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.
Fixes: db559117828d ("bpf: Consolidate spin_lock, timer management into btf_record")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@xxxxxxxxx>
---
kernel/bpf/arraymap.c | 1 -
kernel/bpf/hashtab.c | 1 -
kernel/bpf/map_in_map.c | 1 -
kernel/bpf/syscall.c | 9 +++++----
4 files changed, 5 insertions(+), 7 deletions(-)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 672eb17ac421..484706959556 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -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)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 50d254cd0709..5aa2b5525f79 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -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);
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 8ca0cca39d49..4caf03eb51ab 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -78,7 +78,6 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
void bpf_map_meta_free(struct bpf_map *map_meta)
{
- bpf_map_free_record(map_meta);
btf_put(map_meta->btf);
kfree(map_meta);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0b48e2b13021..0621d2f4e38a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -659,14 +659,15 @@ 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);
+ kfree(foffs);
+ btf_record_free(rec);
}
static void bpf_map_put_uref(struct bpf_map *map)
--
2.38.1
