Sender: Paolo Bonzini <paolo.bonzini@gmail.com>
Message-ID: <3cf70fa7-8e3e-5066-bdf4-59aec5215640@redhat.com>
Date:   Wed, 8 Dec 2021 14:57:31 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.2.0
Subject: Re: Rewording of Setting IA32_XFD[18] (Re: Thoughts of AMX KVM
 support based on latest kernel)
Content-Language: en-US
To:     "Nakajima, Jun" <jun.nakajima@intel.com>,
        Thomas Gleixner <tglx@linutronix.de>
Cc:     "Tian, Kevin" <kevin.tian@intel.com>,
        "Liu, Jing2" <jing2.liu@intel.com>,
        LKML <linux-kernel@vger.kernel.org>,
        "x86@kernel.org" <x86@kernel.org>,
        "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Arjan van de Ven <arjan@linux.intel.com>,
        Jing Liu <jing2.liu@linux.intel.com>,
        "seanjc@google.com" <seanjc@google.com>,
        "Cooper, Andrew" <andrew.cooper3@citrix.com>,
        "Bae, Chang Seok" <chang.seok.bae@intel.com>
References: <BYAPR11MB325685AB8E3DFD245846F854A9939@BYAPR11MB3256.namprd11.prod.outlook.com>
 <878rxn6h6t.ffs@tglx> <16BF8BE6-B7B1-4F3E-B972-9D82CD2F23C8@intel.com>
 <2e2ab02c-b324-e136-924a-0376040163a8@redhat.com>
 <BN9PR11MB5433D6A1368904D9B748846B8C9A9@BN9PR11MB5433.namprd11.prod.outlook.com>
 <c7d87723-5533-257f-fbf0-ecd3a0b96602@redhat.com>
 <D93C093C-8420-45DA-99F5-0A5318ADBBEF@intel.com> <87sfvslaha.ffs@tglx>
 <5ABC728C-9FD3-4BEB-BD02-61E910D69847@intel.com>
 <9F8F8297-E70F-427C-BEDA-9FAB86877DBD@intel.com>
From:   Paolo Bonzini <pbonzini@redhat.com>
In-Reply-To: <9F8F8297-E70F-427C-BEDA-9FAB86877DBD@intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 12/8/21 01:50, Nakajima, Jun wrote:
> 3.3 RECOMMENDATIONS FOR SYSTEM SOFTWARE
> 
> System software may disable use of Intel AMX by clearing XCR0[18:17],
> by clearing CR4.OSXSAVE, or by setting IA32_XFD[18]. System software
> should initialize AMX state (e.g., by executing TILERELEASE) when
> doing so because maintaining AMX state in a non-initialized state may
> have negative power and performance implications. In addition,
> software should not rely on the state of the tile data after setting

I would change this to "must not rely", otherwise looks good.  Thanks!

Paolo

> IA32_XFD[18]; software should always reload or reinitialize the tile
> data after clearing IA32_XFD[18].