Re: [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT compatible

[Mel Gorman]

On Mon, Jun 14, 2021 at 10:49:02AM +0100, Mel Gorman wrote:
> On Wed, Jun 09, 2021 at 01:38:29PM +0200, Vlastimil Babka wrote:
> > Changes since RFC v1 [1]:
> > * Addressed feedback from Christoph and Mel, added their acks.
> > * Finished RT conversion, including adopting 2 patches from the RT tree.
> > * The optional local_lock conversion has to sacrifice lockless fathpaths on RT
> > * Added some more cleanup patches to the front.
> > 
> > This series was initially inspired by Mel's pcplist local_lock rewrite, and
> > also by interest to better understand SLUB's locking and the new locking
> > primitives and their RT variants and implications. It should make SLUB more
> > preemption-friendly and fully RT compatible, hopefully without noticeable
> > regressions on !RT kernels, as the fast paths are not affected there.
> > 
> > Series is based on 5.13-rc5 and also available as a git branch:
> > https://git.kernel.org/pub/scm/linux/kernel/git/vbabka/linux.git/log/?h=slub-local-lock-v2r1
> > 
> 
> This failed to boot for me inside KVM.
> 

Bisection pointed to "mm, slub: use migrate_disable() on PREEMPT_RT".
Off-list, Vlastimil noted that the #ifdef was wrong and the patch below
booted. Wider battery of tests is queued but will take a few days to
complete.

---8<---
mm, slub: use migrate_disable() on PREEMPT_RT -fix

Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
---
 mm/slub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/slub.c b/mm/slub.c
index caa206213e72..f0359b0c8154 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -119,7 +119,7 @@
  * We could simply use migrate_disable()/enable() but as long as it's a
  * function call even on !PREEMPT_RT, use inline preempt_disable() there.
  */
-#ifdef CONFIG_PREEMPT_RT
+#ifndef CONFIG_PREEMPT_RT
 #define slub_get_cpu_ptr(var)	get_cpu_ptr(var)
 #define slub_put_cpu_ptr(var)	put_cpu_ptr(var)
 #else

-- 
Mel Gorman
SUSE Labs