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

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=276002

--- Comment #11 from Rick Macklem <rmacklem@FreeBSD.org> ---
I'll need to take a look at some of the other
NFSv4.2 operations, since they bypass the buffer
cache (and any mmap'd I/O) to see if they need
a similar treatment. I think Allocate/Deallocate
will need this and Seek will need to do a vm_object_page_clean()
as well as the ncl_flush().

I'll look at these once this patch is tested by Alan.

Btw, the workaround for any of these problems is
"minorversion=1" on the mount, for anyone who runs
into these issues in unpatched systems.

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