Merge branch 'Support kernel module ksym variables'

Andrii Nakryiko says:

====================

Add support for using kernel module global variables (__ksym externs in BPF
program). BPF verifier will now support ldimm64 with src_reg=BPF_PSEUDO_BTF_ID
and non-zero insn[1].imm field, specifying module BTF's FD. In such case,
module BTF object, similarly to BPF maps referenced from ldimm64 with
src_reg=BPF_PSEUDO_MAP_FD, will be recorded in bpf_progran's auxiliary data
and refcnt will be increased for both BTF object itself and its kernel module.
This makes sure kernel module won't be unloaded from under active attached BPF
program. These refcounts will be dropped when BPF program is unloaded.

New selftest validates all this is working as intended. bpf_testmod.ko is
extended with per-CPU variable. Selftests expects the latest pahole changes
(soon to be released as v1.20) to generate per-CPU variable BTF info for
kernel module.

v2->v3:
  - added comments, addressed feedack (Yonghong, Hao);
v1->v2:
  - fixed few compiler warnings, posted as separate pre-patches;
rfc->v1:
  - use sys_membarrier(MEMBARRIER_CMD_GLOBAL) (Alexei).

Cc: Hao Luo <haoluo@google.com>
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

14 files changed, 305 insertions, 84 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07cb5d15e743..1aac2af12fed 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -761,9 +761,15 @@ struct bpf_ctx_arg_aux {
 	u32 btf_id;
 };
 
+struct btf_mod_pair {
+	struct btf *btf;
+	struct module *module;
+};
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
+	u32 used_btf_cnt;
 	u32 max_ctx_offset;
 	u32 max_pkt_offset;
 	u32 max_tp_access;
@@ -802,6 +808,7 @@ struct bpf_prog_aux {
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
 	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
+	struct btf_mod_pair *used_btfs;
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
@@ -1206,8 +1213,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i);
 void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-void __bpf_free_used_maps(struct bpf_prog_aux *aux,
-			  struct bpf_map **used_maps, u32 len);
 
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
@@ -1403,7 +1408,10 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
 	      union bpf_attr __user *uattr);
+
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+#endif
 
 struct btf *bpf_get_btf_vmlinux(void);
 
@@ -1667,12 +1675,18 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
+void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
+			  struct btf_mod_pair *used_btfs, u32 len);
+
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
 						 enum bpf_prog_type type)
 {
 	return bpf_prog_get_type_dev(ufd, type, false);
 }
 
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+			  struct bpf_map **used_maps, u32 len);
+
 bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
 
 int bpf_prog_offload_compile(struct bpf_prog *prog);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e941fe1484e5..dfe6f85d97dd 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -340,6 +340,7 @@ struct bpf_insn_aux_data {
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
+#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */
 
 #define BPF_VERIFIER_TMP_LOG_SIZE	1024
 
@@ -398,7 +399,9 @@ struct bpf_verifier_env {
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
+	struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */
 	u32 used_map_cnt;		/* number of used maps */
+	u32 used_btf_cnt;		/* number of used BTF objects */
 	u32 id_gen;			/* used to generate unique reg IDs */
 	bool allow_ptr_leaks;
 	bool allow_ptr_to_map_access;
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 4c200f5d242b..7fabf1428093 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -91,6 +91,9 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
 int btf_get_fd_by_id(u32 id);
 u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
+bool btf_is_module(const struct btf *btf);
+struct module *btf_try_get_module(const struct btf *btf);
+u32 btf_nr_types(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 29c27656165b..5edf2b660881 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -886,7 +886,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 #define __bpf_call_base_args \
 	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
-	 __bpf_call_base)
+	 (void *)__bpf_call_base)
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 8d6bdb4f4d61..7ccc0133723a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -458,7 +458,7 @@ static bool btf_type_is_datasec(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
 }
 
-static u32 btf_nr_types_total(const struct btf *btf)
+u32 btf_nr_types(const struct btf *btf)
 {
 	u32 total = 0;
 
@@ -476,7 +476,7 @@ s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
 	const char *tname;
 	u32 i, total;
 
-	total = btf_nr_types_total(btf);
+	total = btf_nr_types(btf);
 	for (i = 1; i < total; i++) {
 		t = btf_type_by_id(btf, i);
 		if (BTF_INFO_KIND(t->info) != kind)
@@ -5743,6 +5743,11 @@ bool btf_is_kernel(const struct btf *btf)
 	return btf->kernel_btf;
 }
 
+bool btf_is_module(const struct btf *btf)
+{
+	return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0;
+}
+
 static int btf_id_cmp_func(const void *a, const void *b)
 {
 	const int *pa = a, *pb = b;
@@ -5877,3 +5882,25 @@ static int __init btf_module_init(void)
 
 fs_initcall(btf_module_init);
 #endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
+
+struct module *btf_try_get_module(const struct btf *btf)
+{
+	struct module *res = NULL;
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+	struct btf_module *btf_mod, *tmp;
+
+	mutex_lock(&btf_module_mutex);
+	list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+		if (btf_mod->btf != btf)
+			continue;
+
+		if (try_module_get(btf_mod->module))
+			res = btf_mod->module;
+
+		break;
+	}
+	mutex_unlock(&btf_module_mutex);
+#endif
+
+	return res;
+}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 261f8692d0d2..69c3c308de5e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2119,6 +2119,28 @@ static void bpf_free_used_maps(struct bpf_prog_aux *aux)
 	kfree(aux->used_maps);
 }
 
+void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
+			  struct btf_mod_pair *used_btfs, u32 len)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	struct btf_mod_pair *btf_mod;
+	u32 i;
+
+	for (i = 0; i < len; i++) {
+		btf_mod = &used_btfs[i];
+		if (btf_mod->module)
+			module_put(btf_mod->module);
+		btf_put(btf_mod->btf);
+	}
+#endif
+}
+
+static void bpf_free_used_btfs(struct bpf_prog_aux *aux)
+{
+	__bpf_free_used_btfs(aux, aux->used_btfs, aux->used_btf_cnt);
+	kfree(aux->used_btfs);
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;
@@ -2126,6 +2148,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 
 	aux = container_of(work, struct bpf_prog_aux, work);
 	bpf_free_used_maps(aux);
+	bpf_free_used_btfs(aux);
 	if (bpf_prog_is_dev_bound(aux))
 		bpf_prog_offload_destroy(aux->prog);
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5534e667bdb1..ae2aee48cf82 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9703,6 +9703,36 @@ process_bpf_exit:
 	return 0;
 }
 
+static int find_btf_percpu_datasec(struct btf *btf)
+{
+	const struct btf_type *t;
+	const char *tname;
+	int i, n;
+
+	/*
+	 * Both vmlinux and module each have their own ".data..percpu"
+	 * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF
+	 * types to look at only module's own BTF types.
+	 */
+	n = btf_nr_types(btf);
+	if (btf_is_module(btf))
+		i = btf_nr_types(btf_vmlinux);
+	else
+		i = 1;
+
+	for(; i < n; i++) {
+		t = btf_type_by_id(btf, i);
+		if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
+			continue;
+
+		tname = btf_name_by_offset(btf, t->name_off);
+		if (!strcmp(tname, ".data..percpu"))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
 /* replace pseudo btf_id with kernel symbol address */
 static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			       struct bpf_insn *insn,
@@ -9710,48 +9740,57 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 {
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *datasec;
+	struct btf_mod_pair *btf_mod;
 	const struct btf_type *t;
 	const char *sym_name;
 	bool percpu = false;
 	u32 type, id = insn->imm;
+	struct btf *btf;
 	s32 datasec_id;
 	u64 addr;
-	int i;
-
-	if (!btf_vmlinux) {
-		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
-		return -EINVAL;
-	}
+	int i, btf_fd, err;
 
-	if (insn[1].imm != 0) {
-		verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
-		return -EINVAL;
+	btf_fd = insn[1].imm;
+	if (btf_fd) {
+		btf = btf_get_by_fd(btf_fd);
+		if (IS_ERR(btf)) {
+			verbose(env, "invalid module BTF object FD specified.\n");
+			return -EINVAL;
+		}
+	} else {
+		if (!btf_vmlinux) {
+			verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+			return -EINVAL;
+		}
+		btf = btf_vmlinux;
+		btf_get(btf);
 	}
 
-	t = btf_type_by_id(btf_vmlinux, id);
+	t = btf_type_by_id(btf, id);
 	if (!t) {
 		verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
-		return -ENOENT;
+		err = -ENOENT;
+		goto err_put;
 	}
 
 	if (!btf_type_is_var(t)) {
-		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
-			id);
-		return -EINVAL;
+		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id);
+		err = -EINVAL;
+		goto err_put;
 	}
 
-	sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+	sym_name = btf_name_by_offset(btf, t->name_off);
 	addr = kallsyms_lookup_name(sym_name);
 	if (!addr) {
 		verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
 			sym_name);
-		return -ENOENT;
+		err = -ENOENT;
+		goto err_put;
 	}
 
-	datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
-					   BTF_KIND_DATASEC);
+	datasec_id = find_btf_percpu_datasec(btf);
 	if (datasec_id > 0) {
-		datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+		datasec = btf_type_by_id(btf, datasec_id);
 		for_each_vsi(i, datasec, vsi) {
 			if (vsi->type == id) {
 				percpu = true;
@@ -9764,10 +9803,10 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 	insn[1].imm = addr >> 32;
 
 	type = t->type;
-	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+	t = btf_type_skip_modifiers(btf, type, NULL);
 	if (percpu) {
 		aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
-		aux->btf_var.btf = btf_vmlinux;
+		aux->btf_var.btf = btf;
 		aux->btf_var.btf_id = type;
 	} else if (!btf_type_is_struct(t)) {
 		const struct btf_type *ret;
@@ -9775,21 +9814,54 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 		u32 tsize;
 
 		/* resolve the type size of ksym. */
-		ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+		ret = btf_resolve_size(btf, t, &tsize);
 		if (IS_ERR(ret)) {
-			tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+			tname = btf_name_by_offset(btf, t->name_off);
 			verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
 				tname, PTR_ERR(ret));
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_put;
 		}
 		aux->btf_var.reg_type = PTR_TO_MEM;
 		aux->btf_var.mem_size = tsize;
 	} else {
 		aux->btf_var.reg_type = PTR_TO_BTF_ID;
-		aux->btf_var.btf = btf_vmlinux;
+		aux->btf_var.btf = btf;
 		aux->btf_var.btf_id = type;
 	}
+
+	/* 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) {
+			btf_put(btf);
+			return 0;
+		}
+	}
+
+	if (env->used_btf_cnt >= MAX_USED_BTFS) {
+		err = -E2BIG;
+		goto err_put;
+	}
+
+	btf_mod = &env->used_btfs[env->used_btf_cnt];
+	btf_mod->btf = btf;
+	btf_mod->module = NULL;
+
+	/* if we reference variables from kernel module, bump its refcount */
+	if (btf_is_module(btf)) {
+		btf_mod->module = btf_try_get_module(btf);
+		if (!btf_mod->module) {
+			err = -ENXIO;
+			goto err_put;
+		}
+	}
+
+	env->used_btf_cnt++;
+
 	return 0;
+err_put:
+	btf_put(btf);
+	return err;
 }
 
 static int check_map_prealloc(struct bpf_map *map)
@@ -10086,6 +10158,13 @@ static void release_maps(struct bpf_verifier_env *env)
 			     env->used_map_cnt);
 }
 
+/* drop refcnt of maps used by the rejected program */
+static void release_btfs(struct bpf_verifier_env *env)
+{
+	__bpf_free_used_btfs(env->prog->aux, env->used_btfs,
+			     env->used_btf_cnt);
+}
+
 /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
 static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
 {
@@ -12098,7 +12177,10 @@ skip_full_check:
 		goto err_release_maps;
 	}
 
-	if (ret == 0 && env->used_map_cnt) {
+	if (ret)
+		goto err_release_maps;
+
+	if (env->used_map_cnt) {
 		/* if program passed verifier, update used_maps in bpf_prog_info */
 		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
 							  sizeof(env->used_maps[0]),
@@ -12112,15 +12194,29 @@ skip_full_check:
 		memcpy(env->prog->aux->used_maps, env->used_maps,
 		       sizeof(env->used_maps[0]) * env->used_map_cnt);
 		env->prog->aux->used_map_cnt = env->used_map_cnt;
+	}
+	if (env->used_btf_cnt) {
+		/* if program passed verifier, update used_btfs in bpf_prog_aux */
+		env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt,
+							  sizeof(env->used_btfs[0]),
+							  GFP_KERNEL);
+		if (!env->prog->aux->used_btfs) {
+			ret = -ENOMEM;
+			goto err_release_maps;
+		}
 
+		memcpy(env->prog->aux->used_btfs, env->used_btfs,
+		       sizeof(env->used_btfs[0]) * env->used_btf_cnt);
+		env->prog->aux->used_btf_cnt = env->used_btf_cnt;
+	}
+	if (env->used_map_cnt || env->used_btf_cnt) {
 		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
 		 * bpf_ld_imm64 instructions
 		 */
 		convert_pseudo_ld_imm64(env);
 	}
 
-	if (ret == 0)
-		adjust_btf_func(env);
+	adjust_btf_func(env);
 
 err_release_maps:
 	if (!env->prog->aux->used_maps)
@@ -12128,6 +12224,8 @@ err_release_maps:
 		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
+	if (!env->prog->aux->used_btfs)
+		release_btfs(env);
 
 	/* extension progs temporarily inherit the attach_type of their targets
 	   for verification purposes, so set it back to zero before returning
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6ae748f6ea11..2abbc3800568 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -395,7 +395,8 @@ struct extern_desc {
 			unsigned long long addr;
 
 			/* target btf_id of the corresponding kernel var. */
-			int vmlinux_btf_id;
+			int kernel_btf_obj_fd;
+			int kernel_btf_id;
 
 			/* local btf_id of the ksym extern's type. */
 			__u32 type_id;
@@ -6162,7 +6163,8 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			} else /* EXT_KSYM */ {
 				if (ext->ksym.type_id) { /* typed ksyms */
 					insn[0].src_reg = BPF_PSEUDO_BTF_ID;
-					insn[0].imm = ext->ksym.vmlinux_btf_id;
+					insn[0].imm = ext->ksym.kernel_btf_id;
+					insn[1].imm = ext->ksym.kernel_btf_obj_fd;
 				} else { /* typeless ksyms */
 					insn[0].imm = (__u32)ext->ksym.addr;
 					insn[1].imm = ext->ksym.addr >> 32;
@@ -7319,7 +7321,8 @@ out:
 static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 {
 	struct extern_desc *ext;
-	int i, id;
+	struct btf *btf;
+	int i, j, id, btf_fd, err;
 
 	for (i = 0; i < obj->nr_extern; i++) {
 		const struct btf_type *targ_var, *targ_type;
@@ -7331,10 +7334,25 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		if (ext->type != EXT_KSYM || !ext->ksym.type_id)
 			continue;
 
-		id = btf__find_by_name_kind(obj->btf_vmlinux, ext->name,
-					    BTF_KIND_VAR);
+		btf = obj->btf_vmlinux;
+		btf_fd = 0;
+		id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
+		if (id == -ENOENT) {
+			err = load_module_btfs(obj);
+			if (err)
+				return err;
+
+			for (j = 0; j < obj->btf_module_cnt; j++) {
+				btf = obj->btf_modules[j].btf;
+				/* we assume module BTF FD is always >0 */
+				btf_fd = obj->btf_modules[j].fd;
+				id = btf__find_by_name_kind(btf, ext->name, BTF_KIND_VAR);
+				if (id != -ENOENT)
+					break;
+			}
+		}
 		if (id <= 0) {
-			pr_warn("extern (ksym) '%s': failed to find BTF ID in vmlinux BTF.\n",
+			pr_warn("extern (ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
 				ext->name);
 			return -ESRCH;
 		}
@@ -7343,24 +7361,19 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		local_type_id = ext->ksym.type_id;
 
 		/* find target type_id */
-		targ_var = btf__type_by_id(obj->btf_vmlinux, id);
-		targ_var_name = btf__name_by_offset(obj->btf_vmlinux,
-						    targ_var->name_off);
-		targ_type = skip_mods_and_typedefs(obj->btf_vmlinux,
-						   targ_var->type,
-						   &targ_type_id);
+		targ_var = btf__type_by_id(btf, id);
+		targ_var_name = btf__name_by_offset(btf, targ_var->name_off);
+		targ_type = skip_mods_and_typedefs(btf, targ_var->type, &targ_type_id);
 
 		ret = bpf_core_types_are_compat(obj->btf, local_type_id,
-						obj->btf_vmlinux, targ_type_id);
+						btf, targ_type_id);
 		if (ret <= 0) {
 			const struct btf_type *local_type;
 			const char *targ_name, *local_name;
 
 			local_type = btf__type_by_id(obj->btf, local_type_id);
-			local_name = btf__name_by_offset(obj->btf,
-							 local_type->name_off);
-			targ_name = btf__name_by_offset(obj->btf_vmlinux,
-							targ_type->name_off);
+			local_name = btf__name_by_offset(obj->btf, local_type->name_off);
+			targ_name = btf__name_by_offset(btf, targ_type->name_off);
 
 			pr_warn("extern (ksym) '%s': incompatible types, expected [%d] %s %s, but kernel has [%d] %s %s\n",
 				ext->name, local_type_id,
@@ -7370,7 +7383,8 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		}
 
 		ext->is_set = true;
-		ext->ksym.vmlinux_btf_id = id;
+		ext->ksym.kernel_btf_obj_fd = btf_fd;
+		ext->ksym.kernel_btf_id = id;
 		pr_debug("extern (ksym) '%s': resolved to [%d] %s %s\n",
 			 ext->name, id, btf_kind_str(targ_var), targ_var_name);
 	}
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 2df19d73ca49..0b991e115d1f 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -3,6 +3,7 @@
 #include <linux/error-injection.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/percpu-defs.h>
 #include <linux/sysfs.h>
 #include <linux/tracepoint.h>
 #include "bpf_testmod.h"
@@ -10,6 +11,8 @@
 #define CREATE_TRACE_POINTS
 #include "bpf_testmod-events.h"
 
+DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
+
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		      struct bin_attribute *bin_attr,
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index 76ebe4c250f1..eb90a6b8850d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -20,39 +20,6 @@ static __u32 bpf_map_id(struct bpf_map *map)
 	return info.id;
 }
 
-/*
- * Trigger synchronize_rcu() in kernel.
- *
- * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu()
- * if looking up an existing non-NULL element or updating the map with a valid
- * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map,
- * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then
- * cleanup. At the end, at least one synchronize_rcu() would be called.
- */
-static int kern_sync_rcu(void)
-{
-	int inner_map_fd, outer_map_fd, err, zero = 0;
-
-	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
-	if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno))
-		return -1;
-
-	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
-					     sizeof(int), inner_map_fd, 1, 0);
-	if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) {
-		close(inner_map_fd);
-		return -1;
-	}
-
-	err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0);
-	if (err)
-		err = -errno;
-	CHECK(err, "outer_map_update", "failed %d\n", err);
-	close(inner_map_fd);
-	close(outer_map_fd);
-	return err;
-}
-
 static void test_lookup_update(void)
 {
 	int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id;
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
new file mode 100644
index 000000000000..4c232b456479
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "test_ksyms_module.skel.h"
+
+static int duration;
+
+void test_ksyms_module(void)
+{
+	struct test_ksyms_module* skel;
+	int err;
+
+	skel = test_ksyms_module__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	err = test_ksyms_module__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->triggered, true, "triggered");
+	ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val");
+
+cleanup:
+	test_ksyms_module__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c
new file mode 100644
index 000000000000..d6a0b3086b90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+extern const int bpf_testmod_ksym_percpu __ksym;
+
+int out_mod_ksym_global = 0;
+bool triggered = false;
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	int *val;
+	__u32 cpu;
+
+	val = (int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu);
+	out_mod_ksym_global = *val;
+	triggered = true;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 7d077d48cadd..213628ee721c 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -11,6 +11,7 @@
 #include <signal.h>
 #include <string.h>
 #include <execinfo.h> /* backtrace */
+#include <linux/membarrier.h>
 
 #define EXIT_NO_TEST		2
 #define EXIT_ERR_SETUP_INFRA	3
@@ -370,8 +371,18 @@ static int delete_module(const char *name, int flags)
 	return syscall(__NR_delete_module, name, flags);
 }
 
+/*
+ * Trigger synchronize_rcu() in kernel.
+ */
+int kern_sync_rcu(void)
+{
+	return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0);
+}
+
 static void unload_bpf_testmod(void)
 {
+	if (kern_sync_rcu())
+		fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n");
 	if (delete_module("bpf_testmod", 0)) {
 		if (errno == ENOENT) {
 			if (env.verbosity > VERBOSE_NONE)
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 115953243f62..e49e2fdde942 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -219,6 +219,7 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
 int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
+int kern_sync_rcu(void);
 
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"