diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index c06096d..2e586f5 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -504,7 +504,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	u8 *prog;
 	int ret;
 
-	if (!is_kernel_text((long)ip))
+	if (!is_kernel_text((long)ip) &&
+	    !is_bpf_text_address((long)ip))
 		/* BPF trampoline in modules is not supported */
 		return -EINVAL;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c70bf04..5b81cde 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -495,6 +495,7 @@ struct bpf_prog_aux {
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+	struct bpf_prog *linked_prog;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 9dee008..79d4abc 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -88,6 +88,7 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
+struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 69c200e..4842a13 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -425,6 +425,7 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
+		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4620267..40efde5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3530,6 +3530,20 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 	return ctx_type;
 }
 
+static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
+				     struct btf *btf,
+				     const struct btf_type *t,
+				     enum bpf_prog_type prog_type)
+{
+	const struct btf_member *prog_ctx_type, *kern_ctx_type;
+
+	prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type);
+	if (!prog_ctx_type)
+		return -ENOENT;
+	kern_ctx_type = prog_ctx_type + 1;
+	return kern_ctx_type->type;
+}
+
 struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
@@ -3602,15 +3616,29 @@ struct btf *btf_parse_vmlinux(void)
 	return ERR_PTR(err);
 }
 
+struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
+{
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+
+	if (tgt_prog) {
+		return tgt_prog->aux->btf;
+	} else {
+		return btf_vmlinux;
+	}
+}
+
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
 {
 	const struct btf_type *t = prog->aux->attach_func_proto;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct btf *btf = bpf_prog_get_target_btf(prog);
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
 	const struct btf_param *args;
 	u32 nr_args, arg;
+	int ret;
 
 	if (off % 8) {
 		bpf_log(log, "func '%s' offset %d is not multiple of 8\n",
@@ -3619,7 +3647,8 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	}
 	arg = off / 8;
 	args = (const struct btf_param *)(t + 1);
-	nr_args = btf_type_vlen(t);
+	/* if (t == NULL) Fall back to default BPF prog with 5 u64 arguments */
+	nr_args = t ? btf_type_vlen(t) : 5;
 	if (prog->aux->attach_btf_trace) {
 		/* skip first 'void *__data' argument in btf_trace_##name typedef */
 		args++;
@@ -3628,18 +3657,24 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 	if (prog->expected_attach_type == BPF_TRACE_FEXIT &&
 	    arg == nr_args) {
+		if (!t)
+			/* Default prog with 5 args. 6th arg is retval. */
+			return true;
 		/* function return type */
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	} else if (arg >= nr_args) {
 		bpf_log(log, "func '%s' doesn't have %d-th argument\n",
 			tname, arg + 1);
 		return false;
 	} else {
-		t = btf_type_by_id(btf_vmlinux, args[arg].type);
+		if (!t)
+			/* Default prog with 5 args */
+			return true;
+		t = btf_type_by_id(btf, args[arg].type);
 	}
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	if (btf_type_is_int(t))
 		/* accessing a scalar */
 		return true;
@@ -3647,7 +3682,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		bpf_log(log,
 			"func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
 			tname, arg,
-			__btf_name_by_offset(btf_vmlinux, t->name_off),
+			__btf_name_by_offset(btf, t->name_off),
 			btf_kind_str[BTF_INFO_KIND(t->info)]);
 		return false;
 	}
@@ -3662,10 +3697,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	info->reg_type = PTR_TO_BTF_ID;
 	info->btf_id = t->type;
 
-	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (tgt_prog) {
+		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type);
+		if (ret > 0) {
+			info->btf_id = ret;
+			return true;
+		} else {
+			return false;
+		}
+	}
+	t = btf_type_by_id(btf, t->type);
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log,
 			"func '%s' arg%d type %s is not a struct\n",
@@ -3674,7 +3718,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	}
 	bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n",
 		tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)],
-		__btf_name_by_offset(btf_vmlinux, t->name_off));
+		__btf_name_by_offset(btf, t->name_off));
 	return true;
 }
 
@@ -3954,6 +3998,16 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 	u32 i, nargs;
 	int ret;
 
+	if (!func) {
+		/* BTF function prototype doesn't match the verifier types.
+		 * Fall back to 5 u64 args.
+		 */
+		for (i = 0; i < 5; i++)
+			m->arg_size[i] = 8;
+		m->ret_size = 8;
+		m->nr_args = 5;
+		return 0;
+	}
 	args = (const struct btf_param *)(func + 1);
 	nargs = btf_type_vlen(func);
 	if (nargs >= MAX_BPF_FUNC_ARGS) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 75ad0f9..2e319e4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2027,6 +2027,8 @@ void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
 
+	if (aux->linked_prog)
+		bpf_prog_put(aux->linked_prog);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 43ba647..c88c815 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1577,7 +1577,7 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 static int
 bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   enum bpf_attach_type expected_attach_type,
-			   u32 btf_id)
+			   u32 btf_id, u32 prog_fd)
 {
 	switch (prog_type) {
 	case BPF_PROG_TYPE_TRACING:
@@ -1585,7 +1585,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			return -EINVAL;
 		break;
 	default:
-		if (btf_id)
+		if (btf_id || prog_fd)
 			return -EINVAL;
 		break;
 	}
@@ -1636,7 +1636,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD attach_btf_id
+#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1679,7 +1679,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
-				       attr->attach_btf_id))
+				       attr->attach_btf_id,
+				       attr->attach_prog_fd))
 		return -EINVAL;
 
 	/* plain bpf_prog allocation */
@@ -1689,6 +1690,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
+	if (attr->attach_prog_fd) {
+		struct bpf_prog *tgt_prog;
+
+		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			goto free_prog_nouncharge;
+		}
+		prog->aux->linked_prog = tgt_prog;
+	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1191014..e9dc95a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9390,13 +9390,17 @@ static void print_verification_stats(struct bpf_verifier_env *env)
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
+	int ret = 0, subprog = -1, i;
 	struct bpf_trampoline *tr;
 	const struct btf_type *t;
+	bool conservative = true;
 	const char *tname;
-	int ret = 0;
+	struct btf *btf;
 	long addr;
+	u64 key;
 
 	if (prog->type != BPF_PROG_TYPE_TRACING)
 		return 0;
@@ -9405,19 +9409,47 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		verbose(env, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	t = btf_type_by_id(btf_vmlinux, btf_id);
+	btf = bpf_prog_get_target_btf(prog);
+	if (!btf) {
+		verbose(env,
+			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
+		return -EINVAL;
+	}
+	t = btf_type_by_id(btf, btf_id);
 	if (!t) {
 		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
 		return -EINVAL;
 	}
-	tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname) {
 		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
 		return -EINVAL;
 	}
+	if (tgt_prog) {
+		struct bpf_prog_aux *aux = tgt_prog->aux;
+
+		for (i = 0; i < aux->func_info_cnt; i++)
+			if (aux->func_info[i].type_id == btf_id) {
+				subprog = i;
+				break;
+			}
+		if (subprog == -1) {
+			verbose(env, "Subprog %s doesn't exist\n", tname);
+			return -EINVAL;
+		}
+		conservative = aux->func_info_aux[subprog].unreliable;
+		key = ((u64)aux->id) << 32 | btf_id;
+	} else {
+		key = btf_id;
+	}
 
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_RAW_TP:
+		if (tgt_prog) {
+			verbose(env,
+				"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
+			return -EINVAL;
+		}
 		if (!btf_type_is_typedef(t)) {
 			verbose(env, "attach_btf_id %u is not a typedef\n",
 				btf_id);
@@ -9429,11 +9461,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 		tname += sizeof(prefix) - 1;
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_ptr(t))
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
@@ -9452,30 +9484,51 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				btf_id);
 			return -EINVAL;
 		}
-		t = btf_type_by_id(btf_vmlinux, t->type);
+		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		tr = bpf_trampoline_lookup(btf_id);
+		tr = bpf_trampoline_lookup(key);
 		if (!tr)
 			return -ENOMEM;
 		prog->aux->attach_func_name = tname;
+		/* t is either vmlinux type or another program's type */
 		prog->aux->attach_func_proto = t;
 		mutex_lock(&tr->mutex);
 		if (tr->func.addr) {
 			prog->aux->trampoline = tr;
 			goto out;
 		}
-		ret = btf_distill_func_proto(&env->log, btf_vmlinux, t,
+		if (tgt_prog && conservative) {
+			prog->aux->attach_func_proto = NULL;
+			t = NULL;
+		}
+		ret = btf_distill_func_proto(&env->log, btf, t,
 					     tname, &tr->func.model);
 		if (ret < 0)
 			goto out;
-		addr = kallsyms_lookup_name(tname);
-		if (!addr) {
-			verbose(env,
-				"The address of function %s cannot be found\n",
-				tname);
-			ret = -ENOENT;
-			goto out;
+		if (tgt_prog) {
+			if (!tgt_prog->jited) {
+				/* for now */
+				verbose(env, "Can trace only JITed BPF progs\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (tgt_prog->type == BPF_PROG_TYPE_TRACING) {
+				/* prevent cycles */
+				verbose(env, "Cannot recursively attach\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
+		} else {
+			addr = kallsyms_lookup_name(tname);
+			if (!addr) {
+				verbose(env,
+					"The address of function %s cannot be found\n",
+					tname);
+				ret = -ENOENT;
+				goto out;
+			}
 		}
 		tr->func.addr = (void *)addr;
 		prog->aux->trampoline = tr;