From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:42023)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <peter.maydell@linaro.org>) id 1VZStG-0006xP-Ha
	for qemu-devel@nongnu.org; Thu, 24 Oct 2013 17:56:32 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <peter.maydell@linaro.org>) id 1VZSt6-0002EC-Vk
	for qemu-devel@nongnu.org; Thu, 24 Oct 2013 17:56:26 -0400
Received: from mail-lb0-f172.google.com ([209.85.217.172]:47952)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <peter.maydell@linaro.org>) id 1VZSt6-0002DY-P8
	for qemu-devel@nongnu.org; Thu, 24 Oct 2013 17:56:16 -0400
Received: by mail-lb0-f172.google.com with SMTP id c11so105600lbj.31
	for <qemu-devel@nongnu.org>; Thu, 24 Oct 2013 14:56:15 -0700 (PDT)
MIME-Version: 1.0
In-Reply-To: <20131024211249.723543071@amt.cnet>
References: <20131024211158.064049176@amt.cnet>
	<20131024211249.723543071@amt.cnet>
From: Peter Maydell <peter.maydell@linaro.org>
Date: Thu, 24 Oct 2013 22:55:54 +0100
Message-ID: <CAFEAcA99Uo2gbbnzBTaruw-cC-PpLW_8mTbWyVLxyxun=fxUWg@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Subject: Re: [Qemu-devel] [patch 2/2] i386: pc: align gpa<->hpa on 1GB
	boundary
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>, Paolo Bonzini <pbonzini@redhat.com>, QEMU Developers <qemu-devel@nongnu.org>, Gleb Natapov <gleb@redhat.com>

On 24 October 2013 22:12, Marcelo Tosatti <mtosatti@redhat.com> wrote:
> Align guest physical address and host physical address
> beyond guest 4GB on a 1GB boundary, in case hugetlbfs is used.
>
> Otherwise 1GB TLBs cannot be cached for the range.

> +        if (hpagesize == (1<<30)) {
> +            unsigned long holesize = 0x100000000ULL - below_4g_mem_size;
> +
> +            memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
> +                                    0x100000000ULL,
> +                                    above_4g_mem_size - holesize);
> +            memory_region_add_subregion(system_memory, 0x100000000ULL,
> +                                    ram_above_4g);
> +
> +            ram_above_4g_piecetwo = g_malloc(sizeof(*ram_above_4g_piecetwo));
> +            memory_region_init_alias(ram_above_4g_piecetwo, NULL,
> +                                     "ram-above-4g-piecetwo", ram,
> +                                     0x100000000ULL - holesize, holesize);
> +            memory_region_add_subregion(system_memory,
> +                                        0x100000000ULL +
> +                                        above_4g_mem_size - holesize,
> +                                        ram_above_4g_piecetwo);
> +        } else {
> +            memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
> +                                    below_4g_mem_size, above_4g_mem_size);
> +            memory_region_add_subregion(system_memory, 0x100000000ULL,
>                                      ram_above_4g);

This looks pretty weird. Presence or absence of host OS features
shouldn't affect how we model the guest hardware and RAM.
Conversely, if hugetlbs have performance related requirements
then a patch which only touches the x86 pc model seems rather
limited.

-- PMM