[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <17d73d88e08047f09636cf39edd69892@intel.com>
Date: Wed, 16 Mar 2022 22:23:26 +0000
From: "Luck, Tony" <tony.luck@...el.com>
To: Jason Gunthorpe <jgg@...dia.com>,
Jacob Pan <jacob.jun.pan@...ux.intel.com>
CC: "iommu@...ts.linux-foundation.org" <iommu@...ts.linux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>,
Joerg Roedel <joro@...tes.org>,
Christoph Hellwig <hch@...radead.org>,
Lu Baolu <baolu.lu@...ux.intel.com>,
Jean-Philippe Brucker <jean-philippe@...aro.com>,
"Pan, Jacob jun" <jacob.jun.pan@...el.com>,
"Raj, Ashok" <ashok.raj@...el.com>,
"Kumar, Sanjay K" <sanjay.k.kumar@...el.com>,
"Jiang, Dave" <dave.jiang@...el.com>,
"Zanussi, Tom" <tom.zanussi@...el.com>,
"Williams, Dan J" <dan.j.williams@...el.com>,
"Tian, Kevin" <kevin.tian@...el.com>,
"Liu, Yi L" <yi.l.liu@...el.com>
Subject: RE: [PATCH v2 3/8] iommu/vt-d: Implement device_pasid domain attach
ops
> I would expect real applications will try to use the same PASID for
> the same IOVA map to optimize IOTLB caching.
On Intel a ring3 application only gets to use one PASID.
The ENQCMD instruction pick up the PASID for the process
from the IA32_PASID MSR (set by OS when first access,
and on context switches thereafter).
Kernel users (ring0) can supply any PASID when they use
the ENQCMDS instruction. Is that what you mean when you
say "real applications"?
-Tony
Powered by blists - more mailing lists