[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <eb700675-f698-62e5-bbab-3d199ff58dcb@linux.intel.com>
Date: Thu, 15 Apr 2021 13:33:24 +0800
From: Lu Baolu <baolu.lu@...ux.intel.com>
To: Jason Gunthorpe <jgg@...dia.com>
Cc: baolu.lu@...ux.intel.com,
Jacob Pan <jacob.jun.pan@...ux.intel.com>,
Jean-Philippe Brucker <jean-philippe@...aro.org>,
LKML <linux-kernel@...r.kernel.org>,
iommu@...ts.linux-foundation.org, Joerg Roedel <joro@...tes.org>,
Jean-Philippe Brucker <jean-philippe@...aro.com>,
Yi Liu <yi.l.liu@...el.com>, Raj Ashok <ashok.raj@...el.com>,
"Tian, Kevin" <kevin.tian@...el.com>,
Dave Jiang <dave.jiang@...el.com>, wangzhou1@...ilicon.com,
zhangfei.gao@...aro.org, vkoul@...nel.org
Subject: Re: [PATCH 2/2] iommu/sva: Remove mm parameter from SVA bind API
Hi Jason,
On 4/14/21 7:26 PM, Jason Gunthorpe wrote:
> On Wed, Apr 14, 2021 at 02:22:09PM +0800, Lu Baolu wrote:
>
>> I still worry about supervisor pasid allocation.
>>
>> If we use iommu_sva_alloc_pasid() to allocate a supervisor pasid, which
>> mm should the pasid be set? I've ever thought about passing &init_mm to
>> iommu_sva_alloc_pasid(). But if you add "mm != current->mm", this seems
>> not to work. Or do you prefer a separated interface for supervisor pasid
>> allocation/free?
>
> Without a mm_struct it is not SVA, so don't use SVA APIs for whatever
> a 'supervisor pasid' is
The supervisor PASID has its mm_struct. The only difference is that the
device will set priv=1 in its DMA transactions with the PASID.
Best regards,
baolu
Powered by blists - more mailing lists