bpf: pass attached BTF to the bpf_struct_ops subsystem

Pass the fd of a btf from the userspace to the bpf() syscall, and then
convert the fd into a btf. The btf is generated from the module that
defines the target BPF struct_ops type.

In order to inform the kernel about the module that defines the target
struct_ops type, the userspace program needs to provide a btf fd for the
respective module's btf. This btf contains essential information on the
types defined within the module, including the target struct_ops type.

A btf fd must be provided to the kernel for struct_ops maps and for the bpf
programs attached to those maps.

In the case of the bpf programs, the attach_btf_obj_fd parameter is passed
as part of the bpf_attr and is converted into a btf. This btf is then
stored in the prog->aux->attach_btf field. Here, it just let the verifier
access attach_btf directly.

In the case of struct_ops maps, a btf fd is passed as value_type_btf_obj_fd
of bpf_attr. The bpf_struct_ops_map_alloc() function converts the fd to a
btf and stores it as st_map->btf. A flag BPF_F_VTYPE_BTF_OBJ_FD is added
for map_flags to indicate that the value of value_type_btf_obj_fd is set.

Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
Link: https://lore.kernel.org/r/20240119225005.668602-9-thinker.li@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

include/uapi/linux/bpf.h

@@ -1330,6 +1330,9 @@ enum {
 
 /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
 	BPF_F_PATH_FD		= (1U << 14),
+
+/* Flag for value_type_btf_obj_fd, the fd is available */
+	BPF_F_VTYPE_BTF_OBJ_FD	= (1U << 15),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1403,6 +1406,11 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+
+		__s32   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 */

kernel/bpf/bpf_struct_ops.c

@@ -641,6 +641,7 @@ 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);
 }
 
@@ -669,7 +670,8 @@ static void bpf_struct_ops_map_free(struct bpf_map *map)
 static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
 {
 	if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 ||
-	    (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id)
+	    (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) ||
+	    !attr->btf_vmlinux_value_type_id)
 		return -EINVAL;
 	return 0;
 }
@@ -681,15 +683,36 @@ 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_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id);
-	if (!st_ops_desc)
-		return ERR_PTR(-ENOTSUPP);
+	if (attr->map_flags & BPF_F_VTYPE_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_CAST(btf);
+		if (!btf_is_module(btf)) {
+			btf_put(btf);
+			return ERR_PTR(-EINVAL);
+		}
+	} else {
+		btf = bpf_get_btf_vmlinux();
+		if (IS_ERR(btf))
+			return ERR_CAST(btf);
+		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)
-		return ERR_PTR(-EINVAL);
+	if (attr->value_size != vt->size) {
+		ret = -EINVAL;
+		goto errout;
+	}
 
 	t = st_ops_desc->type;
 
@@ -700,17 +723,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		(vt->size - sizeof(struct bpf_struct_ops_value));
 
 	st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
-	if (!st_map)
-		return ERR_PTR(-ENOMEM);
+	if (!st_map) {
+		ret = -ENOMEM;
+		goto errout;
+	}
 
 	st_map->st_ops_desc = st_ops_desc;
 	map = &st_map->map;
 
 	ret = bpf_jit_charge_modmem(PAGE_SIZE);
-	if (ret) {
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(ret);
-	}
+	if (ret)
+		goto errout_free;
 
 	st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!st_map->image) {
@@ -719,24 +742,30 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		 * here.
 		 */
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto errout_free;
 	}
 	st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
 	st_map->links =
 		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
 				   NUMA_NO_NODE);
 	if (!st_map->uvalue || !st_map->links) {
-		__bpf_struct_ops_map_free(map);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto errout_free;
 	}
-
-	st_map->btf = btf_vmlinux;
+	st_map->btf = btf;
 
 	mutex_init(&st_map->lock);
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
+
+errout_free:
+	__bpf_struct_ops_map_free(map);
+errout:
+	btf_put(btf);
+
+	return ERR_PTR(ret);
 }
 
 static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map)

kernel/bpf/syscall.c

@@ -1123,7 +1123,7 @@ free_map_tab:
 	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)
 {

kernel/bpf/verifier.c

@@ -20290,6 +20290,7 @@ 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) {
@@ -20297,8 +20298,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 		return -EINVAL;
 	}
 
+	btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux();
+
 	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);
@@ -20315,8 +20318,8 @@ 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",

tools/include/uapi/linux/bpf.h

@@ -1330,6 +1330,9 @@ enum {
 
 /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
 	BPF_F_PATH_FD		= (1U << 14),
+
+/* Flag for value_type_btf_obj_fd, the fd is available */
+	BPF_F_VTYPE_BTF_OBJ_FD	= (1U << 15),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1403,6 +1406,11 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+
+		__s32   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 */