@@ -430,7 +430,6 @@ static void array_map_free(struct bpf_map *map)
for (i = 0; i < array->map.max_entries; i++)
bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i));
}
- bpf_map_free_record(map);
}
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
@@ -1511,7 +1511,6 @@ static void htab_map_free(struct bpf_map *map)
prealloc_destroy(htab);
}
- bpf_map_free_record(map);
free_percpu(htab->extra_elems);
bpf_map_area_free(htab->buckets);
bpf_mem_alloc_destroy(&htab->pcpu_ma);
@@ -659,14 +659,24 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
+ struct btf_field_offs *foffs = map->field_offs;
+ struct btf_record *rec = map->record;
security_bpf_map_free(map);
- kfree(map->field_offs);
bpf_map_release_memcg(map);
- /* implementation dependent freeing, map_free callback also does
- * bpf_map_free_record, if needed.
- */
+ /* implementation dependent freeing */
map->ops->map_free(map);
+ /* Delay freeing of field_offs and btf_record for maps, as map_free
+ * callback usually needs access to them. It is better to do it here
+ * than require each callback to do the free itself manually.
+ *
+ * Note that the btf_record stashed in map->inner_map_meta->record was
+ * already freed using the map_free callback for map in map case which
+ * eventually calls bpf_map_free_meta, since inner_map_meta is only a
+ * template bpf_map struct used during verification.
+ */
+ kfree(foffs);
+ btf_record_free(rec);
}
static void bpf_map_put_uref(struct bpf_map *map)
Since the commit being fixed, we now miss freeing btf_record for local storage maps which will have a btf_record populated in case they have bpf_spin_lock element. This was missed because I made the choice of offloading the job to free kptr_off_tab (now btf_record) to the map_free callback when adding support for kptrs. Revisiting the reason for this decision, there is the possibility that the btf_record gets used inside map_free callback (e.g. in case of maps embedding kptrs) to iterate over them and free them, hence doing it before the map_free callback would be leaking special field memory, and do invalid memory access. The btf_record keeps module references which is critical to ensure the dtor call made for referenced kptr is safe to do. If doing it after map_free callback, the map area is already freed, so we cannot access bpf_map structure anymore. To fix this and prevent such lapses in future, move bpf_map_free_record out of the map_free callback, and do it after map_free by remembering the btf_record pointer. There is no need to access bpf_map structure in that case, and we can avoid missing this case when support for new map types is added for other special fields. Since a btf_record and its btf_field_offs are used together, for consistency delay freeing of field_offs as well. While not a problem right now, a lot of code assumes that either both record and field_offs are set or none at once. Note that in case of map of maps (outer maps), inner_map_meta->record is only used during verification, not to free fields in map value, hence we simply keep the bpf_map_free_record call as is in bpf_map_meta_free and never touch map->inner_map_meta in bpf_map_free_deferred. Add a comment making note of these details. Fixes: db559117828d ("bpf: Consolidate spin_lock, timer management into btf_record") Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> --- kernel/bpf/arraymap.c | 1 - kernel/bpf/hashtab.c | 1 - kernel/bpf/syscall.c | 18 ++++++++++++++---- 3 files changed, 14 insertions(+), 6 deletions(-)