From: Jason Gunthorpe <jgg@ziepe.ca>
To: lizhe.67@bytedance.com
Cc: david@redhat.com, akpm@linux-foundation.org,
alex.williamson@redhat.com, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
peterx@redhat.com
Subject: Re: [PATCH v4 2/3] gup: introduce unpin_user_folio_dirty_locked()
Date: Thu, 19 Jun 2025 09:35:04 -0300 [thread overview]
Message-ID: <20250619123504.GA1643390@ziepe.ca> (raw)
In-Reply-To: <20250619090542.29974-1-lizhe.67@bytedance.com>
On Thu, Jun 19, 2025 at 05:05:42PM +0800, lizhe.67@bytedance.com wrote:
> As I understand it, there seem to be some issues with this
> implementation. How can we obtain the value of dma->has_reserved
> (acquiring it within vfio_pin_pages_remote() might be a good option)
Yes, you record it during vfio_pin_pages operations. If VFIO call
iommu_map on something that went down the non-GUP path then it sets
the flag.
> and ensure that this value remains unchanged from the time of
> assignment until we perform the unpin operation?
Map/unmap are paired and not allowed to race so that isn't an issue.
> I've searched through the code and it appears that there are
> instances where SetPageReserved() is called outside of the
> initialization phase. Please correct me if I am wrong.
It should not be relevant here, pages under use by VFIO are not
permitted to change it will break things.
Jason
next prev parent reply other threads:[~2025-06-19 12:35 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-17 4:18 [PATCH v4 0/3] optimize vfio_unpin_pages_remote() for large folio lizhe.67
2025-06-17 4:18 ` [PATCH v4 1/3] vfio/type1: batch vfio_find_vpfn() in function vfio_unpin_pages_remote() lizhe.67
2025-06-17 4:18 ` [PATCH v4 2/3] gup: introduce unpin_user_folio_dirty_locked() lizhe.67
2025-06-17 7:35 ` David Hildenbrand
2025-06-17 13:42 ` Jason Gunthorpe
2025-06-17 13:45 ` David Hildenbrand
2025-06-17 13:58 ` David Hildenbrand
2025-06-17 14:04 ` David Hildenbrand
2025-06-17 15:22 ` Jason Gunthorpe
2025-06-18 6:28 ` lizhe.67
2025-06-18 8:20 ` David Hildenbrand
2025-06-18 11:36 ` Jason Gunthorpe
2025-06-18 11:40 ` David Hildenbrand
2025-06-18 11:42 ` David Hildenbrand
2025-06-18 11:46 ` Jason Gunthorpe
2025-06-18 11:52 ` David Hildenbrand
2025-06-18 11:56 ` Jason Gunthorpe
2025-06-18 12:19 ` lizhe.67
2025-06-18 13:23 ` Jason Gunthorpe
2025-06-19 9:05 ` lizhe.67
2025-06-19 12:35 ` Jason Gunthorpe [this message]
2025-06-19 12:49 ` lizhe.67
2025-06-17 4:18 ` [PATCH v4 3/3] vfio/type1: optimize vfio_unpin_pages_remote() for large folio lizhe.67
2025-06-17 7:43 ` David Hildenbrand
2025-06-17 9:21 ` [PATCH v4 2/3] gup: introduce unpin_user_folio_dirty_locked() lizhe.67
2025-06-17 9:27 ` David Hildenbrand
2025-06-17 9:47 ` [PATCH v4 3/3] vfio/type1: optimize vfio_unpin_pages_remote() for large folio lizhe.67
2025-06-17 9:49 ` David Hildenbrand
2025-06-17 12:42 ` lizhe.67
2025-06-17 13:47 ` David Hildenbrand
2025-06-18 6:11 ` lizhe.67
2025-06-18 7:22 ` lizhe.67
2025-06-18 8:54 ` David Hildenbrand
2025-06-18 9:39 ` lizhe.67
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=20250619123504.GA1643390@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=david@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizhe.67@bytedance.com \
--cc=peterx@redhat.com \
/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).