	 * with second loop iteration. Absence of read mark on r7 might affect state
+	 * equivalent logic used for iterator convergence tracking.
+	 *
+	 * r7 = &fp[-16]
+	 * fp[-16] = 0
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   r6++
+	 *   if (r6 != 42) {
+	 *     r7 = 0xdead
+	 *     continue;
+	 *   }
+	 *   bpf_probe_read_user(r7, 8, 0xdeadbeef); // this is not safe
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r7 = r10;"
+		"r7 += -16;"
+		"r0 = 0;"
+		"*(u64 *)(r7 + 0) = r0;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 2f;"
+		"r6 += 1;"
+		"if r6 != 42 goto 3f;"
+		"r7 = 0xdead;"
+		"goto 1b;"
+	"3:"
+		"r1 = r7;"
+		"r2 = 8;"
+		"r3 = 0xdeadbeef;"
+		"call %[bpf_probe_read_user];"
+		"goto 1b;"
+	"2:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_probe_read_user)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__naked int delayed_precision_mark(void)
+{
+	/* This is equivalent to C program below.
+	 * The test is similar to delayed_iter_mark but verifies that incomplete
+	 * precision don't fool verifier.
+	 * The call to bpf_iter_num_next() is reachable with r7 values -16 and -32.
+	 * State with r7=-16 is visited first and follows r6 != 42 ... continue branch.
+	 * At this point iterator next() call is reached with r7 that has no read
+	 * and precision marks.
+	 * Loop body with r7=-32 would only be visited if verifier would decide to continue
+	 * with second loop iteration. Absence of precision mark on r7 might affect state
+	 * equivalent logic used for iterator convergence tracking.
+	 *
+	 * r8 = 0
+	 * fp[-16] = 0
+	 * r7 = -16
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   if (r6 != 42) {
+	 *     r7 = -32
+	 *     r6 = bpf_get_prandom_u32()
+	 *     continue;
+	 *   }
+	 *   r0 = r10
+	 *   r0 += r7
+	 *   r8 = *(u64 *)(r0 + 0)           // this is not safe
+	 *   r6 = bpf_get_prandom_u32()
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return r8
+	 */
+	asm volatile (
+		"r8 = 0;"
+		"*(u64 *)(r10 - 16) = r8;"
+		"r7 = -16;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;\n"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 2f;"
+		"if r6 != 42 goto 3f;"
+		"r7 = -32;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"goto 1b;\n"
+	"3:"
+		"r0 = r10;"
+		"r0 += r7;"
+		"r8 = *(u64 *)(r0 + 0);"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"goto 1b;\n"
+	"2:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = r8;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_probe_read_user)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps1(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 * The case turns out to be tricky in a sense that:
+	 * - states with c=-25 are explored only on a second iteration
+	 *   of the outer loop;
+	 * - states with read+precise mark on c are explored only on
+	 *   second iteration of the inner loop and in a state which
+	 *   is pushed to states stack first.
+	 *
+	 * Depending on the details of iterator convergence logic
+	 * verifier might stop states traversal too early and miss
+	 * unsafe c=-25 memory access.
+	 *
+	 *   j = iter_new();		 // fp[-16]
+	 *   a = 0;			 // r6
+	 *   b = 0;			 // r7
+	 *   c = -24;			 // r8
+	 *   while (iter_next(j)) {
+	 *     i = iter_new();		 // fp[-8]
+	 *     a = 0;			 // r6
+	 *     b = 0;			 // r7
+	 *     while (iter_next(i)) {
+	 *	 if (a == 1) {
+	 *	   a = 0;
+	 *	   b = 1;
+	 *	 } else if (a == 0) {
+	 *	   a = 1;
+	 *	   if (random() == 42)
+	 *	     continue;
+	 *	   if (b == 1) {
+	 *	     *(r10 + c) = 7;  // this is not safe
+	 *	     iter_destroy(i);
+	 *	     iter_destroy(j);
+	 *	     return;
+	 *	   }
+	 *	 }
+	 *     }
+	 *     iter_destroy(i);
+	 *     a = 0;
+	 *     b = 0;
+	 *     c = -25;
+	 *   }
+	 *   iter_destroy(j);
+	 *   return;
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -16;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -24;"
+	"j_loop_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto j_loop_end_%=;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i_loop_end_%=;"
+	"check_one_r6_%=:"
+		"if r6 != 1 goto check_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i_loop_%=;"
+	"check_zero_r6_%=:"
+		"if r6 != 0 goto i_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check_one_r7_%=;"
+		"goto i_loop_%=;"
+	"check_one_r7_%=:"
+		"if r7 != 1 goto i_loop_%=;"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"i_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -25;"
+		"goto j_loop_%=;"
+	"j_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__success
+__naked int triple_continue(void)
+{
+	/* This is equivalent to C program below.
+	 * High branching factor of the loop body turned out to be
+	 * problematic for one of the iterator convergence tracking
+	 * algorithms explored.
+	 *
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   r0 += 0;
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"r0 += 0;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__success
+__naked int widen_spill(void)
+{
+	/* This is equivalent to C program below.
+	 * The counter is stored in fp[-16], if this counter is not widened
+	 * verifier states representing loop iterations would never converge.
+	 *
+	 * fp[-16] = 0
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   r0 = fp[-16];
+	 *   r0 += 1;
+	 *   fp[-16] = r0;
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r0 = 0;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"r0 = *(u64 *)(r10 - 16);"
+		"r0 += 1;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("raw_tp")
+__success
+__naked int checkpoint_states_deletion(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 *   int *a, *b, *c, *d, *e, *f;
+	 *   int i, sum = 0;
+	 *   bpf_for(i, 0, 10) {
+	 *     a = bpf_map_lookup_elem(&amap, &i);
+	 *     b = bpf_map_lookup_elem(&amap, &i);
+	 *     c = bpf_map_lookup_elem(&amap, &i);
+	 *     d = bpf_map_lookup_elem(&amap, &i);
+	 *     e = bpf_map_lookup_elem(&amap, &i);
+	 *     f = bpf_map_lookup_elem(&amap, &i);
+	 *     if (a) sum += 1;
+	 *     if (b) sum += 1;
+	 *     if (c) sum += 1;
+	 *     if (d) sum += 1;
+	 *     if (e) sum += 1;
+	 *     if (f) sum += 1;
+	 *   }
+	 *   return 0;
+	 *
+	 * The body of the loop spawns multiple simulation paths
+	 * with different combination of NULL/non-NULL information for a/b/c/d/e/f.
+	 * Each combination is unique from states_equal() point of view.
+	 * Explored states checkpoint is created after each iterator next call.
+	 * Iterator convergence logic expects that eventually current state
+	 * would get equal to one of the explored states and thus loop
+	 * exploration would be finished (at-least for a specific path).
+	 * Verifier evicts explored states with high miss to hit ratio
+	 * to to avoid comparing current state with too many explored
+	 * states per instruction.
+	 * This test is designed to "stress test" eviction policy defined using formula:
+	 *
+	 *    sl->miss_cnt > sl->hit_cnt * N + N // if true sl->state is evicted
+	 *
+	 * Currently N is set to 64, which allows for 6 variables in this test.
+	 */
+	asm volatile (
+		"r6 = 0;"                  /* a */
+		"r7 = 0;"                  /* b */
+		"r8 = 0;"                  /* c */
+		"*(u64 *)(r10 - 24) = r6;" /* d */
+		"*(u64 *)(r10 - 32) = r6;" /* e */
+		"*(u64 *)(r10 - 40) = r6;" /* f */
+		"r9 = 0;"                  /* sum */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+
+		"*(u64 *)(r10 - 16) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r6 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r7 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r8 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 24) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 32) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 40) = r0;"
+
+		"if r6 == 0 goto +1;"
+		"r9 += 1;"
+		"if r7 == 0 goto +1;"
+		"r9 += 1;"
+		"if r8 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 24);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 32);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 40);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_map_lookup_elem),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm_addr(amap)
+		: __clobber_all
+	);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 64870feebecb7130291a55caf0ce839a87405a70 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 24 Oct 2023 03:09:16 +0300
Subject: selftests/bpf: test if state loops are detected in a tricky case

A convoluted test case for iterators convergence logic that
demonstrates that states with branch count equal to 0 might still be
a part of not completely explored loop.

E.g. consider the following state diagram:

               initial     Here state 'succ' was processed first,
                 |         it was eventually tracked to produce a
                 V         state identical to 'hdr'.
    .---------> hdr        All branches from 'succ' had been explored
    |            |         and thus 'succ' has its .branches == 0.
    |            V
    |    .------...        Suppose states 'cur' and 'succ' correspond
    |    |       |         to the same instruction + callsites.
    |    V       V         In such case it is necessary to check
    |   ...     ...        whether 'succ' and 'cur' are identical.
    |    |       |         If 'succ' and 'cur' are a part of the same loop
    |    V       V         they have to be compared exactly.
    |   succ <- cur
    |    |
    |    V
    |   ...
    |    |
    '----'

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231024000917.12153-7-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/iters.c | 177 ++++++++++++++++++++++++++++++
 1 file changed, 177 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 764a68420c3e..c20c4e38b71c 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -998,6 +998,183 @@ __naked int loop_state_deps1(void)
 	);
 }
 
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps2(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 * The case turns out to be tricky in a sense that:
+	 * - states with read+precise mark on c are explored only on a second
+	 *   iteration of the first inner loop and in a state which is pushed to
+	 *   states stack first.
+	 * - states with c=-25 are explored only on a second iteration of the
+	 *   second inner loop and in a state which is pushed to states stack
+	 *   first.
+	 *
+	 * Depending on the details of iterator convergence logic
+	 * verifier might stop states traversal too early and miss
+	 * unsafe c=-25 memory access.
+	 *
+	 *   j = iter_new();             // fp[-16]
+	 *   a = 0;                      // r6
+	 *   b = 0;                      // r7
+	 *   c = -24;                    // r8
+	 *   while (iter_next(j)) {
+	 *     i = iter_new();           // fp[-8]
+	 *     a = 0;                    // r6
+	 *     b = 0;                    // r7
+	 *     while (iter_next(i)) {
+	 *       if (a == 1) {
+	 *         a = 0;
+	 *         b = 1;
+	 *       } else if (a == 0) {
+	 *         a = 1;
+	 *         if (random() == 42)
+	 *           continue;
+	 *         if (b == 1) {
+	 *           *(r10 + c) = 7;     // this is not safe
+	 *           iter_destroy(i);
+	 *           iter_destroy(j);
+	 *           return;
+	 *         }
+	 *       }
+	 *     }
+	 *     iter_destroy(i);
+	 *     i = iter_new();           // fp[-8]
+	 *     a = 0;                    // r6
+	 *     b = 0;                    // r7
+	 *     while (iter_next(i)) {
+	 *       if (a == 1) {
+	 *         a = 0;
+	 *         b = 1;
+	 *       } else if (a == 0) {
+	 *         a = 1;
+	 *         if (random() == 42)
+	 *           continue;
+	 *         if (b == 1) {
+	 *           a = 0;
+	 *           c = -25;
+	 *         }
+	 *       }
+	 *     }
+	 *     iter_destroy(i);
+	 *   }
+	 *   iter_destroy(j);
+	 *   return;
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -16;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -24;"
+	"j_loop_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto j_loop_end_%=;"
+
+		/* first inner loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i_loop_end_%=;"
+	"check_one_r6_%=:"
+		"if r6 != 1 goto check_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i_loop_%=;"
+	"check_zero_r6_%=:"
+		"if r6 != 0 goto i_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check_one_r7_%=;"
+		"goto i_loop_%=;"
+	"check_one_r7_%=:"
+		"if r7 != 1 goto i_loop_%=;"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"i_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+
+		/* second inner loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i2_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i2_loop_end_%=;"
+	"check2_one_r6_%=:"
+		"if r6 != 1 goto check2_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i2_loop_%=;"
+	"check2_zero_r6_%=:"
+		"if r6 != 0 goto i2_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check2_one_r7_%=;"
+		"goto i2_loop_%=;"
+	"check2_one_r7_%=:"
+		"if r7 != 1 goto i2_loop_%=;"
+		"r6 = 0;"
+		"r8 = -25;"
+		"goto i2_loop_%=;"
+	"i2_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+
+		"r6 = 0;"
+		"r7 = 0;"
+		"goto j_loop_%=;"
+	"j_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
 SEC("?raw_tp")
 __success
 __naked int triple_continue(void)
-- 
cgit v1.2.3


From 0c63ad3795269849782ca24a084952206986d3bf Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 23 Oct 2023 11:17:06 -0700
Subject: tools: ynl-gen: add support for exact-len validation

add support for 'exact-len' validation on netlink attributes.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/340
Acked-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-1-v2-2-16b1f701f900@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      |  3 +++
 Documentation/netlink/genetlink-legacy.yaml |  3 +++
 Documentation/netlink/genetlink.yaml        |  3 +++
 Documentation/netlink/netlink-raw.yaml      |  3 +++
 tools/net/ynl/ynl-gen-c.py                  | 28 +++++++++++++++++-----------
 5 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index c72c8a428911..7ef2496d57c8 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -199,6 +199,9 @@ properties:
                   max-len:
                     description: Max length for a string or a binary attribute.
                     $ref: '#/$defs/len-or-define'
+                  exact-len:
+                    description: Exact length for a string or a binary attribute.
+                    $ref: '#/$defs/len-or-define'
               sub-type: *attr-type
               display-hint: &display-hint
                 description: |
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index d858711f3177..cd5ebe39b52c 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -242,6 +242,9 @@ properties:
                   max-len:
                     description: Max length for a string or a binary attribute.
                     $ref: '#/$defs/len-or-define'
+                  exact-len:
+                    description: Exact length for a string or a binary attribute.
+                    $ref: '#/$defs/len-or-define'
               sub-type: *attr-type
               display-hint: *display-hint
               # Start genetlink-c
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 9ceb096b2df2..501ed2e6c8ef 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -172,6 +172,9 @@ properties:
                   max-len:
                     description: Max length for a string or a binary attribute.
                     $ref: '#/$defs/len-or-define'
+                  exact-len:
+                    description: Exact length for a string or a binary attribute.
+                    $ref: '#/$defs/len-or-define'
               sub-type: *attr-type
               display-hint: &display-hint
                 description: |
diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
index d976851b80f8..48db31f1d059 100644
--- a/Documentation/netlink/netlink-raw.yaml
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -240,6 +240,9 @@ properties:
                   max-len:
                     description: Max length for a string or a binary attribute.
                     $ref: '#/$defs/len-or-define'
+                  exact-len:
+                    description: Exact length for a string or a binary attribute.
+                    $ref: '#/$defs/len-or-define'
               sub-type: *attr-type
               display-hint: *display-hint
               # Start genetlink-c
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 8ae283b1a9bc..0fee68863db4 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -410,10 +410,13 @@ class TypeString(Type):
         return f'.type = YNL_PT_NUL_STR, '
 
     def _attr_policy(self, policy):
-        mem = '{ .type = ' + policy
-        if 'max-len' in self.checks:
-            mem += ', .len = ' + str(self.get_limit('max-len'))
-        mem += ', }'
+        if 'exact-len' in self.checks:
+            mem = 'NLA_POLICY_EXACT_LEN(' + str(self.checks['exact-len']) + ')'
+        else:
+            mem = '{ .type = ' + policy
+            if 'max-len' in self.checks:
+                mem += ', .len = ' + str(self.get_limit('max-len'))
+            mem += ', }'
         return mem
 
     def attr_policy(self, cw):
@@ -459,14 +462,17 @@ class TypeBinary(Type):
         return f'.type = YNL_PT_BINARY,'
 
     def _attr_policy(self, policy):
-        mem = '{ '
-        if len(self.checks) == 1 and 'min-len' in self.checks:
-            mem += '.len = ' + str(self.get_limit('min-len'))
-        elif len(self.checks) == 0:
-            mem += '.type = NLA_BINARY'
+        if 'exact-len' in self.checks:
+            mem = 'NLA_POLICY_EXACT_LEN(' + str(self.checks['exact-len']) + ')'
         else:
-            raise Exception('One or more of binary type checks not implemented, yet')
-        mem += ', }'
+            mem = '{ '
+            if len(self.checks) == 1 and 'min-len' in self.checks:
+                mem += '.len = ' + str(self.get_limit('min-len'))
+            elif len(self.checks) == 0:
+                mem += '.type = NLA_BINARY'
+            else:
+                raise Exception('One or more of binary type checks not implemented, yet')
+            mem += ', }'
         return mem
 
     def attr_put(self, ri, var):
-- 
cgit v1.2.3


From 37a38e439d4ed0e90d7359708ed9fca0216631b6 Mon Sep 17 00:00:00 2001
From: Swarup Laxman Kotiaklapudi <swarupkotikalapudi@gmail.com>
Date: Mon, 23 Oct 2023 18:04:22 +0530
Subject: selftests: net: change ifconfig with ip command

Change ifconfig with ip command, on a system where ifconfig is
not used this script will not work correcly.

Test result with this patchset:

sudo make TARGETS="net" kselftest
....
TAP version 13
1..1
 timeout set to 1500
 selftests: net: route_localnet.sh
 run arp_announce test
 net.ipv4.conf.veth0.route_localnet = 1
 net.ipv4.conf.veth1.route_localnet = 1
 net.ipv4.conf.veth0.arp_announce = 2
 net.ipv4.conf.veth1.arp_announce = 2
 PING 127.25.3.14 (127.25.3.14) from 127.25.3.4 veth0: 56(84)
  bytes of data.
 64 bytes from 127.25.3.14: icmp_seq=1 ttl=64 time=0.038 ms
 64 bytes from 127.25.3.14: icmp_seq=2 ttl=64 time=0.068 ms
 64 bytes from 127.25.3.14: icmp_seq=3 ttl=64 time=0.068 ms
 64 bytes from 127.25.3.14: icmp_seq=4 ttl=64 time=0.068 ms
 64 bytes from 127.25.3.14: icmp_seq=5 ttl=64 time=0.068 ms

 --- 127.25.3.14 ping statistics ---
 5 packets transmitted, 5 received, 0% packet loss, time 4073ms
 rtt min/avg/max/mdev = 0.038/0.062/0.068/0.012 ms
 ok
 run arp_ignore test
 net.ipv4.conf.veth0.route_localnet = 1
 net.ipv4.conf.veth1.route_localnet = 1
 net.ipv4.conf.veth0.arp_ignore = 3
 net.ipv4.conf.veth1.arp_ignore = 3
 PING 127.25.3.14 (127.25.3.14) from 127.25.3.4 veth0: 56(84)
  bytes of data.
 64 bytes from 127.25.3.14: icmp_seq=1 ttl=64 time=0.032 ms
 64 bytes from 127.25.3.14: icmp_seq=2 ttl=64 time=0.065 ms
 64 bytes from 127.25.3.14: icmp_seq=3 ttl=64 time=0.066 ms
 64 bytes from 127.25.3.14: icmp_seq=4 ttl=64 time=0.065 ms
 64 bytes from 127.25.3.14: icmp_seq=5 ttl=64 time=0.065 ms

 --- 127.25.3.14 ping statistics ---
 5 packets transmitted, 5 received, 0% packet loss, time 4092ms
 rtt min/avg/max/mdev = 0.032/0.058/0.066/0.013 ms
 ok
ok 1 selftests: net: route_localnet.sh
...

Signed-off-by: Swarup Laxman Kotiaklapudi <swarupkotikalapudi@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231023123422.2895-1-swarupkotikalapudi@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/route_localnet.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/route_localnet.sh b/tools/testing/selftests/net/route_localnet.sh
index 116bfeab72fa..e08701c750e3 100755
--- a/tools/testing/selftests/net/route_localnet.sh
+++ b/tools/testing/selftests/net/route_localnet.sh
@@ -18,8 +18,10 @@ setup() {
     ip route del 127.0.0.0/8 dev lo table local
     ip netns exec "${PEER_NS}" ip route del 127.0.0.0/8 dev lo table local
 
-    ifconfig veth0 127.25.3.4/24 up
-    ip netns exec "${PEER_NS}" ifconfig veth1 127.25.3.14/24 up
+    ip address add 127.25.3.4/24 dev veth0
+    ip link set dev veth0 up
+    ip netns exec "${PEER_NS}" ip address add 127.25.3.14/24 dev veth1
+    ip netns exec "${PEER_NS}" ip link set dev veth1 up
 
     ip route flush cache
     ip netns exec "${PEER_NS}" ip route flush cache
-- 
cgit v1.2.3


From 35dfaad7188cdc043fde31709c796f5a692ba2bd Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:48:58 +0200
Subject: netkit, bpf: Add bpf programmable net device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This work adds a new, minimal BPF-programmable device called "netkit"
(former PoC code-name "meta") we recently presented at LSF/MM/BPF. The
core idea is that BPF programs are executed within the drivers xmit routine
and therefore e.g. in case of containers/Pods moving BPF processing closer
to the source.

One of the goals was that in case of Pod egress traffic, this allows to
move BPF programs from hostns tcx ingress into the device itself, providing
earlier drop or forward mechanisms, for example, if the BPF program
determines that the skb must be sent out of the node, then a redirect to
the physical device can take place directly without going through per-CPU
backlog queue. This helps to shift processing for such traffic from softirq
to process context, leading to better scheduling decisions/performance (see
measurements in the slides).

In this initial version, the netkit device ships as a pair, but we plan to
extend this further so it can also operate in single device mode. The pair
comes with a primary and a peer device. Only the primary device, typically
residing in hostns, can manage BPF programs for itself and its peer. The
peer device is designated for containers/Pods and cannot attach/detach
BPF programs. Upon the device creation, the user can set the default policy
to 'pass' or 'drop' for the case when no BPF program is attached.

Additionally, the device can be operated in L3 (default) or L2 mode. The
management of BPF programs is done via bpf_mprog, so that multi-attach is
supported right from the beginning with similar API and dependency controls
as tcx. For details on the latter see commit 053c8e1f235d ("bpf: Add generic
attach/detach/query API for multi-progs"). tc BPF compatibility is provided,
so that existing programs can be easily migrated.

Going forward, we plan to use netkit devices in Cilium as the main device
type for connecting Pods. They will be operated in L3 mode in order to
simplify a Pod's neighbor management and the peer will operate in default
drop mode, so that no traffic is leaving between the time when a Pod is
brought up by the CNI plugin and programs attached by the agent.
Additionally, the programs we attach via tcx on the physical devices are
using bpf_redirect_peer() for inbound traffic into netkit device, hence the
latter is also supporting the ndo_get_peer_dev callback. Similarly, we use
bpf_redirect_neigh() for the way out, pushing from netkit peer to phys device
directly. Also, BIG TCP is supported on netkit device. For the follow-up
work in single device mode, we plan to convert Cilium's cilium_host/_net
devices into a single one.

An extensive test suite for checking device operations and the BPF program
and link management API comes as BPF selftests in this series.

Co-developed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://github.com/borkmann/iproute2/tree/pr/netkit
Link: http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf (24ff.)
Link: https://lore.kernel.org/r/20231024214904.29825-2-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 MAINTAINERS                    |   9 +
 drivers/net/Kconfig            |   9 +
 drivers/net/Makefile           |   1 +
 drivers/net/netkit.c           | 940 +++++++++++++++++++++++++++++++++++++++++
 include/net/netkit.h           |  38 ++
 include/uapi/linux/bpf.h       |  14 +
 include/uapi/linux/if_link.h   |  24 ++
 kernel/bpf/syscall.c           |  30 +-
 tools/include/uapi/linux/bpf.h |  14 +
 9 files changed, 1074 insertions(+), 5 deletions(-)
 create mode 100644 drivers/net/netkit.c
 create mode 100644 include/net/netkit.h

(limited to 'tools')

diff --git a/MAINTAINERS b/MAINTAINERS
index ed33b9df8b3d..43be6197e655 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3795,6 +3795,15 @@ L:	bpf@vger.kernel.org
 S:	Odd Fixes
 K:	(?:\b|_)bpf(?:\b|_)
 
+BPF [NETKIT] (BPF-programmable network device)
+M:	Daniel Borkmann <daniel@iogearbox.net>
+M:	Nikolay Aleksandrov <razor@blackwall.org>
+L:	bpf@vger.kernel.org
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/netkit.c
+F:	include/net/netkit.h
+
 BPF [NETWORKING] (struct_ops, reuseport)
 M:	Martin KaFai Lau <martin.lau@linux.dev>
 L:	bpf@vger.kernel.org
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 44eeb5d61ba9..af0da4bb429b 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -448,6 +448,15 @@ config NLMON
 	  diagnostics, etc. This is mostly intended for developers or support
 	  to debug netlink issues. If unsure, say N.
 
+config NETKIT
+	bool "BPF-programmable network device"
+	depends on BPF_SYSCALL
+	help
+	  The netkit device is a virtual networking device where BPF programs
+	  can be attached to the device(s) transmission routine in order to
+	  implement the driver's internal logic. The device can be configured
+	  to operate in L3 or L2 mode. If unsure, say N.
+
 config NET_VRF
 	tristate "Virtual Routing and Forwarding (Lite)"
 	depends on IP_MULTIPLE_TABLES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 8a83db32509d..7cab36f94782 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO) += mdio.o
 obj-$(CONFIG_NET) += loopback.o
 obj-$(CONFIG_NETDEV_LEGACY_INIT) += Space.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
+obj-$(CONFIG_NETKIT) += netkit.o
 obj-y += phy/
 obj-y += pse-pd/
 obj-y += mdio/
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
new file mode 100644
index 000000000000..7e484f9fd3ae
--- /dev/null
+++ b/drivers/net/netkit.c
@@ -0,0 +1,940 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Isovalent */
+
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <linux/netfilter_netdev.h>
+#include <linux/bpf_mprog.h>
+
+#include <net/netkit.h>
+#include <net/dst.h>
+#include <net/tcx.h>
+
+#define DRV_NAME "netkit"
+
+struct netkit {
+	/* Needed in fast-path */
+	struct net_device __rcu *peer;
+	struct bpf_mprog_entry __rcu *active;
+	enum netkit_action policy;
+	struct bpf_mprog_bundle	bundle;
+
+	/* Needed in slow-path */
+	enum netkit_mode mode;
+	bool primary;
+	u32 headroom;
+};
+
+struct netkit_link {
+	struct bpf_link link;
+	struct net_device *dev;
+	u32 location;
+};
+
+static __always_inline int
+netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
+	   enum netkit_action ret)
+{
+	const struct bpf_mprog_fp *fp;
+	const struct bpf_prog *prog;
+
+	bpf_mprog_foreach_prog(entry, fp, prog) {
+		bpf_compute_data_pointers(skb);
+		ret = bpf_prog_run(prog, skb);
+		if (ret != NETKIT_NEXT)
+			break;
+	}
+	return ret;
+}
+
+static void netkit_prep_forward(struct sk_buff *skb, bool xnet)
+{
+	skb_scrub_packet(skb, xnet);
+	skb->priority = 0;
+	nf_skip_egress(skb, true);
+}
+
+static struct netkit *netkit_priv(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	enum netkit_action ret = READ_ONCE(nk->policy);
+	netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
+	const struct bpf_mprog_entry *entry;
+	struct net_device *peer;
+
+	rcu_read_lock();
+	peer = rcu_dereference(nk->peer);
+	if (unlikely(!peer || !(peer->flags & IFF_UP) ||
+		     !pskb_may_pull(skb, ETH_HLEN) ||
+		     skb_orphan_frags(skb, GFP_ATOMIC)))
+		goto drop;
+	netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)));
+	skb->dev = peer;
+	entry = rcu_dereference(nk->active);
+	if (entry)
+		ret = netkit_run(entry, skb, ret);
+	switch (ret) {
+	case NETKIT_NEXT:
+	case NETKIT_PASS:
+		skb->protocol = eth_type_trans(skb, skb->dev);
+		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+		__netif_rx(skb);
+		break;
+	case NETKIT_REDIRECT:
+		skb_do_redirect(skb);
+		break;
+	case NETKIT_DROP:
+	default:
+drop:
+		kfree_skb(skb);
+		dev_core_stats_tx_dropped_inc(dev);
+		ret_dev = NET_XMIT_DROP;
+		break;
+	}
+	rcu_read_unlock();
+	return ret_dev;
+}
+
+static int netkit_open(struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+
+	if (!peer)
+		return -ENOTCONN;
+	if (peer->flags & IFF_UP) {
+		netif_carrier_on(dev);
+		netif_carrier_on(peer);
+	}
+	return 0;
+}
+
+static int netkit_close(struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+
+	netif_carrier_off(dev);
+	if (peer)
+		netif_carrier_off(peer);
+	return 0;
+}
+
+static int netkit_get_iflink(const struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer;
+	int iflink = 0;
+
+	rcu_read_lock();
+	peer = rcu_dereference(nk->peer);
+	if (peer)
+		iflink = peer->ifindex;
+	rcu_read_unlock();
+	return iflink;
+}
+
+static void netkit_set_multicast(struct net_device *dev)
+{
+	/* Nothing to do, we receive whatever gets pushed to us! */
+}
+
+static void netkit_set_headroom(struct net_device *dev, int headroom)
+{
+	struct netkit *nk = netkit_priv(dev), *nk2;
+	struct net_device *peer;
+
+	if (headroom < 0)
+		headroom = NET_SKB_PAD;
+
+	rcu_read_lock();
+	peer = rcu_dereference(nk->peer);
+	if (unlikely(!peer))
+		goto out;
+
+	nk2 = netkit_priv(peer);
+	nk->headroom = headroom;
+	headroom = max(nk->headroom, nk2->headroom);
+
+	peer->needed_headroom = headroom;
+	dev->needed_headroom = headroom;
+out:
+	rcu_read_unlock();
+}
+
+static struct net_device *netkit_peer_dev(struct net_device *dev)
+{
+	return rcu_dereference(netkit_priv(dev)->peer);
+}
+
+static void netkit_uninit(struct net_device *dev);
+
+static const struct net_device_ops netkit_netdev_ops = {
+	.ndo_open		= netkit_open,
+	.ndo_stop		= netkit_close,
+	.ndo_start_xmit		= netkit_xmit,
+	.ndo_set_rx_mode	= netkit_set_multicast,
+	.ndo_set_rx_headroom	= netkit_set_headroom,
+	.ndo_get_iflink		= netkit_get_iflink,
+	.ndo_get_peer_dev	= netkit_peer_dev,
+	.ndo_uninit		= netkit_uninit,
+	.ndo_features_check	= passthru_features_check,
+};
+
+static void netkit_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+}
+
+static const struct ethtool_ops netkit_ethtool_ops = {
+	.get_drvinfo		= netkit_get_drvinfo,
+};
+
+static void netkit_setup(struct net_device *dev)
+{
+	static const netdev_features_t netkit_features_hw_vlan =
+		NETIF_F_HW_VLAN_CTAG_TX |
+		NETIF_F_HW_VLAN_CTAG_RX |
+		NETIF_F_HW_VLAN_STAG_TX |
+		NETIF_F_HW_VLAN_STAG_RX;
+	static const netdev_features_t netkit_features =
+		netkit_features_hw_vlan |
+		NETIF_F_SG |
+		NETIF_F_FRAGLIST |
+		NETIF_F_HW_CSUM |
+		NETIF_F_RXCSUM |
+		NETIF_F_SCTP_CRC |
+		NETIF_F_HIGHDMA |
+		NETIF_F_GSO_SOFTWARE |
+		NETIF_F_GSO_ENCAP_ALL;
+
+	ether_setup(dev);
+	dev->max_mtu = ETH_MAX_MTU;
+
+	dev->flags |= IFF_NOARP;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	dev->priv_flags |= IFF_PHONY_HEADROOM;
+	dev->priv_flags |= IFF_NO_QUEUE;
+
+	dev->ethtool_ops = &netkit_ethtool_ops;
+	dev->netdev_ops  = &netkit_netdev_ops;
+
+	dev->features |= netkit_features | NETIF_F_LLTX;
+	dev->hw_features = netkit_features;
+	dev->hw_enc_features = netkit_features;
+	dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
+	dev->vlan_features = dev->features & ~netkit_features_hw_vlan;
+
+	dev->needs_free_netdev = true;
+
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+}
+
+static struct net *netkit_get_link_net(const struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+
+	return peer ? dev_net(peer) : dev_net(dev);
+}
+
+static int netkit_check_policy(int policy, struct nlattr *tb,
+			       struct netlink_ext_ack *extack)
+{
+	switch (policy) {
+	case NETKIT_PASS:
+	case NETKIT_DROP:
+		return 0;
+	default:
+		NL_SET_ERR_MSG_ATTR(extack, tb,
+				    "Provided default xmit policy not supported");
+		return -EINVAL;
+	}
+}
+
+static int netkit_check_mode(int mode, struct nlattr *tb,
+			     struct netlink_ext_ack *extack)
+{
+	switch (mode) {
+	case NETKIT_L2:
+	case NETKIT_L3:
+		return 0;
+	default:
+		NL_SET_ERR_MSG_ATTR(extack, tb,
+				    "Provided device mode can only be L2 or L3");
+		return -EINVAL;
+	}
+}
+
+static int netkit_validate(struct nlattr *tb[], struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *attr = tb[IFLA_ADDRESS];
+
+	if (!attr)
+		return 0;
+	NL_SET_ERR_MSG_ATTR(extack, attr,
+			    "Setting Ethernet address is not supported");
+	return -EOPNOTSUPP;
+}
+
+static struct rtnl_link_ops netkit_link_ops;
+
+static int netkit_new_link(struct net *src_net, struct net_device *dev,
+			   struct nlattr *tb[], struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr;
+	enum netkit_action default_prim = NETKIT_PASS;
+	enum netkit_action default_peer = NETKIT_PASS;
+	enum netkit_mode mode = NETKIT_L3;
+	unsigned char ifname_assign_type;
+	struct ifinfomsg *ifmp = NULL;
+	struct net_device *peer;
+	char ifname[IFNAMSIZ];
+	struct netkit *nk;
+	struct net *net;
+	int err;
+
+	if (data) {
+		if (data[IFLA_NETKIT_MODE]) {
+			attr = data[IFLA_NETKIT_MODE];
+			mode = nla_get_u32(attr);
+			err = netkit_check_mode(mode, attr, extack);
+			if (err < 0)
+				return err;
+		}
+		if (data[IFLA_NETKIT_PEER_INFO]) {
+			attr = data[IFLA_NETKIT_PEER_INFO];
+			ifmp = nla_data(attr);
+			err = rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack);
+			if (err < 0)
+				return err;
+			err = netkit_validate(peer_tb, NULL, extack);
+			if (err < 0)
+				return err;
+			tbp = peer_tb;
+		}
+		if (data[IFLA_NETKIT_POLICY]) {
+			attr = data[IFLA_NETKIT_POLICY];
+			default_prim = nla_get_u32(attr);
+			err = netkit_check_policy(default_prim, attr, extack);
+			if (err < 0)
+				return err;
+		}
+		if (data[IFLA_NETKIT_PEER_POLICY]) {
+			attr = data[IFLA_NETKIT_PEER_POLICY];
+			default_peer = nla_get_u32(attr);
+			err = netkit_check_policy(default_peer, attr, extack);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	if (ifmp && tbp[IFLA_IFNAME]) {
+		nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		ifname_assign_type = NET_NAME_USER;
+	} else {
+		strscpy(ifname, "nk%d", IFNAMSIZ);
+		ifname_assign_type = NET_NAME_ENUM;
+	}
+
+	net = rtnl_link_get_net(src_net, tbp);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	peer = rtnl_create_link(net, ifname, ifname_assign_type,
+				&netkit_link_ops, tbp, extack);
+	if (IS_ERR(peer)) {
+		put_net(net);
+		return PTR_ERR(peer);
+	}
+
+	netif_inherit_tso_max(peer, dev);
+
+	if (mode == NETKIT_L2)
+		eth_hw_addr_random(peer);
+	if (ifmp && dev->ifindex)
+		peer->ifindex = ifmp->ifi_index;
+
+	nk = netkit_priv(peer);
+	nk->primary = false;
+	nk->policy = default_peer;
+	nk->mode = mode;
+	bpf_mprog_bundle_init(&nk->bundle);
+	RCU_INIT_POINTER(nk->active, NULL);
+	RCU_INIT_POINTER(nk->peer, NULL);
+
+	err = register_netdevice(peer);
+	put_net(net);
+	if (err < 0)
+		goto err_register_peer;
+	netif_carrier_off(peer);
+	if (mode == NETKIT_L2)
+		dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL);
+
+	err = rtnl_configure_link(peer, NULL, 0, NULL);
+	if (err < 0)
+		goto err_configure_peer;
+
+	if (mode == NETKIT_L2)
+		eth_hw_addr_random(dev);
+	if (tb[IFLA_IFNAME])
+		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+	else
+		strscpy(dev->name, "nk%d", IFNAMSIZ);
+
+	nk = netkit_priv(dev);
+	nk->primary = true;
+	nk->policy = default_prim;
+	nk->mode = mode;
+	bpf_mprog_bundle_init(&nk->bundle);
+	RCU_INIT_POINTER(nk->active, NULL);
+	RCU_INIT_POINTER(nk->peer, NULL);
+
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto err_configure_peer;
+	netif_carrier_off(dev);
+	if (mode == NETKIT_L2)
+		dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL);
+
+	rcu_assign_pointer(netkit_priv(dev)->peer, peer);
+	rcu_assign_pointer(netkit_priv(peer)->peer, dev);
+	return 0;
+err_configure_peer:
+	unregister_netdevice(peer);
+	return err;
+err_register_peer:
+	free_netdev(peer);
+	return err;
+}
+
+static struct bpf_mprog_entry *netkit_entry_fetch(struct net_device *dev,
+						  bool bundle_fallback)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct bpf_mprog_entry *entry;
+
+	ASSERT_RTNL();
+	entry = rcu_dereference_rtnl(nk->active);
+	if (entry)
+		return entry;
+	if (bundle_fallback)
+		return &nk->bundle.a;
+	return NULL;
+}
+
+static void netkit_entry_update(struct net_device *dev,
+				struct bpf_mprog_entry *entry)
+{
+	struct netkit *nk = netkit_priv(dev);
+
+	ASSERT_RTNL();
+	rcu_assign_pointer(nk->active, entry);
+}
+
+static void netkit_entry_sync(void)
+{
+	synchronize_rcu();
+}
+
+static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 which)
+{
+	struct net_device *dev;
+	struct netkit *nk;
+
+	ASSERT_RTNL();
+
+	switch (which) {
+	case BPF_NETKIT_PRIMARY:
+	case BPF_NETKIT_PEER:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev = __dev_get_by_index(net, ifindex);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+	if (dev->netdev_ops != &netkit_netdev_ops)
+		return ERR_PTR(-ENXIO);
+
+	nk = netkit_priv(dev);
+	if (!nk->primary)
+		return ERR_PTR(-EACCES);
+	if (which == BPF_NETKIT_PEER) {
+		dev = rcu_dereference_rtnl(nk->peer);
+		if (!dev)
+			return ERR_PTR(-ENODEV);
+	}
+	return dev;
+}
+
+int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct bpf_prog *replace_prog = NULL;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex,
+			       attr->attach_type);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto out;
+	}
+	entry = netkit_entry_fetch(dev, true);
+	if (attr->attach_flags & BPF_F_REPLACE) {
+		replace_prog = bpf_prog_get_type(attr->replace_bpf_fd,
+						 prog->type);
+		if (IS_ERR(replace_prog)) {
+			ret = PTR_ERR(replace_prog);
+			replace_prog = NULL;
+			goto out;
+		}
+	}
+	ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog,
+			       attr->attach_flags, attr->relative_fd,
+			       attr->expected_revision);
+	if (!ret) {
+		if (entry != entry_new) {
+			netkit_entry_update(dev, entry_new);
+			netkit_entry_sync();
+		}
+		bpf_mprog_commit(entry);
+	}
+out:
+	if (replace_prog)
+		bpf_prog_put(replace_prog);
+	rtnl_unlock();
+	return ret;
+}
+
+int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex,
+			       attr->attach_type);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto out;
+	}
+	entry = netkit_entry_fetch(dev, false);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags,
+			       attr->relative_fd, attr->expected_revision);
+	if (!ret) {
+		if (!bpf_mprog_total(entry_new))
+			entry_new = NULL;
+		netkit_entry_update(dev, entry_new);
+		netkit_entry_sync();
+		bpf_mprog_commit(entry);
+	}
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = netkit_dev_fetch(current->nsproxy->net_ns,
+			       attr->query.target_ifindex,
+			       attr->query.attach_type);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto out;
+	}
+	ret = bpf_mprog_query(attr, uattr, netkit_entry_fetch(dev, false));
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+static struct netkit_link *netkit_link(const struct bpf_link *link)
+{
+	return container_of(link, struct netkit_link, link);
+}
+
+static int netkit_link_prog_attach(struct bpf_link *link, u32 flags,
+				   u32 id_or_fd, u64 revision)
+{
+	struct netkit_link *nkl = netkit_link(link);
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev = nkl->dev;
+	int ret;
+
+	ASSERT_RTNL();
+	entry = netkit_entry_fetch(dev, true);
+	ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags,
+			       id_or_fd, revision);
+	if (!ret) {
+		if (entry != entry_new) {
+			netkit_entry_update(dev, entry_new);
+			netkit_entry_sync();
+		}
+		bpf_mprog_commit(entry);
+	}
+	return ret;
+}
+
+static void netkit_link_release(struct bpf_link *link)
+{
+	struct netkit_link *nkl = netkit_link(link);
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	dev = nkl->dev;
+	if (!dev)
+		goto out;
+	entry = netkit_entry_fetch(dev, false);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0);
+	if (!ret) {
+		if (!bpf_mprog_total(entry_new))
+			entry_new = NULL;
+		netkit_entry_update(dev, entry_new);
+		netkit_entry_sync();
+		bpf_mprog_commit(entry);
+		nkl->dev = NULL;
+	}
+out:
+	WARN_ON_ONCE(ret);
+	rtnl_unlock();
+}
+
+static int netkit_link_update(struct bpf_link *link, struct bpf_prog *nprog,
+			      struct bpf_prog *oprog)
+{
+	struct netkit_link *nkl = netkit_link(link);
+	struct bpf_mprog_entry *entry, *entry_new;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	dev = nkl->dev;
+	if (!dev) {
+		ret = -ENOLINK;
+		goto out;
+	}
+	if (oprog && link->prog != oprog) {
+		ret = -EPERM;
+		goto out;
+	}
+	oprog = link->prog;
+	if (oprog == nprog) {
+		bpf_prog_put(nprog);
+		goto out;
+	}
+	entry = netkit_entry_fetch(dev, false);
+	if (!entry) {
+		ret = -ENOENT;
+		goto out;
+	}
+	ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog,
+			       BPF_F_REPLACE | BPF_F_ID,
+			       link->prog->aux->id, 0);
+	if (!ret) {
+		WARN_ON_ONCE(entry != entry_new);
+		oprog = xchg(&link->prog, nprog);
+		bpf_prog_put(oprog);
+		bpf_mprog_commit(entry);
+	}
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+static void netkit_link_dealloc(struct bpf_link *link)
+{
+	kfree(netkit_link(link));
+}
+
+static void netkit_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
+{
+	const struct netkit_link *nkl = netkit_link(link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (nkl->dev)
+		ifindex = nkl->dev->ifindex;
+	rtnl_unlock();
+
+	seq_printf(seq, "ifindex:\t%u\n", ifindex);
+	seq_printf(seq, "attach_type:\t%u (%s)\n",
+		   nkl->location,
+		   nkl->location == BPF_NETKIT_PRIMARY ? "primary" : "peer");
+}
+
+static int netkit_link_fill_info(const struct bpf_link *link,
+				 struct bpf_link_info *info)
+{
+	const struct netkit_link *nkl = netkit_link(link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (nkl->dev)
+		ifindex = nkl->dev->ifindex;
+	rtnl_unlock();
+
+	info->netkit.ifindex = ifindex;
+	info->netkit.attach_type = nkl->location;
+	return 0;
+}
+
+static int netkit_link_detach(struct bpf_link *link)
+{
+	netkit_link_release(link);
+	return 0;
+}
+
+static const struct bpf_link_ops netkit_link_lops = {
+	.release	= netkit_link_release,
+	.detach		= netkit_link_detach,
+	.dealloc	= netkit_link_dealloc,
+	.update_prog	= netkit_link_update,
+	.show_fdinfo	= netkit_link_fdinfo,
+	.fill_link_info	= netkit_link_fill_info,
+};
+
+static int netkit_link_init(struct netkit_link *nkl,
+			    struct bpf_link_primer *link_primer,
+			    const union bpf_attr *attr,
+			    struct net_device *dev,
+			    struct bpf_prog *prog)
+{
+	bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT,
+		      &netkit_link_lops, prog);
+	nkl->location = attr->link_create.attach_type;
+	nkl->dev = dev;
+	return bpf_link_prime(&nkl->link, link_primer);
+}
+
+int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct netkit_link *nkl;
+	struct net_device *dev;
+	int ret;
+
+	rtnl_lock();
+	dev = netkit_dev_fetch(current->nsproxy->net_ns,
+			       attr->link_create.target_ifindex,
+			       attr->link_create.attach_type);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto out;
+	}
+	nkl = kzalloc(sizeof(*nkl), GFP_KERNEL_ACCOUNT);
+	if (!nkl) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ret = netkit_link_init(nkl, &link_primer, attr, dev, prog);
+	if (ret) {
+		kfree(nkl);
+		goto out;
+	}
+	ret = netkit_link_prog_attach(&nkl->link,
+				      attr->link_create.flags,
+				      attr->link_create.netkit.relative_fd,
+				      attr->link_create.netkit.expected_revision);
+	if (ret) {
+		nkl->dev = NULL;
+		bpf_link_cleanup(&link_primer);
+		goto out;
+	}
+	ret = bpf_link_settle(&link_primer);
+out:
+	rtnl_unlock();
+	return ret;
+}
+
+static void netkit_release_all(struct net_device *dev)
+{
+	struct bpf_mprog_entry *entry;
+	struct bpf_tuple tuple = {};
+	struct bpf_mprog_fp *fp;
+	struct bpf_mprog_cp *cp;
+
+	entry = netkit_entry_fetch(dev, false);
+	if (!entry)
+		return;
+	netkit_entry_update(dev, NULL);
+	netkit_entry_sync();
+	bpf_mprog_foreach_tuple(entry, fp, cp, tuple) {
+		if (tuple.link)
+			netkit_link(tuple.link)->dev = NULL;
+		else
+			bpf_prog_put(tuple.prog);
+	}
+}
+
+static void netkit_uninit(struct net_device *dev)
+{
+	netkit_release_all(dev);
+}
+
+static void netkit_del_link(struct net_device *dev, struct list_head *head)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+
+	RCU_INIT_POINTER(nk->peer, NULL);
+	unregister_netdevice_queue(dev, head);
+	if (peer) {
+		nk = netkit_priv(peer);
+		RCU_INIT_POINTER(nk->peer, NULL);
+		unregister_netdevice_queue(peer, head);
+	}
+}
+
+static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
+			      struct nlattr *data[],
+			      struct netlink_ext_ack *extack)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+	enum netkit_action policy;
+	struct nlattr *attr;
+	int err;
+
+	if (!nk->primary) {
+		NL_SET_ERR_MSG(extack,
+			       "netkit link settings can be changed only through the primary device");
+		return -EACCES;
+	}
+
+	if (data[IFLA_NETKIT_MODE]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE],
+				    "netkit link operating mode cannot be changed after device creation");
+		return -EACCES;
+	}
+
+	if (data[IFLA_NETKIT_POLICY]) {
+		attr = data[IFLA_NETKIT_POLICY];
+		policy = nla_get_u32(attr);
+		err = netkit_check_policy(policy, attr, extack);
+		if (err)
+			return err;
+		WRITE_ONCE(nk->policy, policy);
+	}
+
+	if (data[IFLA_NETKIT_PEER_POLICY]) {
+		err = -EOPNOTSUPP;
+		attr = data[IFLA_NETKIT_PEER_POLICY];
+		policy = nla_get_u32(attr);
+		if (peer)
+			err = netkit_check_policy(policy, attr, extack);
+		if (err)
+			return err;
+		nk = netkit_priv(peer);
+		WRITE_ONCE(nk->policy, policy);
+	}
+
+	return 0;
+}
+
+static size_t netkit_get_size(const struct net_device *dev)
+{
+	return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */
+	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */
+	       nla_total_size(sizeof(u8))  + /* IFLA_NETKIT_PRIMARY */
+	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */
+	       0;
+}
+
+static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct netkit *nk = netkit_priv(dev);
+	struct net_device *peer = rtnl_dereference(nk->peer);
+
+	if (nla_put_u8(skb, IFLA_NETKIT_PRIMARY, nk->primary))
+		return -EMSGSIZE;
+	if (nla_put_u32(skb, IFLA_NETKIT_POLICY, nk->policy))
+		return -EMSGSIZE;
+	if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode))
+		return -EMSGSIZE;
+
+	if (peer) {
+		nk = netkit_priv(peer);
+		if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy))
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
+	[IFLA_NETKIT_PEER_INFO]		= { .len = sizeof(struct ifinfomsg) },
+	[IFLA_NETKIT_POLICY]		= { .type = NLA_U32 },
+	[IFLA_NETKIT_MODE]		= { .type = NLA_U32 },
+	[IFLA_NETKIT_PEER_POLICY]	= { .type = NLA_U32 },
+	[IFLA_NETKIT_PRIMARY]		= { .type = NLA_REJECT,
+					    .reject_message = "Primary attribute is read-only" },
+};
+
+static struct rtnl_link_ops netkit_link_ops = {
+	.kind		= DRV_NAME,
+	.priv_size	= sizeof(struct netkit),
+	.setup		= netkit_setup,
+	.newlink	= netkit_new_link,
+	.dellink	= netkit_del_link,
+	.changelink	= netkit_change_link,
+	.get_link_net	= netkit_get_link_net,
+	.get_size	= netkit_get_size,
+	.fill_info	= netkit_fill_info,
+	.policy		= netkit_policy,
+	.validate	= netkit_validate,
+	.maxtype	= IFLA_NETKIT_MAX,
+};
+
+static __init int netkit_init(void)
+{
+	BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT ||
+		     (int)NETKIT_PASS != (int)TCX_PASS ||
+		     (int)NETKIT_DROP != (int)TCX_DROP ||
+		     (int)NETKIT_REDIRECT != (int)TCX_REDIRECT);
+
+	return rtnl_link_register(&netkit_link_ops);
+}
+
+static __exit void netkit_exit(void)
+{
+	rtnl_link_unregister(&netkit_link_ops);
+}
+
+module_init(netkit_init);
+module_exit(netkit_exit);
+
+MODULE_DESCRIPTION("BPF-programmable network device");
+MODULE_AUTHOR("Daniel Borkmann <daniel@iogearbox.net>");
+MODULE_AUTHOR("Nikolay Aleksandrov <razor@blackwall.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
diff --git a/include/net/netkit.h b/include/net/netkit.h
new file mode 100644
index 000000000000..0ba2e6b847ca
--- /dev/null
+++ b/include/net/netkit.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __NET_NETKIT_H
+#define __NET_NETKIT_H
+
+#include <linux/bpf.h>
+
+#ifdef CONFIG_NETKIT
+int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
+int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+#else
+static inline int netkit_prog_attach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_link_attach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_prog_detach(const union bpf_attr *attr,
+				     struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int netkit_prog_query(const union bpf_attr *attr,
+				    union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_NETKIT */
+#endif /* __NET_NETKIT_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7ba61b75bc0e..0f6cdf52b1da 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1052,6 +1052,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_UNIX_RECVMSG,
 	BPF_CGROUP_UNIX_GETPEERNAME,
 	BPF_CGROUP_UNIX_GETSOCKNAME,
+	BPF_NETKIT_PRIMARY,
+	BPF_NETKIT_PEER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1071,6 +1073,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
+	BPF_LINK_TYPE_NETKIT = 13,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1656,6 +1659,13 @@ union bpf_attr {
 				__u32		flags;
 				__u32		pid;
 			} uprobe_multi;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} netkit;
 		};
 	} link_create;
 
@@ -6576,6 +6586,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} tcx;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} netkit;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index fac351a93aed..a0aa05a28cf2 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -756,6 +756,30 @@ struct tunnel_msg {
 	__u32 ifindex;
 };
 
+/* netkit section */
+enum netkit_action {
+	NETKIT_NEXT	= -1,
+	NETKIT_PASS	= 0,
+	NETKIT_DROP	= 2,
+	NETKIT_REDIRECT	= 7,
+};
+
+enum netkit_mode {
+	NETKIT_L2,
+	NETKIT_L3,
+};
+
+enum {
+	IFLA_NETKIT_UNSPEC,
+	IFLA_NETKIT_PEER_INFO,
+	IFLA_NETKIT_PRIMARY,
+	IFLA_NETKIT_POLICY,
+	IFLA_NETKIT_PEER_POLICY,
+	IFLA_NETKIT_MODE,
+	__IFLA_NETKIT_MAX,
+};
+#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
+
 /* VXLAN section */
 
 /* include statistics in the dump */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a9b2cb500bf7..0ed286b8a0f0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -35,8 +35,9 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
 #include <linux/trace_events.h>
-#include <net/netfilter/nf_bpf_link.h>
 
+#include <net/netfilter/nf_bpf_link.h>
+#include <net/netkit.h>
 #include <net/tcx.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -3730,6 +3731,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_LSM;
 	case BPF_TCX_INGRESS:
 	case BPF_TCX_EGRESS:
+	case BPF_NETKIT_PRIMARY:
+	case BPF_NETKIT_PEER:
 		return BPF_PROG_TYPE_SCHED_CLS;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
@@ -3781,7 +3784,9 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 		return 0;
 	case BPF_PROG_TYPE_SCHED_CLS:
 		if (attach_type != BPF_TCX_INGRESS &&
-		    attach_type != BPF_TCX_EGRESS)
+		    attach_type != BPF_TCX_EGRESS &&
+		    attach_type != BPF_NETKIT_PRIMARY &&
+		    attach_type != BPF_NETKIT_PEER)
 			return -EINVAL;
 		return 0;
 	default:
@@ -3864,7 +3869,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 			ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 		break;
 	case BPF_PROG_TYPE_SCHED_CLS:
-		ret = tcx_prog_attach(attr, prog);
+		if (attr->attach_type == BPF_TCX_INGRESS ||
+		    attr->attach_type == BPF_TCX_EGRESS)
+			ret = tcx_prog_attach(attr, prog);
+		else
+			ret = netkit_prog_attach(attr, prog);
 		break;
 	default:
 		ret = -EINVAL;
@@ -3925,7 +3934,11 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		ret = cgroup_bpf_prog_detach(attr, ptype);
 		break;
 	case BPF_PROG_TYPE_SCHED_CLS:
-		ret = tcx_prog_detach(attr, prog);
+		if (attr->attach_type == BPF_TCX_INGRESS ||
+		    attr->attach_type == BPF_TCX_EGRESS)
+			ret = tcx_prog_detach(attr, prog);
+		else
+			ret = netkit_prog_detach(attr, prog);
 		break;
 	default:
 		ret = -EINVAL;
@@ -3992,6 +4005,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_TCX_INGRESS:
 	case BPF_TCX_EGRESS:
 		return tcx_prog_query(attr, uattr);
+	case BPF_NETKIT_PRIMARY:
+	case BPF_NETKIT_PEER:
+		return netkit_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
@@ -4973,7 +4989,11 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = bpf_xdp_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_SCHED_CLS:
-		ret = tcx_link_attach(attr, prog);
+		if (attr->link_create.attach_type == BPF_TCX_INGRESS ||
+		    attr->link_create.attach_type == BPF_TCX_EGRESS)
+			ret = tcx_link_attach(attr, prog);
+		else
+			ret = netkit_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_NETFILTER:
 		ret = bpf_nf_link_attach(attr, prog);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7ba61b75bc0e..0f6cdf52b1da 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1052,6 +1052,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_UNIX_RECVMSG,
 	BPF_CGROUP_UNIX_GETPEERNAME,
 	BPF_CGROUP_UNIX_GETSOCKNAME,
+	BPF_NETKIT_PRIMARY,
+	BPF_NETKIT_PEER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1071,6 +1073,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
+	BPF_LINK_TYPE_NETKIT = 13,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1656,6 +1659,13 @@ union bpf_attr {
 				__u32		flags;
 				__u32		pid;
 			} uprobe_multi;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} netkit;
 		};
 	} link_create;
 
@@ -6576,6 +6586,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} tcx;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} netkit;
 	};
 } __attribute__((aligned(8)));
 
-- 
cgit v1.2.3


From 5c1b994de4be8a27afa3281be2ff58b38e8bc50c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:48:59 +0200
Subject: tools: Sync if_link uapi header

Sync if_link uapi header to the latest version as we need the refresher
in tooling for netkit device. Given it's been a while since the last sync
and the diff is fairly big, it has been done as its own commit.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-3-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/include/uapi/linux/if_link.h | 141 +++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 39e659c83cfd..a0aa05a28cf2 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -211,6 +211,9 @@ struct rtnl_link_stats {
  * @rx_nohandler: Number of packets received on the interface
  *   but dropped by the networking stack because the device is
  *   not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ *   in destination MAC address.
  */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;
@@ -243,6 +246,23 @@ struct rtnl_link_stats64 {
 	__u64	rx_compressed;
 	__u64	tx_compressed;
 	__u64	rx_nohandler;
+
+	__u64	rx_otherhost_dropped;
+};
+
+/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
+ * for struct rtnl_link_stats64.
+ */
+struct rtnl_hw_stats64 {
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -350,7 +370,13 @@ enum {
 	IFLA_GRO_MAX_SIZE,
 	IFLA_TSO_MAX_SIZE,
 	IFLA_TSO_MAX_SEGS,
+	IFLA_ALLMULTI,		/* Allmulti count: > 0 means acts ALLMULTI */
+
+	IFLA_DEVLINK_PORT,
 
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+	IFLA_DPLL_PIN,
 	__IFLA_MAX
 };
 
@@ -539,6 +565,12 @@ enum {
 	IFLA_BRPORT_MRP_IN_OPEN,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
+	IFLA_BRPORT_LOCKED,
+	IFLA_BRPORT_MAB,
+	IFLA_BRPORT_MCAST_N_GROUPS,
+	IFLA_BRPORT_MCAST_MAX_GROUPS,
+	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -716,7 +748,79 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
+/* Tunnel RTM header */
+struct tunnel_msg {
+	__u8 family;
+	__u8 flags;
+	__u16 reserved2;
+	__u32 ifindex;
+};
+
+/* netkit section */
+enum netkit_action {
+	NETKIT_NEXT	= -1,
+	NETKIT_PASS	= 0,
+	NETKIT_DROP	= 2,
+	NETKIT_REDIRECT	= 7,
+};
+
+enum netkit_mode {
+	NETKIT_L2,
+	NETKIT_L3,
+};
+
+enum {
+	IFLA_NETKIT_UNSPEC,
+	IFLA_NETKIT_PEER_INFO,
+	IFLA_NETKIT_PRIMARY,
+	IFLA_NETKIT_POLICY,
+	IFLA_NETKIT_PEER_POLICY,
+	IFLA_NETKIT_MODE,
+	__IFLA_NETKIT_MAX,
+};
+#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
+
 /* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS	0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+	VNIFILTER_ENTRY_STATS_UNSPEC,
+	VNIFILTER_ENTRY_STATS_RX_BYTES,
+	VNIFILTER_ENTRY_STATS_RX_PKTS,
+	VNIFILTER_ENTRY_STATS_RX_DROPS,
+	VNIFILTER_ENTRY_STATS_RX_ERRORS,
+	VNIFILTER_ENTRY_STATS_TX_BYTES,
+	VNIFILTER_ENTRY_STATS_TX_PKTS,
+	VNIFILTER_ENTRY_STATS_TX_DROPS,
+	VNIFILTER_ENTRY_STATS_TX_ERRORS,
+	VNIFILTER_ENTRY_STATS_PAD,
+	__VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_ENTRY_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY_START,
+	VXLAN_VNIFILTER_ENTRY_END,
+	VXLAN_VNIFILTER_ENTRY_GROUP,
+	VXLAN_VNIFILTER_ENTRY_GROUP6,
+	VXLAN_VNIFILTER_ENTRY_STATS,
+	__VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY,
+	__VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
+
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -748,6 +852,8 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
+	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
+	IFLA_VXLAN_LOCALBYPASS,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -781,6 +887,7 @@ enum {
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
+	IFLA_GENEVE_INNER_PROTO_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -826,6 +933,8 @@ enum {
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
 	IFLA_GTP_ROLE,
+	IFLA_GTP_CREATE_SOCKETS,
+	IFLA_GTP_RESTART_COUNT,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1162,6 +1271,17 @@ enum {
 
 #define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
 
+enum {
+	IFLA_STATS_GETSET_UNSPEC,
+	IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
+				 * a filter mask for the corresponding group.
+				 */
+	IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
+	__IFLA_STATS_GETSET_MAX,
+};
+
+#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
+
 /* These are embedded into IFLA_STATS_LINK_XSTATS:
  * [IFLA_STATS_LINK_XSTATS]
  * -> [LINK_XSTATS_TYPE_xxx]
@@ -1179,10 +1299,21 @@ enum {
 enum {
 	IFLA_OFFLOAD_XSTATS_UNSPEC,
 	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO,	/* HW stats info. A nest */
+	IFLA_OFFLOAD_XSTATS_L3_STATS,	/* struct rtnl_hw_stats64 */
 	__IFLA_OFFLOAD_XSTATS_MAX
 };
 #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
 
+enum {
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST,		/* u8 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED,		/* u8 */
+	__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
+};
+#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
+	(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
+
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
@@ -1281,4 +1412,14 @@ enum {
 
 #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
 
+/* DSA section */
+
+enum {
+	IFLA_DSA_UNSPEC,
+	IFLA_DSA_MASTER,
+	__IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
-- 
cgit v1.2.3


From 05c31b4ab20527c4d1695130aaecc54ef59a0e54 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:49:00 +0200
Subject: libbpf: Add link-based API for netkit

This adds bpf_program__attach_netkit() API to libbpf. Overall it is very
similar to tcx. The API looks as following:

  LIBBPF_API struct bpf_link *
  bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
                             const struct bpf_netkit_opts *opts);

The struct bpf_netkit_opts is done in similar way as struct bpf_tcx_opts
for supporting bpf_mprog control parameters. The attach location for the
primary and peer device is derived from the program section "netkit/primary"
and "netkit/peer", respectively.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-4-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/lib/bpf/bpf.c      | 16 ++++++++++++++++
 tools/lib/bpf/bpf.h      |  5 +++++
 tools/lib/bpf/libbpf.c   | 39 +++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h   | 15 +++++++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 5 files changed, 76 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index b0f1913763a3..9dc9625651dc 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -810,6 +810,22 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tcx))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_NETKIT_PRIMARY:
+	case BPF_NETKIT_PEER:
+		relative_fd = OPTS_GET(opts, netkit.relative_fd, 0);
+		relative_id = OPTS_GET(opts, netkit.relative_id, 0);
+		if (relative_fd && relative_id)
+			return libbpf_err(-EINVAL);
+		if (relative_id) {
+			attr.link_create.netkit.relative_id = relative_id;
+			attr.link_create.flags |= BPF_F_ID;
+		} else {
+			attr.link_create.netkit.relative_fd = relative_fd;
+		}
+		attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0);
+		if (!OPTS_ZEROED(opts, netkit))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 74c2887cfd24..d0f53772bdc0 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -415,6 +415,11 @@ struct bpf_link_create_opts {
 			__u32 relative_id;
 			__u64 expected_revision;
 		} tcx;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} netkit;
 	};
 	size_t :0;
 };
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a295f6acf98f..e067be95da3c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -126,6 +126,8 @@ static const char * const attach_type_name[] = {
 	[BPF_TCX_INGRESS]		= "tcx_ingress",
 	[BPF_TCX_EGRESS]		= "tcx_egress",
 	[BPF_TRACE_UPROBE_MULTI]	= "trace_uprobe_multi",
+	[BPF_NETKIT_PRIMARY]		= "netkit_primary",
+	[BPF_NETKIT_PEER]		= "netkit_peer",
 };
 
 static const char * const link_type_name[] = {
@@ -142,6 +144,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_NETFILTER]		= "netfilter",
 	[BPF_LINK_TYPE_TCX]			= "tcx",
 	[BPF_LINK_TYPE_UPROBE_MULTI]		= "uprobe_multi",
+	[BPF_LINK_TYPE_NETKIT]			= "netkit",
 };
 
 static const char * const map_type_name[] = {
@@ -8915,6 +8918,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
 	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */
 	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */
+	SEC_DEF("netkit/primary",	SCHED_CLS, BPF_NETKIT_PRIMARY, SEC_NONE),
+	SEC_DEF("netkit/peer",		SCHED_CLS, BPF_NETKIT_PEER, SEC_NONE),
 	SEC_DEF("tracepoint+",		TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("tp+",			TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("raw_tracepoint+",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
@@ -12126,6 +12131,40 @@ bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
 	return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts);
 }
 
+struct bpf_link *
+bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
+			   const struct bpf_netkit_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+	__u32 relative_id;
+	int relative_fd;
+
+	if (!OPTS_VALID(opts, bpf_netkit_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.netkit.expected_revision = OPTS_GET(opts, expected_revision, 0);
+	link_create_opts.netkit.relative_fd = relative_fd;
+	link_create_opts.netkit.relative_id = relative_id;
+	link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+	return bpf_program_attach_fd(prog, ifindex, "netkit", &link_create_opts);
+}
+
 struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 					      int target_fd,
 					      const char *attach_func_name)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 475378438545..6cd9c501624f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -800,6 +800,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
 			const struct bpf_tcx_opts *opts);
 
+struct bpf_netkit_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_netkit_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
+			   const struct bpf_netkit_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index cc973b678a39..b52dc28dc8af 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -398,6 +398,7 @@ LIBBPF_1.3.0 {
 		bpf_object__unpin;
 		bpf_prog_detach_opts;
 		bpf_program__attach_netfilter;
+		bpf_program__attach_netkit;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
 		ring__avail_data_size;
-- 
cgit v1.2.3


From 92a85e18ad4705c66ace55a19f4f8301ef0eb59f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:49:01 +0200
Subject: bpftool: Implement link show support for netkit

Add support to dump netkit link information to bpftool in similar way as
we have for XDP. The netkit link info only exposes the ifindex and the
attach_type.

Below shows an example link dump output, and a cgroup link is included for
comparison, too:

  # bpftool link
  [...]
  10: cgroup  prog 2466
        cgroup_id 1  attach_type cgroup_inet6_post_bind
  [...]
  8: netkit  prog 35
        ifindex nk1(18)  attach_type netkit_primary
  [...]

Equivalent json output:

  # bpftool link --json
  [...]
  {
    "id": 10,
    "type": "cgroup",
    "prog_id": 2466,
    "cgroup_id": 1,
    "attach_type": "cgroup_inet6_post_bind"
  },
  [...]
  {
    "id": 12,
    "type": "netkit",
    "prog_id": 61,
    "devname": "nk1",
    "ifindex": 21,
    "attach_type": "netkit_primary"
  }
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-5-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/link.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 4b1407b05056..a1528cde81ab 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -451,6 +451,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		show_link_ifindex_json(info->tcx.ifindex, json_wtr);
 		show_link_attach_type_json(info->tcx.attach_type, json_wtr);
 		break;
+	case BPF_LINK_TYPE_NETKIT:
+		show_link_ifindex_json(info->netkit.ifindex, json_wtr);
+		show_link_attach_type_json(info->netkit.attach_type, json_wtr);
+		break;
 	case BPF_LINK_TYPE_XDP:
 		show_link_ifindex_json(info->xdp.ifindex, json_wtr);
 		break;
@@ -791,6 +795,11 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		show_link_ifindex_plain(info->tcx.ifindex);
 		show_link_attach_type_plain(info->tcx.attach_type);
 		break;
+	case BPF_LINK_TYPE_NETKIT:
+		printf("\n\t");
+		show_link_ifindex_plain(info->netkit.ifindex);
+		show_link_attach_type_plain(info->netkit.attach_type);
+		break;
 	case BPF_LINK_TYPE_XDP:
 		printf("\n\t");
 		show_link_ifindex_plain(info->xdp.ifindex);
-- 
cgit v1.2.3


From bec981a4add6dd6a63065e54e2b2e67c2af6c3fa Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:49:02 +0200
Subject: bpftool: Extend net dump with netkit progs

Add support to dump BPF programs on netkit via bpftool. This includes both
the BPF link and attach ops programs. Dumped information contain the attach
location, function entry name, program ID and link ID when applicable.

Example with tc BPF link:

  # ./bpftool net
  xdp:

  tc:
  nk1(22) netkit/peer tc1 prog_id 43 link_id 12

  [...]

Example with json dump:

  # ./bpftool net --json | jq
  [
    {
      "xdp": [],
      "tc": [
        {
          "devname": "nk1",
          "ifindex": 18,
          "kind": "netkit/primary",
          "name": "tc1",
          "prog_id": 29,
          "prog_flags": [],
          "link_id": 8,
          "link_flags": []
        }
      ],
      "flow_dissector": [],
      "netfilter": []
    }
  ]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-6-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-net.rst | 8 ++++----
 tools/bpf/bpftool/net.c                         | 7 ++++++-
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 5e2abd3de5ab..dd3f9469765b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -37,7 +37,7 @@ DESCRIPTION
 	**bpftool net { show | list }** [ **dev** *NAME* ]
 		  List bpf program attachments in the kernel networking subsystem.
 
-		  Currently, device driver xdp attachments, tcx and old-style tc
+		  Currently, device driver xdp attachments, tcx, netkit and old-style tc
 		  classifier/action attachments, flow_dissector as well as netfilter
 		  attachments are implemented, i.e., for
 		  program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**,
@@ -52,11 +52,11 @@ DESCRIPTION
 		  bpf programs, users should consult other tools, e.g., iproute2.
 
 		  The current output will start with all xdp program attachments, followed by
-		  all tcx, then tc class/qdisc bpf program attachments, then flow_dissector
-		  and finally netfilter programs. Both xdp programs and tcx/tc programs are
+		  all tcx, netkit, then tc class/qdisc bpf program attachments, then flow_dissector
+		  and finally netfilter programs. Both xdp programs and tcx/netkit/tc programs are
 		  ordered based on ifindex number. If multiple bpf programs attached
 		  to the same networking device through **tc**, the order will be first
-		  all bpf programs attached to tcx, then tc classes, then all bpf programs
+		  all bpf programs attached to tcx, netkit, then tc classes, then all bpf programs
 		  attached to non clsact qdiscs, and finally all bpf programs attached
 		  to root and clsact qdisc.
 
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 66a8ce8ae012..968714b4c3d4 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -79,6 +79,8 @@ static const char * const attach_type_strings[] = {
 static const char * const attach_loc_strings[] = {
 	[BPF_TCX_INGRESS]		= "tcx/ingress",
 	[BPF_TCX_EGRESS]		= "tcx/egress",
+	[BPF_NETKIT_PRIMARY]		= "netkit/primary",
+	[BPF_NETKIT_PEER]		= "netkit/peer",
 };
 
 const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings);
@@ -506,6 +508,9 @@ 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);
+
+	__show_dev_tc_bpf(dev, BPF_NETKIT_PRIMARY);
+	__show_dev_tc_bpf(dev, BPF_NETKIT_PEER);
 }
 
 static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid,
@@ -926,7 +931,7 @@ static int do_help(int argc, char **argv)
 		"       ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n"
 		"       " HELP_SPEC_OPTIONS " }\n"
 		"\n"
-		"Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n"
+		"Note: Only xdp, tcx, tc, netkit, 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"
-- 
cgit v1.2.3


From 51f1892b5289f0c09745d3bedb36493555d6d90c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:49:03 +0200
Subject: selftests/bpf: Add netlink helper library

Add a minimal netlink helper library for the BPF selftests. This has been
taken and cut down and cleaned up from iproute2. This covers basics such
as netdevice creation which we need for BPF selftests / BPF CI given
iproute2 package cannot cover it yet.

Stanislav Fomichev suggested that this could be replaced in future by ynl
tool generated C code once it has RTNL support to create devices. Once we
get to this point the BPF CI would also need to add libmnl. If no further
extensions are needed, a second option could be that we remove this code
again once iproute2 package has support.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-7-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/Makefile          |  19 +-
 tools/testing/selftests/bpf/netlink_helpers.c | 358 ++++++++++++++++++++++++++
 tools/testing/selftests/bpf/netlink_helpers.h |  46 ++++
 3 files changed, 418 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/netlink_helpers.c
 create mode 100644 tools/testing/selftests/bpf/netlink_helpers.h

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4225f975fce3..9c27b67bc7b1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -585,11 +585,20 @@ endef
 # Define test_progs test runner.
 TRUNNER_TESTS_DIR := prog_tests
 TRUNNER_BPF_PROGS_DIR := progs
-TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
-			 network_helpers.c testing_helpers.c		\
-			 btf_helpers.c flow_dissector_load.h		\
-			 cap_helpers.c test_loader.c xsk.c disasm.c	\
-			 json_writer.c unpriv_helpers.c 		\
+TRUNNER_EXTRA_SOURCES := test_progs.c		\
+			 cgroup_helpers.c	\
+			 trace_helpers.c	\
+			 network_helpers.c	\
+			 testing_helpers.c	\
+			 btf_helpers.c		\
+			 cap_helpers.c		\
+			 unpriv_helpers.c 	\
+			 netlink_helpers.c	\
+			 test_loader.c		\
+			 xsk.c			\
+			 disasm.c		\
+			 json_writer.c 		\
+			 flow_dissector_load.h	\
 			 ip_check_defrag_frags.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
 		       $(OUTPUT)/liburandom_read.so			\
diff --git a/tools/testing/selftests/bpf/netlink_helpers.c b/tools/testing/selftests/bpf/netlink_helpers.c
new file mode 100644
index 000000000000..caf36eb1d032
--- /dev/null
+++ b/tools/testing/selftests/bpf/netlink_helpers.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Taken & modified from iproute2's libnetlink.c
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/socket.h>
+
+#include "netlink_helpers.h"
+
+static int rcvbuf = 1024 * 1024;
+
+void rtnl_close(struct rtnl_handle *rth)
+{
+	if (rth->fd >= 0) {
+		close(rth->fd);
+		rth->fd = -1;
+	}
+}
+
+int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions,
+		      int protocol)
+{
+	socklen_t addr_len;
+	int sndbuf = 32768;
+	int one = 1;
+
+	memset(rth, 0, sizeof(*rth));
+	rth->proto = protocol;
+	rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol);
+	if (rth->fd < 0) {
+		perror("Cannot open netlink socket");
+		return -1;
+	}
+	if (setsockopt(rth->fd, SOL_SOCKET, SO_SNDBUF,
+		       &sndbuf, sizeof(sndbuf)) < 0) {
+		perror("SO_SNDBUF");
+		goto err;
+	}
+	if (setsockopt(rth->fd, SOL_SOCKET, SO_RCVBUF,
+		       &rcvbuf, sizeof(rcvbuf)) < 0) {
+		perror("SO_RCVBUF");
+		goto err;
+	}
+
+	/* Older kernels may no support extended ACK reporting */
+	setsockopt(rth->fd, SOL_NETLINK, NETLINK_EXT_ACK,
+		   &one, sizeof(one));
+
+	memset(&rth->local, 0, sizeof(rth->local));
+	rth->local.nl_family = AF_NETLINK;
+	rth->local.nl_groups = subscriptions;
+
+	if (bind(rth->fd, (struct sockaddr *)&rth->local,
+		 sizeof(rth->local)) < 0) {
+		perror("Cannot bind netlink socket");
+		goto err;
+	}
+	addr_len = sizeof(rth->local);
+	if (getsockname(rth->fd, (struct sockaddr *)&rth->local,
+			&addr_len) < 0) {
+		perror("Cannot getsockname");
+		goto err;
+	}
+	if (addr_len != sizeof(rth->local)) {
+		fprintf(stderr, "Wrong address length %d\n", addr_len);
+		goto err;
+	}
+	if (rth->local.nl_family != AF_NETLINK) {
+		fprintf(stderr, "Wrong address family %d\n",
+			rth->local.nl_family);
+		goto err;
+	}
+	rth->seq = time(NULL);
+	return 0;
+err:
+	rtnl_close(rth);
+	return -1;
+}
+
+int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
+{
+	return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE);
+}
+
+static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(fd, msg, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+	if (len < 0) {
+		fprintf(stderr, "netlink receive error %s (%d)\n",
+			strerror(errno), errno);
+		return -errno;
+	}
+	if (len == 0) {
+		fprintf(stderr, "EOF on netlink\n");
+		return -ENODATA;
+	}
+	return len;
+}
+
+static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer)
+{
+	struct iovec *iov = msg->msg_iov;
+	char *buf;
+	int len;
+
+	iov->iov_base = NULL;
+	iov->iov_len = 0;
+
+	len = __rtnl_recvmsg(fd, msg, MSG_PEEK | MSG_TRUNC);
+	if (len < 0)
+		return len;
+	if (len < 32768)
+		len = 32768;
+	buf = malloc(len);
+	if (!buf) {
+		fprintf(stderr, "malloc error: not enough buffer\n");
+		return -ENOMEM;
+	}
+	iov->iov_base = buf;
+	iov->iov_len = len;
+	len = __rtnl_recvmsg(fd, msg, 0);
+	if (len < 0) {
+		free(buf);
+		return len;
+	}
+	if (answer)
+		*answer = buf;
+	else
+		free(buf);
+	return len;
+}
+
+static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err,
+			    nl_ext_ack_fn_t errfn)
+{
+	fprintf(stderr, "RTNETLINK answers: %s\n",
+		strerror(-err->error));
+}
+
+static int __rtnl_talk_iov(struct rtnl_handle *rtnl, struct iovec *iov,
+			   size_t iovlen, struct nlmsghdr **answer,
+			   bool show_rtnl_err, nl_ext_ack_fn_t errfn)
+{
+	struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+	struct iovec riov;
+	struct msghdr msg = {
+		.msg_name	= &nladdr,
+		.msg_namelen	= sizeof(nladdr),
+		.msg_iov	= iov,
+		.msg_iovlen	= iovlen,
+	};
+	unsigned int seq = 0;
+	struct nlmsghdr *h;
+	int i, status;
+	char *buf;
+
+	for (i = 0; i < iovlen; i++) {
+		h = iov[i].iov_base;
+		h->nlmsg_seq = seq = ++rtnl->seq;
+		if (answer == NULL)
+			h->nlmsg_flags |= NLM_F_ACK;
+	}
+	status = sendmsg(rtnl->fd, &msg, 0);
+	if (status < 0) {
+		perror("Cannot talk to rtnetlink");
+		return -1;
+	}
+	/* change msg to use the response iov */
+	msg.msg_iov = &riov;
+	msg.msg_iovlen = 1;
+	i = 0;
+	while (1) {
+next:
+		status = rtnl_recvmsg(rtnl->fd, &msg, &buf);
+		++i;
+		if (status < 0)
+			return status;
+		if (msg.msg_namelen != sizeof(nladdr)) {
+			fprintf(stderr,
+				"Sender address length == %d!\n",
+				msg.msg_namelen);
+			exit(1);
+		}
+		for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) {
+			int len = h->nlmsg_len;
+			int l = len - sizeof(*h);
+
+			if (l < 0 || len > status) {
+				if (msg.msg_flags & MSG_TRUNC) {
+					fprintf(stderr, "Truncated message!\n");
+					free(buf);
+					return -1;
+				}
+				fprintf(stderr,
+					"Malformed message: len=%d!\n",
+					len);
+				exit(1);
+			}
+			if (nladdr.nl_pid != 0 ||
+			    h->nlmsg_pid != rtnl->local.nl_pid ||
+			    h->nlmsg_seq > seq || h->nlmsg_seq < seq - iovlen) {
+				/* Don't forget to skip that message. */
+				status -= NLMSG_ALIGN(len);
+				h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
+				continue;
+			}
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h);
+				int error = err->error;
+
+				if (l < sizeof(struct nlmsgerr)) {
+					fprintf(stderr, "ERROR truncated\n");
+					free(buf);
+					return -1;
+				}
+				if (error) {
+					errno = -error;
+					if (rtnl->proto != NETLINK_SOCK_DIAG &&
+					    show_rtnl_err)
+						rtnl_talk_error(h, err, errfn);
+				}
+				if (i < iovlen) {
+					free(buf);
+					goto next;
+				}
+				if (error) {
+					free(buf);
+					return -i;
+				}
+				if (answer)
+					*answer = (struct nlmsghdr *)buf;
+				else
+					free(buf);
+				return 0;
+			}
+			if (answer) {
+				*answer = (struct nlmsghdr *)buf;
+				return 0;
+			}
+			fprintf(stderr, "Unexpected reply!\n");
+			status -= NLMSG_ALIGN(len);
+			h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
+		}
+		free(buf);
+		if (msg.msg_flags & MSG_TRUNC) {
+			fprintf(stderr, "Message truncated!\n");
+			continue;
+		}
+		if (status) {
+			fprintf(stderr, "Remnant of size %d!\n", status);
+			exit(1);
+		}
+	}
+}
+
+static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+		       struct nlmsghdr **answer, bool show_rtnl_err,
+		       nl_ext_ack_fn_t errfn)
+{
+	struct iovec iov = {
+		.iov_base	= n,
+		.iov_len	= n->nlmsg_len,
+	};
+
+	return __rtnl_talk_iov(rtnl, &iov, 1, answer, show_rtnl_err, errfn);
+}
+
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+	      struct nlmsghdr **answer)
+{
+	return __rtnl_talk(rtnl, n, answer, true, NULL);
+}
+
+int addattr(struct nlmsghdr *n, int maxlen, int type)
+{
+	return addattr_l(n, maxlen, type, NULL, 0);
+}
+
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u8));
+}
+
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u16));
+}
+
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u32));
+}
+
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u64));
+}
+
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str)
+{
+	return addattr_l(n, maxlen, type, str, strlen(str)+1);
+}
+
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data,
+	      int alen)
+{
+	int len = RTA_LENGTH(alen);
+	struct rtattr *rta;
+
+	if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) {
+		fprintf(stderr, "%s: Message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -1;
+	}
+	rta = NLMSG_TAIL(n);
+	rta->rta_type = type;
+	rta->rta_len = len;
+	if (alen)
+		memcpy(RTA_DATA(rta), data, alen);
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+	return 0;
+}
+
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len)
+{
+	if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) {
+		fprintf(stderr, "%s: Message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -1;
+	}
+
+	memcpy(NLMSG_TAIL(n), data, len);
+	memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len);
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len);
+	return 0;
+}
+
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type)
+{
+	struct rtattr *nest = NLMSG_TAIL(n);
+
+	addattr_l(n, maxlen, type, NULL, 0);
+	return nest;
+}
+
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest)
+{
+	nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest;
+	return n->nlmsg_len;
+}
diff --git a/tools/testing/selftests/bpf/netlink_helpers.h b/tools/testing/selftests/bpf/netlink_helpers.h
new file mode 100644
index 000000000000..68116818a47e
--- /dev/null
+++ b/tools/testing/selftests/bpf/netlink_helpers.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef NETLINK_HELPERS_H
+#define NETLINK_HELPERS_H
+
+#include <string.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+struct rtnl_handle {
+	int			fd;
+	struct sockaddr_nl	local;
+	struct sockaddr_nl	peer;
+	__u32			seq;
+	__u32			dump;
+	int			proto;
+	FILE			*dump_fp;
+#define RTNL_HANDLE_F_LISTEN_ALL_NSID		0x01
+#define RTNL_HANDLE_F_SUPPRESS_NLERR		0x02
+#define RTNL_HANDLE_F_STRICT_CHK		0x04
+	int			flags;
+};
+
+#define NLMSG_TAIL(nmsg) \
+	((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len)))
+
+typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
+			       const struct nlmsghdr *inner_nlh);
+
+int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
+	      __attribute__((warn_unused_result));
+void rtnl_close(struct rtnl_handle *rth);
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+	      struct nlmsghdr **answer)
+	      __attribute__((warn_unused_result));
+
+int addattr(struct nlmsghdr *n, int maxlen, int type);
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data);
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data);
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data);
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data);
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen);
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
+#endif /* NETLINK_HELPERS_H */
-- 
cgit v1.2.3


From ace15f91e569172dac71ae0aeb3a2e76d1ce1b17 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 24 Oct 2023 23:49:04 +0200
Subject: selftests/bpf: Add selftests for netkit

Add a bigger batch of test coverage to assert correct operation of
netkit devices and their BPF program management:

  # ./test_progs -t tc_netkit
  [...]
  [    1.166267] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.166831] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  [    1.270957] tsc: Refined TSC clocksource calibration: 3407.988 MHz
  [    1.272579] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fc932722, max_idle_ns: 440795381586 ns
  [    1.275336] clocksource: Switched to clocksource tsc
  #257     tc_netkit_basic:OK
  #258     tc_netkit_device:OK
  #259     tc_netkit_multi_links:OK
  #260     tc_netkit_multi_opts:OK
  #261     tc_netkit_neigh_links:OK
  Summary: 5/0 PASSED, 0 SKIPPED, 0 FAILED
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20231024214904.29825-8-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/config                 |   1 +
 .../testing/selftests/bpf/prog_tests/tc_helpers.h  |   4 +
 tools/testing/selftests/bpf/prog_tests/tc_netkit.c | 687 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_tc_link.c   |  13 +
 4 files changed, 705 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_netkit.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 02dd4409200e..3ec5927ec3e5 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -71,6 +71,7 @@ CONFIG_NETFILTER_SYNPROXY=y
 CONFIG_NETFILTER_XT_CONNMARK=y
 CONFIG_NETFILTER_XT_MATCH_STATE=y
 CONFIG_NETFILTER_XT_TARGET_CT=y
+CONFIG_NETKIT=y
 CONFIG_NF_CONNTRACK=y
 CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_DEFRAG_IPV4=y
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
index 67f985f7d215..924d0e25320c 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
@@ -4,6 +4,10 @@
 #define TC_HELPERS
 #include <test_progs.h>
 
+#ifndef loopback
+# define loopback 1
+#endif
+
 static inline __u32 id_from_prog_fd(int fd)
 {
 	struct bpf_prog_info prog_info = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
new file mode 100644
index 000000000000..15ee7b2fc410
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -0,0 +1,687 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define netkit_peer "nk0"
+#define netkit_name "nk1"
+
+#define ping_addr_neigh		0x0a000002 /* 10.0.0.2 */
+#define ping_addr_noneigh	0x0a000003 /* 10.0.0.3 */
+
+#include "test_tc_link.skel.h"
+#include "netlink_helpers.h"
+#include "tc_helpers.h"
+
+#define ICMP_ECHO 8
+
+struct icmphdr {
+	__u8		type;
+	__u8		code;
+	__sum16		checksum;
+	struct {
+		__be16	id;
+		__be16	sequence;
+	} echo;
+};
+
+struct iplink_req {
+	struct nlmsghdr  n;
+	struct ifinfomsg i;
+	char             buf[1024];
+};
+
+static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
+			 bool same_netns)
+{
+	struct rtnl_handle rth = { .fd = -1 };
+	struct iplink_req req = {};
+	struct rtattr *linkinfo, *data;
+	const char *type = "netkit";
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+	req.i.ifi_family = AF_UNSPEC;
+
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, netkit_name,
+		  strlen(netkit_name));
+	linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+	addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
+	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	addattr_nest_end(&req.n, data);
+	addattr_nest_end(&req.n, linkinfo);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	*ifindex = if_nametoindex(netkit_name);
+
+	ASSERT_GT(*ifindex, 0, "retrieve_ifindex");
+	ASSERT_OK(system("ip netns add foo"), "create netns");
+	ASSERT_OK(system("ip link set dev " netkit_name " up"),
+			 "up primary");
+	ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"),
+			 "addr primary");
+	if (same_netns) {
+		ASSERT_OK(system("ip link set dev " netkit_peer " up"),
+				 "up peer");
+		ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"),
+				 "addr peer");
+	} else {
+		ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
+				 "move peer");
+		ASSERT_OK(system("ip netns exec foo ip link set dev "
+				 netkit_peer " up"), "up peer");
+		ASSERT_OK(system("ip netns exec foo ip addr add dev "
+				 netkit_peer " 10.0.0.2/24"), "addr peer");
+	}
+	return err;
+}
+
+static void destroy_netkit(void)
+{
+	ASSERT_OK(system("ip link del dev " netkit_name), "del primary");
+	ASSERT_OK(system("ip netns del foo"), "delete netns");
+	ASSERT_EQ(if_nametoindex(netkit_name), 0, netkit_name "_ifindex");
+}
+
+static int __send_icmp(__u32 dest)
+{
+	struct sockaddr_in addr;
+	struct icmphdr icmp;
+	int sock, ret;
+
+	ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0");
+	if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)"))
+		return ret;
+
+	sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP);
+	if (!ASSERT_GE(sock, 0, "icmp_socket"))
+		return -errno;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+			 netkit_name, strlen(netkit_name) + 1);
+	if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)"))
+		goto out;
+
+	memset(&addr, 0, sizeof(addr));
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(dest);
+
+	memset(&icmp, 0, sizeof(icmp));
+	icmp.type = ICMP_ECHO;
+	icmp.echo.id = 1234;
+	icmp.echo.sequence = 1;
+
+	ret = sendto(sock, &icmp, sizeof(icmp), 0,
+		     (struct sockaddr *)&addr, sizeof(addr));
+	if (!ASSERT_GE(ret, 0, "icmp_sendto"))
+		ret = -errno;
+	else
+		ret = 0;
+out:
+	close(sock);
+	return ret;
+}
+
+static int send_icmp(void)
+{
+	return __send_icmp(ping_addr_neigh);
+}
+
+void serial_test_tc_netkit_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  BPF_NETKIT_PEER), 0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PEER, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+static void serial_test_tc_netkit_multi_links_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[3], link_ids[3];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  target), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  target), 0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_multi_links(void)
+{
+	serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PEER);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PEER);
+}
+
+static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 pid1, pid2, fd1, fd2;
+	__u32 prog_ids[3];
+	struct test_tc_link *skel;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false);
+	if (err)
+		return;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	pid1 = id_from_prog_fd(fd1);
+	pid2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd1, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_fd1;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd2, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_fd1;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_fd2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+cleanup_fd2:
+	err = bpf_prog_detach_opts(fd2, ifindex, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count_ifindex(ifindex, target, 1);
+cleanup_fd1:
+	err = bpf_prog_detach_opts(fd1, ifindex, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count_ifindex(ifindex, target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_multi_opts(void)
+{
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PEER);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PEER);
+}
+
+void serial_test_tc_netkit_device(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex, ifindex2;
+
+	err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, true);
+	if (err)
+		return;
+
+	ifindex2 = if_nametoindex(netkit_peer);
+	ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  BPF_NETKIT_PEER), 0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3,
+		  BPF_NETKIT_PRIMARY), 0, "tc3_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PRIMARY, &optq);
+	ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
+
+	err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PEER, &optq);
+	ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex2, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	link = bpf_program__attach_netkit(skel->progs.tc3, ifindex2, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, false);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(__send_icmp(ping_addr_noneigh), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true /* L2: ARP */, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, mode == NETKIT_L3, "seen_eth");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_neigh_links(void)
+{
+	serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index 30e7124c49a1..992400acb957 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -1,7 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2023 Isovalent */
 #include <stdbool.h>
+
 #include <linux/bpf.h>
+#include <linux/if_ether.h>
+
+#include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
 
 char LICENSE[] SEC("license") = "GPL";
@@ -12,10 +16,19 @@ bool seen_tc3;
 bool seen_tc4;
 bool seen_tc5;
 bool seen_tc6;
+bool seen_eth;
 
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
 {
+	struct ethhdr eth = {};
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		goto out;
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
+		goto out;
+	seen_eth = eth.h_proto == bpf_htons(ETH_P_IP);
+out:
 	seen_tc1 = true;
 	return TCX_NEXT;
 }
-- 
cgit v1.2.3


From 399f6185a1c02f39bcadb8749bc2d9d48685816f Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 25 Oct 2023 03:11:44 +0000
Subject: selftests/bpf: Fix selftests broken by mitigations=off

When we configure the kernel command line with 'mitigations=off' and set
the sysctl knob 'kernel.unprivileged_bpf_disabled' to 0, the commit
bc5bc309db45 ("bpf: Inherit system settings for CPU security mitigations")
causes issues in the execution of `test_progs -t verifier`. This is
because 'mitigations=off' bypasses Spectre v1 and Spectre v4 protections.

Currently, when a program requests to run in unprivileged mode
(kernel.unprivileged_bpf_disabled = 0), the BPF verifier may prevent
it from running due to the following conditions not being enabled:

  - bypass_spec_v1
  - bypass_spec_v4
  - allow_ptr_leaks
  - allow_uninit_stack

While 'mitigations=off' enables the first two conditions, it does not
enable the latter two. As a result, some test cases in
'test_progs -t verifier' that were expected to fail to run may run
successfully, while others still fail but with different error messages.
This makes it challenging to address them comprehensively.

Moreover, in the future, we may introduce more fine-grained control over
CPU mitigations, such as enabling only bypass_spec_v1 or bypass_spec_v4.

Given the complexity of the situation, rather than fixing each broken test
case individually, it's preferable to skip them when 'mitigations=off' is
in effect and introduce specific test cases for the new 'mitigations=off'
scenario. For instance, we can introduce new BTF declaration tags like
'__failure__nospec', '__failure_nospecv1' and '__failure_nospecv4'.

In this patch, the approach is to simply skip the broken test cases when
'mitigations=off' is enabled. The result of `test_progs -t verifier` as
follows after this commit,

Before this commit
==================

- without 'mitigations=off'
  - kernel.unprivileged_bpf_disabled = 2
    Summary: 74/948 PASSED, 388 SKIPPED, 0 FAILED
  - kernel.unprivileged_bpf_disabled = 0
    Summary: 74/1336 PASSED, 0 SKIPPED, 0 FAILED    <<<<
- with 'mitigations=off'
  - kernel.unprivileged_bpf_disabled = 2
    Summary: 74/948 PASSED, 388 SKIPPED, 0 FAILED
  - kernel.unprivileged_bpf_disabled = 0
    Summary: 63/1276 PASSED, 0 SKIPPED, 11 FAILED   <<<< 11 FAILED

After this commit
=================

- without 'mitigations=off'
  - kernel.unprivileged_bpf_disabled = 2
    Summary: 74/948 PASSED, 388 SKIPPED, 0 FAILED
  - kernel.unprivileged_bpf_disabled = 0
    Summary: 74/1336 PASSED, 0 SKIPPED, 0 FAILED    <<<<
- with this patch, with 'mitigations=off'
  - kernel.unprivileged_bpf_disabled = 2
    Summary: 74/948 PASSED, 388 SKIPPED, 0 FAILED
  - kernel.unprivileged_bpf_disabled = 0
    Summary: 74/948 PASSED, 388 SKIPPED, 0 FAILED   <<<< SKIPPED

Fixes: bc5bc309db45 ("bpf: Inherit system settings for CPU security mitigations")
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Closes: https://lore.kernel.org/bpf/CAADnVQKUBJqg+hHtbLeeC2jhoJAWqnmRAzXW3hmUCNSV9kx4sQ@mail.gmail.com
Link: https://lore.kernel.org/bpf/20231025031144.5508-1-laoar.shao@gmail.com
---
 tools/testing/selftests/bpf/unpriv_helpers.c | 33 +++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c
index 2a6efbd0401e..b6d016461fb0 100644
--- a/tools/testing/selftests/bpf/unpriv_helpers.c
+++ b/tools/testing/selftests/bpf/unpriv_helpers.c
@@ -4,9 +4,40 @@
 #include <stdlib.h>
 #include <error.h>
 #include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
 
 #include "unpriv_helpers.h"
 
+static bool get_mitigations_off(void)
+{
+	char cmdline[4096], *c;
+	int fd, ret = false;
+
+	fd = open("/proc/cmdline", O_RDONLY);
+	if (fd < 0) {
+		perror("open /proc/cmdline");
+		return false;
+	}
+
+	if (read(fd, cmdline, sizeof(cmdline) - 1) < 0) {
+		perror("read /proc/cmdline");
+		goto out;
+	}
+
+	cmdline[sizeof(cmdline) - 1] = '\0';
+	for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) {
+		if (strncmp(c, "mitigations=off", strlen(c)))
+			continue;
+		ret = true;
+		break;
+	}
+out:
+	close(fd);
+	return ret;
+}
+
 bool get_unpriv_disabled(void)
 {
 	bool disabled;
@@ -22,5 +53,5 @@ bool get_unpriv_disabled(void)
 		disabled = true;
 	}
 
-	return disabled;
+	return disabled ? true : get_mitigations_off();
 }
-- 
cgit v1.2.3


From ea23fbd2a8f7dadfa9cd9b9d73f3b8a69eec0671 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 25 Oct 2023 09:22:04 -0700
Subject: netlink: make range pointers in policies const

struct nla_policy is usually constant itself, but unless
we make the ranges inside constant we won't be able to
make range structs const. The ranges are not modified
by the core.

Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231025162204.132528-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_netlink.c | 2 +-
 drivers/net/vxlan/vxlan_mdb.c      | 2 +-
 include/net/netlink.h              | 4 ++--
 net/ipv6/ioam6_iptunnel.c          | 2 +-
 net/sched/sch_fq.c                 | 2 +-
 net/sched/sch_fq_pie.c             | 2 +-
 net/sched/sch_qfq.c                | 2 +-
 net/sched/sch_taprio.c             | 2 +-
 net/wireless/nl80211.c             | 2 +-
 tools/net/ynl/ynl-gen-c.py         | 2 +-
 10 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 27cbe148f0db..cfa74cf8bb1a 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -85,7 +85,7 @@ nla_put_failure:
 }
 
 /* Limit the max delay range to 300s */
-static struct netlink_range_validation delay_range = {
+static const struct netlink_range_validation delay_range = {
 	.max = 300000,
 };
 
diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c
index 5e041622261a..3a21389658ce 100644
--- a/drivers/net/vxlan/vxlan_mdb.c
+++ b/drivers/net/vxlan/vxlan_mdb.c
@@ -311,7 +311,7 @@ vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = {
 	[MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol),
 };
 
-static struct netlink_range_validation vni_range = {
+static const struct netlink_range_validation vni_range = {
 	.max = VXLAN_N_VID - 1,
 };
 
diff --git a/include/net/netlink.h b/include/net/netlink.h
index aba2b162a226..83bdf787aeee 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -360,8 +360,8 @@ struct nla_policy {
 		const u32 mask;
 		const char *reject_message;
 		const struct nla_policy *nested_policy;
-		struct netlink_range_validation *range;
-		struct netlink_range_validation_signed *range_signed;
+		const struct netlink_range_validation *range;
+		const struct netlink_range_validation_signed *range_signed;
 		struct {
 			s16 min, max;
 		};
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index f6f5b83dd954..7563f8c6aa87 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -46,7 +46,7 @@ struct ioam6_lwt {
 	struct ioam6_lwt_encap	tuninfo;
 };
 
-static struct netlink_range_validation freq_range = {
+static const struct netlink_range_validation freq_range = {
 	.min = IOAM6_IPTUNNEL_FREQ_MIN,
 	.max = IOAM6_IPTUNNEL_FREQ_MAX,
 };
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index bf9d00518a60..0fd18c344ab5 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -897,7 +897,7 @@ static int fq_resize(struct Qdisc *sch, u32 log)
 	return 0;
 }
 
-static struct netlink_range_validation iq_range = {
+static const struct netlink_range_validation iq_range = {
 	.max = INT_MAX,
 };
 
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 68e6acd0f130..5b595773e59b 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -202,7 +202,7 @@ out:
 	return NET_XMIT_CN;
 }
 
-static struct netlink_range_validation fq_pie_q_range = {
+static const struct netlink_range_validation fq_pie_q_range = {
 	.min = 1,
 	.max = 1 << 20,
 };
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 5598f8be18ae..28315166fe8e 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -213,7 +213,7 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 	return container_of(clc, struct qfq_class, common);
 }
 
-static struct netlink_range_validation lmax_range = {
+static const struct netlink_range_validation lmax_range = {
 	.min = QFQ_MIN_LMAX,
 	.max = QFQ_MAX_LMAX,
 };
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1cb5e41c0ec7..2e1949de4171 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1015,7 +1015,7 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = {
 							      TC_FP_PREEMPTIBLE),
 };
 
-static struct netlink_range_validation_signed taprio_cycle_time_range = {
+static const struct netlink_range_validation_signed taprio_cycle_time_range = {
 	.min = 0,
 	.max = INT_MAX,
 };
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2650543dcebe..2f8353bf603c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -463,7 +463,7 @@ nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] = {
 	[NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 },
 };
 
-static struct netlink_range_validation nl80211_punct_bitmap_range = {
+static const struct netlink_range_validation nl80211_punct_bitmap_range = {
 	.min = 0,
 	.max = 0xffff,
 };
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 0fee68863db4..31fd96f14fc0 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2038,7 +2038,7 @@ def print_kernel_policy_ranges(family, cw):
                 first = False
 
             sign = '' if attr.type[0] == 'u' else '_signed'
-            cw.block_start(line=f'struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =')
+            cw.block_start(line=f'static const struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =')
             members = []
             if 'min' in attr.checks:
                 members.append(('min', attr.get_limit('min')))
-- 
cgit v1.2.3


From bc30bb88ff3153fba7693557d15733179adf7492 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 25 Oct 2023 09:22:53 -0700
Subject: netlink: specs: support conditional operations

Page pool code is compiled conditionally, but the operations
are part of the shared netlink family. We can handle this
by reporting empty list of pools or -EOPNOTSUPP / -ENOSYS
but the cleanest way seems to be removing the ops completely
at compilation time. That way user can see that the page
pool ops are not present using genetlink introspection.
Same way they'd check if the kernel is "new enough" to
support the ops.

Extend the specs with the ability to specify the config
condition under which op (and its policies, etc.) should
be hidden.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231025162253.133159-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      |  5 +++++
 Documentation/netlink/genetlink-legacy.yaml |  5 +++++
 Documentation/netlink/genetlink.yaml        |  5 +++++
 tools/net/ynl/ynl-gen-c.py                  | 22 ++++++++++++++++++++++
 4 files changed, 37 insertions(+)

(limited to 'tools')

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 7ef2496d57c8..9d13bbb7ae47 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -295,6 +295,11 @@ properties:
               type: array
               items:
                 enum: [ strict, dump, dump-strict ]
+            config-cond:
+              description: |
+                Name of the kernel config option gating the presence of
+                the operation, without the 'CONFIG_' prefix.
+              type: string
             do: &subop-type
               description: Main command handler.
               type: object
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index cd5ebe39b52c..0daf40402a29 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -346,6 +346,11 @@ properties:
               type: array
               items:
                 enum: [ strict, dump, dump-strict ]
+            config-cond:
+              description: |
+                Name of the kernel config option gating the presence of
+                the operation, without the 'CONFIG_' prefix.
+              type: string
             # Start genetlink-legacy
             fixed-header: *fixed-header
             # End genetlink-legacy
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 501ed2e6c8ef..3283bf458ff1 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -264,6 +264,11 @@ properties:
               type: array
               items:
                 enum: [ strict, dump, dump-strict ]
+            config-cond:
+              description: |
+                Name of the kernel config option gating the presence of
+                the operation, without the 'CONFIG_' prefix.
+              type: string
             do: &subop-type
               description: Main command handler.
               type: object
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 31fd96f14fc0..1c7474ad92dc 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -1162,6 +1162,7 @@ class CodeWriter:
         self._block_end = False
         self._silent_block = False
         self._ind = 0
+        self._ifdef_block = None
         if out_file is None:
             self._out = os.sys.stdout
         else:
@@ -1202,6 +1203,8 @@ class CodeWriter:
         if self._silent_block:
             ind += 1
         self._silent_block = line.endswith(')') and CodeWriter._is_cond(line)
+        if line[0] == '#':
+            ind = 0
         if add_ind:
             ind += add_ind
         self._out.write('\t' * ind + line + '\n')
@@ -1328,6 +1331,19 @@ class CodeWriter:
             line += '= ' + str(one[1]) + ','
             self.p(line)
 
+    def ifdef_block(self, config):
+        config_option = None
+        if config:
+            config_option = 'CONFIG_' + c_upper(config)
+        if self._ifdef_block == config_option:
+            return
+
+        if self._ifdef_block:
+            self.p('#endif /* ' + self._ifdef_block + ' */')
+        if config_option:
+            self.p('#ifdef ' + config_option)
+        self._ifdef_block = config_option
+
 
 scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64', 'uint', 'sint'}
 
@@ -2006,10 +2022,13 @@ def print_req_policy_fwd(cw, struct, ri=None, terminate=True):
 
 
 def print_req_policy(cw, struct, ri=None):
+    if ri and ri.op:
+        cw.ifdef_block(ri.op.get('config-cond', None))
     print_req_policy_fwd(cw, struct, ri=ri, terminate=False)
     for _, arg in struct.member_list():
         arg.attr_policy(cw)
     cw.p("};")
+    cw.ifdef_block(None)
     cw.nl()
 
 
@@ -2127,6 +2146,7 @@ def print_kernel_op_table(family, cw):
             if op.is_async:
                 continue
 
+            cw.ifdef_block(op.get('config-cond', None))
             cw.block_start()
             members = [('cmd', op.enum_name)]
             if 'dont-validate' in op:
@@ -2157,6 +2177,7 @@ def print_kernel_op_table(family, cw):
                 if op.is_async or op_mode not in op:
                     continue
 
+                cw.ifdef_block(op.get('config-cond', None))
                 cw.block_start()
                 members = [('cmd', op.enum_name)]
                 if 'dont-validate' in op:
@@ -2192,6 +2213,7 @@ def print_kernel_op_table(family, cw):
                 members.append(('flags', ' | '.join([c_upper('genl-' + x) for x in flags])))
                 cw.write_struct_init(members)
                 cw.block_end(line=',')
+    cw.ifdef_block(None)
 
     cw.block_end(line=';')
     cw.nl()
-- 
cgit v1.2.3


From eb9df668381d350e462fdf840907388e0a9b80fe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 25 Oct 2023 11:27:39 -0700
Subject: tools: ynl-gen: respect attr-cnt-name at the attr set level

Davide reports that we look for the attr-cnt-name in the wrong
object. We try to read it from the family, but the schema only
allows for it to exist at attr-set level.

Reported-by: Davide Caratti <dcaratti@redhat.com>
Link: https://lore.kernel.org/all/CAKa-r6vCj+gPEUKpv7AsXqM77N6pB0evuh7myHq=585RA3oD5g@mail.gmail.com/
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231025182739.184706-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 1c7474ad92dc..13427436bfb7 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -789,9 +789,11 @@ class AttrSet(SpecAttrSet):
                 pfx = f"{family.name}-a-{self.name}-"
             self.name_prefix = c_upper(pfx)
             self.max_name = c_upper(self.yaml.get('attr-max-name', f"{self.name_prefix}max"))
+            self.cnt_name = c_upper(self.yaml.get('attr-cnt-name', f"__{self.name_prefix}max"))
         else:
             self.name_prefix = family.attr_sets[self.subset_of].name_prefix
             self.max_name = family.attr_sets[self.subset_of].max_name
+            self.cnt_name = family.attr_sets[self.subset_of].cnt_name
 
         # Added by resolve:
         self.c_name = None
@@ -2354,8 +2356,7 @@ def render_uapi(family, cw):
         if attr_set.subset_of:
             continue
 
-        cnt_name = c_upper(family.get('attr-cnt-name', f"__{attr_set.name_prefix}MAX"))
-        max_value = f"({cnt_name} - 1)"
+        max_value = f"({attr_set.cnt_name} - 1)"
 
         val = 0
         uapi_enum_start(family, cw, attr_set.yaml, 'enum-name')
@@ -2367,7 +2368,7 @@ def render_uapi(family, cw):
             val += 1
             cw.p(attr.enum_name + suffix)
         cw.nl()
-        cw.p(cnt_name + ('' if max_by_define else ','))
+        cw.p(attr_set.cnt_name + ('' if max_by_define else ','))
         if not max_by_define:
             cw.p(f"{attr_set.max_name} = {max_value}")
         cw.block_end(line=';')
-- 
cgit v1.2.3


From e8bba9e83c88ea951dafd3319c97c55a52b3637d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 25 Oct 2023 15:30:19 +0300
Subject: selftests: bridge_mdb: Use MDB get instead of dump

Test the new MDB get functionality by converting dump and grep to MDB
get.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/bridge_mdb.sh | 184 ++++++++-------------
 1 file changed, 71 insertions(+), 113 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index d0c6c499d5da..e4e3e9405056 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -145,14 +145,14 @@ cfg_test_host_common()
 
 	# Check basic add, replace and delete behavior.
 	bridge mdb add dev br0 port br0 grp $grp $state vid 10
-	bridge mdb show dev br0 vid 10 | grep -q "$grp"
+	bridge mdb get dev br0 grp $grp vid 10 &> /dev/null
 	check_err $? "Failed to add $name host entry"
 
 	bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null
 	check_fail $? "Managed to replace $name host entry"
 
 	bridge mdb del dev br0 port br0 grp $grp $state vid 10
-	bridge mdb show dev br0 vid 10 | grep -q "$grp"
+	bridge mdb get dev br0 grp $grp vid 10 &> /dev/null
 	check_fail $? "Failed to delete $name host entry"
 
 	# Check error cases.
@@ -200,7 +200,7 @@ cfg_test_port_common()
 
 	# Check basic add, replace and delete behavior.
 	bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10
-	bridge mdb show dev br0 vid 10 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 10 &> /dev/null
 	check_err $? "Failed to add $name entry"
 
 	bridge mdb replace dev br0 port $swp1 $grp_key permanent vid 10 \
@@ -208,31 +208,31 @@ cfg_test_port_common()
 	check_err $? "Failed to replace $name entry"
 
 	bridge mdb del dev br0 port $swp1 $grp_key permanent vid 10
-	bridge mdb show dev br0 vid 10 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 10 &> /dev/null
 	check_fail $? "Failed to delete $name entry"
 
 	# Check default protocol and replacement.
 	bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "static"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "static"
 	check_err $? "$name entry not added with default \"static\" protocol"
 
 	bridge mdb replace dev br0 port $swp1 $grp_key permanent vid 10 \
 		proto 123
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "123"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "123"
 	check_err $? "Failed to replace protocol of $name entry"
 	bridge mdb del dev br0 port $swp1 $grp_key permanent vid 10
 
 	# Check behavior when VLAN is not specified.
 	bridge mdb add dev br0 port $swp1 $grp_key permanent
-	bridge mdb show dev br0 vid 10 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 10 &> /dev/null
 	check_err $? "$name entry with VLAN 10 not added when VLAN was not specified"
-	bridge mdb show dev br0 vid 20 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 20 &> /dev/null
 	check_err $? "$name entry with VLAN 20 not added when VLAN was not specified"
 
 	bridge mdb del dev br0 port $swp1 $grp_key permanent
-	bridge mdb show dev br0 vid 10 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 10 &> /dev/null
 	check_fail $? "$name entry with VLAN 10 not deleted when VLAN was not specified"
-	bridge mdb show dev br0 vid 20 | grep -q "$grp_key"
+	bridge mdb get dev br0 $grp_key vid 20 &> /dev/null
 	check_fail $? "$name entry with VLAN 20 not deleted when VLAN was not specified"
 
 	# Check behavior when bridge port is down.
@@ -298,21 +298,21 @@ __cfg_test_port_ip_star_g()
 	RET=0
 
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "exclude"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude"
 	check_err $? "Default filter mode is not \"exclude\""
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
 
 	# Check basic add and delete behavior.
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10 filter_mode exclude \
 		source_list $src1
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q -v "src"
+	bridge -d mdb get dev br0 grp $grp vid 10 &> /dev/null
 	check_err $? "(*, G) entry not created"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null
 	check_err $? "(S, G) entry not created"
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q -v "src"
+	bridge -d mdb get dev br0 grp $grp vid 10 &> /dev/null
 	check_fail $? "(*, G) entry not deleted"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null
 	check_fail $? "(S, G) entry not deleted"
 
 	## State (permanent / temp) tests.
@@ -321,18 +321,15 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp permanent vid 10 \
 		filter_mode exclude source_list $src1
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "permanent"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "permanent"
 	check_err $? "(*, G) entry not added as \"permanent\" when should"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | \
 		grep -q "permanent"
 	check_err $? "(S, G) entry not added as \"permanent\" when should"
 
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) \"permanent\" entry has a pending group timer"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
 	check_err $? "\"permanent\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -342,18 +339,14 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp"
 	check_err $? "(*, G) EXCLUDE entry not added as \"temp\" when should"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp"
 	check_err $? "(S, G) \"blocked\" entry not added as \"temp\" when should"
 
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
 	check_err $? "\"blocked\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -363,18 +356,14 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode include source_list $src1
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp"
 	check_err $? "(*, G) INCLUDE entry not added as \"temp\" when should"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp"
 	check_err $? "(S, G) entry not added as \"temp\" when should"
 
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) INCLUDE entry has a pending group timer"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
 	check_fail $? "Source entry does not have a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -383,8 +372,7 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode include source_list $src1
 
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 grp $grp src $src1 vid 10 | grep -q " 0.00"
 	check_err $? "(S, G) entry has a pending group timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -396,11 +384,9 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10 \
 		filter_mode include source_list $src1
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "include"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "include"
 	check_err $? "(*, G) INCLUDE not added with \"include\" filter mode"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "blocked"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked"
 	check_fail $? "(S, G) entry marked as \"blocked\" when should not"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -410,11 +396,9 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10 \
 		filter_mode exclude source_list $src1
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "exclude"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude"
 	check_err $? "(*, G) EXCLUDE not added with \"exclude\" filter mode"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "blocked"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked"
 	check_err $? "(S, G) entry not marked as \"blocked\" when should"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -426,11 +410,9 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10 \
 		filter_mode exclude source_list $src1 proto zebra
 
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "zebra"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "zebra"
 	check_err $? "(*, G) entry not added with \"zebra\" protocol"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "zebra"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "zebra"
 	check_err $? "(S, G) entry not marked added with \"zebra\" protocol"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -443,20 +425,16 @@ __cfg_test_port_ip_star_g()
 
 	bridge mdb replace dev br0 port $swp1 grp $grp permanent vid 10 \
 		filter_mode exclude source_list $src1
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "permanent"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "permanent"
 	check_err $? "(*, G) entry not marked as \"permanent\" after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "permanent"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "permanent"
 	check_err $? "(S, G) entry not marked as \"permanent\" after replace"
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp"
 	check_err $? "(*, G) entry not marked as \"temp\" after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp"
 	check_err $? "(S, G) entry not marked as \"temp\" after replace"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -467,20 +445,16 @@ __cfg_test_port_ip_star_g()
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode include source_list $src1
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "include"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "include"
 	check_err $? "(*, G) not marked with \"include\" filter mode after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "blocked"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked"
 	check_fail $? "(S, G) marked as \"blocked\" after replace"
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "exclude"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude"
 	check_err $? "(*, G) not marked with \"exclude\" filter mode after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "blocked"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked"
 	check_err $? "(S, G) not marked as \"blocked\" after replace"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -491,20 +465,20 @@ __cfg_test_port_ip_star_g()
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1,$src2,$src3
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null
 	check_err $? "(S, G) entry for source $src1 not created after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src2"
+	bridge -d mdb get dev br0 grp $grp src $src2 vid 10 &> /dev/null
 	check_err $? "(S, G) entry for source $src2 not created after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src3"
+	bridge -d mdb get dev br0 grp $grp src $src3 vid 10 &> /dev/null
 	check_err $? "(S, G) entry for source $src3 not created after replace"
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1,$src3
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null
 	check_err $? "(S, G) entry for source $src1 not created after second replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src2"
+	bridge -d mdb get dev br0 grp $grp src $src2 vid 10 &> /dev/null
 	check_fail $? "(S, G) entry for source $src2 created after second replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src3"
+	bridge -d mdb get dev br0 grp $grp src $src3 vid 10 &> /dev/null
 	check_err $? "(S, G) entry for source $src3 not created after second replace"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -515,11 +489,9 @@ __cfg_test_port_ip_star_g()
 
 	bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \
 		filter_mode exclude source_list $src1 proto bgp
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \
-		grep -q "bgp"
+	bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "bgp"
 	check_err $? "(*, G) protocol not changed to \"bgp\" after replace"
-	bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \
-		grep -q "bgp"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "bgp"
 	check_err $? "(S, G) protocol not changed to \"bgp\" after replace"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -532,8 +504,8 @@ __cfg_test_port_ip_star_g()
 	bridge mdb add dev br0 port $swp2 grp $grp vid 10 \
 		filter_mode include source_list $src1
 	bridge mdb add dev br0 port $swp1 grp $grp vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$swp1" | grep "$grp" | \
-		grep "$src1" | grep -q "added_by_star_ex"
+	bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep "$swp1" | \
+		grep -q "added_by_star_ex"
 	check_err $? "\"added_by_star_ex\" entry not created after adding (*, G) entry"
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
 	bridge mdb del dev br0 port $swp2 grp $grp src $src1 vid 10
@@ -606,27 +578,23 @@ __cfg_test_port_ip_sg()
 	RET=0
 
 	bridge mdb add dev br0 port $swp1 $grp_key vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "include"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "include"
 	check_err $? "Default filter mode is not \"include\""
 	bridge mdb del dev br0 port $swp1 $grp_key vid 10
 
 	# Check that entries can be added as both permanent and temp and that
 	# group timer is set correctly.
 	bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q "permanent"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "permanent"
 	check_err $? "Entry not added as \"permanent\" when should"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00"
 	check_err $? "\"permanent\" entry has a pending group timer"
 	bridge mdb del dev br0 port $swp1 $grp_key vid 10
 
 	bridge mdb add dev br0 port $swp1 $grp_key temp vid 10
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "temp"
 	check_err $? "Entry not added as \"temp\" when should"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00"
 	check_fail $? "\"temp\" entry has an unpending group timer"
 	bridge mdb del dev br0 port $swp1 $grp_key vid 10
 
@@ -650,24 +618,19 @@ __cfg_test_port_ip_sg()
 	# Check that we can replace available attributes.
 	bridge mdb add dev br0 port $swp1 $grp_key vid 10 proto 123
 	bridge mdb replace dev br0 port $swp1 $grp_key vid 10 proto 111
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q "111"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "111"
 	check_err $? "Failed to replace protocol"
 
 	bridge mdb replace dev br0 port $swp1 $grp_key vid 10 permanent
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q "permanent"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "permanent"
 	check_err $? "Entry not marked as \"permanent\" after replace"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00"
 	check_err $? "Entry has a pending group timer after replace"
 
 	bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp
-	bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q "temp"
+	bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "temp"
 	check_err $? "Entry not marked as \"temp\" after replace"
-	bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \
-		grep -q " 0.00"
+	bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00"
 	check_fail $? "Entry has an unpending group timer after replace"
 	bridge mdb del dev br0 port $swp1 $grp_key vid 10
 
@@ -675,7 +638,7 @@ __cfg_test_port_ip_sg()
 	# (*, G) ports need to be added to it.
 	bridge mdb add dev br0 port $swp2 grp $grp vid 10
 	bridge mdb add dev br0 port $swp1 $grp_key vid 10
-	bridge mdb show dev br0 vid 10 | grep "$grp_key" | grep $swp2 | \
+	bridge mdb get dev br0 $grp_key vid 10 | grep $swp2 | \
 		grep -q "added_by_star_ex"
 	check_err $? "\"added_by_star_ex\" entry not created after adding (S, G) entry"
 	bridge mdb del dev br0 port $swp1 $grp_key vid 10
@@ -1132,7 +1095,7 @@ ctrl_igmpv3_is_in_test()
 	$MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \
 		-t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q
 
-	bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2
+	bridge mdb get dev br0 grp 239.1.1.1 src 192.0.2.2 vid 10 &> /dev/null
 	check_fail $? "Permanent entry affected by IGMP packet"
 
 	# Replace the permanent entry with a temporary one and check that after
@@ -1145,12 +1108,10 @@ ctrl_igmpv3_is_in_test()
 	$MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \
 		-t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q
 
-	bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \
-		grep -q 192.0.2.2
+	bridge -d mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q 192.0.2.2
 	check_err $? "Source not add to source list"
 
-	bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | \
-		grep -q "src 192.0.2.2"
+	bridge mdb get dev br0 grp 239.1.1.1 src 192.0.2.2 vid 10 &> /dev/null
 	check_err $? "(S, G) entry not created for new source"
 
 	bridge mdb del dev br0 port $swp1 grp 239.1.1.1 vid 10
@@ -1172,8 +1133,7 @@ ctrl_mldv2_is_in_test()
 	$MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \
 		-t ip hop=1,next=0,p="$p" -q
 
-	bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \
-		grep -q 2001:db8:1::2
+	bridge mdb get dev br0 grp ff0e::1 src 2001:db8:1::2 vid 10 &> /dev/null
 	check_fail $? "Permanent entry affected by MLD packet"
 
 	# Replace the permanent entry with a temporary one and check that after
@@ -1186,12 +1146,10 @@ ctrl_mldv2_is_in_test()
 	$MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \
 		-t ip hop=1,next=0,p="$p" -q
 
-	bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \
-		grep -q 2001:db8:1::2
+	bridge -d mdb get dev br0 grp ff0e::1 vid 10 | grep -q 2001:db8:1::2
 	check_err $? "Source not add to source list"
 
-	bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \
-		grep -q "src 2001:db8:1::2"
+	bridge mdb get dev br0 grp ff0e::1 src 2001:db8:1::2 vid 10 &> /dev/null
 	check_err $? "(S, G) entry not created for new source"
 
 	bridge mdb del dev br0 port $swp1 grp ff0e::1 vid 10
@@ -1208,8 +1166,8 @@ ctrl_test()
 	ctrl_mldv2_is_in_test
 }
 
-if ! bridge mdb help 2>&1 | grep -q "replace"; then
-	echo "SKIP: iproute2 too old, missing bridge mdb replace support"
+if ! bridge mdb help 2>&1 | grep -q "get"; then
+	echo "SKIP: iproute2 too old, missing bridge mdb get support"
 	exit $ksft_skip
 fi
 
-- 
cgit v1.2.3


From 0514dd05939a998abcd2f03f69cc15908072a198 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 25 Oct 2023 15:30:20 +0300
Subject: selftests: vxlan_mdb: Use MDB get instead of dump

Test the new MDB get functionality by converting dump and grep to MDB
get.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/test_vxlan_mdb.sh | 108 +++++++++++++-------------
 1 file changed, 54 insertions(+), 54 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh
index 31e5f0f8859d..6e996f8063cd 100755
--- a/tools/testing/selftests/net/test_vxlan_mdb.sh
+++ b/tools/testing/selftests/net/test_vxlan_mdb.sh
@@ -337,62 +337,62 @@ basic_common()
 	# Basic add, replace and delete behavior.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
 	log_test $? 0 "MDB entry addition"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010"
 	log_test $? 0 "MDB entry presence after addition"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
 	log_test $? 0 "MDB entry replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010"
 	log_test $? 0 "MDB entry presence after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
 	log_test $? 0 "MDB entry deletion"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\""
-	log_test $? 1 "MDB entry presence after deletion"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010"
+	log_test $? 254 "MDB entry presence after deletion"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
 	log_test $? 255 "Non-existent MDB entry deletion"
 
 	# Default protocol and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \"proto static\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \"proto static\""
 	log_test $? 0 "MDB entry default protocol"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 $grp_key permanent proto 123 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \"proto 123\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \"proto 123\""
 	log_test $? 0 "MDB entry protocol replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
 
 	# Default destination port and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \" dst_port \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \" dst_port \""
 	log_test $? 1 "MDB entry default destination port"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 $grp_key permanent dst $vtep_ip dst_port 1234 src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \"dst_port 1234\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \"dst_port 1234\""
 	log_test $? 0 "MDB entry destination port replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
 
 	# Default destination VNI and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \" vni \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \" vni \""
 	log_test $? 1 "MDB entry default destination VNI"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 $grp_key permanent dst $vtep_ip vni 1234 src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \"vni 1234\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \"vni 1234\""
 	log_test $? 0 "MDB entry destination VNI replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
 
 	# Default outgoing interface and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \" via \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \" via \""
 	log_test $? 1 "MDB entry default outgoing interface"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 $grp_key permanent dst $vtep_ip src_vni 10010 via veth0"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep \"$grp_key\" | grep \"via veth0\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 $grp_key src_vni 10010 | grep \"via veth0\""
 	log_test $? 0 "MDB entry outgoing interface replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 $grp_key dst $vtep_ip src_vni 10010"
@@ -550,127 +550,127 @@ star_g_common()
 	# Basic add, replace and delete behavior.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
 	log_test $? 0 "(*, G) MDB entry addition with source list"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010"
 	log_test $? 0 "(*, G) MDB entry presence after addition"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry presence after addition"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
 	log_test $? 0 "(*, G) MDB entry replacement with source list"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010"
 	log_test $? 0 "(*, G) MDB entry presence after replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry presence after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 	log_test $? 0 "(*, G) MDB entry deletion"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \""
-	log_test $? 1 "(*, G) MDB entry presence after deletion"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
-	log_test $? 1 "(S, G) MDB entry presence after deletion"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010"
+	log_test $? 254 "(*, G) MDB entry presence after deletion"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
+	log_test $? 254 "(S, G) MDB entry presence after deletion"
 
 	# Default filter mode and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep exclude"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep exclude"
 	log_test $? 0 "(*, G) MDB entry default filter mode"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode include source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep include"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep include"
 	log_test $? 0 "(*, G) MDB entry after replacing filter mode to \"include\""
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry after replacing filter mode to \"include\""
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\" | grep blocked"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep blocked"
 	log_test $? 1 "\"blocked\" flag after replacing filter mode to \"include\""
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep exclude"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep exclude"
 	log_test $? 0 "(*, G) MDB entry after replacing filter mode to \"exclude\""
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grep grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry after replacing filter mode to \"exclude\""
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\" | grep blocked"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep blocked"
 	log_test $? 0 "\"blocked\" flag after replacing filter mode to \"exclude\""
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 
 	# Default source list and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep source_list"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep source_list"
 	log_test $? 1 "(*, G) MDB entry default source list"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1,$src2,$src3 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry of 1st source after replacing source list"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src2\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src2 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry of 2nd source after replacing source list"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src3\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src3 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry of 3rd source after replacing source list"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1,$src3 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src1\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry of 1st source after removing source"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src2\""
-	log_test $? 1 "(S, G) MDB entry of 2nd source after removing source"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \"src $src3\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src2 src_vni 10010"
+	log_test $? 254 "(S, G) MDB entry of 2nd source after removing source"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src3 src_vni 10010"
 	log_test $? 0 "(S, G) MDB entry of 3rd source after removing source"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 
 	# Default protocol and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \"proto static\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \"proto static\""
 	log_test $? 0 "(*, G) MDB entry default protocol"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \"proto static\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \"proto static\""
 	log_test $? 0 "(S, G) MDB entry default protocol"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 proto bgp dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \"proto bgp\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \"proto bgp\""
 	log_test $? 0 "(*, G) MDB entry protocol after replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \"proto bgp\""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \"proto bgp\""
 	log_test $? 0 "(S, G) MDB entry protocol after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 
 	# Default destination port and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" dst_port \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" dst_port \""
 	log_test $? 1 "(*, G) MDB entry default destination port"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" dst_port \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" dst_port \""
 	log_test $? 1 "(S, G) MDB entry default destination port"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip dst_port 1234 src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" dst_port 1234 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" dst_port 1234 \""
 	log_test $? 0 "(*, G) MDB entry destination port after replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" dst_port 1234 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" dst_port 1234 \""
 	log_test $? 0 "(S, G) MDB entry destination port after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 
 	# Default destination VNI and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" vni \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" vni \""
 	log_test $? 1 "(*, G) MDB entry default destination VNI"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" vni \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" vni \""
 	log_test $? 1 "(S, G) MDB entry default destination VNI"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip vni 1234 src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" vni 1234 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" vni 1234 \""
 	log_test $? 0 "(*, G) MDB entry destination VNI after replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" vni 1234 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" vni 1234 \""
 	log_test $? 0 "(S, G) MDB entry destination VNI after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
 
 	# Default outgoing interface and replacement.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" via \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" via \""
 	log_test $? 1 "(*, G) MDB entry default outgoing interface"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" via \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" via \""
 	log_test $? 1 "(S, G) MDB entry default outgoing interface"
 
 	run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $src1 dst $vtep_ip src_vni 10010 via veth0"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep -v \" src \" | grep \" via veth0 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src_vni 10010 | grep \" via veth0 \""
 	log_test $? 0 "(*, G) MDB entry outgoing interface after replacement"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep \" src \" | grep \" via veth0 \""
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src1 src_vni 10010 | grep \" via veth0 \""
 	log_test $? 0 "(S, G) MDB entry outgoing interface after replacement"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep_ip src_vni 10010"
@@ -772,7 +772,7 @@ sg_common()
 
 	# Default filter mode.
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $src permanent dst $vtep_ip src_vni 10010"
-	run_cmd "bridge -n $ns1 -d -s mdb show dev vx0 | grep $grp | grep include"
+	run_cmd "bridge -n $ns1 -d -s mdb get dev vx0 grp $grp src $src src_vni 10010 | grep include"
 	log_test $? 0 "(S, G) MDB entry default filter mode"
 
 	run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp src $src permanent dst $vtep_ip src_vni 10010"
@@ -2296,9 +2296,9 @@ if [ ! -x "$(command -v jq)" ]; then
 	exit $ksft_skip
 fi
 
-bridge mdb help 2>&1 | grep -q "src_vni"
+bridge mdb help 2>&1 | grep -q "get"
 if [ $? -ne 0 ]; then
-   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB support"
+   echo "SKIP: iproute2 bridge too old, missing VXLAN MDB get support"
    exit $ksft_skip
 fi
 
-- 
cgit v1.2.3


From f4a75e9d11001481dca005541b6dc861e1472f03 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 25 Oct 2023 16:37:02 -0700
Subject: selftests: mptcp: run userspace pm tests slower

Some userspace pm tests failed are reported by CI:

112 userspace pm add & remove address
      syn                                 [ ok ]
      synack                              [ ok ]
      ack                                 [ ok ]
      add                                 [ ok ]
      echo                                [ ok ]
      mptcp_info subflows=1:1             [ ok ]
      subflows_total 2:2                  [ ok ]
      mptcp_info add_addr_signal=1:1      [ ok ]
      rm                                  [ ok ]
      rmsf                                [ ok ]
      Info: invert
      mptcp_info subflows=0:0             [ ok ]
      subflows_total 1:1                  [fail]
                         got subflows 0:0 expected 1:1
Server ns stats
TcpPassiveOpens                 2                  0.0
TcpInSegs                       118                0.0

This patch fixes them by changing 'speed' to 5 to run the tests much more
slowly.

Fixes: 4369c198e599 ("selftests: mptcp: test userspace pm out of transfer")
Cc: stable@vger.kernel.org
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231025-send-net-next-20231025-v1-1-db8f25f798eb@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index dc895b7b94e1..edc569bab4b8 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3417,7 +3417,7 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
 		pm_nl_set_limits $ns2 1 1
-		speed=10 \
+		speed=5 \
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns1
@@ -3438,7 +3438,7 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns2
 		pm_nl_set_limits $ns1 0 1
-		speed=10 \
+		speed=5 \
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns2
-- 
cgit v1.2.3


From 9168ea02b898d3dde98b51e4bd3fb082bd438dab Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 25 Oct 2023 16:37:03 -0700
Subject: selftests: mptcp: fix wait_rm_addr/sf parameters

The second input parameter of 'wait_rm_addr/sf $1 1' is misused. If it's
1, wait_rm_addr/sf will never break, and will loop ten times, then
'wait_rm_addr/sf' equals to 'sleep 1'. This delay time is too long,
which can sometimes make the tests fail.

A better way to use wait_rm_addr/sf is to use rm_addr/sf_count to obtain
the current value, and then pass into wait_rm_addr/sf.

Fixes: 4369c198e599 ("selftests: mptcp: test userspace pm out of transfer")
Cc: stable@vger.kernel.org
Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231025-send-net-next-20231025-v1-2-db8f25f798eb@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index edc569bab4b8..5917a74b749d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3289,6 +3289,7 @@ userspace_pm_rm_sf_addr_ns1()
 	local addr=$1
 	local id=$2
 	local tk sp da dp
+	local cnt_addr cnt_sf
 
 	tk=$(grep "type:1," "$evts_ns1" |
 	     sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q')
@@ -3298,11 +3299,13 @@ userspace_pm_rm_sf_addr_ns1()
 	     sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q')
 	dp=$(grep "type:10" "$evts_ns1" |
 	     sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q')
+	cnt_addr=$(rm_addr_count ${ns1})
+	cnt_sf=$(rm_sf_count ${ns1})
 	ip netns exec $ns1 ./pm_nl_ctl rem token $tk id $id
 	ip netns exec $ns1 ./pm_nl_ctl dsf lip "::ffff:$addr" \
 				lport $sp rip $da rport $dp token $tk
-	wait_rm_addr $ns1 1
-	wait_rm_sf $ns1 1
+	wait_rm_addr $ns1 "${cnt_addr}"
+	wait_rm_sf $ns1 "${cnt_sf}"
 }
 
 userspace_pm_add_sf()
@@ -3324,17 +3327,20 @@ userspace_pm_rm_sf_addr_ns2()
 	local addr=$1
 	local id=$2
 	local tk da dp sp
+	local cnt_addr cnt_sf
 
 	tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
 	da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2")
 	dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2")
 	sp=$(grep "type:10" "$evts_ns2" |
 	     sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q')
+	cnt_addr=$(rm_addr_count ${ns2})
+	cnt_sf=$(rm_sf_count ${ns2})
 	ip netns exec $ns2 ./pm_nl_ctl rem token $tk id $id
 	ip netns exec $ns2 ./pm_nl_ctl dsf lip $addr lport $sp \
 				rip $da rport $dp token $tk
-	wait_rm_addr $ns2 1
-	wait_rm_sf $ns2 1
+	wait_rm_addr $ns2 "${cnt_addr}"
+	wait_rm_sf $ns2 "${cnt_sf}"
 }
 
 userspace_tests()
-- 
cgit v1.2.3


From e71aab6777a4f906149d0b5f12507fad5e164b3b Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 25 Oct 2023 16:37:10 -0700
Subject: selftests: mptcp: sockopt: drop mptcp_connect var

Global var mptcp_connect defined at the front of mptcp_sockopt.sh is
duplicate with local var mptcp_connect defined in do_transfer(), drop
this useless global one.

Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231025-send-net-next-20231025-v1-9-db8f25f798eb@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 8c8694f21e7d..a817af6616ec 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -11,7 +11,6 @@ cout=""
 ksft_skip=4
 timeout_poll=30
 timeout_test=$((timeout_poll * 2 + 1))
-mptcp_connect=""
 iptables="iptables"
 ip6tables="ip6tables"
 
-- 
cgit v1.2.3


From 629b35a225b0d49fbcff3b5c22e3b983c7c7b36f Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Wed, 25 Oct 2023 16:37:11 -0700
Subject: selftests: mptcp: display simult in extra_msg

Just like displaying "invert" after "Info: ", "simult" should be
displayed too when rm_subflow_nr doesn't match the expect value in
chk_rm_nr():

      syn                                 [ ok ]
      synack                              [ ok ]
      ack                                 [ ok ]
      add                                 [ ok ]
      echo                                [ ok ]
      rm                                  [ ok ]
      rmsf                                [ ok ] 3 in [2:4]
      Info: invert simult

      syn                                 [ ok ]
      synack                              [ ok ]
      ack                                 [ ok ]
      add                                 [ ok ]
      echo                                [ ok ]
      rm                                  [ ok ]
      rmsf                                [ ok ]
      Info: invert

Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231025-send-net-next-20231025-v1-10-db8f25f798eb@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 5917a74b749d..75a2438efdf3 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1770,7 +1770,10 @@ chk_rm_nr()
 		# in case of simult flush, the subflow removal count on each side is
 		# unreliable
 		count=$((count + cnt))
-		[ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
+		if [ "$count" != "$rm_subflow_nr" ]; then
+			suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
+			extra_msg="$extra_msg simult"
+		fi
 		if [ $count -ge "$rm_subflow_nr" ] && \
 		   [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then
 			print_ok "$suffix"
-- 
cgit v1.2.3


From d96e48a3d55db7ee62e607ad2d89eee1a8585028 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Fri, 27 Oct 2023 11:25:25 +0200
Subject: tools: ynl: introduce option to process unknown attributes or types

In case the kernel sends message back containing attribute not defined
in family spec, following exception is raised to the user:

$ sudo ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/devlink.yaml --do trap-get --json '{"bus-name": "netdevsim", "dev-name": "netdevsim1", "trap-name": "source_mac_is_multicast"}'
Traceback (most recent call last):
  File "/home/jiri/work/linux/tools/net/ynl/lib/ynl.py", line 521, in _decode
    attr_spec = attr_space.attrs_by_val[attr.type]
                ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^
KeyError: 132

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/jiri/work/linux/./tools/net/ynl/cli.py", line 61, in <module>
    main()
  File "/home/jiri/work/linux/./tools/net/ynl/cli.py", line 49, in main
    reply = ynl.do(args.do, attrs, args.flags)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jiri/work/linux/tools/net/ynl/lib/ynl.py", line 731, in do
    return self._op(method, vals, flags)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jiri/work/linux/tools/net/ynl/lib/ynl.py", line 719, in _op
    rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jiri/work/linux/tools/net/ynl/lib/ynl.py", line 525, in _decode
    raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'")
Exception: Space 'devlink' has no attribute with value '132'

Introduce a command line option "process-unknown" and pass it down to
YnlFamily class constructor to allow user to process unknown
attributes and types and print them as binaries.

$ sudo ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/devlink.yaml --do trap-get --json '{"bus-name": "netdevsim", "dev-name": "netdevsim1", "trap-name": "source_mac_is_multicast"}' --process-unknown
{'UnknownAttr(129)': {'UnknownAttr(0)': b'\x00\x00\x00\x00\x00\x00\x00\x00',
                      'UnknownAttr(1)': b'\x00\x00\x00\x00\x00\x00\x00\x00',
                      'UnknownAttr(2)': b'\x0e\x00\x00\x00\x00\x00\x00\x00'},
 'UnknownAttr(132)': b'\x00',
 'UnknownAttr(133)': b'',
 'UnknownAttr(134)': {'UnknownAttr(0)': b''},
 'bus-name': 'netdevsim',
 'dev-name': 'netdevsim1',
 'trap-action': 'drop',
 'trap-group-name': 'l2_drops',
 'trap-name': 'source_mac_is_multicast'}

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231027092525.956172-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/cli.py     |  3 ++-
 tools/net/ynl/lib/ynl.py | 48 +++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 39 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py
index 564ecf07cd2c..2ad9ec0f5545 100755
--- a/tools/net/ynl/cli.py
+++ b/tools/net/ynl/cli.py
@@ -27,6 +27,7 @@ def main():
                         const=Netlink.NLM_F_CREATE)
     parser.add_argument('--append', dest='flags', action='append_const',
                         const=Netlink.NLM_F_APPEND)
+    parser.add_argument('--process-unknown', action=argparse.BooleanOptionalAction)
     args = parser.parse_args()
 
     if args.no_schema:
@@ -36,7 +37,7 @@ def main():
     if args.json_text:
         attrs = json.loads(args.json_text)
 
-    ynl = YnlFamily(args.spec, args.schema)
+    ynl = YnlFamily(args.spec, args.schema, args.process_unknown)
 
     if args.ntf:
         ynl.ntf_subscribe(args.ntf)
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index b1da4aea9336..92995bca14e1 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -100,6 +100,7 @@ class NlAttr:
     def __init__(self, raw, offset):
         self._len, self._type = struct.unpack("HH", raw[offset:offset + 4])
         self.type = self._type & ~Netlink.NLA_TYPE_MASK
+        self.is_nest = self._type & Netlink.NLA_F_NESTED
         self.payload_len = self._len
         self.full_len = (self.payload_len + 3) & ~3
         self.raw = raw[offset + 4:offset + self.payload_len]
@@ -411,10 +412,11 @@ class GenlProtocol(NetlinkProtocol):
 
 
 class YnlFamily(SpecFamily):
-    def __init__(self, def_path, schema=None):
+    def __init__(self, def_path, schema=None, process_unknown=False):
         super().__init__(def_path, schema)
 
         self.include_raw = False
+        self.process_unknown = process_unknown
 
         try:
             if self.proto == "netlink-raw":
@@ -526,14 +528,41 @@ class YnlFamily(SpecFamily):
             decoded.append({ item.type: subattrs })
         return decoded
 
+    def _decode_unknown(self, attr):
+        if attr.is_nest:
+            return self._decode(NlAttrs(attr.raw), None)
+        else:
+            return attr.as_bin()
+
+    def _rsp_add(self, rsp, name, is_multi, decoded):
+        if is_multi == None:
+            if name in rsp and type(rsp[name]) is not list:
+                rsp[name] = [rsp[name]]
+                is_multi = True
+            else:
+                is_multi = False
+
+        if not is_multi:
+            rsp[name] = decoded
+        elif name in rsp:
+            rsp[name].append(decoded)
+        else:
+            rsp[name] = [decoded]
+
     def _decode(self, attrs, space):
-        attr_space = self.attr_sets[space]
+        if space:
+            attr_space = self.attr_sets[space]
         rsp = dict()
         for attr in attrs:
             try:
                 attr_spec = attr_space.attrs_by_val[attr.type]
-            except KeyError:
-                raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'")
+            except (KeyError, UnboundLocalError):
+                if not self.process_unknown:
+                    raise Exception(f"Space '{space}' has no attribute with value '{attr.type}'")
+                attr_name = f"UnknownAttr({attr.type})"
+                self._rsp_add(rsp, attr_name, None, self._decode_unknown(attr))
+                continue
+
             if attr_spec["type"] == 'nest':
                 subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'])
                 decoded = subdict
@@ -558,14 +587,11 @@ class YnlFamily(SpecFamily):
                     selector = self._decode_enum(selector, attr_spec)
                 decoded = {"value": value, "selector": selector}
             else:
-                raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}')
+                if not self.process_unknown:
+                    raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}')
+                decoded = self._decode_unknown(attr)
 
-            if not attr_spec.is_multi:
-                rsp[attr_spec['name']] = decoded
-            elif attr_spec.name in rsp:
-                rsp[attr_spec.name].append(decoded)
-            else:
-                rsp[attr_spec.name] = [decoded]
+            self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded)
 
         return rsp
 
-- 
cgit v1.2.3