> diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> index d029690246f8..8665eb6b8a7d 100644
> --- a/kernel/bpf/hashtab.c
> +++ b/kernel/bpf/hashtab.c
[ ... ]
> +static int htab_lru_map_update_elem_in_place(struct bpf_htab *htab, void
> *key, void *value,
> + u64 map_flags, struct bucket *b,
> + struct hlist_nulls_head *head, u32
> hash,
> + bool percpu, bool onallcpus)
> +{
> + struct htab_elem *l_new, *l_old, *l_free;
> + struct bpf_map *map = &htab->map;
> + u32 key_size = map->key_size;
> + struct bpf_lru_node *node;
> + unsigned long flags;
> + void *l_val;
> + int ret;
> +
> + node = bpf_lru_pop_extra(&htab->lru);
> + if (!node)
> + return -ENOENT;
> +
> + l_new = container_of(node, struct htab_elem, lru_node);
> + l_new->hash = hash;
> + memcpy(l_new->key, key, key_size);
> + if (!percpu) {
> + l_val = htab_elem_value(l_new, map->key_size);
> + copy_map_value(map, l_val, value);
> + bpf_obj_free_fields(map->record, l_val);
> + }
Should bpf_obj_free_fields() be called here on l_new? The value was just
copied into l_new and l_new will be inserted into the hash table when
l_old is found. Calling bpf_obj_free_fields() on l_new's value frees the
special fields (kptr, bpf_list_head, etc.) that were just copied, then
l_new is inserted with freed fields. This appears to be a use-after-free
for maps with special fields.
Looking at htab_lru_map_update_elem(), the pattern is to copy the value
and NOT call bpf_obj_free_fields() on the new element. The fields are
only freed when an element is removed from the hash table.
> +
> + ret = htab_lock_bucket(b, &flags);
> + if (ret)
> + goto err_lock_bucket;
> +
> + l_old = lookup_elem_raw(head, hash, key, key_size);
> +
> + ret = check_flags(htab, l_old, map_flags);
> + if (ret)
> + goto err;
> +
> + if (l_old) {
> + bpf_lru_node_set_ref(&l_new->lru_node);
> + if (percpu) {
> + /* per-cpu hash map can update value in-place.
> + * Keep the same logic in
> __htab_lru_percpu_map_update_elem().
> + */
> + pcpu_copy_value(htab, htab_elem_get_ptr(l_old,
> key_size),
> + value, onallcpus);
> + l_free = l_new;
> + } else {
> + hlist_nulls_add_head_rcu(&l_new->hash_node, head);
> + hlist_nulls_del_rcu(&l_old->hash_node);
> + l_free = l_old;
> + }
> + } else {
> + ret = -ENOENT;
> + }
> +
> +err:
> + htab_unlock_bucket(b, flags);
> +
> +err_lock_bucket:
> + bpf_lru_push_free(&htab->lru, ret ? node : &l_free->lru_node);
^^^^^^^^^^^^^^^^^^
When ret == 0 and !percpu, l_free points to l_old which is being removed
from the hash table. The code calls bpf_lru_push_free() directly instead
of htab_lru_push_free(). Looking at htab_lru_push_free():
static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem
*elem)
{
check_and_free_fields(htab, elem);
bpf_map_dec_elem_count(&htab->map);
bpf_lru_push_free(&htab->lru, &elem->lru_node);
}
It calls check_and_free_fields() to free special fields in the element
before pushing to the free list. The code here bypasses that, which would
leak special fields (kptr, etc.) in l_old when it has them.
Should this use htab_lru_push_free() instead of bpf_lru_push_free() for
the non-error path where l_old is being freed?
> +
> + return ret;
> +}
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/20720201621
