Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 79 files changed, 5275 insertions(+), 600 deletions(-).

The main changes are:

1) Basic BTF validation in libbpf, from Andrii Nakryiko.

2) bpf_assert(), bpf_throw(), exceptions in bpf progs, from Kumar Kartikeya Dwivedi.

3) next_thread cleanups, from Oleg Nesterov.

4) Add mcpu=v4 support to arm32, from Puranjay Mohan.

5) Add support for __percpu pointers in bpf progs, from Yonghong Song.

6) Fix bpf tailcall interaction with bpf trampoline, from Leon Hwang.

7) Raise irq_work in bpf_mem_alloc while irqs are disabled to improve refill probabablity, from Hou Tao.

Please consider pulling these changes from:

  git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git

Thanks a lot!

Also thanks to reporters, reviewers and testers of commits in this pull-request:

Alan Maguire, Andrey Konovalov, Dave Marchevsky, "Eric W. Biederman",
Jiri Olsa, Maciej Fijalkowski, Quentin Monnet, Russell King (Oracle),
Song Liu, Stanislav Fomichev, Yonghong Song
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

45 files changed, 3585 insertions, 365 deletions

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\
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/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)
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");	\
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/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 96ff1aa4bf6a..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;
@@ -6235,13 +6320,45 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 }
 
 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)
 {
-	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);
@@ -6316,25 +6433,7 @@ 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);
@@ -6568,6 +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++) {
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);
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/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 209811b1993a..9aa29564bd74 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -131,4 +131,323 @@ 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)
+
+/* 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,
+ *	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.
+ *
+ *	Note that callbacks *cannot* call this helper.
+ * Returns
+ *	Never.
+ * Throws
+ *	An exception with the specified 'cookie' value.
+ */
+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)))
+
+#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
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] */
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/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/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/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=" },
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,
 	);
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..9541e9b3a034
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+#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)
+{
+	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);
+}
+
+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);
+}
+
+static void test_failure(void) {
+	RUN_TESTS(percpu_alloc_fail);
+}
+
+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();
+	if (test__start_subtest("failure_tests"))
+		test_failure();
+}
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/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 58fe2c586ed7..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,
@@ -265,23 +267,105 @@ 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");
 
 	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);
 	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
@@ -352,11 +440,11 @@ 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 +530,11 @@ 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 +719,11 @@ 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 +893,11 @@ 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 +960,7 @@ 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;
@@ -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/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";
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..bbc45346e006
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -0,0 +1,183 @@
+#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);
+		}
+	}
+
+	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";
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";
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";
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;
+}
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";
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")
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()
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 2aa5a3445056..65aafe0003db 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -73,17 +73,33 @@
 #
 # 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
+#
+# List available tests
+#   ./test_xsk.sh -l
+#
+# 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:d" flag
+while getopts "vi:dm:lt:h" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
 		d) debug=1;;
 		i) ETH=${OPTARG};;
+		m) MODE=${OPTARG};;
+		l) list=1;;
+		t) TEST=${OPTARG};;
+		h) help=1;;
 	esac
 done
 
@@ -131,6 +147,16 @@ setup_vethPairs() {
 	ip link set ${VETH0} up
 }
 
+if [[ $list -eq 1 ]]; then
+        ./${XSKOBJ} -l
+        exit
+fi
+
+if [[ $help -eq 1 ]]; then
+	./${XSKOBJ}
+        exit
+fi
+
 if [ ! -z $ETH ]; then
 	VETH0=${ETH}
 	VETH1=${ETH}
@@ -153,6 +179,14 @@ if [[ $verbose -eq 1 ]]; then
 	ARGS+="-v "
 fi
 
+if [ -n "$MODE" ]; then
+	ARGS+="-m ${MODE} "
+fi
+
+if [ -n "$TEST" ]; then
+	ARGS+="-t ${TEST} "
+fi
+
 retval=$?
 test_status $retval "${TEST_NAME}"
 
@@ -175,6 +209,10 @@ 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/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index f83d9f65c65b..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>
@@ -14,104 +15,165 @@
 #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 pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+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();
+	pthread_mutex_lock(&ksyms_mutex);
+	if (!ksyms)
+		ksyms = load_kallsyms_local();
+	pthread_mutex_unlock(&ksyms_mutex);
+	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);
 
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 2827f2d7cf30..43e0a5796929 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -107,6 +107,11 @@
 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 u32 opt_run_test = RUN_ALL_TESTS;
+
 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,
@@ -310,19 +315,28 @@ 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'},
+	{"list", no_argument, 0, 'l'},
+	{"test", required_argument, 0, 't'},
+	{"help", no_argument, 0, 'h'},
 	{0, 0, 0, 0}
 };
 
-static void usage(const char *prog)
+static void print_usage(char **argv)
 {
 	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"
+		"  -l, --list           List all available tests\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, prog);
+	ksft_print_msg(str, basename(argv[0]));
+	ksft_exit_xfail();
 }
 
 static bool validate_interface(struct ifobject *ifobj)
@@ -342,7 +356,7 @@ 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:lt:", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -371,9 +385,28 @@ 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
+				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;
+		case 'h':
 		default:
-			usage(basename(argv[0]));
-			ksft_exit_xfail();
+			print_usage(argv);
 		}
 	}
 }
@@ -427,7 +460,8 @@ 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;
@@ -449,6 +483,8 @@ 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);
 }
@@ -458,11 +494,6 @@ 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)
@@ -747,6 +778,9 @@ 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++;
@@ -777,7 +811,7 @@ 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++;
 	}
 }
@@ -789,13 +823,13 @@ 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 {
@@ -803,15 +837,15 @@ 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)
@@ -916,36 +950,42 @@ 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) {
@@ -993,11 +1033,14 @@ 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))
@@ -1018,12 +1061,10 @@ 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);
 			}
@@ -1042,6 +1083,9 @@ 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)))
@@ -1104,7 +1148,9 @@ 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;
 	}
 
@@ -1165,6 +1211,9 @@ 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)
@@ -1207,10 +1256,29 @@ 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)
@@ -1233,8 +1301,7 @@ 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)
@@ -1266,7 +1333,9 @@ 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)
@@ -1292,7 +1361,9 @@ 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)
@@ -1311,7 +1382,9 @@ 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)
@@ -1475,8 +1548,6 @@ 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)
@@ -1500,7 +1571,8 @@ 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);
 		}
 	}
@@ -1564,7 +1636,7 @@ 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);
 	}
 
@@ -1682,7 +1754,6 @@ 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;
@@ -1704,18 +1775,17 @@ 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;
 	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);
 
@@ -1723,7 +1793,7 @@ static int testapp_bidi(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;
 
@@ -1734,31 +1804,31 @@ 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_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))
 		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);
 }
 
 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;
@@ -1774,7 +1844,6 @@ 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);
@@ -1782,7 +1851,6 @@ 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);
@@ -1795,7 +1863,6 @@ 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);
@@ -1805,9 +1872,8 @@ 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 */
@@ -1816,9 +1882,8 @@ 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;
@@ -1834,9 +1899,8 @@ static int testapp_single_pkt(struct test_spec *test)
 	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, "RUN_TO_COMPLETION_9K_PACKETS");
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 	pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE);
 
@@ -1933,7 +1997,6 @@ 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);
 
@@ -1941,7 +2004,7 @@ 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;
@@ -1955,19 +2018,21 @@ static int testapp_xdp_metadata_count(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);
 }
 
 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;
@@ -1977,7 +2042,6 @@ 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);
 }
@@ -1987,7 +2051,6 @@ 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
@@ -2067,7 +2130,7 @@ 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);
 	}
 
@@ -2091,138 +2154,98 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	}
 }
 
-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:
-		test_spec_set_name(test, "RUN_TO_COMPLETION");
-		ret = testapp_validate_traffic(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);
-		break;
-	case TEST_TYPE_RX_POLL:
-		test->ifobj_rx->use_poll = true;
-		test_spec_set_name(test, "POLL_RX");
-		ret = testapp_validate_traffic(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);
-		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:
-		test_spec_set_name(test, "ALIGNED_INV_DESC");
-		ret = testapp_invalid_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);
-		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);
-		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);
-		break;
-	}
-	case TEST_TYPE_ALIGNED_INV_DESC_MB:
-		test_spec_set_name(test, "ALIGNED_INV_DESC_MULTI_BUFF");
-		ret = testapp_invalid_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);
-		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:
-		test_spec_set_name(test, "XDP_METADATA_COUNT");
-		ret = testapp_xdp_metadata_count(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);
-		break;
-	case TEST_TYPE_TOO_MANY_FRAGS:
-		ret = testapp_too_many_frags(test);
-		break;
-	default:
-		break;
-	}
+static int testapp_send_receive(struct test_spec *test)
+{
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_send_receive_2k_frame(struct test_spec *test)
+{
+	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;
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_poll_tx(struct test_spec *test)
+{
+	test->ifobj_tx->use_poll = true;
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_aligned_inv_desc(struct test_spec *test)
+{
+	return testapp_invalid_desc(test);
+}
+
+static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
+{
+	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->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;
+
+	/* 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)
+{
+	return testapp_invalid_desc_mb(test);
+}
+
+static int testapp_unaligned_inv_desc_mb(struct test_spec *test)
+{
+	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)
+{
+	return testapp_xdp_metadata_copy(test);
+}
+
+static int testapp_xdp_metadata_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	return testapp_xdp_metadata_copy(test);
+}
+
+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),
@@ -2290,13 +2313,55 @@ 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},
+};
+
+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;
 	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;
 
@@ -2314,14 +2379,21 @@ int main(int argc, char **argv)
 
 	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
 
+	if (opt_print_tests) {
+		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++;
@@ -2332,7 +2404,7 @@ 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)
@@ -2340,12 +2412,35 @@ 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_run_test == RUN_ALL_TESTS)
+		nb_tests = ARRAY_SIZE(tests);
+	else
+		nb_tests = 1;
+	if (opt_mode == TEST_MODE_ALL) {
+		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");
+			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(nb_tests);
+	}
 
 	for (i = 0; i < modes; i++) {
-		for (j = 0; j < TEST_TYPE_MAX; j++) {
-			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
-			run_pkt_test(&test, i, j);
+		if (opt_mode != TEST_MODE_ALL && i != opt_mode)
+			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);
 
 			if (test.fail)
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 233b66cef64a..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
@@ -34,7 +36,7 @@
 #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
@@ -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)
 
@@ -63,43 +66,9 @@ enum test_mode {
 	TEST_MODE_SKB,
 	TEST_MODE_DRV,
 	TEST_MODE_ZC,
-	TEST_MODE_MAX
-};
-
-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
+	TEST_MODE_ALL
 };
 
-static bool opt_verbose;
-
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
 	struct xsk_ring_cons cq;
@@ -139,8 +108,10 @@ 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];
@@ -182,6 +153,7 @@ 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;