On 03.02.2021 20:20, Yang Shi wrote:
> Now nr_deferred is available on per memcg level for memcg aware shrinkers, so don't need
> allocate shrinker->nr_deferred for such shrinkers anymore.
>
> The prealloc_memcg_shrinker() would return -ENOSYS if !CONFIG_MEMCG or memcg is disabled
> by kernel command line, then shrinker's SHRINKER_MEMCG_AWARE flag would be cleared.
> This makes the implementation of this patch simpler.
>
> Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
> Signed-off-by: Yang Shi <shy828301@xxxxxxxxx>
> ---
> mm/vmscan.c | 31 ++++++++++++++++---------------
> 1 file changed, 16 insertions(+), 15 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 545422d2aeec..20a35d26ae12 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -334,6 +334,9 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
> {
> int id, ret = -ENOMEM;
>
> + if (mem_cgroup_disabled())
> + return -ENOSYS;
> +
> down_write(&shrinker_rwsem);
> /* This may call shrinker, so it must use down_read_trylock() */
> id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL);
> @@ -414,7 +417,7 @@ static bool writeback_throttling_sane(struct scan_control *sc)
> #else
> static int prealloc_memcg_shrinker(struct shrinker *shrinker)
> {
> - return 0;
> + return -ENOSYS;
> }
>
> static void unregister_memcg_shrinker(struct shrinker *shrinker)
> @@ -525,8 +528,18 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
> */
> int prealloc_shrinker(struct shrinker *shrinker)
> {
> - unsigned int size = sizeof(*shrinker->nr_deferred);
> + unsigned int size;
> + int err;
> +
> + if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
> + err = prealloc_memcg_shrinker(shrinker);
> + if (err != -ENOSYS)
> + return err;
>
> + shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
> + }
> +
> + size = sizeof(*shrinker->nr_deferred);
> if (shrinker->flags & SHRINKER_NUMA_AWARE)
> size *= nr_node_ids;
This may sound surprisingly, but IIRC do_shrink_slab() may be called on early boot
*even before* root_mem_cgroup is allocated. AFAIR, I received syzcaller crash report
because of this, when I was implementing shrinker_maps.
This is a reason why we don't use shrinker_maps even in case of mem cgroup is not
disabled: we iterate every shrinker of shrinker_list. See check in shrink_slab():
if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
Possible, we should do the same for nr_deferred: 1)always allocate shrinker->nr_deferred,
2)use shrinker->nr_deferred in count_nr_deferred() and set_nr_deferred().
>
> @@ -534,26 +547,14 @@ int prealloc_shrinker(struct shrinker *shrinker)
> if (!shrinker->nr_deferred)
> return -ENOMEM;
>
> - if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
> - if (prealloc_memcg_shrinker(shrinker))
> - goto free_deferred;
> - }
>
> return 0;
> -
> -free_deferred:
> - kfree(shrinker->nr_deferred);
> - shrinker->nr_deferred = NULL;
> - return -ENOMEM;
> }
>
> void free_prealloced_shrinker(struct shrinker *shrinker)
> {
> - if (!shrinker->nr_deferred)
> - return;
> -
> if (shrinker->flags & SHRINKER_MEMCG_AWARE)
> - unregister_memcg_shrinker(shrinker);
> + return unregister_memcg_shrinker(shrinker);
>
> kfree(shrinker->nr_deferred);
> shrinker->nr_deferred = NULL;
>
