[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7D1E33F3-A390-4691-86C2-F7CB3E8309B3@alien8.de>
Date: Thu, 14 Jul 2022 19:58:08 +0000
From: Boris Petkov <bp@...en8.de>
To: Daniel Sneddon <daniel.sneddon@...ux.intel.com>,
Jonathan Corbet <corbet@....net>,
Ingo Molnar <mingo@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org
CC: pawan.kumar.gupta@...ux.intel.com,
antonio.gomez.iglesias@...ux.intel.com, linux-doc@...r.kernel.org,
"H. Peter Anvin" <hpa@...or.com>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] x86/speculation: Add BHI_DIS support
On July 14, 2022 7:52:35 PM UTC, Daniel Sneddon <daniel.sneddon@...ux.intel.com> 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).
>
>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.
Why is this a separately selectable option and not automatically enabled?
--
Sent from a small device: formatting sux and brevity is inevitable.
Powered by blists - more mailing lists