From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:43266)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <agraf@suse.de>) id 1YnNto-00077M-EP
	for qemu-devel@nongnu.org; Wed, 29 Apr 2015 05:03:21 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <agraf@suse.de>) id 1YnNtk-0003VA-5w
	for qemu-devel@nongnu.org; Wed, 29 Apr 2015 05:03:20 -0400
Received: from cantor2.suse.de ([195.135.220.15]:37951 helo=mx2.suse.de)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <agraf@suse.de>) id 1YnNtj-0003R8-W7
	for qemu-devel@nongnu.org; Wed, 29 Apr 2015 05:03:16 -0400
Message-ID: <55409E4E.3090905@suse.de>
Date: Wed, 29 Apr 2015 11:03:10 +0200
From: Alexander Graf <agraf@suse.de>
MIME-Version: 1.0
References: <1426705700-2564-1-git-send-email-drjones@redhat.com>
	<1426705833-2679-1-git-send-email-drjones@redhat.com>
In-Reply-To: <1426705833-2679-1-git-send-email-drjones@redhat.com>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] [RFC PATCH 0/3] KVM: Introduce KVM_MEM_UNCACHED
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: Andrew Jones <drjones@redhat.com>, kvmarm@lists.cs.columbia.edu, qemu-devel@nongnu.org, ard.biesheuvel@linaro.org, christoffer.dall@linaro.org, marc.zyngier@arm.com, peter.maydell@linaro.org, pbonzini@redhat.com
Cc: catalin.marinas@arm.com, lersek@redhat.com, m.smarduch@samsung.com



On 18.03.15 20:10, Andrew Jones wrote:
> Introduce a new memory region flag, KVM_MEM_UNCACHED, which
> is needed by ARM. This flag informs KVM that the given memory
> region is typically mapped by the guest as uncached. KVM for
> ARM then maps that region as uncached for userspace as well,
> in order to keep coherency.

I finally managed to give this a spin and immediately ran into an
unaligned access trap:

[  116.509976] Unhandled fault: alignment fault (0x92000061) at
0x000003ffb1300000

Program received signal SIGBUS, Bus error.
[Switching to Thread 0x3ffb317ecb0 (LWP 1956)]
0x000003ffb685ed68 in memset () from /lib64/libc.so.6
(gdb) bt
#0  0x000003ffb685ed68 in memset () from /lib64/libc.so.6
#1  0x000002aaaac013ec in memset (__len=3D<optimized out>, __ch=3D0,
__dest=3D<optimized out>) at /usr/include/bits/string3.h:90
#2  vbe_ioport_write_data (opaque=3D0x2aaabbd3600, addr=3D<optimized out>=
,
val=3D65) at /usr/src/debug/qemu-2.3.0-rc4/hw/display/vga.c:739
#3  0x000002aaaabe07dc in memory_region_write_accessor (mr=3D<optimized
out>, addr=3D<optimized out>, value=3D<optimized out>, size=3D<optimized =
out>,
    shift=3D<optimized out>, mask=3D<optimized out>) at
/usr/src/debug/qemu-2.3.0-rc4/memory.c:430
[...]

So maybe forcing the guest to see VRAM as cached is the safer choice
after all?

Alex