Messages in this thread | | | Subject | Re: [RFC PATCH] docs/memory-barriers.txt: Rewrite "KERNEL I/O BARRIER EFFECTS" section | From | Benjamin Herrenschmidt <> | Date | Tue, 12 Feb 2019 15:01:13 +1100 |
| |
On Mon, 2019-02-11 at 14:34 -0800, Linus Torvalds wrote: > On Mon, Feb 11, 2019 at 9:30 AM Will Deacon <will.deacon@arm.com> wrote: > > + > > + 1. All readX() and writeX() accesses to the same peripheral are ordered > > + with respect to each other. For example, this ensures that MMIO register > > + writes by the CPU to a particular device will arrive in program order. > > Hmm. I'd like more people look at strengthening this one wrt across > CPUs and locking. > > Right now we document mmiowb(), but that "documentation" is really > just a fairy tale. Very *very* few drivers actually do mmiowb() on > their own. > > IOW, we should seriously just consider making the rule be that locking > will order mmio too. Because that's practically the rule anyway. > > Powerpc already does it. IO within a locked region will serialize with the lock.
Yup. It's a bit ugly but I felt back then that getting drivers to use mmiowb() properly was going to be a losing battle.
Cheers, Ben.
| |