Re: [PATCH] md: optimize barrier usage for Rmw atomic bitops

[Song Liu]

On Fri, Jan 31, 2020 at 8:43 AM Guoqing Jiang
<guoqing.jiang@xxxxxxxxxxxxxxx> wrote:
>
>
>
> On 1/29/20 7:14 PM, Davidlohr Bueso wrote:
> > For both set and clear_bit, we can avoid the unnecessary barrier
> > on non LL/SC architectures, such as x86. Instead, use the
> > smp_mb__{before,after}_atomic() calls.
> >
> > Signed-off-by: Davidlohr Bueso <dbueso@xxxxxxx>

./scripts/checkpatch.pl reports the following:

=============== 8< =================
WARNING: memory barrier without comment
#81: FILE: drivers/md/md.c:2564:
+                       smp_mb__before_atomic();

WARNING: memory barrier without comment
#112: FILE: drivers/md/raid5.c:367:
+               smp_mb__before_atomic();

WARNING: Missing Signed-off-by: line by nominal patch author
'Davidlohr Bueso <dave@xxxxxxxxxxxx>'

total: 0 errors, 3 warnings, 42 lines checked
=============== 8< =================

Since we are on it, let's add comments for the barriers. Also, please
double check the email
is correct.

Thanks,
Song