Messages in this thread | | | From | Maurizio Lombardi <> | Date | Tue, 30 Aug 2022 21:03:11 +0200 | Subject | Re: [PATCH RFC] mm: slub: fix flush_cpu_slab()/__free_slab() invocations in task context. |
| |
út 30. 8. 2022 v 20:59 odesílatel Sebastian Andrzej Siewior <bigeasy@linutronix.de> napsal: > > On 2022-08-30 17:48:06 [+0200], Maurizio Lombardi wrote: > > Hmm, this is not good indeed. I guess I should have used for_each_online_cpu() > > instead of on_each_cpu_cond(). > > But you must not invoked that function cross-CPU since the code expects > to access the per-CPU variables always from the local-CPU.
Ok, thanks for the clarification.
> > > > > > > Couldn't we instead use a workqueue with that WQ_MEM_RECLAIM bit? It may > > > reclaim memory after all ;) > > > > That should also fix it, do you think it would be ok to allocate a workqueue in > > in kmem_cache_init() ? > > I guess so. There is probably none that is already available. >
Will test it and submit a patch soon.
Thanks, Maurizio
| |