Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 18 Dec 2018 14:05:37 -0800
From:   Andi Kleen <ak@linux.intel.com>
To:     Dave Hansen <dave.hansen@intel.com>
Cc:     "Li, Aubrey" <aubrey.li@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Aubrey Li <aubrey.li@intel.com>, mingo@redhat.com,
        peterz@infradead.org, hpa@zytor.com, tim.c.chen@linux.intel.com,
        arjan@linux.intel.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v6 1/3] x86/fpu: track AVX-512 usage of tasks
Message-ID: <20181218220537.GJ25620@tassilo.jf.intel.com>
References: <20181218042218.8653-1-aubrey.li@intel.com>
 <alpine.DEB.2.21.1812181448170.12686@nanos.tec.linutronix.de>
 <62997df2-0817-b54d-b11e-00a567f1d67c@linux.intel.com>
 <alpine.DEB.2.21.1812181630530.14031@nanos.tec.linutronix.de>
 <b14a9c82-3336-0f13-1a27-fba929e6b4fb@linux.intel.com>
 <20181218213826.GI25620@tassilo.jf.intel.com>
 <d892d7bb-2a66-497c-4728-138c8e5e077f@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <d892d7bb-2a66-497c-4728-138c8e5e077f@intel.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Dec 18, 2018 at 01:44:41PM -0800, Dave Hansen wrote:
> On 12/18/18 1:38 PM, Andi Kleen wrote:
> >> I misunderstood, you mean 32bit kernel, not 32bit machine. Theoretically 32bit
> >> kernel can use AVX512, but not sure if anyone use it like this. get_jiffies_64()
> >> includes jiffies_lock ops so not good in context switch. So I want to use raw
> >> jiffies_64 here. jiffies is a good candidate but it has wraparound overflow issue.
> >> Other time source are expensive here.
> >>
> >> Should I limit the code only running on 64bit kernel? 
> > Yes making it 64bit only should be fine.
> 
> I think I'd rather just disable AVX512 itself on 32-bit and be done with
> it.  I think more than half of the ~2k of XSAVE space that it consumes
> in *every* *task* is just pure waste because it has to be 0's.
> 
> This ~2k of extra space is also lowmem, which makes it even more valuable.

That will actually break programs.

If someone compiled binaries with -march=native on a system with AVX512
they wouldn't work anymore.

Don't think we can do it.


-Andi