[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [V10 1/4] hw/i386: Introduce AMD IOMMU
|
From: |
Jan Kiszka |
|
Subject: |
Re: [Qemu-devel] [V10 1/4] hw/i386: Introduce AMD IOMMU |
|
Date: |
Mon, 16 May 2016 08:51:32 +0200 |
|
User-agent: |
Mozilla/5.0 (X11; U; Linux i686 (x86_64); de; rv:1.8.1.12) Gecko/20080226 SUSE/2.0.0.12-1.1 Thunderbird/2.0.0.12 Mnenhy/0.7.5.666 |
On 2016-05-16 07:59, David Kiarie wrote:
> On Sun, May 15, 2016 at 10:29 PM, Jan Kiszka <address@hidden> wrote:
>> On 2016-05-09 14:15, David Kiarie wrote:
>>> + ret->iova = addr & AMDVI_PAGE_MASK_4K;
>>> + ret->translated_addr = (pte & AMDVI_DEV_PT_ROOT_MASK) &
>>> + AMDVI_PAGE_MASK_4K;
>>> + ret->addr_mask = ~AMDVI_PAGE_MASK_4K;
>>
>> This does not take huge pages (2M, 1G, ...) into account. Jailhouse
>> creates them, and its Linux guest goes mad. You need to use the correct
>> page size here, analogously to intel_iommu.c.
>
> Yes, this was meant to work with normal pages only. Until recently
> intel iommu supported 4k pages only so I figured I could as well work
> with 4k pages. Anyway, will fix this.
Huge pages are optional on Intel. Not AMD.
Jan