[Bug 276002] nfscl: data corruption using both copy_file_range and mmap'd I/O

From: <bugzilla-noreply_at_freebsd.org>
Date: Mon, 01 Jan 2024 22:30:07 UTC
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=276002

Konstantin Belousov <kib@FreeBSD.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |pho@FreeBSD.org

--- Comment #39 from Konstantin Belousov <kib@FreeBSD.org> ---
(In reply to Rick Macklem from comment #37)
I though about doing vm_object_page_clean() before starting RA, but the problem
is that current lock is shared, while we need exclusively locked vnode for
write.

Lets try my patch first.  I added Peter Holm in a hope that he has some spare
circles to reproduce the issue and to check my patchset.

-- 
You are receiving this mail because:
You are the assignee for the bug.