Message-ID: <20181017233026.1071519-3-yhs@fb.com>
Date:   Wed, 17 Oct 2018 16:30:24 -0700
From:   Yonghong Song <yhs@...com>
To:     <ast@...com>, <kafai@...com>, <daniel@...earbox.net>,
        <netdev@...r.kernel.org>
CC:     <kernel-team@...com>
Subject: [PATCH bpf-next v3 02/13] bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO

This patch adds BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO
support to the type section. BTF_KIND_FUNC_PROTO is used
to specify the type of a function pointer. With this,
BTF has a complete set of C types (except float).

BTF_KIND_FUNC is used to specify the signature of a
defined subprogram. BTF_KIND_FUNC_PROTO can be referenced
by another type, e.g., a pointer type, and BTF_KIND_FUNC
type cannot be referenced by another type.

For both BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO types,
the func return type is in t->type (where t is a
"struct btf_type" object). The func args are an array of
u32s immediately following object "t".

As a concrete example, for the C program below,
  $ cat test.c
  int foo(int (*bar)(int)) { return bar(5); }
with LLVM patch https://reviews.llvm.org/D53261
in Debug mode, we have
  $ clang -target bpf -g -O2 -mllvm -debug-only=btf -c test.c
  Type Table:
  [1] FUNC NameOff=1 Info=0x0c000001 Size/Type=2
          ParamType=3
  [2] INT NameOff=11 Info=0x01000000 Size/Type=4
          Desc=0x01000020
  [3] PTR NameOff=0 Info=0x02000000 Size/Type=4
  [4] FUNC_PROTO NameOff=0 Info=0x0d000001 Size/Type=2
          ParamType=2

  String Table:
  0 :
  1 : foo
  5 : .text
  11 : int
  15 : test.c
  22 : int foo(int (*bar)(int)) { return bar(5); }

  FuncInfo Table:
  SecNameOff=5
          InsnOffset=<Omitted> TypeId=1

  ...

(Eventually we shall have bpftool to dump btf information
 like the above.)

Function "foo" has a FUNC type (type_id = 1).
The parameter of "foo" has type_id 3 which is PTR->FUNC_PROTO,
where FUNC_PROTO refers to function pointer "bar".

In FuncInfo Table, for section .text, the function,
with to-be-determined offset (marked as <Omitted>),
has type_id=1 which refers to a FUNC type.
This way, the function signature is
available to both kernel and user space.
Here, the insn offset is not available during the dump time
as relocation is resolved pretty late in the compilation process.

Signed-off-by: Martin KaFai Lau <kafai@...com>
Signed-off-by: Yonghong Song <yhs@...com>
---
 include/uapi/linux/btf.h |   9 +-
 kernel/bpf/btf.c         | 280 ++++++++++++++++++++++++++++++++++-----
 2 files changed, 253 insertions(+), 36 deletions(-)

diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 972265f32871..63f8500e6f34 100644
--- a/include/uapi/linux/btf.h
+++ b/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 Prototype	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index be406d8906ce..763f8e06bc91 100644
--- a/kernel/bpf/btf.c
+++ b/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 +450,27 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 		offset < btf->hdr.str_len;
 }
 
+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)
@@ -747,7 +785,9 @@ 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 or func_ptoto is a sink
+		 * for ptr
+		 */
 		return !btf_type_is_modifier(next_type) &&
 			!btf_type_is_ptr(next_type);
 	case RESOLVE_STRUCT_OR_ARRAY:
@@ -1170,6 +1210,14 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_is_func_proto(next_type)) {
+		if (env->resolve_mode == RESOLVE_PTR)
+			goto resolved;
+
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
 	/* "typedef void new_void", "const void"...etc */
 	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
 		goto resolved;
@@ -1185,7 +1233,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	 * 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_type_nosize(btf_type_id_resolve(btf, &next_type_id)) ||
+	     btf_type_is_func(next_type))) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1212,7 +1261,8 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	}
 
 	/* "void *" */
-	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type))
+	if (btf_type_is_void(next_type) || btf_type_is_fwd(next_type) ||
+	    btf_type_is_func_proto(next_type))
 		goto resolved;
 
 	if (!env_type_is_resolve_sink(env, next_type) &&
@@ -1242,7 +1292,8 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	}
 
 	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
-	    !btf_type_nosize(btf_type_id_resolve(btf, &next_type_id))) {
+	    (!btf_type_nosize(btf_type_id_resolve(btf, &next_type_id)) ||
+	     btf_type_is_func(next_type))) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1550,6 +1601,14 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		if (member->name_off &&
+		    !btf_name_valid_identifier(btf, member->name_off)) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid member name:%s",
+						btf_name_by_offset(btf, member->name_off));
+			return -EINVAL;
+		}
+
 		/* A member cannot be in type void */
 		if (!member->type || !BTF_TYPE_ID_VALID(member->type)) {
 			btf_verifier_log_member(env, t, member,
@@ -1787,6 +1846,142 @@ static struct btf_kind_operations enum_ops = {
 	.seq_show = btf_enum_seq_show,
 };
 
+static s32 btf_func_check_meta(struct btf_verifier_env *env,
+			       const struct btf_type *t,
+			       u32 meta_left)
+{
+	u32 meta_needed = btf_type_vlen(t) * sizeof(u32);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static void btf_func_log(struct btf_verifier_env *env,
+			 const struct btf_type *t)
+{
+	u16 nr_args = btf_type_vlen(t), i;
+	u32 *args = (u32 *)(t + 1);
+
+	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]) {
+		/* Only one vararg */
+		btf_verifier_log(env, "vararg");
+		goto done;
+	}
+
+	btf_verifier_log(env, "%u", args[0]);
+	for (i = 1; i < nr_args - 1; i++)
+		btf_verifier_log(env, ", %u", args[i]);
+	if (nr_args > 1) {
+		u32 last_arg = args[nr_args - 1];
+
+		if (last_arg)
+			btf_verifier_log(env, ", %u", last_arg);
+		else
+			btf_verifier_log(env, ", vararg");
+	}
+
+done:
+	btf_verifier_log(env, ")");
+}
+
+static int btf_func_check(struct btf_verifier_env *env,
+			  const struct btf_type *t,
+			  u32 type_id)
+{
+	u16 nr_args = btf_type_vlen(t), i;
+	const struct btf *btf = env->btf;
+	const struct btf_type *ret_type;
+	u32 *args = (u32 *)(t + 1);
+	u32 ret_type_id;
+	int err;
+
+	/* Check func return type which could be "void" (t->type == 0) */
+	ret_type_id = t->type;
+	if (ret_type_id) {
+		/* return type is not "void" */
+		ret_type = btf_type_by_id(btf, ret_type_id);
+		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])
+		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];
+		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 (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 struct btf_kind_operations func_ops = {
+	.check_meta = btf_func_check_meta,
+	.resolve = btf_df_resolve,
+	/*
+	 * BPF_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_log,
+	.seq_show = btf_df_seq_show,
+};
+
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_INT] = &int_ops,
 	[BTF_KIND_PTR] = &ptr_ops,
@@ -1799,6 +1994,8 @@ 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_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -1870,30 +2067,6 @@ 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 +2100,39 @@ 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 +2155,18 @@ 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(t) || btf_type_is_func_proto(t)) {
+			if (btf_type_is_func(t) &&
+			    (!btf_name_offset_valid(btf, t->name_off) ||
+			     !btf_name_valid_identifier(btf, t->name_off))) {
+				btf_verifier_log_type(env, t,
+						      "Invalid type_id");
+				return -EINVAL;
+			}
+
+			err = btf_func_check(env, t, type_id);
+			if (err)
+				return err;
 		}
 	}
 
-- 
2.17.1

Powered by blists - more mailing lists