Re: [PATCH v7u1 26/31] x86: Don't enable swiotlb if there is notenough ram for it

[Shuah Khan]

On Thu, Jan 24, 2013 at 9:51 AM, Shuah Khan <shuahkhan@xxxxxxxxx> wrote:
> On Thu, Jan 24, 2013 at 8:39 AM, Konrad Rzeszutek Wilk
> <konrad@xxxxxxxxxx> wrote:
>> On Fri, Jan 18, 2013 at 10:55:35AM -0500, Konrad Rzeszutek Wilk wrote:
>>> On Mon, Jan 14, 2013 at 10:19:22PM -0800, Yinghai Lu wrote:
>>> > On Fri, Jan 11, 2013 at 9:49 AM, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
>>> > > On Fri, Jan 11, 2013 at 8:52 AM, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
>>> > >>>
>>> > >>> I need to check this patch out and then also test-run them on IA64, AMD-VI, Calgary-X
>>> > >>> GART and Intel VT-d to make a sanity test.
>>> > >>
>>> > >> that will be great, and please check attached two patches, or you want
>>> > >> to me update
>>> > >> for-x86-boot branch and you test that instead?
>>> > >>
>>> > >> but if you want to check memmap=4095M$1M, then will need to test on
>>> > >> newer branch.
>>> > >
>>> > >
>>> > > I updated the for-x86-boot branch.
>>> > >
>>> > > git://git.kernel.org/pub/scm/linux/kernel/git/yinghai/linux-yinghai.git
>>> > > for-x86-boot
>>> > >
>>> >
>>> > Konrad,
>>> >
>>> > Did you get chance to test that branch on your setups?
>>>
>>> I tested it on the IA64 box - it worked without any hiccups. Going to
>>> try the Calgary-X and the rest of the machines over the weekend.
>>
>> Worked without issues on AMD GART, AMD Vi, Intel VT-d, and on boxes
>> without any IOMMU.
>>
>> I am having trouble getting my Calgary-X box to power on, so that
>> testing is taking a bit longer.
>>
>
> I still have the AMD system I tested earlier versions of this work. I
> started compiles with these patches on 3.7 and will let you know the
> status.

Tested 3.8-rc4 with the patches on AMD system with IOMMU on. Looks
good. I can't test low memory paths on this system very easily without
mucking with the code and force it treat it as low memory. So I just
tested the normal path. My main goal was to make sure AMD iommu driver
can still enable switolb and it does.

If you would like to me test the error cases, please let me know.

-- Shuah
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/