* [PATCH] arm64: Implement cpu_relax as yield
@ 2015-03-02 19:19 ` Peter Crosthwaite
0 siblings, 0 replies; 6+ messages in thread
From: Peter Crosthwaite @ 2015-03-02 19:19 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel
Cc: will.deacon, catalin.marinas, michals, peter.crosthwaite
ARM64 has the yield nop hint which has the intended semantics of
cpu_relax. Implement.
The immediate application is ARM CPU emulators. An emulator can take
advantage of the yield hint to de-prioritise an emulated CPU in favor
of other emulation tasks. QEMU A64 SMP emulation has yield awareness,
and sees a significant boot time performance increase with this change.
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Acked-by: Will Deacon <will.deacon@arm.com>
---
arch/arm64/include/asm/processor.h | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index f9be30e..ac2381d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -126,7 +126,11 @@ extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
-#define cpu_relax() barrier()
+static inline void cpu_relax(void)
+{
+ asm volatile("yield" ::: "memory");
+}
+
#define cpu_relax_lowlatency() cpu_relax()
/* Thread switching */
--
2.3.0.1.g27a12f1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH] arm64: Implement cpu_relax as yield
@ 2015-03-02 19:19 ` Peter Crosthwaite
0 siblings, 0 replies; 6+ messages in thread
From: Peter Crosthwaite @ 2015-03-02 19:19 UTC (permalink / raw)
To: linux-arm-kernel
ARM64 has the yield nop hint which has the intended semantics of
cpu_relax. Implement.
The immediate application is ARM CPU emulators. An emulator can take
advantage of the yield hint to de-prioritise an emulated CPU in favor
of other emulation tasks. QEMU A64 SMP emulation has yield awareness,
and sees a significant boot time performance increase with this change.
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Acked-by: Will Deacon <will.deacon@arm.com>
---
arch/arm64/include/asm/processor.h | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index f9be30e..ac2381d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -126,7 +126,11 @@ extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
-#define cpu_relax() barrier()
+static inline void cpu_relax(void)
+{
+ asm volatile("yield" ::: "memory");
+}
+
#define cpu_relax_lowlatency() cpu_relax()
/* Thread switching */
--
2.3.0.1.g27a12f1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH] arm64: Implement cpu_relax as yield
2015-03-02 19:19 ` Peter Crosthwaite
@ 2015-03-25 9:58 ` Peter Crosthwaite
-1 siblings, 0 replies; 6+ messages in thread
From: Peter Crosthwaite @ 2015-03-25 9:58 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel
Cc: Will Deacon, Catalin Marinas, michals, Peter Crosthwaite
Ping!
Anything I need to do or send to to get a merge on this?
Regards,
Peter
On Tue, Mar 3, 2015 at 12:49 AM, Peter Crosthwaite
<peter.crosthwaite@xilinx.com> wrote:
> ARM64 has the yield nop hint which has the intended semantics of
> cpu_relax. Implement.
>
> The immediate application is ARM CPU emulators. An emulator can take
> advantage of the yield hint to de-prioritise an emulated CPU in favor
> of other emulation tasks. QEMU A64 SMP emulation has yield awareness,
> and sees a significant boot time performance increase with this change.
>
> Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
> Acked-by: Will Deacon <will.deacon@arm.com>
> ---
> arch/arm64/include/asm/processor.h | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index f9be30e..ac2381d 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -126,7 +126,11 @@ extern void release_thread(struct task_struct *);
>
> unsigned long get_wchan(struct task_struct *p);
>
> -#define cpu_relax() barrier()
> +static inline void cpu_relax(void)
> +{
> + asm volatile("yield" ::: "memory");
> +}
> +
> #define cpu_relax_lowlatency() cpu_relax()
>
> /* Thread switching */
> --
> 2.3.0.1.g27a12f1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH] arm64: Implement cpu_relax as yield
@ 2015-03-25 9:58 ` Peter Crosthwaite
0 siblings, 0 replies; 6+ messages in thread
From: Peter Crosthwaite @ 2015-03-25 9:58 UTC (permalink / raw)
To: linux-arm-kernel
Ping!
Anything I need to do or send to to get a merge on this?
Regards,
Peter
On Tue, Mar 3, 2015 at 12:49 AM, Peter Crosthwaite
<peter.crosthwaite@xilinx.com> wrote:
> ARM64 has the yield nop hint which has the intended semantics of
> cpu_relax. Implement.
>
> The immediate application is ARM CPU emulators. An emulator can take
> advantage of the yield hint to de-prioritise an emulated CPU in favor
> of other emulation tasks. QEMU A64 SMP emulation has yield awareness,
> and sees a significant boot time performance increase with this change.
>
> Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
> Acked-by: Will Deacon <will.deacon@arm.com>
> ---
> arch/arm64/include/asm/processor.h | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index f9be30e..ac2381d 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -126,7 +126,11 @@ extern void release_thread(struct task_struct *);
>
> unsigned long get_wchan(struct task_struct *p);
>
> -#define cpu_relax() barrier()
> +static inline void cpu_relax(void)
> +{
> + asm volatile("yield" ::: "memory");
> +}
> +
> #define cpu_relax_lowlatency() cpu_relax()
>
> /* Thread switching */
> --
> 2.3.0.1.g27a12f1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo at vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] arm64: Implement cpu_relax as yield
2015-03-25 9:58 ` Peter Crosthwaite
@ 2015-03-25 11:31 ` Will Deacon
-1 siblings, 0 replies; 6+ messages in thread
From: Will Deacon @ 2015-03-25 11:31 UTC (permalink / raw)
To: Peter Crosthwaite
Cc: linux-arm-kernel, linux-kernel, Catalin Marinas, michals
On Wed, Mar 25, 2015 at 09:58:26AM +0000, Peter Crosthwaite wrote:
> Ping!
>
> Anything I need to do or send to to get a merge on this?
It's queued for 4.1 and should already be in linux-next.
Cheers,
Will
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH] arm64: Implement cpu_relax as yield
@ 2015-03-25 11:31 ` Will Deacon
0 siblings, 0 replies; 6+ messages in thread
From: Will Deacon @ 2015-03-25 11:31 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Mar 25, 2015 at 09:58:26AM +0000, Peter Crosthwaite wrote:
> Ping!
>
> Anything I need to do or send to to get a merge on this?
It's queued for 4.1 and should already be in linux-next.
Cheers,
Will
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2015-03-25 11:31 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-03-02 19:19 [PATCH] arm64: Implement cpu_relax as yield Peter Crosthwaite
2015-03-02 19:19 ` Peter Crosthwaite
2015-03-25 9:58 ` Peter Crosthwaite
2015-03-25 9:58 ` Peter Crosthwaite
2015-03-25 11:31 ` Will Deacon
2015-03-25 11:31 ` Will Deacon
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.