[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180618105928.oblisvtr2cpitilj@black.fi.intel.com>
Date: Mon, 18 Jun 2018 13:59:29 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: Dave Hansen <dave.hansen@...el.com>
Cc: Ingo Molnar <mingo@...hat.com>, x86@...nel.org,
Thomas Gleixner <tglx@...utronix.de>,
"H. Peter Anvin" <hpa@...or.com>,
Tom Lendacky <thomas.lendacky@....com>,
Kai Huang <kai.huang@...ux.intel.com>,
Jacob Pan <jacob.jun.pan@...ux.intel.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCHv3 12/17] x86/mm: Allow to disable MKTME after enumeration
On Wed, Jun 13, 2018 at 06:30:02PM +0000, Dave Hansen wrote:
> On 06/12/2018 07:39 AM, Kirill A. Shutemov wrote:
> > Separate MKTME enumaration from enabling. We need to postpone enabling
> > until initialization is complete.
>
> ^ enumeration
Nope.
I want to differentiate enumeration in detect_tme() and the point where
MKTME is usable: after mktme_init().
> > The new helper mktme_disable() allows to disable MKTME even if it's
>
> s/to disable/disabling/
> > enumerated successfully. MKTME initialization may fail and this
> > functionallity allows system to boot regardless of the failure.
>
> What can make it fail?
I'll add this to commit message:
MKTME needs per-KeyID direct mapping. It requires a lot more virtual
address space which may be a problem in 4-level paging mode. If the
system has more physical memory than we can handle with MKTME.
The feature allows to fail MKTME, but boot the system successfully.
--
Kirill A. Shutemov
Powered by blists - more mailing lists