On Sat, Aug 26, 2017 at 03:46:22PM -0700, Dan Williams wrote:

On Sat, Aug 26, 2017 at 12:50 PM, Helge Deller [off-list ref] wrote:

quoted

On 26.08.2017 17:15, Dan Williams wrote:

[..]

quoted

quoted

I have not seen any patches for parisc pmem+dax enabling so it seems
too early to worry about these "last mile" enabling features of
MAP_DIRECT and MAP_SYNC. In particular parisc doesn't appear to have
ARCH_ENABLE_MEMORY_HOTPLUG, so as far as I can see it can't yet
support the ZONE_DEVICE scheme that is a pre-requisite for MAP_DIRECT.

I see, but then it's probably best to not to define any MAP_DIRECT or
MAP_SYNC at all in the headers of those arches which don't support
pmem+dax (parisc, m68k, alpha, and probably quite some others).
That way applications can detect at configure time if the platform
supports that, and can leave out the functionality completely.

Yes, that's a good idea we can handle this similar to
CONFIG_MMAP_ALLOW_UNINITIALIZED. These patches will also modify
'struct file_operations' so that do_mmap() can validate whether a flag
is supported on per architecture basis. Also the plan is to plumb the
flags passed to the syscall all the way down to the individual mmap
implementations. The ext4 and xfs ->mmap() operations will be able to
return -EOPNOTSUP based on runtime variables.

BTW, we may be able to reuse the bit used for MAP_UNINITIALIZED -- it's
only used on !MMU machines.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>