bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO

This patch adds BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO
to support the function debug info.

BTF_KIND_FUNC_PROTO must not have a name (i.e. !t->name_off)
and it is followed by >= 0 'struct bpf_param' objects to
describe the function arguments.

The BTF_KIND_FUNC must have a valid name and it must
refer back to a BTF_KIND_FUNC_PROTO.

The above is the conclusion after the discussion between
Edward Cree, Alexei, Daniel, Yonghong and Martin.

By combining BTF_KIND_FUNC and BTF_LIND_FUNC_PROTO,
a complete function signature can be obtained.  It will be
used in the later patches to learn the function signature of
a running bpf program.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/uapi/linux/btf.h

@@ -40,7 +40,8 @@ struct btf_type {
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
 	 * "size" tells the size of the type it is describing.
 	 *
-	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+	 * FUNC and FUNC_PROTO.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -64,8 +65,10 @@ struct btf_type {
 #define BTF_KIND_VOLATILE	9	/* Volatile	*/
 #define BTF_KIND_CONST		10	/* Const	*/
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_MAX		11
-#define NR_BTF_KINDS		12
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
 	__u32	offset;	/* offset in bits */
 };
 
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+	__u32	name_off;
+	__u32	type;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

kernel/bpf/btf.c

@@ -5,6 +5,7 @@
 #include <uapi/linux/types.h>
 #include <linux/seq_file.h>
 #include <linux/compiler.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
@@ -259,6 +260,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VOLATILE]	= "VOLATILE",
 	[BTF_KIND_CONST]	= "CONST",
 	[BTF_KIND_RESTRICT]	= "RESTRICT",
+	[BTF_KIND_FUNC]		= "FUNC",
+	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
 };
 
 struct btf_kind_operations {
@@ -281,6 +284,9 @@ struct btf_kind_operations {
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
 static struct btf_type btf_void;
 
+static int btf_resolve(struct btf_verifier_env *env,
+		       const struct btf_type *t, u32 type_id);
+
 static bool btf_type_is_modifier(const struct btf_type *t)
 {
 	/* Some of them is not strictly a C modifier
@@ -314,9 +320,20 @@ static bool btf_type_is_fwd(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
 }
 
+static bool btf_type_is_func(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC;
+}
+
+static bool btf_type_is_func_proto(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
+}
+
 static bool btf_type_nosize(const struct btf_type *t)
 {
-	return btf_type_is_void(t) || btf_type_is_fwd(t);
+	return btf_type_is_void(t) || btf_type_is_fwd(t) ||
+	       btf_type_is_func(t) || btf_type_is_func_proto(t);
 }
 
 static bool btf_type_nosize_or_null(const struct btf_type *t)
@@ -433,6 +450,30 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 		offset < btf->hdr.str_len;
 }
 
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+	/* offset must be valid */
+	const char *src = &btf->strings[offset];
+	const char *src_limit;
+
+	if (!isalpha(*src) && *src != '_')
+		return false;
+
+	/* set a limit on identifier length */
+	src_limit = src + KSYM_NAME_LEN;
+	src++;
+	while (*src && src < src_limit) {
+		if (!isalnum(*src) && *src != '_')
+			return false;
+		src++;
+	}
+
+	return !*src;
+}
+
 static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
@@ -747,11 +788,15 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
 		/* int, enum or void is a sink */
 		return !btf_type_needs_resolve(next_type);
 	case RESOLVE_PTR:
-		/* int, enum, void, struct or array is a sink for ptr */
+		/* int, enum, void, struct, array, func or func_proto is a sink
+		 * for ptr
+		 */
 		return !btf_type_is_modifier(next_type) &&
 			!btf_type_is_ptr(next_type);
 	case RESOLVE_STRUCT_OR_ARRAY:
-		/* int, enum, void or ptr is a sink for struct and array */
+		/* int, enum, void, ptr, func or func_proto is a sink
+		 * for struct and array
+		 */
 		return !btf_type_is_modifier(next_type) &&
 			!btf_type_is_array(next_type) &&
 			!btf_type_is_struct(next_type);
@@ -1170,10 +1215,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* "typedef void new_void", "const void"...etc */
-	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
-		goto resolved;
-
 	if (!env_type_is_resolve_sink(env, next_type) &&
 	    !env_type_is_resolved(env, next_type_id))
 		return env_stack_push(env, next_type, next_type_id);
@@ -1184,13 +1225,18 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	 * save us a few type-following when we use it later (e.g. in
 	 * pretty print).
 	 */
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
-		btf_verifier_log_type(env, v->t, "Invalid type_id");
-		return -EINVAL;
+	if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+		if (env_type_is_resolved(env, next_type_id))
+			next_type = btf_type_id_resolve(btf, &next_type_id);
+
+		/* "typedef void new_void", "const void"...etc */
+		if (!btf_type_is_void(next_type) &&
+		    !btf_type_is_fwd(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid type_id");
+			return -EINVAL;
+		}
 	}
 
-resolved:
 	env_stack_pop_resolved(env, next_type_id, next_type_size);
 
 	return 0;
@@ -1203,7 +1249,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	const struct btf_type *t = v->t;
 	u32 next_type_id = t->type;
 	struct btf *btf = env->btf;
-	u32 next_type_size = 0;
 
 	next_type = btf_type_by_id(btf, next_type_id);
 	if (!next_type) {
@@ -1211,10 +1256,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* "void *" */
-	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
-		goto resolved;
-
 	if (!env_type_is_resolve_sink(env, next_type) &&
 	    !env_type_is_resolved(env, next_type_id))
 		return env_stack_push(env, next_type, next_type_id);
@@ -1241,13 +1282,18 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 					      resolved_type_id);
 	}
 
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
-		btf_verifier_log_type(env, v->t, "Invalid type_id");
-		return -EINVAL;
+	if (!btf_type_id_size(btf, &next_type_id, NULL)) {
+		if (env_type_is_resolved(env, next_type_id))
+			next_type = btf_type_id_resolve(btf, &next_type_id);
+
+		if (!btf_type_is_void(next_type) &&
+		    !btf_type_is_fwd(next_type) &&
+		    !btf_type_is_func_proto(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid type_id");
+			return -EINVAL;
+		}
 	}
 
-resolved:
 	env_stack_pop_resolved(env, next_type_id, 0);
 
 	return 0;
@@ -1787,6 +1833,232 @@ static struct btf_kind_operations enum_ops = {
 	.seq_show = btf_enum_seq_show,
 };
 
+static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
+				     const struct btf_type *t,
+				     u32 meta_left)
+{
+	u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (t->name_off) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static void btf_func_proto_log(struct btf_verifier_env *env,
+			       const struct btf_type *t)
+{
+	const struct btf_param *args = (const struct btf_param *)(t + 1);
+	u16 nr_args = btf_type_vlen(t), i;
+
+	btf_verifier_log(env, "return=%u args=(", t->type);
+	if (!nr_args) {
+		btf_verifier_log(env, "void");
+		goto done;
+	}
+
+	if (nr_args == 1 && !args[0].type) {
+		/* Only one vararg */
+		btf_verifier_log(env, "vararg");
+		goto done;
+	}
+
+	btf_verifier_log(env, "%u %s", args[0].type,
+			 btf_name_by_offset(env->btf,
+					    args[0].name_off));
+	for (i = 1; i < nr_args - 1; i++)
+		btf_verifier_log(env, ", %u %s", args[i].type,
+				 btf_name_by_offset(env->btf,
+						    args[i].name_off));
+
+	if (nr_args > 1) {
+		const struct btf_param *last_arg = &args[nr_args - 1];
+
+		if (last_arg->type)
+			btf_verifier_log(env, ", %u %s", last_arg->type,
+					 btf_name_by_offset(env->btf,
+							    last_arg->name_off));
+		else
+			btf_verifier_log(env, ", vararg");
+	}
+
+done:
+	btf_verifier_log(env, ")");
+}
+
+static struct btf_kind_operations func_proto_ops = {
+	.check_meta = btf_func_proto_check_meta,
+	.resolve = btf_df_resolve,
+	/*
+	 * BTF_KIND_FUNC_PROTO cannot be directly referred by
+	 * a struct's member.
+	 *
+	 * It should be a funciton pointer instead.
+	 * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO)
+	 *
+	 * Hence, there is no btf_func_check_member().
+	 */
+	.check_member = btf_df_check_member,
+	.log_details = btf_func_proto_log,
+	.seq_show = btf_df_seq_show,
+};
+
+static s32 btf_func_check_meta(struct btf_verifier_env *env,
+			       const struct btf_type *t,
+			       u32 meta_left)
+{
+	if (!t->name_off ||
+	    !btf_name_valid_identifier(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return 0;
+}
+
+static struct btf_kind_operations func_ops = {
+	.check_meta = btf_func_check_meta,
+	.resolve = btf_df_resolve,
+	.check_member = btf_df_check_member,
+	.log_details = btf_ref_type_log,
+	.seq_show = btf_df_seq_show,
+};
+
+static int btf_func_proto_check(struct btf_verifier_env *env,
+				const struct btf_type *t)
+{
+	const struct btf_type *ret_type;
+	const struct btf_param *args;
+	const struct btf *btf;
+	u16 nr_args, i;
+	int err;
+
+	btf = env->btf;
+	args = (const struct btf_param *)(t + 1);
+	nr_args = btf_type_vlen(t);
+
+	/* Check func return type which could be "void" (t->type == 0) */
+	if (t->type) {
+		u32 ret_type_id = t->type;
+
+		ret_type = btf_type_by_id(btf, ret_type_id);
+		if (!ret_type) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+
+		if (btf_type_needs_resolve(ret_type) &&
+		    !env_type_is_resolved(env, ret_type_id)) {
+			err = btf_resolve(env, ret_type, ret_type_id);
+			if (err)
+				return err;
+		}
+
+		/* Ensure the return type is a type that has a size */
+		if (!btf_type_id_size(btf, &ret_type_id, NULL)) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+	}
+
+	if (!nr_args)
+		return 0;
+
+	/* Last func arg type_id could be 0 if it is a vararg */
+	if (!args[nr_args - 1].type) {
+		if (args[nr_args - 1].name_off) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u",
+					      nr_args);
+			return -EINVAL;
+		}
+		nr_args--;
+	}
+
+	err = 0;
+	for (i = 0; i < nr_args; i++) {
+		const struct btf_type *arg_type;
+		u32 arg_type_id;
+
+		arg_type_id = args[i].type;
+		arg_type = btf_type_by_id(btf, arg_type_id);
+		if (!arg_type) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+
+		if (args[i].name_off &&
+		    (!btf_name_offset_valid(btf, args[i].name_off) ||
+		     !btf_name_valid_identifier(btf, args[i].name_off))) {
+			btf_verifier_log_type(env, t,
+					      "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+
+		if (btf_type_needs_resolve(arg_type) &&
+		    !env_type_is_resolved(env, arg_type_id)) {
+			err = btf_resolve(env, arg_type, arg_type_id);
+			if (err)
+				break;
+		}
+
+		if (!btf_type_id_size(btf, &arg_type_id, NULL)) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int btf_func_check(struct btf_verifier_env *env,
+			  const struct btf_type *t)
+{
+	const struct btf_type *proto_type;
+	const struct btf_param *args;
+	const struct btf *btf;
+	u16 nr_args, i;
+
+	btf = env->btf;
+	proto_type = btf_type_by_id(btf, t->type);
+
+	if (!proto_type || !btf_type_is_func_proto(proto_type)) {
+		btf_verifier_log_type(env, t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	args = (const struct btf_param *)(proto_type + 1);
+	nr_args = btf_type_vlen(proto_type);
+	for (i = 0; i < nr_args; i++) {
+		if (!args[i].name_off && args[i].type) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_INT] = &int_ops,
 	[BTF_KIND_PTR] = &ptr_ops,
@@ -1799,6 +2071,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_VOLATILE] = &modifier_ops,
 	[BTF_KIND_CONST] = &modifier_ops,
 	[BTF_KIND_RESTRICT] = &modifier_ops,
+	[BTF_KIND_FUNC] = &func_ops,
+	[BTF_KIND_FUNC_PROTO] = &func_proto_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -1870,30 +2144,6 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
 	return 0;
 }
 
-static int btf_resolve(struct btf_verifier_env *env,
-		       const struct btf_type *t, u32 type_id)
-{
-	const struct resolve_vertex *v;
-	int err = 0;
-
-	env->resolve_mode = RESOLVE_TBD;
-	env_stack_push(env, t, type_id);
-	while (!err && (v = env_stack_peak(env))) {
-		env->log_type_id = v->type_id;
-		err = btf_type_ops(v->t)->resolve(env, v);
-	}
-
-	env->log_type_id = type_id;
-	if (err == -E2BIG)
-		btf_verifier_log_type(env, t,
-				      "Exceeded max resolving depth:%u",
-				      MAX_RESOLVE_DEPTH);
-	else if (err == -EEXIST)
-		btf_verifier_log_type(env, t, "Loop detected");
-
-	return err;
-}
-
 static bool btf_resolve_valid(struct btf_verifier_env *env,
 			      const struct btf_type *t,
 			      u32 type_id)
@@ -1927,6 +2177,39 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
 	return false;
 }
 
+static int btf_resolve(struct btf_verifier_env *env,
+		       const struct btf_type *t, u32 type_id)
+{
+	u32 save_log_type_id = env->log_type_id;
+	const struct resolve_vertex *v;
+	int err = 0;
+
+	env->resolve_mode = RESOLVE_TBD;
+	env_stack_push(env, t, type_id);
+	while (!err && (v = env_stack_peak(env))) {
+		env->log_type_id = v->type_id;
+		err = btf_type_ops(v->t)->resolve(env, v);
+	}
+
+	env->log_type_id = type_id;
+	if (err == -E2BIG) {
+		btf_verifier_log_type(env, t,
+				      "Exceeded max resolving depth:%u",
+				      MAX_RESOLVE_DEPTH);
+	} else if (err == -EEXIST) {
+		btf_verifier_log_type(env, t, "Loop detected");
+	}
+
+	/* Final sanity check */
+	if (!err && !btf_resolve_valid(env, t, type_id)) {
+		btf_verifier_log_type(env, t, "Invalid resolve state");
+		err = -EINVAL;
+	}
+
+	env->log_type_id = save_log_type_id;
+	return err;
+}
+
 static int btf_check_all_types(struct btf_verifier_env *env)
 {
 	struct btf *btf = env->btf;
@@ -1949,10 +2232,16 @@ static int btf_check_all_types(struct btf_verifier_env *env)
 				return err;
 		}
 
-		if (btf_type_needs_resolve(t) &&
-		    !btf_resolve_valid(env, t, type_id)) {
-			btf_verifier_log_type(env, t, "Invalid resolve state");
-			return -EINVAL;
+		if (btf_type_is_func_proto(t)) {
+			err = btf_func_proto_check(env, t);
+			if (err)
+				return err;
+		}
+
+		if (btf_type_is_func(t)) {
+			err = btf_func_check(env, t);
+			if (err)
+				return err;
 		}
 	}