Re: [PATCH v1 16/20] ARC: [plat-eznps] Use dedicated cpu_relax()
From: Peter Zijlstra
Date: Mon Nov 02 2015 - 04:22:01 EST
On Sat, Oct 31, 2015 at 03:15:23PM +0200, Noam Camus wrote:
> From: Tal Zilcer <talz@xxxxxxxxxx>
>
> Since the CTOP is SMT hardware multi-threaded, we need to hint
> the HW that now will be a very good time to do a hardware
> thread context switching. This is done by issuing the schd.rw
> instruction (binary coded here so as to not require specific
> revision of GCC to build the kernel).
> sched.rw means that Thread becomes eligible for execution by
> the threads scheduler after all pending read/write
> transactions were completed.
>
> Signed-off-by: Noam Camus <noamc@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> ---
> arch/arc/include/asm/processor.h | 5 +++++
> 1 files changed, 5 insertions(+), 0 deletions(-)
>
> diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
> index 7266ede..f1a51a6 100644
> --- a/arch/arc/include/asm/processor.h
> +++ b/arch/arc/include/asm/processor.h
> @@ -58,7 +58,12 @@ struct task_struct;
> * get optimised away by gcc
> */
> #ifdef CONFIG_SMP
> +#ifdef CONFIG_EZNPS_MTM_EXT
> +#define cpu_relax() \
> + __asm__ __volatile__ (".word %0" : : "i"(CTOP_INST_SCHD_RW) : "memory")
> +#else
> #define cpu_relax() __asm__ __volatile__ ("" : : : "memory")
> +#endif
> #else
> #define cpu_relax() do { } while (0)
> #endif
At which point you might want to revisit:
arch/arc/include/asm/processor.h:#define cpu_relax_lowlatency() cpu_relax()
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/