Re: [PATCH 3/3] WorkStruct: Use direct assignment rather than cmpxchg()

[David Howells]

James Bottomley <James.Bottomley@xxxxxxxxxxxx> wrote:

> That we'd have to put a conditional jump in there is an incorrect
> assumption on risc machines.

I didn't say we would *have* to put a conditional jump in there.  But I don't
know that I it can be avoided on all archs.

I don't know that sparc32 can do conditional instructions for example.  If we
force this assumption it becomes a potential limitation on the archs we can
support.  OTOH, it may be that every arch that supports SMP and has to emulate
bitops with spinlocks also supports conditional stores; but I don't know that.

David
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/