From: Jason Gunthorpe <jgg@ziepe.ca>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>,
arnd@arndb.de, "Yu, Fenghua" <fenghua.yu@intel.com>,
gregkh@linuxfoundation.org, iommu@lists.linux-foundation.org,
zhangfei.gao@linaro.org, linux-accelerators@lists.ozlabs.org
Subject: Re: [PATCH 0/2] iommu: Remove iommu_sva_ops::mm_exit()
Date: Thu, 9 Apr 2020 11:25:19 -0300 [thread overview]
Message-ID: <20200409142519.GH11886@ziepe.ca> (raw)
In-Reply-To: <20200409071424.1653b889@jacob-builder>
On Thu, Apr 09, 2020 at 07:14:24AM -0700, Jacob Pan wrote:
> > When the process is killed, mm release can happen before fds are
> > released. If you look at do_exit() in kernel/exit.c:
> >
> > exit_mm()
> > mmput()
> > -> mmu release notifier
> > ...
> > exit_files()
> > close_files()
> > fput()
> > exit_task_work()
> > __fput()
> > -> unbind()
> >
> So unbind is coming anyway, the difference in handling in mmu release
> notifier is whether we silently drop DMA fault vs. reporting fault?
Userspace can significantly delay the final fput triggering the
unbind, the above is only for the trivial case where the process
owning the mm_struct is the only process holding the fd.
The destruction of a mm_struct should be treated the same as unmapping
every vma in the process. The observable effect should be no different
than munmap.
Jason
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2020-04-09 14:25 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-08 14:04 [PATCH 0/2] iommu: Remove iommu_sva_ops::mm_exit() Jean-Philippe Brucker
2020-04-08 14:04 ` [PATCH 1/2] uacce: Remove mm_exit() op Jean-Philippe Brucker
2020-04-09 9:07 ` Zhangfei Gao
2020-04-09 9:44 ` Jean-Philippe Brucker
2020-04-08 14:04 ` [PATCH 2/2] iommu: Remove iommu_sva_ops::mm_exit() Jean-Philippe Brucker
2020-04-08 18:35 ` [PATCH 0/2] " Jacob Pan
2020-04-08 19:02 ` Jason Gunthorpe
2020-04-08 21:35 ` Jacob Pan
2020-04-08 22:32 ` Jason Gunthorpe
2020-04-08 23:48 ` Jacob Pan
2020-04-09 6:39 ` Jean-Philippe Brucker
2020-04-09 14:14 ` Jacob Pan
2020-04-09 14:25 ` Jason Gunthorpe [this message]
2020-04-09 16:21 ` Jacob Pan
2020-04-09 16:58 ` Jason Gunthorpe
2020-04-09 14:50 ` Jean-Philippe Brucker
2020-04-09 16:27 ` Jacob Pan
2020-04-10 15:52 ` Jacob Pan
2020-04-15 7:47 ` Jean-Philippe Brucker
2020-04-16 20:58 ` Jacob Pan
2020-04-20 8:02 ` Jean-Philippe Brucker
2020-04-09 12:08 ` Jason Gunthorpe
2020-04-09 16:31 ` Jacob Pan
2020-04-08 23:49 ` Fenghua Yu
2020-04-09 12:12 ` Jason Gunthorpe
2020-04-08 19:04 ` Jason Gunthorpe
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=20200409142519.GH11886@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=arnd@arndb.de \
--cc=fenghua.yu@intel.com \
--cc=gregkh@linuxfoundation.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe@linaro.org \
--cc=linux-accelerators@lists.ozlabs.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).