I propose to delete current use of __HAVE_ATOMIC_AS_MEMBAR because it
is a bad API, and replace it by one of two options:
(a) Add membar_release_preatomic and membar_acquire_postatomic: noop
if __HAVE_ATOMIC_AS_MEMBAR, alias for membar_release/acquire
otherwise.
(Maybe also add
> On Feb 22, 2023, at 9:40 AM, Taylor R Campbell
> wrote:
>
> I believe this is guaranteed as rwlock(9) is currently implemented.
> (Whether it is _intended_ to be guaranteed, I'm not sure.)
That guarantee certainly falls in line with the principle of least
astonishment. We should
Questions about rwlock(9) memory ordering semantics:
1. Is rw_tryupgrade an acquire operation, so that all prior reader
critical sections happen-before anything sequenced after it?
Or does it only order stores issued by the caller, while loads in
the following write section can be
Hello. I'm running a series of machines, both Xen VM machines and
machines running on
bare metal, and I notice that on my systems running NetBSD-9.99.77, vmstat -s
shows that
local-cpu page allocations are never available on the xen VM's, see below.
Yet, on machines
running on bare
> Date: Wed, 22 Feb 2023 12:57:24 +
> From: Taylor R Campbell
>
> I propose to delete current use of __HAVE_ATOMIC_AS_MEMBAR because it
> is a bad API, and replace it by one of two options:
>
> (a) Add membar_release_preatomic and membar_acquire_postatomic: noop
> if
> On Feb 22, 2023, at 4:48 PM, Taylor R Campbell
> wrote:
>
> (c) Just make the membars unconditional -- take off the #ifndefs, but
>don't add any new functions or change the semantics of existing
>ones.
That’s my preference. Having ti at all is confusing.
-- thorpej
