[ofa-general] Re: [PATCH 01 of 11] mmu-notifier-core

Jack Steiner steiner at sgi.com
Mon May 5 12:46:25 PDT 2008


On Mon, May 05, 2008 at 08:34:05PM +0200, Andrea Arcangeli wrote:
> On Mon, May 05, 2008 at 12:25:06PM -0500, Jack Steiner wrote:
> > Agree. My apologies... I should have caught it.
> 
> No problem.
> 
> > __mmu_notifier_register/__mmu_notifier_unregister seems like a better way to
> > go, although either is ok.
> 
> If you also like __mmu_notifier_register more I'll go with it. The
> bitflags seems like a bit of overkill as I can't see the need of any
> other bitflag other than this one and they also can't be removed as
> easily in case you'll find a way to call it outside the lock later.
> 
> > Let me finish my testing. At one time, I did not use ->release but
> > with all the locking & teardown changes, I need to do some reverification.

I finished testing & everything looks good. I do use the ->release callout but
mainly as a performance hint that teardown is in progress & that TLB flushing is
no longer needed. (GRU TLB entries are tagged with a task-specific ID that will
not be reused until a full TLB purge is done. This eliminates the requirement
to purge at task-exit.)


Normally, a notifier is registered when a GRU segment is mmaped, and unregistered
when the segment is unmapped. Well behaved tasks will not have a GRU or
a notifier when exit starts.

If a task fails to unmap a GRU segment, they still exist at the start of
exit. On the ->release callout, I set a flag in the container of my
mmu_notifier that exit has started. As VMA are cleaned up, TLB flushes
are skipped because of the flag is set. When the GRU VMA is deleted, I free
my structure containing the notifier.

I _think_ works. Do you see any problems?

I should also mention that I have an open-coded function that possibly
belongs in mmu_notifier.c. A user is allowed to have multiple GRU segments.
Each GRU has a couple of data structures linked to the VMA. All, however,
need to share the same notifier. I currently open code a function that
scans the notifier list to determine if a GRU notifier already exists.
If it does, I update a refcnt & use it. Otherwise, I register a new
one. All of this is protected by the mmap_sem.

Just in case I mangled the above description, I'll attach a copy of the GRU mmuops
code.

--- jack
-------------- next part --------------
A non-text attachment was scrubbed...
Name: z
Type: application/x-compress
Size: 2662 bytes
Desc: not available
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20080505/0132d0c4/attachment.bin>


More information about the general mailing list