[bpf-next,v10,07/13] bpf: pass attached BTF to the bpf_struct_ops subsystem

Commit Message

Kui-Feng Lee Nov. 3, 2023, 11:21 p.m. UTC

From: Kui-Feng Lee <[e-mail]>

Every kernel module has its BTF, comprising information on types defined in
the module. The BTF fd (attr->value_type_btf_obj_fd) passed from userspace
helps the bpf_struct_ops to lookup type information and description of the
struct_ops type, which is necessary for parsing the layout of map element
values and registering maps. The descriptions are looked up by matching a
type id (attr->btf_vmlinux_value_type_id) against bpf_struct_ops_desc(s)
defined in a BTF. If the struct_ops type is defined in a module, the
bpf_struct_ops needs to know the module BTF to lookup the
bpf_struct_ops_desc.

The bpf_prog includes attach_btf in aux which is passed along with the
bpf_attr when loading the program. The purpose of attach_btf is to
determine the btf type of attach_btf_id. The attach_btf_id is then used to
identify the traced function for a trace program. In the case of struct_ops
programs, it is used to identify the struct_ops type of the struct_ops
object that a program is attached to.

Signed-off-by: Kui-Feng Lee <[e-mail]>
---
 include/uapi/linux/bpf.h       |  5 +++++
 kernel/bpf/bpf_struct_ops.c    | 31 ++++++++++++++++++++++++++-----
 kernel/bpf/syscall.c           |  2 +-
 kernel/bpf/verifier.c          |  9 ++++++---
 tools/include/uapi/linux/bpf.h |  5 +++++
 5 files changed, 43 insertions(+), 9 deletions(-)

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0f6cdf52b1da..fd20c52606b2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1398,6 +1398,11 @@  union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+
+		__u32   value_type_btf_obj_fd;	/* fd pointing to a BTF
+						 * type data for
+						 * btf_vmlinux_value_type_id.
+						 */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 4ba6181ed1c4..8aaaa5121a56 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -635,6 +635,7 @@  static void __bpf_struct_ops_map_free(struct bpf_map *map)
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
 	}
 	bpf_map_area_free(st_map->uvalue);
+	btf_put(st_map->btf);
 	bpf_map_area_free(st_map);
 }
 
@@ -675,11 +676,24 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	struct bpf_struct_ops_map *st_map;
 	const struct btf_type *t, *vt;
 	struct bpf_map *map;
+	struct btf *btf;
 	int ret;
 
-	st_ops_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id);
-	if (!st_ops_desc)
-		return ERR_PTR(-ENOTSUPP);
+	if (attr->value_type_btf_obj_fd) {
+		/* The map holds btf for its whole life time. */
+		btf = btf_get_by_fd(attr->value_type_btf_obj_fd);
+		if (IS_ERR(btf))
+			return ERR_PTR(PTR_ERR(btf));
+	} else {
+		btf = btf_vmlinux;
+		btf_get(btf);
+	}
+
+	st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id);
+	if (!st_ops_desc) {
+		ret = -ENOTSUPP;
+		goto errout;
+	}
 
 	vt = st_ops_desc->value_type;
 	if (attr->value_size != vt->size)
@@ -697,6 +711,7 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	if (!st_map)
 		return ERR_PTR(-ENOMEM);
 
+	st_map->btf = btf;
 	st_map->st_ops_desc = st_ops_desc;
 	map = &st_map->map;
 
@@ -725,13 +740,19 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	st_map->btf = btf_vmlinux;
-
 	mutex_init(&st_map->lock);
 	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
+
+errout_free:
+	__bpf_struct_ops_map_free(map);
+	btf = NULL;		/* has been released */
+errout:
+	btf_put(btf);
+
+	return ERR_PTR(ret);
 }
 
 static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0ed286b8a0f0..974651fe2bee 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1096,7 +1096,7 @@  static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	return ret;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_extra
+#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bdd166cab977..3f446f76d4bf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20086,6 +20086,7 @@  static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	const struct btf_member *member;
 	struct bpf_prog *prog = env->prog;
 	u32 btf_id, member_idx;
+	struct btf *btf;
 	const char *mname;
 
 	if (!prog->gpl_compatible) {
@@ -20093,8 +20094,10 @@  static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 		return -EINVAL;
 	}
 
+	btf = prog->aux->attach_btf;
+
 	btf_id = prog->aux->attach_btf_id;
-	st_ops_desc = bpf_struct_ops_find(btf_vmlinux, btf_id);
+	st_ops_desc = bpf_struct_ops_find(btf, btf_id);
 	if (!st_ops_desc) {
 		verbose(env, "attach_btf_id %u is not a supported struct\n",
 			btf_id);
@@ -20111,8 +20114,8 @@  static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	}
 
 	member = &btf_type_member(t)[member_idx];
-	mname = btf_name_by_offset(btf_vmlinux, member->name_off);
-	func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
+	mname = btf_name_by_offset(btf, member->name_off);
+	func_proto = btf_type_resolve_func_ptr(btf, member->type,
 					       NULL);
 	if (!func_proto) {
 		verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0f6cdf52b1da..fd20c52606b2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1398,6 +1398,11 @@  union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+
+		__u32   value_type_btf_obj_fd;	/* fd pointing to a BTF
+						 * type data for
+						 * btf_vmlinux_value_type_id.
+						 */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */