Re: [PATCH v3] arch/riscv: add Zihintpause support

From: Samuel Holland
Date: Thu Jun 16 2022 - 23:49:53 EST


On 6/15/22 4:14 PM, Dao Lu wrote:
> Implement support for the ZiHintPause extension.
>
> The PAUSE instruction is a HINT that indicates the current hart’s rate
> of instruction retirement should be temporarily reduced or paused.
>
> Reviewed-by: Heiko Stuebner <heiko@xxxxxxxxx>
> Tested-by: Heiko Stuebner <heiko@xxxxxxxxx>
> Signed-off-by: Dao Lu <daolu@xxxxxxxxxxxx>
> ---
>
> v1 -> v2:
> Remove the usage of static branch, use PAUSE if toolchain supports it
> v2 -> v3:
> Added the static branch back, cpu_relax() behavior is unchanged if either the
> system or the toolchain does not support ZiHintPause
> ---
> arch/riscv/Makefile | 4 ++++
> arch/riscv/include/asm/hwcap.h | 1 +
> arch/riscv/include/asm/vdso/processor.h | 19 ++++++++++++++++---
> arch/riscv/kernel/cpu.c | 1 +
> arch/riscv/kernel/cpufeature.c | 8 ++++++++
> 5 files changed, 30 insertions(+), 3 deletions(-)
>
> diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
> index 34cf8a598617..6ddacc6f44b9 100644
> --- a/arch/riscv/Makefile
> +++ b/arch/riscv/Makefile
> @@ -56,6 +56,10 @@ riscv-march-$(CONFIG_RISCV_ISA_C) := $(riscv-march-y)c
> toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zicsr_zifencei)
> riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei
>
> +# Check if the toolchain supports Zihintpause extension
> +toolchain-supports-zihintpause := $(call cc-option-yn, -march=$(riscv-march-y)_zihintpause)
> +riscv-march-$(toolchain-supports-zihintpause) := $(riscv-march-y)_zihintpause
> +
> KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
> KBUILD_AFLAGS += -march=$(riscv-march-y)
>
> diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
> index 4e2486881840..f24f4f8c9144 100644
> --- a/arch/riscv/include/asm/hwcap.h
> +++ b/arch/riscv/include/asm/hwcap.h
> @@ -53,6 +53,7 @@ extern unsigned long elf_hwcap;
> enum riscv_isa_ext_id {
> RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
> RISCV_ISA_EXT_SVPBMT,
> + RISCV_ISA_EXT_ZIHINTPAUSE,
> RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
> };
>
> diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
> index 134388cbaaa1..314ec17c40d8 100644
> --- a/arch/riscv/include/asm/vdso/processor.h
> +++ b/arch/riscv/include/asm/vdso/processor.h
> @@ -4,15 +4,28 @@
>
> #ifndef __ASSEMBLY__
>
> +#include <linux/jump_label.h>
> #include <asm/barrier.h>
> +#include <asm/hwcap.h>
>
> +extern struct static_key_false riscv_pause_available;
> static inline void cpu_relax(void)
> {
> + if (!static_branch_likely(&riscv_pause_available)) {
> #ifdef __riscv_muldiv
> - int dummy;
> - /* In lieu of a halt instruction, induce a long-latency stall. */
> - __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
> + int dummy;
> + /* In lieu of a halt instruction, induce a long-latency stall. */
> + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
> #endif
> +#ifdef __riscv_zihintpause
> + } else {
> + /*
> + * Reduce instruction retirement.
> + * This assumes the PC changes.
> + */
> + __asm__ __volatile__ ("pause");
> +#endif
> + }
> barrier();
> }
>
> diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
> index fba9e9f46a8c..a123e92b14dd 100644
> --- a/arch/riscv/kernel/cpu.c
> +++ b/arch/riscv/kernel/cpu.c
> @@ -89,6 +89,7 @@ int riscv_of_parent_hartid(struct device_node *node)
> static struct riscv_isa_ext_data isa_ext_arr[] = {
> __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
> __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
> + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
> __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
> };
>
> diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
> index a6f62a6d1edd..78c284c487e8 100644
> --- a/arch/riscv/kernel/cpufeature.c
> +++ b/arch/riscv/kernel/cpufeature.c
> @@ -30,6 +30,8 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
> #ifdef CONFIG_FPU
> __ro_after_init DEFINE_STATIC_KEY_FALSE(cpu_hwcap_fpu);
> #endif
> +DEFINE_STATIC_KEY_FALSE(riscv_pause_available);
> +EXPORT_SYMBOL_GPL(riscv_pause_available);

This patch should probably be rebased to use the unified static key
mechanism[1], since that patch has now been merged.

Regards,
Samuel

[1]: https://lore.kernel.org/linux-riscv/20220522153543.2656-2-jszhang@xxxxxxxxxx/