linux-kernel - Re: [PATCH v6] x86/mm: Don't disable INVLPG if "incomplete Global INVLPG flushes" is fixed by microcode or the kernel is running in a hypervisor

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: <3ee70b6c-3399-43f9-8934-cb5a0e51f006@intel.com>
Date: Thu, 11 Apr 2024 07:44:43 -0700
From: Dave Hansen <dave.hansen@...el.com>
To: Xi Ruoyao <xry111@...111.site>, Dave Hansen
 <dave.hansen@...ux.intel.com>, Michael Kelley <mhklinux@...look.com>,
 Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>
Cc: Andy Lutomirski <luto@...nel.org>, Peter Zijlstra <peterz@...radead.org>,
 Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
 Borislav Petkov <bp@...en8.de>, "H. Peter Anvin" <hpa@...or.com>,
 x86@...nel.org, linux-kernel@...r.kernel.org,
 Sean Christopherson <seanjc@...gle.com>,
 Andrew Cooper <andrew.cooper3@...rix.com>
Subject: Re: [PATCH v6] x86/mm: Don't disable INVLPG if "incomplete Global
 INVLPG flushes" is fixed by microcode or the kernel is running in a
 hypervisor

On 4/11/24 03:48, Xi Ruoyao wrote:
> +	/*
> +	 * The Intel errata claims: "this erratum does not apply in VMX
> +	 * non-root operation.  It applies only when PCIDs are enabled
> +	 * and either in VMX root operation or outside VMX operation."
> +	 * So we are safe if we are surely running in a hypervisor.
> +	 */

When you revise this, could you please work to make this more succinct?
The Intel language on these things tends to be a bit flowery and is not
always well-suited for the kernel.

Also, saying that the erratum "claims" this casts doubt on it.  That's
counterproductive.  I believe the current documentation is correct.  My
original ce0b15d11ad8 ("x86/mm: Avoid incomplete Global INVLPG flushes")
should have considered virtualized systems immune to this issue.

I agree that it sounds weird.  It _is_ weird that systems running under
hypervisors aren't affected.  But that's all it is: a weird bug.  The
documentation is correct.