Re: [linux-next:master] [mm/vmpressure] ea928e9e18: stress-ng.mremap.ops_per_sec 36.2% regression

[Usama Arif <usama.arif@linux.dev>]

On 13/08/2026 18:01, Shakeel Butt wrote:
> On Thu, Aug 13, 2026 at 09:16:22PM +0800, kernel test robot wrote:
>>
>>
>> Hello,
>>
>> kernel test robot noticed a 36.2% regression of stress-ng.mremap.ops_per_sec on:
>>
>> commit: ea928e9e18da682e9a5bc40aa862bff7ce5ae42e ("mm/vmpressure: move v1 userspace eventfd code into memcontrol-v1.c") https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
>>
>> in testcase: stress-ng
>> version: stress-ng-x86_64-29ce10a2c-1_20260712
>> with following parameters:
>>
>> 	nr_threads: 100%
>> 	testtime: 60s
>> 	test: mremap
>> 	cpufreq_governor: performance
>>
>>
>>
>> config: x86_64-rhel-9.4 (CONFIG_MEMCG=y and CONFIG_MEMCG_V1 is not set)
>> compiler: gcc-14
>> test machine: 256 threads 4 sockets INTEL(R) XEON(R) PLATINUM 8592+ (Emerald Rapids) with 256G memory
>>
>> (please refer to attached dmesg/kmsg for entire log/backtrace)
>>
> 
> Hi there,
> 
> Can you please test the following patch and see if it fixes the regression?
> 
> 
> From 84c0b05b3bc5cf73ee66ead75aafb1ad684462c3 Mon Sep 17 00:00:00 2001
> From: Shakeel Butt <shakeel.butt@linux.dev>
> Date: Thu, 13 Aug 2026 09:38:28 -0700
> Subject: [PATCH] memcg: keep vmstats_percpu off the memory_events[] cacheline
> 
> Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
> ---
>  include/linux/memcontrol.h | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index e78bc98ab229..e25d5b9a1db8 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -246,8 +246,13 @@ struct mem_cgroup {
>  	/* handle for "memory.swap.events" */
>  	struct cgroup_file swap_events_file;
>  
> -	/* memory.stat */
> +	/* Read-mostly. */
>  	struct memcg_vmstats	*vmstats;
> +	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
> +	int			kmemcg_id;
> +
> +	/* Write-hot from here on; do not let it share with the above. */
> +	CACHELINE_PADDING(_pad_);
>  
>  	/* memory.events */
>  	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
> @@ -266,9 +271,6 @@ struct mem_cgroup {
>  #if BITS_PER_LONG < 64
>  	seqlock_t		socket_pressure_seqlock;
>  #endif
> -	int kmemcg_id;
> -
> -	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
>  
>  #ifdef CONFIG_CGROUP_WRITEBACK
>  	struct list_head cgwb_list;


I was currently testing this diff, not sure which one would be better.

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e78bc98ab229b..215e2e87f42b2 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