linux-kernel - Re: [PATCH] x86/mm/tlb: avoid reading mm_tlb

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: <20220328103551.GY8939@worktop.programming.kicks-ass.net>
Date:   Mon, 28 Mar 2022 12:35:51 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Nadav Amit <nadav.amit@...il.com>
Cc:     Thomas Gleixner <tglx@...utronix.de>, linux-kernel@...r.kernel.org,
        Nadav Amit <namit@...are.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Ingo Molnar <mingo@...nel.org>,
        Andy Lutomirski <luto@...nel.org>, x86@...nel.org
Subject: Re: [PATCH] x86/mm/tlb: avoid reading mm_tlb_gen when possible

On Tue, Mar 22, 2022 at 10:07:57PM +0000, Nadav Amit wrote:
> From: Nadav Amit <namit@...are.com>
> 
> On extreme TLB shootdown storms, the mm's tlb_gen cacheline is highly
> contended and reading it should (arguably) be avoided as much as
> possible.
> 
> Currently, flush_tlb_func() reads the mm's tlb_gen unconditionally,
> even when it is not necessary (e.g., the mm was already switched).
> This is wasteful.
> 
> Moreover, one of the existing optimizations is to read mm's tlb_gen to
> see if there are additional in-flight TLB invalidations and flush the
> entire TLB in such a case. However, if the request's tlb_gen was already
> flushed, the benefit of checking the mm's tlb_gen is likely to be offset
> by the overhead of the check itself.
> 
> Running will-it-scale with tlb_flush1_threads show a considerable
> benefit on 56-core Skylake (up to +24%):
> 
> threads		Baseline (v5.17+)	+Patch
> 1		159960			160202
> 5		310808			308378 (-0.7%)
> 10		479110			490728
> 15		526771			562528
> 20		534495			587316
> 25		547462			628296
> 30		579616			666313
> 35		594134			701814
> 40		612288			732967
> 45		617517			749727
> 50		637476			735497
> 55		614363			778913 (+24%)
> 

Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>