[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <b9f4958b-ecd6-4a44-afd7-b39b21053630@huawei.com>
Date: Wed, 16 Oct 2024 19:53:52 +0800
From: Jijie Shao <shaojijie@...wei.com>
To: Jakub Kicinski <kuba@...nel.org>
CC: <shaojijie@...wei.com>, <davem@...emloft.net>, <edumazet@...gle.com>,
<pabeni@...hat.com>, <shenjian15@...wei.com>, <salil.mehta@...wei.com>,
<liuyonglong@...wei.com>, <wangpeiyang1@...wei.com>, <lanhao@...wei.com>,
<chenhao418@...wei.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH net 2/9] net: hns3: add sync command to sync io-pgtable
on 2024/10/16 9:19, Jakub Kicinski wrote:
> On Fri, 11 Oct 2024 17:45:14 +0800 Jijie Shao wrote:
>> To avoid errors in pgtable prefectch, add a sync command to sync
>> io-pagtable.
> I've never seen net drivers call iommu_iotlb functions.
> Could you provide more context on what this is doing and
> why such unusual handling is necessary?
Follow the reply of the previous patch.
In the case of large traffic, the TX bounce buffer may be used up.
At this point, we go to mapping/unmapping on TX path again.
So we added the sync command in driver to avoid hardware issue.
Thanks
Jijie Shao
Powered by blists - more mailing lists