linux-kernel - Re: [PATCH v10 09/12] x86/mm: enable broadcast TLB invalidation for multi-threaded processes

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 for Android: free password hash cracker in your pocket

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

Message-Id: <940E9420-0CD3-4C9A-AFCC-23433AF8EFA4@gmail.com>
Date: Wed, 12 Feb 2025 14:07:08 +0200
From: Nadav Amit <nadav.amit@...il.com>
To: Rik van Riel <riel@...riel.com>
Cc: the arch/x86 maintainers <x86@...nel.org>,
 Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
 Borislav Petkov <bp@...en8.de>,
 peterz@...radead.org,
 Dave Hansen <dave.hansen@...ux.intel.com>,
 zhengqi.arch@...edance.com,
 thomas.lendacky@....com,
 kernel-team@...a.com,
 "open list:MEMORY MANAGEMENT" <linux-mm@...ck.org>,
 Andrew Morton <akpm@...ux-foundation.org>,
 jackmanb@...gle.com,
 jannh@...gle.com,
 mhklinux@...look.com,
 andrew.cooper3@...rix.com,
 Manali Shukla <Manali.Shukla@....com>
Subject: Re: [PATCH v10 09/12] x86/mm: enable broadcast TLB invalidation for
 multi-threaded processes

It all looks pretty sane to me.

One small note:

> On 11 Feb 2025, at 23:08, Rik van Riel <riel@...riel.com> wrote:
> 
> +/*
> + * Check whether a process is currently active on more than "threshold" CPUs.
> + * This is a cheap estimation on whether or not it may make sense to assign
> + * a global ASID to this process, and use broadcast TLB invalidation.
> + */
> +static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
> +{
> +	int count = 0;
> +	int cpu;
> +
> +	/* This quick check should eliminate most single threaded programs. */
> +	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
> +		return false;
> +

Does it make sense to first check mm.mm_users against the threshold? It might
be less cache-contended.

Anyhow, for what’s it worth:

Reviewed-by: Nadav Amit <nadav.amit@...il.com <mailto:nadav.amit@...il.com>>