Messages in this thread | | | Date | Wed, 25 May 2016 18:28:29 +0200 | From | Peter Zijlstra <> | Subject | Re: [RFC][PATCH 1/3] locking: Introduce smp_acquire__after_ctrl_dep |
| |
On Wed, May 25, 2016 at 08:57:47AM -0700, Paul E. McKenney wrote: > For your example, but keeping the compiler in check: > > if (READ_ONCE(a)) > WRITE_ONCE(b, 1); > smp_rmb(); > WRITE_ONCE(c, 2); > > On x86, the smp_rmb() is as you say nothing but barrier(). However, > x86's TSO prohibits reordering reads with subsequent writes. So the > read from "a" is ordered before the write to "c". > > On powerpc, the smp_rmb() will be the lwsync instruction plus a compiler > barrier. This orders prior reads against subsequent reads and writes, so > again the read from "a" will be ordered befoer the write to "c". But the > ordering against subsequent writes is an accident of implementation. > The real guarantee comes from powerpc's guarantee that stores won't be > speculated, so that the read from "a" is guaranteed to be ordered before > the write to "c" even without the smp_rmb(). > > On arm, the smp_rmb() is a full memory barrier, so you are good > there. On arm64, it is the "dmb ishld" instruction, which only orders > reads.
IIRC dmb ishld orders more than load vs load (like the manual states), but I forgot the details; we'll have to wait for Will to clarify. But yes, it also orders loads vs loads so it sufficient here.
> But in both arm and arm64, speculative stores are forbidden, > just as in powerpc. So in both cases, the load from "a" is ordered > before the store to "c". > > Other CPUs are required to behave similarly, but hopefully those > examples help.
I would consider any architecture that allows speculative stores as broken. They are values out of thin air and would make any kind of concurrency extremely 'interesting'.
| |