Re: [RFC v2 12/34] mm, slub: move disabling/enabling irqs to ___slab_alloc()
From: Mike Galbraith <hidden>
Date: 2021-07-06 04:39:04
Also in:
lkml
Greetings, On Wed, 2021-06-09 at 13:38 +0200, Vlastimil Babka wrote:
quoted hunk ↗ jump to hunk
@@ -3313,6 +3320,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s,gfp_t flags, size_t size, */ c->tid = next_tid(c->tid); + local_irq_enable(); + /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist
This addition should have been followed by removal of the one in the error path. At the end of the series, RT ends up doing a double local_unlock_irq() instead of post ___slab_alloc() slub_put_cpu_ptr(). -Mike