From: Hou Tao <houtao1@xxxxxxxxxx> For get_next_key operation, unext_key is used as an output argument. When there is dynptr in map key, unext_key will also be used as an input argument, because the userspace application needs to pre-allocate a buffer for each variable-length part in the map key and save the length and the address of these buffers in bpf_dynptr_user objects. To support get_next_key op for map with dynptr key, map_get_next_key() first calls bpf_copy_from_dynptr_ukey() to construct a map key in which each bpf_dynptr_kern object has the same size as the corresponding bpf_dynptr_user object. It then calls ->map_get_next_key() to get the next_key, and finally calls bpf_copy_to_dynptr_ukey() to copy both the non-dynptr part and dynptr part in the map key to unext_key. Signed-off-by: Hou Tao <houtao1@xxxxxxxxxx> --- kernel/bpf/syscall.c | 88 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 73 insertions(+), 15 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5bd75db9b12f..338f17530068 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1540,7 +1540,7 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) return -ENOTSUPP; } -static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey) +static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey, bool copy_data) { const struct btf_record *record; const struct btf_field *field; @@ -1548,7 +1548,6 @@ static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey) struct bpf_dynptr_kern *kptr; void *key, *new_key, *kdata; unsigned int key_size, size; - bpfptr_t udata; unsigned int i; int err; @@ -1563,6 +1562,7 @@ static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey) field = &record->fields[i]; if (field->type != BPF_DYNPTR) continue; + uptr = key + field->offset; if (!uptr->size || uptr->size > map->map_extra || uptr->rsvd) { err = -EINVAL; @@ -1593,10 +1593,13 @@ static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey) uptr = key + field->offset; size = uptr->size; - udata = make_bpfptr(uptr->data, bpfptr_is_kernel(ukey)); - if (copy_from_bpfptr(kdata, udata, size)) { - err = -EFAULT; - goto free_key; + if (copy_data) { + bpfptr_t udata = make_bpfptr(uptr->data, bpfptr_is_kernel(ukey)); + + if (copy_from_bpfptr(kdata, udata, size)) { + err = -EFAULT; + goto free_key; + } } kptr = (struct bpf_dynptr_kern *)uptr; bpf_dynptr_init(kptr, kdata, BPF_DYNPTR_TYPE_LOCAL, 0, size); @@ -1613,7 +1616,7 @@ static void *bpf_copy_from_dynptr_ukey(const struct bpf_map *map, bpfptr_t ukey) static void *__bpf_copy_key(const struct bpf_map *map, void __user *ukey) { if (bpf_map_has_dynptr_key(map)) - return bpf_copy_from_dynptr_ukey(map, USER_BPFPTR(ukey)); + return bpf_copy_from_dynptr_ukey(map, USER_BPFPTR(ukey), true); if (map->key_size) return vmemdup_user(ukey, map->key_size); @@ -1627,7 +1630,7 @@ static void *__bpf_copy_key(const struct bpf_map *map, void __user *ukey) static void *___bpf_copy_key(const struct bpf_map *map, bpfptr_t ukey) { if (bpf_map_has_dynptr_key(map)) - return bpf_copy_from_dynptr_ukey(map, ukey); + return bpf_copy_from_dynptr_ukey(map, ukey, true); if (map->key_size) return kvmemdup_bpfptr(ukey, map->key_size); @@ -1638,6 +1641,51 @@ static void *___bpf_copy_key(const struct bpf_map *map, bpfptr_t ukey) return NULL; } +static int bpf_copy_to_dynptr_ukey(const struct bpf_map *map, + void __user *ukey, void *key) +{ + struct bpf_dynptr_user __user *uptr; + struct bpf_dynptr_kern *kptr; + struct btf_record *record; + unsigned int i, offset; + + offset = 0; + record = map->key_record; + for (i = 0; i < record->cnt; i++) { + struct btf_field *field; + unsigned int size; + u64 udata; + + field = &record->fields[i]; + if (field->type != BPF_DYNPTR) + continue; + + /* Any no-dynptr part before the dynptr ? */ + if (offset < field->offset && + copy_to_user(ukey + offset, key + offset, field->offset - offset)) + return -EFAULT; + + /* dynptr part */ + uptr = ukey + field->offset; + if (copy_from_user(&udata, &uptr->data, sizeof(udata))) + return -EFAULT; + + kptr = key + field->offset; + size = __bpf_dynptr_size(kptr); + if (copy_to_user(u64_to_user_ptr(udata), __bpf_dynptr_data(kptr, size), size) || + put_user(size, &uptr->size) || put_user(0, &uptr->rsvd)) + return -EFAULT; + + offset = field->offset + field->size; + } + + if (offset < map->key_size && + copy_to_user(ukey + offset, key + offset, map->key_size - offset)) + return -EFAULT; + + return 0; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags @@ -1840,10 +1888,19 @@ static int map_get_next_key(union bpf_attr *attr) key = NULL; } - err = -ENOMEM; - next_key = kvmalloc(map->key_size, GFP_USER); - if (!next_key) + if (bpf_map_has_dynptr_key(map)) + next_key = bpf_copy_from_dynptr_ukey(map, USER_BPFPTR(unext_key), false); + else + next_key = kvmalloc(map->key_size, GFP_USER); + if (IS_ERR_OR_NULL(next_key)) { + if (!next_key) { + err = -ENOMEM; + } else { + err = PTR_ERR(next_key); + next_key = NULL; + } goto free_key; + } if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); @@ -1857,12 +1914,13 @@ static int map_get_next_key(union bpf_attr *attr) if (err) goto free_next_key; - err = -EFAULT; - if (copy_to_user(unext_key, next_key, map->key_size) != 0) + if (bpf_map_has_dynptr_key(map)) + err = bpf_copy_to_dynptr_ukey(map, unext_key, next_key); + else + err = copy_to_user(unext_key, next_key, map->key_size) ? -EFAULT : 0; + if (err) goto free_next_key; - err = 0; - free_next_key: kvfree(next_key); free_key: -- 2.44.0