[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240103175202.GT50406@nvidia.com>
Date: Wed, 3 Jan 2024 13:52:02 -0400
From: Jason Gunthorpe <jgg@...dia.com>
To: Nicolin Chen <nicolinc@...dia.com>
Cc: Yi Liu <yi.l.liu@...el.com>, "Tian, Kevin" <kevin.tian@...el.com>,
"joro@...tes.org" <joro@...tes.org>,
"alex.williamson@...hat.com" <alex.williamson@...hat.com>,
"robin.murphy@....com" <robin.murphy@....com>,
"baolu.lu@...ux.intel.com" <baolu.lu@...ux.intel.com>,
"cohuck@...hat.com" <cohuck@...hat.com>,
"eric.auger@...hat.com" <eric.auger@...hat.com>,
"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
"mjrosato@...ux.ibm.com" <mjrosato@...ux.ibm.com>,
"chao.p.peng@...ux.intel.com" <chao.p.peng@...ux.intel.com>,
"yi.y.sun@...ux.intel.com" <yi.y.sun@...ux.intel.com>,
"peterx@...hat.com" <peterx@...hat.com>,
"jasowang@...hat.com" <jasowang@...hat.com>,
"shameerali.kolothum.thodi@...wei.com" <shameerali.kolothum.thodi@...wei.com>,
"lulu@...hat.com" <lulu@...hat.com>,
"suravee.suthikulpanit@....com" <suravee.suthikulpanit@....com>,
"iommu@...ts.linux.dev" <iommu@...ts.linux.dev>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-kselftest@...r.kernel.org" <linux-kselftest@...r.kernel.org>,
"Duan, Zhenzhong" <zhenzhong.duan@...el.com>,
"joao.m.martins@...cle.com" <joao.m.martins@...cle.com>,
"Zeng, Xin" <xin.zeng@...el.com>,
"Zhao, Yan Y" <yan.y.zhao@...el.com>
Subject: Re: [PATCH v7 1/3] iommufd: Add data structure for Intel VT-d
stage-1 cache invalidation
On Wed, Jan 03, 2024 at 09:06:23AM -0800, Nicolin Chen wrote:
> On Wed, Jan 03, 2024 at 12:58:48PM -0400, Jason Gunthorpe wrote:
> > On Wed, Jan 03, 2024 at 08:48:46AM -0800, Nicolin Chen wrote:
> > > > You can pass the ctx to the invalidate op, it is already implied
> > > > because the passed iommu_domain is linked to a single iommufd ctx.
> > >
> > > The device virtual id lookup API needs something similar, yet it
> > > likely needs a viommu pointer (or its id) instead? As the table
> > > is attached to a viommu while an ictx can have multiple viommus,
> > > right?
> >
> > Yes, when we get to an API for that it will have to be some op
> > 'invalidate_viommu(..)' and it can get the necessary pointers.
>
> OK! I will try that first.
>
> > The viommu object will have to be some driver object like the
> > iommu_domain.
>
> I drafted something like this, linking it to struct iommu_device:
>
> +struct iommufd_viommu {
> + struct iommufd_object obj;
> + struct iommufd_ctx *ictx;
> + struct iommu_device *iommu_dev;
> + struct iommufd_hwpt_paging *hwpt;
> + /* array of struct iommufd_device, indexed by device virtual id */
> + struct xarray device_ids;
> +};
The driver would have to create it and there would be some driver
specific enclosing struct to go with it
Perhaps device_ids goes in the driver specific struct, I don't know.
Not sure it should have hwpt at all, probably vmid should come from
the driver specific struct in some driver specific way
Jason
Powered by blists - more mailing lists