[PATCH bpf-next v4 5/9] bpf: pass attached BTF to the bpf_struct_ops subsystem

[thinker.li@gmail.com]

From: Kui-Feng Lee <thinker.li@gmail.com>

Giving a BTF, the bpf_struct_ops knows the right place to look up type info
associated with a type ID. This enables a user space program to load a
struct_ops object linked to a struct_ops type defined by a module, by
providing the module BTF (fd).

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 <thinker.li@gmail.com>
---
 include/uapi/linux/bpf.h       |  5 +++++
 kernel/bpf/bpf_struct_ops.c    | 34 +++++++++++++++++++++++++++-------
 kernel/bpf/syscall.c           |  2 +-
 kernel/bpf/verifier.c          |  4 +++-
 tools/include/uapi/linux/bpf.h |  5 +++++
 5 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 73b155e52204..b5ef22f65f35 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1390,6 +1390,11 @@ 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 69703584fa4a..60445ff32275 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -677,6 +677,7 @@ 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->st_ops->btf);
 	module_put(st_map->st_ops->owner);
 	bpf_map_area_free(st_map);
 }
@@ -718,23 +719,36 @@ 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 = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id);
-	if (!st_ops)
+	if (attr->value_type_btf_obj_fd) {
+		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 = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id);
+	if (!st_ops) {
+		btf_put(btf);
 		return ERR_PTR(-ENOTSUPP);
+	}
 
 	/* If st_ops->owner is NULL, it means the struct_ops is
 	 * statically defined in the kernel.  We don't need to
 	 * take a refcount on it.
 	 */
-	if (st_ops->owner && !btf_try_get_module(st_ops->btf))
+	if (st_ops->owner && !btf_try_get_module(st_ops->btf)) {
+		btf_put(btf);
 		return ERR_PTR(-EINVAL);
+	}
 
 	vt = st_ops->value_type;
 	if (attr->value_size != vt->size) {
-		module_put(st_ops->owner);
-		return ERR_PTR(-EINVAL);
+		ret = -EINVAL;
+		goto errout;
 	}
 
 	t = st_ops->type;
@@ -747,8 +761,8 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 
 	st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
 	if (!st_map) {
-		module_put(st_ops->owner);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto errout;
 	}
 
 	st_map->st_ops = st_ops;
@@ -784,6 +798,12 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
+
+errout:
+	btf_put(btf);
+	module_put(st_ops->owner);
+
+	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 85c1d908f70f..5daf8a2c2bba 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1097,7 +1097,7 @@ 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 6564a03c425d..ce4df24eb03b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19623,6 +19623,7 @@ 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) {
@@ -19630,8 +19631,9 @@ 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 = bpf_struct_ops_find(btf_vmlinux, btf_id);
+	st_ops = bpf_struct_ops_find(btf, btf_id);
 	if (!st_ops) {
 		verbose(env, "attach_btf_id %u is not a supported struct\n",
 			btf_id);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 73b155e52204..b5ef22f65f35 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1390,6 +1390,11 @@ 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 */
-- 
2.34.1