On Wed, 22 Jul 2015, Michael Ellerman wrote:

On Tue, 2015-07-21 at 13:44 -0700, Andrew Morton wrote:

quoted

On Tue, 21 Jul 2015 15:59:37 -0400 Eric B Munson [off-list ref] wrote:

quoted

With the refactored mlock code, introduce new system calls for mlock,
munlock, and munlockall.  The new calls will allow the user to specify
what lock states are being added or cleared.  mlock2 and munlock2 are
trivial at the moment, but a follow on patch will add a new mlock state
making them useful.

munlock2 addresses a limitation of the current implementation.  If a
user calls mlockall(MCL_CURRENT | MCL_FUTURE) and then later decides
that MCL_FUTURE should be removed, they would have to call munlockall()
followed by mlockall(MCL_CURRENT) which could potentially be very
expensive.  The new munlockall2 system call allows a user to simply
clear the MCL_FUTURE flag.

This is hard.  Maybe we shouldn't have wired up anything other than
x86.  That's what we usually do with new syscalls.

Yeah I think so.

You haven't wired it up properly on powerpc, but I haven't mentioned it because
I'd rather we did it.

cheers

It looks like I will be spinning a V5, so I will drop all but the x86
system calls additions in that version.