[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ab6265e3-5adf-1129-fba7-cbcd2e6776b5@amd.com>
Date: Thu, 30 Mar 2023 17:37:35 +0530
From: Vasant Hegde <vasant.hegde@....com>
To: Joerg Roedel <joro@...tes.org>, Jakub Kicinski <kuba@...nel.org>,
Robin Murphy <robin.murphy@....com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@....com>,
iommu@...ts.linux.dev,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
Willem de Bruijn <willemb@...gle.com>,
Saeed Mahameed <saeed@...nel.org>
Subject: Re: AMD IOMMU problem after NIC uses multi-page allocation
Hi Jakub,
On 3/30/2023 1:11 PM, Joerg Roedel wrote:
> Also adding Vasant and Robin.
>
> Vasant, Robin, any idea?
>
I tried few things on my Milan system. I can't reproduce the issue.
Can you please try the patch mentioned by Yunsheng?
If its still an issue, can you please provide steps to reproduce? I will take a
look.
-Vasant
> On Wed, Mar 29, 2023 at 06:14:07PM -0700, Jakub Kicinski wrote:
>> Hi Joerg, Suravee,
>>
>> I see an odd NIC behavior with AMD IOMMU in lazy mode (on 5.19).
>>
>> The NIC allocates a buffer for Rx packets which is MTU rounded up
>> to page size. If I run it with 1500B MTU or 9000 MTU everything is
>> fine, slight but manageable perf hit.
>>
>> But if I flip the MTU to 9k, run some traffic and then go back to 1.5k
>> - 70%+ of CPU cycles are spent in alloc_iova (and children).
>>
>> Does this ring any bells?
Powered by blists - more mailing lists