Messages in this thread | | | Date | Fri, 19 Jul 2013 15:27:18 +0100 | From | Russell King - ARM Linux <> | Subject | Re: [PATCH v4 02/17] sched_clock: Use seqcount instead of rolling our own |
| |
On Fri, Jul 19, 2013 at 10:20:19AM -0400, Nicolas Pitre wrote: > On Fri, 19 Jul 2013, Will Deacon wrote: > > > Looks good to me. The current scheme would be very fiddly to extend to > > 64-bit values on 32-bit architectures without cheap atomic doubleword > > accesses. > > You should have a look at include/linux/cnt32_to_63.h. > This could be applied to pure software counters if the low part is > atomically increased.
But this can't be used for sched_clock(). That's exactly why I originally had to rewrite that thing in the first place.
| |