Merge branch 'bpf: add support for new btf kind BTF_KIND_TAG'

Yonghong Song says:

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

LLVM14 added support for a new C attribute ([1])
  __attribute__((btf_tag("arbitrary_str")))
This attribute will be emitted to dwarf ([2]) and pahole
will convert it to BTF. Or for bpf target, this
attribute will be emitted to BTF directly ([3], [4]).
The attribute is intended to provide additional
information for
  - struct/union type or struct/union member
  - static/global variables
  - static/global function or function parameter.

This new attribute can be used to add attributes
to kernel codes, e.g., pre- or post- conditions,
allow/deny info, or any other info in which only
the kernel is interested. Such attributes will
be processed by clang frontend and emitted to
dwarf, converting to BTF by pahole. Ultimiately
the verifier can use these information for
verification purpose.

The new attribute can also be used for bpf
programs, e.g., tagging with __user attributes
for function parameters, specifying global
function preconditions, etc. Such information
may help verifier to detect user program
bugs.

After this series, pahole dwarf->btf converter
will be enhanced to support new llvm tag
for btf_tag attribute. With pahole support,
we will then try to add a few real use case,
e.g., __user/__rcu tagging, allow/deny list,
some kernel function precondition, etc,
in the kernel.

In the rest of the series, Patches 1-2 had
kernel support. Patches 3-4 added
libbpf support. Patch 5 added bpftool
support. Patches 6-10 added various selftests.
Patch 11 added documentation for the new kind.

  [1] https://reviews.llvm.org/D106614
  [2] https://reviews.llvm.org/D106621
  [3] https://reviews.llvm.org/D106622
  [4] https://reviews.llvm.org/D109560

Changelog:
  v2 -> v3:
    - put NR_BTF_KINDS and BTF_KIND_MAX into enum as well
    - check component_idx earlier (check_meta stage) in kernel
    - add more tests
    - fix misc nits
  v1 -> v2:
    - BTF ELF format changed in llvm ([4] above),
      so cross-board change to use the new format.
    - Clarified in commit message that BTF_KIND_TAG
      is not emitted by bpftool btf dump format c.
    - Fix various comments from Andrii.
====================

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: Alexei Starovoitov

Documentation/bpf/btf.rst

@@ -85,6 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_VAR            14      /* Variable     */
     #define BTF_KIND_DATASEC        15      /* Section      */
     #define BTF_KIND_FLOAT          16      /* Floating point       */
+    #define BTF_KIND_TAG            17      /* Tag          */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -106,7 +107,7 @@ Each type contains the following common data::
          * "size" tells the size of the type it is describing.
          *
          * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-         * FUNC and FUNC_PROTO.
+         * FUNC, FUNC_PROTO and TAG.
          * "type" is a type_id referring to another type.
          */
         union {
@@ -465,6 +466,32 @@ map definition.
 
 No additional type data follow ``btf_type``.
 
+2.2.17 BTF_KIND_TAG
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+ * ``name_off``: offset to a non-empty string
+ * ``info.kind_flag``: 0
+ * ``info.kind``: BTF_KIND_TAG
+ * ``info.vlen``: 0
+ * ``type``: ``struct``, ``union``, ``func`` or ``var``
+
+``btf_type`` is followed by ``struct btf_tag``.::
+
+    struct btf_tag {
+        __u32   component_idx;
+    };
+
+The ``name_off`` encodes btf_tag attribute string.
+The ``type`` should be ``struct``, ``union``, ``func`` or ``var``.
+For ``var`` type, ``btf_tag.component_idx`` must be ``-1``.
+For the other three types, if the btf_tag attribute is
+applied to the ``struct``, ``union`` or ``func`` itself,
+``btf_tag.component_idx`` must be ``-1``. Otherwise,
+the attribute is applied to a ``struct``/``union`` member or
+a ``func`` argument, and ``btf_tag.component_idx`` should be a
+valid index (starting from 0) pointing to a member or an argument.
+
 3. BTF Kernel API
 *****************
 

include/uapi/linux/btf.h

@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO and VAR.
+	 * FUNC, FUNC_PROTO, VAR and TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -56,25 +56,29 @@ struct btf_type {
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
 #define BTF_INFO_KFLAG(info)	((info) >> 31)
 
-#define BTF_KIND_UNKN		0	/* Unknown	*/
-#define BTF_KIND_INT		1	/* Integer	*/
-#define BTF_KIND_PTR		2	/* Pointer	*/
-#define BTF_KIND_ARRAY		3	/* Array	*/
-#define BTF_KIND_STRUCT		4	/* Struct	*/
-#define BTF_KIND_UNION		5	/* Union	*/
-#define BTF_KIND_ENUM		6	/* Enumeration	*/
-#define BTF_KIND_FWD		7	/* Forward	*/
-#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
-#define BTF_KIND_VOLATILE	9	/* Volatile	*/
-#define BTF_KIND_CONST		10	/* Const	*/
-#define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_FUNC		12	/* Function	*/
-#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_VAR		14	/* Variable	*/
-#define BTF_KIND_DATASEC	15	/* Section	*/
-#define BTF_KIND_FLOAT		16	/* Floating point	*/
-#define BTF_KIND_MAX		BTF_KIND_FLOAT
-#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
+enum {
+	BTF_KIND_UNKN		= 0,	/* Unknown	*/
+	BTF_KIND_INT		= 1,	/* Integer	*/
+	BTF_KIND_PTR		= 2,	/* Pointer	*/
+	BTF_KIND_ARRAY		= 3,	/* Array	*/
+	BTF_KIND_STRUCT		= 4,	/* Struct	*/
+	BTF_KIND_UNION		= 5,	/* Union	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_FWD		= 7,	/* Forward	*/
+	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
+	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
+	BTF_KIND_CONST		= 10,	/* Const	*/
+	BTF_KIND_RESTRICT	= 11,	/* Restrict	*/
+	BTF_KIND_FUNC		= 12,	/* Function	*/
+	BTF_KIND_FUNC_PROTO	= 13,	/* Function Proto	*/
+	BTF_KIND_VAR		= 14,	/* Variable	*/
+	BTF_KIND_DATASEC	= 15,	/* Section	*/
+	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+	BTF_KIND_TAG		= 17,	/* Tag */
+
+	NR_BTF_KINDS,
+	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
+};
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -170,4 +174,15 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
+/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_tag {
+       __s32   component_idx;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

kernel/bpf/btf.c

@@ -281,6 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
+	[BTF_KIND_TAG]		= "TAG",
 };
 
 const char *btf_type_str(const struct btf_type *t)
@@ -459,6 +460,17 @@ static bool btf_type_is_datasec(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
 }
 
+static bool btf_type_is_tag(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_TAG;
+}
+
+static bool btf_type_is_tag_target(const struct btf_type *t)
+{
+	return btf_type_is_func(t) || btf_type_is_struct(t) ||
+	       btf_type_is_var(t);
+}
+
 u32 btf_nr_types(const struct btf *btf)
 {
 	u32 total = 0;
@@ -537,6 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
 static bool btf_type_is_resolve_source_only(const struct btf_type *t)
 {
 	return btf_type_is_var(t) ||
+	       btf_type_is_tag(t) ||
 	       btf_type_is_datasec(t);
 }
 
@@ -563,6 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t)
 	       btf_type_is_struct(t) ||
 	       btf_type_is_array(t) ||
 	       btf_type_is_var(t) ||
+	       btf_type_is_tag(t) ||
 	       btf_type_is_datasec(t);
 }
 
@@ -616,6 +630,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t)
 	return (const struct btf_var *)(t + 1);
 }
 
+static const struct btf_tag *btf_type_tag(const struct btf_type *t)
+{
+	return (const struct btf_tag *)(t + 1);
+}
+
 static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 {
 	return kind_ops[BTF_INFO_KIND(t->info)];
@@ -3801,6 +3820,110 @@ static const struct btf_kind_operations float_ops = {
 	.show = btf_df_show,
 };
 
+static s32 btf_tag_check_meta(struct btf_verifier_env *env,
+			      const struct btf_type *t,
+			      u32 meta_left)
+{
+	const struct btf_tag *tag;
+	u32 meta_needed = sizeof(*tag);
+	s32 component_idx;
+	const char *value;
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	value = btf_name_by_offset(env->btf, t->name_off);
+	if (!value || !value[0]) {
+		btf_verifier_log_type(env, t, "Invalid value");
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
+	component_idx = btf_type_tag(t)->component_idx;
+	if (component_idx < -1) {
+		btf_verifier_log_type(env, t, "Invalid component_idx");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static int btf_tag_resolve(struct btf_verifier_env *env,
+			   const struct resolve_vertex *v)
+{
+	const struct btf_type *next_type;
+	const struct btf_type *t = v->t;
+	u32 next_type_id = t->type;
+	struct btf *btf = env->btf;
+	s32 component_idx;
+	u32 vlen;
+
+	next_type = btf_type_by_id(btf, next_type_id);
+	if (!next_type || !btf_type_is_tag_target(next_type)) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	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);
+
+	component_idx = btf_type_tag(t)->component_idx;
+	if (component_idx != -1) {
+		if (btf_type_is_var(next_type)) {
+			btf_verifier_log_type(env, v->t, "Invalid component_idx");
+			return -EINVAL;
+		}
+
+		if (btf_type_is_struct(next_type)) {
+			vlen = btf_type_vlen(next_type);
+		} else {
+			/* next_type should be a function */
+			next_type = btf_type_by_id(btf, next_type->type);
+			vlen = btf_type_vlen(next_type);
+		}
+
+		if ((u32)component_idx >= vlen) {
+			btf_verifier_log_type(env, v->t, "Invalid component_idx");
+			return -EINVAL;
+		}
+	}
+
+	env_stack_pop_resolved(env, next_type_id, 0);
+
+	return 0;
+}
+
+static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t)
+{
+	btf_verifier_log(env, "type=%u component_idx=%d", t->type,
+			 btf_type_tag(t)->component_idx);
+}
+
+static const struct btf_kind_operations tag_ops = {
+	.check_meta = btf_tag_check_meta,
+	.resolve = btf_tag_resolve,
+	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
+	.log_details = btf_tag_log,
+	.show = btf_df_show,
+};
+
 static int btf_func_proto_check(struct btf_verifier_env *env,
 				const struct btf_type *t)
 {
@@ -3935,6 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR] = &var_ops,
 	[BTF_KIND_DATASEC] = &datasec_ops,
 	[BTF_KIND_FLOAT] = &float_ops,
+	[BTF_KIND_TAG] = &tag_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -4019,6 +4143,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
 		return !btf_resolved_type_id(btf, type_id) &&
 		       !btf_resolved_type_size(btf, type_id);
 
+	if (btf_type_is_tag(t))
+		return btf_resolved_type_id(btf, type_id) &&
+		       !btf_resolved_type_size(btf, type_id);
+
 	if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
 	    btf_type_is_var(t)) {
 		t = btf_type_id_resolve(btf, &type_id);

tools/bpf/bpftool/btf.c

@@ -37,6 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
+	[BTF_KIND_TAG]		= "TAG",
 };
 
 struct btf_attach_table {
@@ -347,6 +348,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 			printf(" size=%u", t->size);
 		break;
 	}
+	case BTF_KIND_TAG: {
+		const struct btf_tag *tag = (const void *)(t + 1);
+
+		if (json_output) {
+			jsonw_uint_field(w, "type_id", t->type);
+			jsonw_int_field(w, "component_idx", tag->component_idx);
+		} else {
+			printf(" type_id=%u component_idx=%d", t->type, tag->component_idx);
+		}
+		break;
+	}
 	default:
 		break;
 	}