Messages in this thread | | | Date | Fri, 7 Nov 2008 12:17:03 -0500 | From | Mathieu Desnoyers <> | Subject | Re: [RFC patch 08/18] cnt32_to_63 should use smp_rmb() |
| |
* David Howells (dhowells@redhat.com) wrote: > Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote: > > > First off, using this macro with get_cycles() is simply buggy, because the > > macro expects _perfect_ order of timestamps, no skew whatsoever, or > > otherwise time could jump. > > Erm... Why can't I pass it get_cycles()? Are you saying that sched_clock() > in MN10300 is wrong for it's use of get_cycles() with cnt32_to_63()? >
Yes. Do you think the synchronization of the cycles counters is _perfect_ across CPUs so that there is no possible way whatsoever that two cycle counter values appear to go backward between CPUs ? (also taking in account delays in __m_cnt_hi write-back...)
As I showed in my previous example, if you are unlucky enough to hit the spot where the cycle counters go backward at the time warp edge, time will jump of 2^32, so about 4.29s at 1GHz.
> > __x.lo = readl(cnt_lo); /* mmio read */ > > readl() might insert an extra barrier instruction. Not only that, io_addr > must be unsigned long.
If we expect the only correct use-case to be with readl(), I don't see the problem with added synchronization.
>
Ah, right, then the parameters should be updated accordingly.
static inline u64 cnt32_to_63(unsigned long io_addr, u32 *__m_cnt_hi) { union cnt32_to_63 __x; __x.hi = *__m_cnt_hi; /* memory read for high bits internal state */ rmb(); /* * read high bits before low bits insures time * does not go backward. Sync across * CPUs and for interrupts. */ __x.lo = readl(io_addr); /* mmio read */ if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) *__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); return __x.val; }
Mathieu
> David
-- Mathieu Desnoyers OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
| |