Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Alexei Starovoitov:

 - Fix invalid write loop logic in libbpf's bpf_linker__add_buf() (Amery
   Hung)

 - Fix a potential use-after-free of BTF object (Anton Protopopov)

 - Add feature detection to libbpf and avoid moving arena global
   variables on older kernels (Emil Tsalapatis)

 - Remove extern declaration of bpf_stream_vprintk() from libbpf headers
   (Ihor Solodrai)

 - Fix truncated netlink dumps in bpftool (Jakub Kicinski)

 - Fix map_kptr grace period wait in bpf selftests (Kumar Kartikeya
   Dwivedi)

 - Remove hexdump dependency while building bpf selftests (Matthieu
   Baerts)

 - Complete fsession support in BPF trampolines on riscv (Menglong Dong)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Remove hexdump dependency
  libbpf: Remove extern declaration of bpf_stream_vprintk()
  selftests/bpf: Use vmlinux.h in test_xdp_meta
  bpftool: Fix truncated netlink dumps
  libbpf: Delay feature gate check until object prepare time
  libbpf: Do not use PROG_TYPE_TRACEPOINT program for feature gating
  bpf: Add a map/btf from a fd array more consistently
  selftests/bpf: Fix map_kptr grace period wait
  selftests/bpf: enable fsession_test on riscv64
  selftests/bpf: Adjust selftest due to function rename
  bpf, riscv: add fsession support for trampolines
  bpf: Fix a potential use-after-free of BTF object
  bpf, riscv: introduce emit_store_stack_imm64() for trampoline
  libbpf: Fix invalid write loop logic in bpf_linker__add_buf()
  libbpf: Add gating for arena globals relocation feature

19 files changed, 242 insertions, 101 deletions

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 37888abee70c..f065b45e8d8f 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -926,6 +926,14 @@ static void restore_stack_args(int nr_stack_args, int args_off, int stk_arg_off,
 	}
 }
 
+static void emit_store_stack_imm64(u8 reg, int stack_off, u64 imm64,
+				   struct rv_jit_context *ctx)
+{
+	/* Load imm64 into reg and store it at [FP + stack_off]. */
+	emit_imm(reg, (s64)imm64, ctx);
+	emit_sd(RV_REG_FP, stack_off, reg, ctx);
+}
+
 static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_off,
 			   int run_ctx_off, bool save_ret, struct rv_jit_context *ctx)
 {
@@ -933,12 +941,10 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
 	struct bpf_prog *p = l->link.prog;
 	int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
 
-	if (l->cookie) {
-		emit_imm(RV_REG_T1, l->cookie, ctx);
-		emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_T1, ctx);
-	} else {
+	if (l->cookie)
+		emit_store_stack_imm64(RV_REG_T1, -run_ctx_off + cookie_off, l->cookie, ctx);
+	else
 		emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_ZERO, ctx);
-	}
 
 	/* arg1: prog */
 	emit_imm(RV_REG_A0, (const s64)p, ctx);
@@ -990,6 +996,29 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
 	return ret;
 }
 
+static int invoke_bpf(struct bpf_tramp_links *tl, int args_off, int retval_off,
+		      int run_ctx_off, int func_meta_off, bool save_ret, u64 func_meta,
+		      int cookie_off, struct rv_jit_context *ctx)
+{
+	int i, cur_cookie = (cookie_off - args_off) / 8;
+
+	for (i = 0; i < tl->nr_links; i++) {
+		int err;
+
+		if (bpf_prog_calls_session_cookie(tl->links[i])) {
+			u64 meta = func_meta | ((u64)cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT);
+
+			emit_store_stack_imm64(RV_REG_T1, -func_meta_off, meta, ctx);
+			cur_cookie--;
+		}
+		err = invoke_bpf_prog(tl->links[i], args_off, retval_off, run_ctx_off,
+				      save_ret, ctx);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 					 const struct btf_func_model *m,
 					 struct bpf_tramp_links *tlinks,
@@ -999,13 +1028,15 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	int i, ret, offset;
 	int *branches_off = NULL;
 	int stack_size = 0, nr_arg_slots = 0;
-	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off, stk_arg_off;
+	int retval_off, args_off, func_meta_off, ip_off, run_ctx_off, sreg_off, stk_arg_off;
+	int cookie_off, cookie_cnt;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
 	void *orig_call = func_addr;
 	bool save_ret;
+	u64 func_meta;
 	u32 insn;
 
 	/* Two types of generated trampoline stack layout:
@@ -1036,10 +1067,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	 *                  [ ...               ]
 	 * FP - args_off    [ arg1              ]
 	 *
-	 * FP - nregs_off   [ regs count        ]
+	 * FP - func_meta_off [ regs count, etc ]
 	 *
 	 * FP - ip_off      [ traced func	] BPF_TRAMP_F_IP_ARG
 	 *
+	 *                  [ stack cookie N    ]
+	 *                  [ ...               ]
+	 * FP - cookie_off  [ stack cookie 1    ]
+	 *
 	 * FP - run_ctx_off [ bpf_tramp_run_ctx ]
 	 *
 	 * FP - sreg_off    [ callee saved reg	]
@@ -1071,14 +1106,20 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	stack_size += nr_arg_slots * 8;
 	args_off = stack_size;
 
+	/* function metadata, such as regs count */
 	stack_size += 8;
-	nregs_off = stack_size;
+	func_meta_off = stack_size;
 
 	if (flags & BPF_TRAMP_F_IP_ARG) {
 		stack_size += 8;
 		ip_off = stack_size;
 	}
 
+	cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+	/* room for session cookies */
+	stack_size += cookie_cnt * 8;
+	cookie_off = stack_size;
+
 	stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8);
 	run_ctx_off = stack_size;
 
@@ -1123,16 +1164,22 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx);
 
 	/* store ip address of the traced function */
-	if (flags & BPF_TRAMP_F_IP_ARG) {
-		emit_imm(RV_REG_T1, (const s64)func_addr, ctx);
-		emit_sd(RV_REG_FP, -ip_off, RV_REG_T1, ctx);
-	}
+	if (flags & BPF_TRAMP_F_IP_ARG)
+		emit_store_stack_imm64(RV_REG_T1, -ip_off, (u64)func_addr, ctx);
 
-	emit_li(RV_REG_T1, nr_arg_slots, ctx);
-	emit_sd(RV_REG_FP, -nregs_off, RV_REG_T1, ctx);
+	func_meta = nr_arg_slots;
+	emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx);
 
 	store_args(nr_arg_slots, args_off, ctx);
 
+	if (bpf_fsession_cnt(tlinks)) {
+		/* clear all session cookies' value */
+		for (i = 0; i < cookie_cnt; i++)
+			emit_sd(RV_REG_FP, -cookie_off + 8 * i, RV_REG_ZERO, ctx);
+		/* clear return value to make sure fentry always get 0 */
+		emit_sd(RV_REG_FP, -retval_off, RV_REG_ZERO, ctx);
+	}
+
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx);
 		ret = emit_call((const u64)__bpf_tramp_enter, true, ctx);
@@ -1140,9 +1187,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 			return ret;
 	}
 
-	for (i = 0; i < fentry->nr_links; i++) {
-		ret = invoke_bpf_prog(fentry->links[i], args_off, retval_off, run_ctx_off,
-				      flags & BPF_TRAMP_F_RET_FENTRY_RET, ctx);
+	if (fentry->nr_links) {
+		ret = invoke_bpf(fentry, args_off, retval_off, run_ctx_off, func_meta_off,
+				 flags & BPF_TRAMP_F_RET_FENTRY_RET, func_meta, cookie_off, ctx);
 		if (ret)
 			return ret;
 	}
@@ -1189,9 +1236,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 		*(u32 *)(ctx->insns + branches_off[i]) = insn;
 	}
 
-	for (i = 0; i < fexit->nr_links; i++) {
-		ret = invoke_bpf_prog(fexit->links[i], args_off, retval_off,
-				      run_ctx_off, false, ctx);
+	/* set "is_return" flag for fsession */
+	func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT);
+	if (bpf_fsession_cnt(tlinks))
+		emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx);
+
+	if (fexit->nr_links) {
+		ret = invoke_bpf(fexit, args_off, retval_off, run_ctx_off, func_meta_off,
+				 false, func_meta, cookie_off, ctx);
 		if (ret)
 			goto out;
 	}
@@ -2091,3 +2143,8 @@ bool bpf_jit_inlines_helper_call(s32 imm)
 		return false;
 	}
 }
+
+bool bpf_jit_supports_fsession(void)
+{
+	return true;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index edf5342b982f..dbaafb64d3bd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21333,29 +21333,29 @@ static int find_btf_percpu_datasec(struct btf *btf)
 }
 
 /*
- * Add btf to the used_btfs array and return the index. (If the btf was
- * already added, then just return the index.) Upon successful insertion
- * increase btf refcnt, and, if present, also refcount the corresponding
- * kernel module.
+ * Add btf to the env->used_btfs array. If needed, refcount the
+ * corresponding kernel module. To simplify caller's logic
+ * in case of error or if btf was added before the function
+ * decreases the btf refcount.
  */
 static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf)
 {
 	struct btf_mod_pair *btf_mod;
+	int ret = 0;
 	int i;
 
 	/* check whether we recorded this BTF (and maybe module) already */
 	for (i = 0; i < env->used_btf_cnt; i++)
 		if (env->used_btfs[i].btf == btf)
-			return i;
+			goto ret_put;
 
 	if (env->used_btf_cnt >= MAX_USED_BTFS) {
 		verbose(env, "The total number of btfs per program has reached the limit of %u\n",
 			MAX_USED_BTFS);
-		return -E2BIG;
+		ret = -E2BIG;
+		goto ret_put;
 	}
 
-	btf_get(btf);
-
 	btf_mod = &env->used_btfs[env->used_btf_cnt];
 	btf_mod->btf = btf;
 	btf_mod->module = NULL;
@@ -21364,12 +21364,18 @@ static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf)
 	if (btf_is_module(btf)) {
 		btf_mod->module = btf_try_get_module(btf);
 		if (!btf_mod->module) {
-			btf_put(btf);
-			return -ENXIO;
+			ret = -ENXIO;
+			goto ret_put;
 		}
 	}
 
-	return env->used_btf_cnt++;
+	env->used_btf_cnt++;
+	return 0;
+
+ret_put:
+	/* Either error or this BTF was already added */
+	btf_put(btf);
+	return ret;
 }
 
 /* replace pseudo btf_id with kernel symbol address */
@@ -21466,9 +21472,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 
 	btf_fd = insn[1].imm;
 	if (btf_fd) {
-		CLASS(fd, f)(btf_fd);
-
-		btf = __btf_get_by_fd(f);
+		btf = btf_get_by_fd(btf_fd);
 		if (IS_ERR(btf)) {
 			verbose(env, "invalid module BTF object FD specified.\n");
 			return -EINVAL;
@@ -21478,17 +21482,17 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
 			return -EINVAL;
 		}
+		btf_get(btf_vmlinux);
 		btf = btf_vmlinux;
 	}
 
 	err = __check_pseudo_btf_id(env, insn, aux, btf);
-	if (err)
+	if (err) {
+		btf_put(btf);
 		return err;
+	}
 
-	err = __add_used_btf(env, btf);
-	if (err < 0)
-		return err;
-	return 0;
+	return __add_used_btf(env, btf);
 }
 
 static bool is_tracing_prog_type(enum bpf_prog_type type)
@@ -25370,10 +25374,8 @@ static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd)
 
 	btf = __btf_get_by_fd(f);
 	if (!IS_ERR(btf)) {
-		err = __add_used_btf(env, btf);
-		if (err < 0)
-			return err;
-		return 0;
+		btf_get(btf);
+		return __add_used_btf(env, btf);
 	}
 
 	verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd);
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index f25d66c8395e..974189da8a91 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -156,7 +156,7 @@ static int netlink_recv(int sock, __u32 nl_pid, __u32 seq,
 	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
-	char buf[4096];
+	char buf[8192];
 	int len, ret;
 
 	while (multipart) {
@@ -201,6 +201,9 @@ static int netlink_recv(int sock, __u32 nl_pid, __u32 seq,
 					return ret;
 			}
 		}
+
+		if (len)
+			p_err("Invalid message or trailing data in Netlink response: %d bytes left", len);
 	}
 	ret = 0;
 done:
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index c145da05a67c..9d160b5b9c0e 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -315,9 +315,6 @@ enum libbpf_tristate {
 			  ___param, sizeof(___param));		\
 })
 
-extern int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args,
-			      __u32 len__sz) __weak __ksym;
-
 #define bpf_stream_printk(stream_id, fmt, args...)					\
 ({											\
 	static const char ___fmt[] = fmt;						\
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index b842b83e2480..2fa434f09cce 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -506,6 +506,68 @@ static int probe_kern_arg_ctx_tag(int token_fd)
 	return probe_fd(prog_fd);
 }
 
+static int probe_ldimm64_full_range_off(int token_fd)
+{
+	char log_buf[1024];
+	int prog_fd, map_fd;
+	int ret;
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.token_fd = token_fd,
+		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+		.log_buf = log_buf,
+		.log_size = sizeof(log_buf),
+	);
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1UL << 30),
+		BPF_EXIT_INSN(),
+	};
+	int insn_cnt = ARRAY_SIZE(insns);
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr", sizeof(int), 1, 1, &map_opts);
+	if (map_fd < 0) {
+		ret = -errno;
+		pr_warn("Error in %s(): %s. Couldn't create simple array map.\n",
+			__func__, errstr(ret));
+		return ret;
+	}
+	insns[0].imm = map_fd;
+
+	log_buf[0] = '\0';
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "global_reloc", "GPL", insns, insn_cnt, &prog_opts);
+	ret = -errno;
+
+	close(map_fd);
+
+	if (prog_fd >= 0) {
+		pr_warn("Error in %s(): Program loading unexpectedly succeeded.\n", __func__);
+		close(prog_fd);
+		return -EINVAL;
+	}
+
+	/*
+	 * Feature is allowed if we're not failing with the error message
+	 * "direct value offset of %u is not allowed" removed in
+	 * 12a1fe6e12db ("bpf/verifier: Do not limit maximum direct offset into arena map").
+	 * We should instead fail with "invalid access to map value pointer".
+	 * Ensure we match with one of the two and we're not failing with a
+	 * different, unexpected message.
+	 */
+	if (strstr(log_buf, "direct value offset of"))
+		return 0;
+
+	if (!strstr(log_buf, "invalid access to map value pointer")) {
+		pr_warn("Error in %s(): Program unexpectedly failed with message: %s.\n",
+			__func__, log_buf);
+		return ret;
+	}
+
+	return 1;
+}
+
 typedef int (*feature_probe_fn)(int /* token_fd */);
 
 static struct kern_feature_cache feature_cache;
@@ -581,6 +643,9 @@ static struct kern_feature_desc {
 	[FEAT_BTF_QMARK_DATASEC] = {
 		"BTF DATASEC names starting from '?'", probe_kern_btf_qmark_datasec,
 	},
+	[FEAT_LDIMM64_FULL_RANGE_OFF] = {
+		"full range LDIMM64 support", probe_ldimm64_full_range_off,
+	},
 };
 
 bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0c8bf0b5cce4..0be7017800fe 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3009,9 +3009,6 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map,
 	memcpy(obj->arena_data, data, data_sz);
 	obj->arena_data_sz = data_sz;
 
-	/* place globals at the end of the arena */
-	obj->arena_data_off = mmap_sz - data_alloc_sz;
-
 	/* make bpf_map__init_value() work for ARENA maps */
 	map->mmaped = obj->arena_data;
 
@@ -4669,7 +4666,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 		reloc_desc->type = RELO_DATA;
 		reloc_desc->insn_idx = insn_idx;
 		reloc_desc->map_idx = obj->arena_map_idx;
-		reloc_desc->sym_off = sym->st_value + obj->arena_data_off;
+		reloc_desc->sym_off = sym->st_value;
 
 		map = &obj->maps[obj->arena_map_idx];
 		pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n",
@@ -6383,6 +6380,10 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 		case RELO_DATA:
 			map = &obj->maps[relo->map_idx];
 			insn[1].imm = insn[0].imm + relo->sym_off;
+
+			if (relo->map_idx == obj->arena_map_idx)
+				insn[1].imm += obj->arena_data_off;
+
 			if (obj->gen_loader) {
 				insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
 				insn[0].imm = relo->map_idx;
@@ -7384,6 +7385,14 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat
 		bpf_object__sort_relos(obj);
 	}
 
+	/* place globals at the end of the arena (if supported) */
+	if (obj->arena_map_idx >= 0 && kernel_supports(obj, FEAT_LDIMM64_FULL_RANGE_OFF)) {
+		struct bpf_map *arena_map = &obj->maps[obj->arena_map_idx];
+
+		obj->arena_data_off = bpf_map_mmap_sz(arena_map) -
+				      roundup(obj->arena_data_sz, sysconf(_SC_PAGE_SIZE));
+	}
+
 	/* Before relocating calls pre-process relocations and mark
 	 * few ld_imm64 instructions that points to subprogs.
 	 * Otherwise bpf_object__reloc_code() later would have to consider
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index fc59b21b51b5..974147e8a8aa 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -392,6 +392,8 @@ enum kern_feature_id {
 	FEAT_ARG_CTX_TAG,
 	/* Kernel supports '?' at the front of datasec names */
 	FEAT_BTF_QMARK_DATASEC,
+	/* Kernel supports LDIMM64 imm offsets past 512 MiB. */
+	FEAT_LDIMM64_FULL_RANGE_OFF,
 	__FEAT_CNT,
 };
 
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index f4403e3cf994..78f92c39290a 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -581,7 +581,7 @@ int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz,
 
 	written = 0;
 	while (written < buf_sz) {
-		ret = write(fd, buf, buf_sz);
+		ret = write(fd, buf + written, buf_sz - written);
 		if (ret < 0) {
 			ret = -errno;
 			pr_warn("failed to write '%s': %s\n", filename, errstr(ret));
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index c997e69d507f..c9a78fb16f11 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -143,7 +143,7 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 	struct nlmsghdr *nh;
 	int len, ret;
 
-	ret = alloc_iov(&iov, 4096);
+	ret = alloc_iov(&iov, 8192);
 	if (ret)
 		goto done;
 
@@ -212,6 +212,8 @@ start:
 				}
 			}
 		}
+		if (len)
+			pr_warn("Invalid message or trailing data in Netlink response: %d bytes left\n", len);
 	}
 	ret = 0;
 done:
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c6bf4dfb1495..6776158f1f3e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -723,7 +723,7 @@ $(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP)
 # Generates a header with C array declaration, containing test_progs_verification_cert bytes
 $(VERIFY_SIG_HDR): $(VERIFICATION_CERT)
 	$(Q)(echo "unsigned char test_progs_verification_cert[] = {"; \
-	 hexdump -v -e '12/1 "  0x%02x," "\n"' $< | sed 's/0x  ,//g; $$s/,$$//'; \
+	 od -v -t 'xC' -w12 $< | sed 's/ \(\S\+\)/ 0x\1,/g;s/^\S\+/ /;$$d'; \
 	 echo "};"; \
 	 echo "unsigned int test_progs_verification_cert_len = $$(wc -c < $<);") > $@
 
diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr.c b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
index f372162c0280..03b46f17cf53 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
@@ -118,15 +118,16 @@ exit:
 
 static int kern_sync_rcu_tasks_trace(struct rcu_tasks_trace_gp *rcu)
 {
-	long gp_seq = READ_ONCE(rcu->bss->gp_seq);
 	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	int ret;
 
-	if (!ASSERT_OK(bpf_prog_test_run_opts(bpf_program__fd(rcu->progs.do_call_rcu_tasks_trace),
-					      &opts), "do_call_rcu_tasks_trace"))
+	WRITE_ONCE(rcu->bss->done, 0);
+	ret = bpf_prog_test_run_opts(bpf_program__fd(rcu->progs.call_rcu_tasks_trace), &opts);
+	if (!ASSERT_OK(ret, "call_rcu_tasks_trace"))
 		return -EFAULT;
-	if (!ASSERT_OK(opts.retval, "opts.retval == 0"))
+	if (!ASSERT_OK(opts.retval, "call_rcu_tasks_trace retval"))
 		return -EFAULT;
-	while (gp_seq == READ_ONCE(rcu->bss->gp_seq))
+	while (!READ_ONCE(rcu->bss->done))
 		sched_yield();
 	return 0;
 }
@@ -159,8 +160,6 @@ void serial_test_map_kptr(void)
 	skel = rcu_tasks_trace_gp__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "rcu_tasks_trace_gp__open_and_load"))
 		return;
-	if (!ASSERT_OK(rcu_tasks_trace_gp__attach(skel), "rcu_tasks_trace_gp__attach"))
-		goto end;
 
 	if (test__start_subtest("success-map")) {
 		test_map_kptr_success(true);
@@ -180,7 +179,5 @@ void serial_test_map_kptr(void)
 		test_map_kptr_success(true);
 	}
 
-end:
 	rcu_tasks_trace_gp__destroy(skel);
-	return;
 }
diff --git a/tools/testing/selftests/bpf/progs/get_func_args_test.c b/tools/testing/selftests/bpf/progs/get_func_args_test.c
index 180ba5098ca1..075a1180ec26 100644
--- a/tools/testing/selftests/bpf/progs/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c
@@ -167,7 +167,7 @@ int BPF_PROG(tp_test2)
 }
 
 __u64 test7_result = 0;
-#if defined(bpf_target_x86) || defined(bpf_target_arm64)
+#if defined(bpf_target_x86) || defined(bpf_target_arm64) || defined(bpf_target_riscv)
 SEC("fsession/bpf_fentry_test1")
 int BPF_PROG(test7)
 {
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
index 43ff836a8ed8..45eaa54d1ac7 100644
--- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -106,7 +106,7 @@ int BPF_URETPROBE(test8, int ret)
 
 __u64 test9_entry_result = 0;
 __u64 test9_exit_result = 0;
-#if defined(bpf_target_x86) || defined(bpf_target_arm64)
+#if defined(bpf_target_x86) || defined(bpf_target_arm64) || defined(bpf_target_riscv)
 SEC("fsession/bpf_fentry_test1")
 int BPF_PROG(test9, int a)
 {
diff --git a/tools/testing/selftests/bpf/progs/profiler.h b/tools/testing/selftests/bpf/progs/profiler.h
index 3bac4fdd4bdf..637fbf2c2652 100644
--- a/tools/testing/selftests/bpf/progs/profiler.h
+++ b/tools/testing/selftests/bpf/progs/profiler.h
@@ -169,7 +169,7 @@ enum bpf_function_id {
 	profiler_bpf_sched_process_exec,
 	profiler_bpf_sched_process_exit,
 	profiler_bpf_sys_enter_kill,
-	profiler_bpf_do_filp_open_ret,
+	profiler_bpf_do_file_open_ret,
 	profiler_bpf_sched_process_fork,
 	profiler_bpf_vfs_link,
 	profiler_bpf_vfs_symlink,
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 813143b4985d..9044dd8aff11 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -751,11 +751,11 @@ out:
 	return 0;
 }
 
-SEC("kretprobe/do_filp_open")
-int kprobe_ret__do_filp_open(struct pt_regs* ctx)
+SEC("kretprobe/do_file_open")
+int kprobe_ret__do_file_open(struct pt_regs *ctx)
 {
 	struct bpf_func_stats_ctx stats_ctx;
-	bpf_stats_enter(&stats_ctx, profiler_bpf_do_filp_open_ret);
+	bpf_stats_enter(&stats_ctx, profiler_bpf_do_file_open_ret);
 
 	struct file* filp = (struct file*)PT_REGS_RC_CORE(ctx);
 
diff --git a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c
index df4873558634..189c05c6abcc 100644
--- a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c
+++ b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c
@@ -1,36 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <vmlinux.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
-struct task_ls_map {
-	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
-	__uint(map_flags, BPF_F_NO_PREALLOC);
-	__type(key, int);
-	__type(value, int);
-} task_ls_map SEC(".maps");
-
-long gp_seq;
+int done;
 
 SEC("syscall")
-int do_call_rcu_tasks_trace(void *ctx)
-{
-    struct task_struct *current;
-    int *v;
-
-    current = bpf_get_current_task_btf();
-    v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
-    if (!v)
-        return 1;
-    /* Invoke call_rcu_tasks_trace */
-    return bpf_task_storage_delete(&task_ls_map, current);
-}
-
-SEC("kprobe/rcu_tasks_trace_postgp")
-int rcu_tasks_trace_postgp(void *ctx)
+int call_rcu_tasks_trace(void *ctx)
 {
-    __sync_add_and_fetch(&gp_seq, 1);
-    return 0;
+	return bpf_kfunc_call_test_call_rcu_tasks_trace(&done);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index 0a0f371a2dec..fa73b17cb999 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -1,12 +1,12 @@
-#include <stdbool.h>
-#include <linux/bpf.h>
-#include <linux/errno.h>
-#include <linux/if_ether.h>
-#include <linux/pkt_cls.h>
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
 
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
+#include <errno.h>
+
 #include "bpf_kfuncs.h"
+#include "bpf_tracing_net.h"
 
 #define META_SIZE 32
 
@@ -42,7 +42,7 @@ static bool check_metadata(const char *file, int line, __u8 *meta_have)
 	if (!__builtin_memcmp(meta_have, meta_want, META_SIZE))
 		return true;
 
-	bpf_stream_printk(BPF_STREAM_STDERR,
+	bpf_stream_printk(BPF_STDERR,
 			  "FAIL:%s:%d: metadata mismatch\n"
 			  "  have:\n    %pI6\n    %pI6\n"
 			  "  want:\n    %pI6\n    %pI6\n",
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index 186a25ab429a..e62c6b78657f 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -18,6 +18,7 @@
 #include <linux/in6.h>
 #include <linux/un.h>
 #include <linux/filter.h>
+#include <linux/rcupdate_trace.h>
 #include <net/sock.h>
 #include <linux/namei.h>
 #include "bpf_testmod.h"
@@ -885,6 +886,32 @@ __bpf_kfunc void bpf_kfunc_call_test_sleepable(void)
 {
 }
 
+struct bpf_kfunc_rcu_tasks_trace_data {
+	struct rcu_head rcu;
+	int *done;
+};
+
+static void bpf_kfunc_rcu_tasks_trace_cb(struct rcu_head *rhp)
+{
+	struct bpf_kfunc_rcu_tasks_trace_data *data;
+
+	data = container_of(rhp, struct bpf_kfunc_rcu_tasks_trace_data, rcu);
+	WRITE_ONCE(*data->done, 1);
+	kfree(data);
+}
+
+__bpf_kfunc int bpf_kfunc_call_test_call_rcu_tasks_trace(int *done)
+{
+	struct bpf_kfunc_rcu_tasks_trace_data *data;
+
+	data = kmalloc(sizeof(*data), GFP_ATOMIC);
+	if (!data)
+		return -ENOMEM;
+	data->done = done;
+	call_rcu_tasks_trace(&data->rcu, bpf_kfunc_rcu_tasks_trace_cb);
+	return 0;
+}
+
 __bpf_kfunc int bpf_kfunc_init_sock(struct init_sock_args *args)
 {
 	int proto;
@@ -1222,6 +1249,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_sleepable, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_call_rcu_tasks_trace)
 BTF_ID_FLAGS(func, bpf_kfunc_init_sock, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_close_sock, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_connect, KF_SLEEPABLE)
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
index d5c5454e257e..b393bf771131 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
@@ -118,6 +118,7 @@ void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym;
 
 void bpf_kfunc_call_test_destructive(void) __ksym;
 void bpf_kfunc_call_test_sleepable(void) __ksym;
+int bpf_kfunc_call_test_call_rcu_tasks_trace(int *done) __ksym;
 
 void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p);
 struct prog_test_member *bpf_kfunc_call_memb_acquire(void);