Re: [RFC][PATCH 1/3] locking: Introduce smp_acquire__after_ctrl_dep

From: Peter Zijlstra
Date: Wed May 25 2016 - 12:28:58 EST

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'.