All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nicolin Chen <nicolinc@nvidia.com>
To: Zhangfei Gao <zhangfei.gao@linaro.org>,
	Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>,
	Robin Murphy <robin.murphy@arm.com>,
	"kevin.tian@intel.com" <kevin.tian@intel.com>,
	"yi.l.liu@intel.com" <yi.l.liu@intel.com>,
	"eric.auger@redhat.com" <eric.auger@redhat.com>,
	"baolu.lu@linux.intel.com" <baolu.lu@linux.intel.com>,
	"jean-philippe@linaro.org" <jean-philippe@linaro.org>,
	"iommu@lists.linux.dev" <iommu@lists.linux.dev>,
	qianweili <qianweili@huawei.com>
Subject: Re: Cache Invalidation Solution for Nested IOMMU
Date: Wed, 3 May 2023 16:44:48 -0700	[thread overview]
Message-ID: <ZFLx8Ltv/3TL5eFm@Asurada-Nvidia> (raw)
In-Reply-To: <0d41efe6b0a844878eadccddc2e12679@huawei.com>

On Wed, May 03, 2023 at 03:14:28PM +0000, Shameerali Kolothum Thodi wrote:

> > > On my emulation environment (very slow), with mmap, I see
> > > improvements. I'll also try setting up a test suite on a proper HW
> > > this week.
> > >
> >
> > Still debugging the mmap method here,
> >
> > Status 4.12
> >
> > 1.  ioctl method works, based on iommufd
 
> I had a go with your above branches. The issue below seems to happen only
> when you assign multiple devices to Guest. It looks like when you have multiple devices
> attached to Guest, the host kernel receives invalid Guest cmd(0x0) and ends up issuing
> that to HW triggering the below errors.

I actually found a bug in my previous wip branch (non-mmap),
resulting in a cons/prod index overflow. But the mmap branch
seems to be okay, since my QEMU code copies all TLBI commands
starting from index=0x0.

You may compare the git-diff, just in case that it helps:
https://github.com/nicolinc/iommufd/commits/wip/iommufd_nesting-04262023-Nic
https://github.com/nicolinc/qemu/commits/wip/iommufd_nesting-04222023

Btw, I ran a comparison on a real hardware. But it does not
show significant improvements between the ioctl solution and
the mmap solution. So I kept the ioctl one in v2.

Thanks
Nic

  reply	other threads:[~2023-05-03 23:45 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-03  0:33 Cache Invalidation Solution for Nested IOMMU Nicolin Chen
2023-04-03  7:26 ` Liu, Yi L
2023-04-03  8:39   ` Tian, Kevin
2023-04-03 15:24     ` Nicolin Chen
2023-04-04  2:42       ` Tian, Kevin
2023-04-04  3:12         ` Nicolin Chen
2023-04-03 12:23   ` Jason Gunthorpe
2023-04-03  8:00 ` Tian, Kevin
2023-04-03 14:29   ` Nicolin Chen
2023-04-04  2:15     ` Tian, Kevin
2023-04-04  2:47       ` Nicolin Chen
2023-04-03 14:08 ` Jason Gunthorpe
2023-04-03 14:51   ` Nicolin Chen
2023-04-03 19:15     ` Robin Murphy
2023-04-04  0:02       ` Nicolin Chen
2023-04-04 16:20         ` Jason Gunthorpe
2023-04-04 16:50           ` Shameerali Kolothum Thodi
2023-04-05 11:57             ` Jason Gunthorpe
2023-04-06  6:23             ` Zhangfei Gao
2023-04-06  6:39               ` Nicolin Chen
2023-04-06 11:40               ` Jason Gunthorpe
2023-04-10  1:08                 ` Nicolin Chen
2023-04-11  9:07                   ` Jean-Philippe Brucker
2023-04-11 11:57                     ` Jason Gunthorpe
2023-04-11 18:39                       ` Nicolin Chen
2023-04-11 18:41                         ` Jason Gunthorpe
2023-04-11 19:02                           ` Nicolin Chen
2023-04-11 18:43                     ` Nicolin Chen
2023-04-12  2:47                   ` Zhangfei Gao
2023-04-12  5:47                     ` Nicolin Chen
2023-05-03 15:14                     ` Shameerali Kolothum Thodi
2023-05-03 23:44                       ` Nicolin Chen [this message]
2023-04-05  5:45           ` Nicolin Chen
2023-04-05 11:37             ` Jason Gunthorpe
2023-04-05 15:34               ` Nicolin Chen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ZFLx8Ltv/3TL5eFm@Asurada-Nvidia \
    --to=nicolinc@nvidia.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=eric.auger@redhat.com \
    --cc=iommu@lists.linux.dev \
    --cc=jean-philippe@linaro.org \
    --cc=jgg@nvidia.com \
    --cc=kevin.tian@intel.com \
    --cc=qianweili@huawei.com \
    --cc=robin.murphy@arm.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=yi.l.liu@intel.com \
    --cc=zhangfei.gao@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.