linux-kernel - Re: [PATCH 2/3] mm, memcg: inline mem_cgroup_{charge/uncharge} to improve disabled memcg config

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <YOhh0IabpRk/W/qR@cmpxchg.org>
Date:   Fri, 9 Jul 2021 10:48:48 -0400
From:   Johannes Weiner <hannes@...xchg.org>
To:     Suren Baghdasaryan <surenb@...gle.com>
Cc:     tj@...nel.org, mhocko@...nel.org, vdavydov.dev@...il.com,
        akpm@...ux-foundation.org, shakeelb@...gle.com, guro@...com,
        songmuchun@...edance.com, shy828301@...il.com, alexs@...nel.org,
        alexander.h.duyck@...ux.intel.com, richard.weiyang@...il.com,
        vbabka@...e.cz, axboe@...nel.dk, iamjoonsoo.kim@....com,
        david@...hat.com, willy@...radead.org, apopple@...dia.com,
        minchan@...nel.org, linmiaohe@...wei.com,
        linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
        linux-mm@...ck.org, kernel-team@...roid.com
Subject: Re: [PATCH 2/3] mm, memcg: inline mem_cgroup_{charge/uncharge} to
 improve disabled memcg config

On Thu, Jul 08, 2021 at 05:05:08PM -0700, Suren Baghdasaryan wrote:
> Inline mem_cgroup_{charge/uncharge} and mem_cgroup_uncharge_list functions
> functions to perform mem_cgroup_disabled static key check inline before
> calling the main body of the function. This minimizes the memcg overhead
> in the pagefault and exit_mmap paths when memcgs are disabled using
> cgroup_disable=memory command-line option.
> This change results in ~0.4% overhead reduction when running PFT test
> comparing {CONFIG_MEMCG=n} against {CONFIG_MEMCG=y, cgroup_disable=memory}
> configurationon on an 8-core ARM64 Android device.
> 
> Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>

Sounds reasonable to me as well. One comment:

> @@ -693,13 +693,59 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
>  		page_counter_read(&memcg->memory);
>  }
>  
> -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
> +struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
> +
> +int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg,
> +			gfp_t gfp);
> +/**
> + * mem_cgroup_charge - charge a newly allocated page to a cgroup
> + * @page: page to charge
> + * @mm: mm context of the victim
> + * @gfp_mask: reclaim mode
> + *
> + * Try to charge @page to the memcg that @mm belongs to, reclaiming
> + * pages according to @gfp_mask if necessary. if @mm is NULL, try to
> + * charge to the active memcg.
> + *
> + * Do not use this for pages allocated for swapin.
> + *
> + * Returns 0 on success. Otherwise, an error code is returned.
> + */
> +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
> +				    gfp_t gfp_mask)
> +{
> +	struct mem_cgroup *memcg;
> +	int ret;
> +
> +	if (mem_cgroup_disabled())
> +		return 0;
> +
> +	memcg = get_mem_cgroup_from_mm(mm);
> +	ret = __mem_cgroup_charge(page, memcg, gfp_mask);
> +	css_put(&memcg->css);
> +
> +	return ret;

Why not do

int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
			gfp_t gfp_mask);

static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
				    gfp_t gfp_mask)
{
	if (mem_cgroup_disabled())
		return 0;

	return __mem_cgroup_charge(page, memcg, gfp_mask);
}

like in the other cases as well?

That would avoid inlining two separate function calls into all the
callsites...

There is an (internal) __mem_cgroup_charge() already, but you can
rename it charge_memcg().