* [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire}
@ 2018-02-27 2:24 Andrea Parri
2018-02-27 18:21 ` Palmer Dabbelt
0 siblings, 1 reply; 4+ messages in thread
From: Andrea Parri @ 2018-02-27 2:24 UTC (permalink / raw)
To: Palmer Dabbelt, Albert Ou; +Cc: linux-riscv, linux-kernel, Andrea Parri
Introduce __smp_{store_release,load_acquire}, and rely on the generic
definitions for smp_{store_release,load_acquire}. This avoids the use
of full ("rw,rw") fences on SMP.
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
---
arch/riscv/include/asm/barrier.h | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 5510366d169ae..d4628e4b3a5ea 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -38,6 +38,21 @@
#define __smp_rmb() RISCV_FENCE(r,r)
#define __smp_wmb() RISCV_FENCE(w,w)
+#define __smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ RISCV_FENCE(rw,w); \
+ WRITE_ONCE(*p, v); \
+} while (0)
+
+#define __smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = READ_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ RISCV_FENCE(r,rw); \
+ ___p1; \
+})
+
/*
* This is a very specific barrier: it's currently only used in two places in
* the kernel, both in the scheduler. See include/linux/spinlock.h for the two
--
2.7.4
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire}
2018-02-27 2:24 [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire} Andrea Parri
@ 2018-02-27 18:21 ` Palmer Dabbelt
2018-02-27 22:20 ` Daniel Lustig
0 siblings, 1 reply; 4+ messages in thread
From: Palmer Dabbelt @ 2018-02-27 18:21 UTC (permalink / raw)
To: parri.andrea, Daniel Lustig
Cc: albert, linux-riscv, linux-kernel, parri.andrea
On Mon, 26 Feb 2018 18:24:11 PST (-0800), parri.andrea@gmail.com wrote:
> Introduce __smp_{store_release,load_acquire}, and rely on the generic
> definitions for smp_{store_release,load_acquire}. This avoids the use
> of full ("rw,rw") fences on SMP.
>
> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
> ---
> arch/riscv/include/asm/barrier.h | 15 +++++++++++++++
> 1 file changed, 15 insertions(+)
>
> diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
> index 5510366d169ae..d4628e4b3a5ea 100644
> --- a/arch/riscv/include/asm/barrier.h
> +++ b/arch/riscv/include/asm/barrier.h
> @@ -38,6 +38,21 @@
> #define __smp_rmb() RISCV_FENCE(r,r)
> #define __smp_wmb() RISCV_FENCE(w,w)
>
> +#define __smp_store_release(p, v) \
> +do { \
> + compiletime_assert_atomic_type(*p); \
> + RISCV_FENCE(rw,w); \
> + WRITE_ONCE(*p, v); \
> +} while (0)
> +
> +#define __smp_load_acquire(p) \
> +({ \
> + typeof(*p) ___p1 = READ_ONCE(*p); \
> + compiletime_assert_atomic_type(*p); \
> + RISCV_FENCE(r,rw); \
> + ___p1; \
> +})
> +
> /*
> * This is a very specific barrier: it's currently only used in two places in
> * the kernel, both in the scheduler. See include/linux/spinlock.h for the two
I'm adding Daniel just in case I misunderstood what's going on here, but these
look good to me. As this is a non-trivial memory model change I'm going to let
it bake in linux-next for a bit just so it gets some visibility.
Thanks!
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire}
2018-02-27 18:21 ` Palmer Dabbelt
@ 2018-02-27 22:20 ` Daniel Lustig
2018-02-28 0:15 ` Andrea Parri
0 siblings, 1 reply; 4+ messages in thread
From: Daniel Lustig @ 2018-02-27 22:20 UTC (permalink / raw)
To: Palmer Dabbelt, parri.andrea; +Cc: albert, linux-riscv, linux-kernel
On 2/27/2018 10:21 AM, Palmer Dabbelt wrote:
> On Mon, 26 Feb 2018 18:24:11 PST (-0800), parri.andrea@gmail.com wrote:
>> Introduce __smp_{store_release,load_acquire}, and rely on the generic
>> definitions for smp_{store_release,load_acquire}. This avoids the use
>> of full ("rw,rw") fences on SMP.
>>
>> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
>> ---
>> arch/riscv/include/asm/barrier.h | 15 +++++++++++++++
>> 1 file changed, 15 insertions(+)
>>
>> diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
>> index 5510366d169ae..d4628e4b3a5ea 100644
>> --- a/arch/riscv/include/asm/barrier.h
>> +++ b/arch/riscv/include/asm/barrier.h
>> @@ -38,6 +38,21 @@
>> #define __smp_rmb() RISCV_FENCE(r,r)
>> #define __smp_wmb() RISCV_FENCE(w,w)
>>
>> +#define __smp_store_release(p, v) \
>> +do { \
>> + compiletime_assert_atomic_type(*p); \
>> + RISCV_FENCE(rw,w); \
>> + WRITE_ONCE(*p, v); \
>> +} while (0)
>> +
>> +#define __smp_load_acquire(p) \
>> +({ \
>> + typeof(*p) ___p1 = READ_ONCE(*p); \
>> + compiletime_assert_atomic_type(*p); \
>> + RISCV_FENCE(r,rw); \
>> + ___p1; \
>> +})
>> +
>> /*
>> * This is a very specific barrier: it's currently only used in two places in
>> * the kernel, both in the scheduler. See include/linux/spinlock.h for the two
>
> I'm adding Daniel just in case I misunderstood what's going on here,
> but these look good to me. As this is a non-trivial memory model
> change I'm going to let it bake in linux-next for a bit just so it
> gets some visibility.
Looks good to me too. In particular, it also covers the
Write->release(p)->acquire(p)->Write ordering that we were debating
in the broader LKMM thread, which is good.
Dan
>
> Thanks
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire}
2018-02-27 22:20 ` Daniel Lustig
@ 2018-02-28 0:15 ` Andrea Parri
0 siblings, 0 replies; 4+ messages in thread
From: Andrea Parri @ 2018-02-28 0:15 UTC (permalink / raw)
To: Daniel Lustig; +Cc: Palmer Dabbelt, albert, linux-riscv, linux-kernel
On Tue, Feb 27, 2018 at 02:20:37PM -0800, Daniel Lustig wrote:
> On 2/27/2018 10:21 AM, Palmer Dabbelt wrote:
> > On Mon, 26 Feb 2018 18:24:11 PST (-0800), parri.andrea@gmail.com wrote:
> >> Introduce __smp_{store_release,load_acquire}, and rely on the generic
> >> definitions for smp_{store_release,load_acquire}. This avoids the use
> >> of full ("rw,rw") fences on SMP.
> >>
> >> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
> >> ---
> >> arch/riscv/include/asm/barrier.h | 15 +++++++++++++++
> >> 1 file changed, 15 insertions(+)
> >>
> >> diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
> >> index 5510366d169ae..d4628e4b3a5ea 100644
> >> --- a/arch/riscv/include/asm/barrier.h
> >> +++ b/arch/riscv/include/asm/barrier.h
> >> @@ -38,6 +38,21 @@
> >> #define __smp_rmb() RISCV_FENCE(r,r)
> >> #define __smp_wmb() RISCV_FENCE(w,w)
> >>
> >> +#define __smp_store_release(p, v) \
> >> +do { \
> >> + compiletime_assert_atomic_type(*p); \
> >> + RISCV_FENCE(rw,w); \
> >> + WRITE_ONCE(*p, v); \
> >> +} while (0)
> >> +
> >> +#define __smp_load_acquire(p) \
> >> +({ \
> >> + typeof(*p) ___p1 = READ_ONCE(*p); \
> >> + compiletime_assert_atomic_type(*p); \
> >> + RISCV_FENCE(r,rw); \
> >> + ___p1; \
> >> +})
> >> +
> >> /*
> >> * This is a very specific barrier: it's currently only used in two places in
> >> * the kernel, both in the scheduler. See include/linux/spinlock.h for the two
> >
> > I'm adding Daniel just in case I misunderstood what's going on here,
> > but these look good to me. As this is a non-trivial memory model
> > change I'm going to let it bake in linux-next for a bit just so it
> > gets some visibility.
>
> Looks good to me too. In particular, it also covers the
> Write->release(p)->acquire(p)->Write ordering that we were debating
> in the broader LKMM thread, which is good.
Yeah, I think that other changes would be required to completely cover
the issues debated in that thread: I plan to prepare and to post a new
series/RFC to address those (unless someone precedes me of course ;-).
Andrea
>
> Dan
>
> >
> > Thanks
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2018-02-28 0:15 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-02-27 2:24 [PATCH] riscv/barrier: Define __smp_{store_release,load_acquire} Andrea Parri
2018-02-27 18:21 ` Palmer Dabbelt
2018-02-27 22:20 ` Daniel Lustig
2018-02-28 0:15 ` Andrea Parri
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).