[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK8P3a03tXXHQ00QEGg=7p17mmseuJqRhuumWKzS8dCYvXHkBg@mail.gmail.com>
Date: Tue, 30 Jul 2019 15:29:38 +0200
From: Arnd Bergmann <arnd@...db.de>
To: Guo Ren <guoren@...nel.org>
Cc: Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
linux-arch <linux-arch@...r.kernel.org>,
linux-csky@...r.kernel.org, feng_shizhu@...uatech.com,
zhang_jian5@...uatech.com, zheng_xingjian@...uatech.com,
zhu_peng@...uatech.com, Guo Ren <ren_guo@...ky.com>
Subject: Re: [PATCH 1/4] csky: Fixup dma_rmb/wmb synchronization problem
On Tue, Jul 30, 2019 at 2:15 PM <guoren@...nel.org> wrote:
>
> From: Guo Ren <ren_guo@...ky.com>
>
> If arch didn't define dma_r/wmb(), linux will use w/rmb instead. Csky
> use bar.xxx to implement mb() and that will cause problem when sync data
> with dma device, becasue bar.xxx couldn't guarantee bus transactions
> finished at outside bus level. We must use sync.s instead of bar.xxx for
> dma data synchronization and it will guarantee retirement after getting
> the bus bresponse.
>
> Signed-off-by: Guo Ren <ren_guo@...ky.com>
This change looks good to me, but I think your regular barriers
(mb, rmb, wmb) are still wrong: These are meant to be the superset
of dma_{r,w}mb and smp_{,r,w}mb, and synchronize
against both SMP and DMA interactions.
I suspect you can drop the '.s' for non-SMP builds. What I don't
see is whether you might need to add '.i' for dma_wmb() or
dma_rmb().
Arnd
Powered by blists - more mailing lists