linux-kernel - Re: [PATCH] x86/speculation: Add BHI

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] [day] [month] [year] [list]

Date:   Thu, 14 Jul 2022 22:04:20 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Daniel Sneddon <daniel.sneddon@...ux.intel.com>
Cc:     Jonathan Corbet <corbet@....net>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@...nel.org>,
        pawan.kumar.gupta@...ux.intel.com,
        antonio.gomez.iglesias@...ux.intel.com,
        "H. Peter Anvin" <hpa@...or.com>,
        "open list:DOCUMENTATION" <linux-doc@...r.kernel.org>,
        open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] x86/speculation: Add BHI_DIS support

On Thu, Jul 14, 2022 at 12:52:35PM -0700, Daniel Sneddon wrote:
> Branch History Injection (BHI) attacks can be mitigated using the
> BHI_DIS_S indirect predictor control bit located in MSR_IA32_SPEC_CTRL
> register. Set BHI_DIS in MSR_IA32_SPC_CTRL to prevent predicted
> targets of indirect branches executed in CPL0, CPL1, or CPL2 from
> being selected based on branch history from branches executed in CPL3.
> Support for this feature is enumerated by CPUID.7.2.EDX[BHI_CTRL] (bit 4).

What actual hardware will have this?

> Users wanting BHI protection can specify spectre_v2=eibrs,bhi_dis to
> enable hardware BHI protections.  On platforms where BHI protections
> are not available in the hardware revert to eibrs,retpoline
> mitigations.

AFAICT this doesn't get auto-selected; how bad is performance for this
to not be so?