Date: Mon, 25 Jan 2021 23:56:37 +0000 From: Jessica Clarke <jrtc27@freebsd.org> To: Mateusz Guzik <mjg@FreeBSD.org> Cc: "src-committers@freebsd.org" <src-committers@FreeBSD.org>, "dev-commits-src-all@freebsd.org" <dev-commits-src-all@FreeBSD.org>, "dev-commits-src-main@freebsd.org" <dev-commits-src-main@FreeBSD.org> Subject: Re: git: 054ce2b03710 - main - atomic: add stub atomic_load_consume_ptr Message-ID: <18A79D6D-BCBE-4B6B-88F0-47931508C476@freebsd.org> In-Reply-To: <202101252242.10PMgaWJ026291@gitrepo.freebsd.org> References: <202101252242.10PMgaWJ026291@gitrepo.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 25 Jan 2021, at 22:42, Mateusz Guzik <mjg@FreeBSD.org> wrote: >=20 > The branch main has been updated by mjg: >=20 > URL: = https://cgit.FreeBSD.org/src/commit/?id=3D054ce2b0371042c0dbc4b3ab1d7e7795= ad75d51e >=20 > commit 054ce2b0371042c0dbc4b3ab1d7e7795ad75d51e > Author: Mateusz Guzik <mjg@FreeBSD.org> > AuthorDate: 2021-01-25 20:09:41 +0000 > Commit: Mateusz Guzik <mjg@FreeBSD.org> > CommitDate: 2021-01-25 22:40:15 +0000 >=20 > atomic: add stub atomic_load_consume_ptr Consume semantics is a waste of time, it's basically impossible to implement in an optimising compiler as, in order to not emit the same fences as an acquire, you need the source dependencies to be mapped to data dependencies in the output assembly, but all manner of transformations can cause that to break. And that's before you get to hand-written atomic implementations where it is impossible for you to ensure that, as you're not even telling the compiler what you're doing. For example: int x =3D atomic_load_consume_int(p); int y =3D q[x - x]; This looks like stupid code, but the `x - x` cannot be constant-folded without inserting a barrier, as currently there is data dependence at the source level. If you use language-level atomics then it "works" by virtue of compilers just turning consumes into acquires so the later constant folding is safe. But if your atomic_load_consume_int is hand-rolled magic assembly then the compiler has no clue and will blindly go and constant fold that subtraction for you, completely breaking your synchronisation. Providing consume loads just doesn't make sense for FreeBSD's atomics except for documenting the exact requirements of the code being written; they can never be implemented as anything other than acquire loads unless we migrate to using actual C11 atomics, but even then you won't get any code generation difference and likely never will. Jess
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?18A79D6D-BCBE-4B6B-88F0-47931508C476>