From: Alex Mastro <amastro@fb.com>
To: <peterx@redhat.com>
Cc: <akpm@linux-foundation.org>, <alex.williamson@redhat.com>,
<david@redhat.com>, <jgg@nvidia.com>, <kvm@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
<npache@redhat.com>, <ziy@nvidia.com>,
Alex Mastro <amastro@fb.com>
Subject: Re: [PATCH 5/5] vfio-pci: Best-effort huge pfnmaps with !MAP_FIXED mappings
Date: Fri, 13 Jun 2025 10:44:42 -0700 [thread overview]
Message-ID: <20250613174442.1589882-1-amastro@fb.com> (raw)
In-Reply-To: <20250613134111.469884-6-peterx@redhat.com>
Thank you Peter!
I packported this series to our 6.13.2 tree and validated that it does indeed
provide equivalent, optimal faulting to our manual alignment approach when we
mmap with !MAP_FIXED. This addresses the issue we discovered in [1].
The test case is performing mmap with offset=0x40006000000, size=0xdf9e00000,
and we see that the head and tail (975) are faulted at 2M, and middle (54) at
1G. The vma returned by mmap looks nice: 0x7f8646000000.
$ sudo bpftrace -q -e 'fexit:vfio_pci_mmap_huge_fault { printf("order=%d, ret=0x%x\n", args.order, retval); }' 2>&1 > ~/dump
$ cat ~/dump | sort | uniq -c | sort -nr
975 order=9, ret=0x100
54 order=18, ret=0x100
2 order=18, ret=0x800
[1] https://lore.kernel.org/linux-pci/20250529214414.1508155-1-amastro@fb.com/
Tested-by: Alex Mastro <amastro@fb.com>
next prev parent reply other threads:[~2025-06-13 17:48 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-13 13:41 [PATCH 0/5] mm/vfio: " Peter Xu
2025-06-13 13:41 ` [PATCH 1/5] mm: Deduplicate mm_get_unmapped_area() Peter Xu
2025-06-13 14:12 ` Jason Gunthorpe
2025-06-13 14:55 ` Oscar Salvador
2025-06-13 14:58 ` Zi Yan
2025-06-13 15:57 ` Lorenzo Stoakes
2025-06-13 17:00 ` Pedro Falcato
2025-06-13 18:00 ` David Hildenbrand
2025-06-16 8:01 ` David Laight
2025-06-17 21:13 ` Peter Xu
2025-06-13 13:41 ` [PATCH 2/5] mm/hugetlb: Remove prepare_hugepage_range() Peter Xu
2025-06-13 14:12 ` Jason Gunthorpe
2025-06-13 14:59 ` Oscar Salvador
2025-06-13 15:13 ` Zi Yan
2025-06-13 16:24 ` Peter Xu
2025-06-13 18:01 ` David Hildenbrand
2025-06-14 4:11 ` Liam R. Howlett
2025-06-17 21:07 ` Peter Xu
2025-06-13 13:41 ` [PATCH 3/5] mm: Rename __thp_get_unmapped_area to mm_get_unmapped_area_aligned Peter Xu
2025-06-13 14:17 ` Jason Gunthorpe
2025-06-13 15:13 ` Peter Xu
2025-06-13 16:00 ` Jason Gunthorpe
2025-06-13 18:31 ` Peter Xu
2025-06-13 15:19 ` Zi Yan
2025-06-13 18:33 ` Peter Xu
2025-06-13 15:36 ` Lorenzo Stoakes
2025-06-13 18:45 ` Peter Xu
2025-06-13 19:18 ` Lorenzo Stoakes
2025-06-13 20:34 ` Peter Xu
2025-06-14 5:58 ` Lorenzo Stoakes
2025-06-14 5:23 ` Liam R. Howlett
2025-06-16 12:14 ` Jason Gunthorpe
2025-06-16 12:20 ` Lorenzo Stoakes
2025-06-16 12:26 ` Jason Gunthorpe
2025-06-13 13:41 ` [PATCH 4/5] vfio: Introduce vfio_device_ops.get_unmapped_area hook Peter Xu
2025-06-13 14:18 ` Jason Gunthorpe
2025-06-13 18:03 ` David Hildenbrand
2025-06-14 14:46 ` kernel test robot
2025-06-17 15:39 ` Peter Xu
2025-06-17 15:41 ` Jason Gunthorpe
2025-06-17 16:47 ` Peter Xu
2025-06-17 19:39 ` Peter Xu
2025-06-17 19:46 ` Jason Gunthorpe
2025-06-17 20:01 ` Peter Xu
2025-06-17 23:00 ` Jason Gunthorpe
2025-06-17 23:26 ` Peter Xu
2025-06-13 13:41 ` [PATCH 5/5] vfio-pci: Best-effort huge pfnmaps with !MAP_FIXED mappings Peter Xu
2025-06-13 14:29 ` Jason Gunthorpe
2025-06-13 15:26 ` Peter Xu
2025-06-13 16:09 ` Jason Gunthorpe
2025-06-13 19:15 ` Peter Xu
2025-06-13 23:16 ` Jason Gunthorpe
2025-06-16 22:06 ` Peter Xu
2025-06-16 23:00 ` Jason Gunthorpe
2025-06-17 20:56 ` Peter Xu
2025-06-17 23:18 ` Jason Gunthorpe
2025-06-17 23:36 ` Peter Xu
2025-06-18 16:56 ` Peter Xu
2025-06-18 17:46 ` Jason Gunthorpe
2025-06-18 19:15 ` Peter Xu
2025-06-19 13:58 ` Jason Gunthorpe
2025-06-19 14:55 ` Peter Xu
2025-06-19 18:40 ` Jason Gunthorpe
2025-06-24 20:37 ` Peter Xu
2025-06-24 20:51 ` Peter Xu
2025-06-24 23:40 ` Jason Gunthorpe
2025-06-25 0:48 ` Peter Xu
2025-06-25 13:07 ` Jason Gunthorpe
2025-06-25 17:12 ` Peter Xu
2025-06-25 18:41 ` Jason Gunthorpe
2025-06-25 19:26 ` Peter Xu
2025-06-30 14:05 ` Jason Gunthorpe
2025-07-02 20:58 ` Peter Xu
2025-07-02 23:32 ` Jason Gunthorpe
2025-06-13 17:44 ` Alex Mastro [this message]
2025-06-13 18:53 ` Peter Xu
2025-06-13 18:09 ` David Hildenbrand
2025-06-13 19:21 ` Peter Xu
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=20250613174442.1589882-1-amastro@fb.com \
--to=amastro@fb.com \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=david@redhat.com \
--cc=jgg@nvidia.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=npache@redhat.com \
--cc=peterx@redhat.com \
--cc=ziy@nvidia.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