From c1afbd5de131f5e3c4fc7559acf055f8d9d86868 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Mon, 17 Aug 2026 03:38:35 -0700 Subject: [PATCH] mm/memcontrol: avoid false sharing between vmstats and events Moving v1 userspace eventfd handling into memcontrol-v1.c shrank struct vmpressure from 112 to 24 bytes when CONFIG_MEMCG_V1 is disabled. This moved memory_events_local[MEMCG_SWAP_FAIL] and the hot vmstats_percpu pointer onto the same cacheline. The stress-ng mremap stressor exercises MADV_PAGEOUT with swap disabled, generating about 20 million MEMCG_SWAP_FAIL updates per 60-second run on a 176-CPU test system. Those writes bounce the line while memcg statistics paths load vmstats_percpu. Move cgwb_list into the existing alignment gap and cacheline-align vmstats_percpu. This separates the pointer from the event counters without increasing the size of struct mem_cgroup in the tested configuration. The blamed commit reduced median mremap throughput by 4.38% on the test system with one socket. The patched kernel brings the performance to within 0.5% of the parent which is within the observed boot-to-boot spread (up to 1.2%). Link: https://lore.kernel.org/20260817103835.2937733-1-usama.arif@linux.dev Fixes: ea928e9e18da ("mm/vmpressure: move v1 userspace eventfd code into memcontrol-v1.c") Signed-off-by: Usama Arif Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202608131743.c6a7dda4-lkp@intel.com Tested-by: kernel test robot Link: http://lore.kernel.org/aoAABX59IzUXz/Rv@ly-workstation Acked-by: Shakeel Butt Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Johannes Weiner Cc: Muchun Song Cc: Roman Gushchin Cc: Yi Lai Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e78bc98ab229..215e2e87f42b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -268,10 +268,15 @@ struct mem_cgroup { #endif int kmemcg_id; - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; +#endif + + /* Keep the hot per-CPU stats pointer away from memory event counters. */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu + ____cacheline_aligned_in_smp; + +#ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif