[PATCH -next v14 08/19] riscv: Introduce struct/helpers to save/restore per-task Vector state

[Björn Töpel]

Andy Chiu <andy.chiu at sifive.com> writes:

> diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
> index 692d3ee2d2d3..9c025f2efdc3 100644
> --- a/arch/riscv/include/asm/vector.h
> +++ b/arch/riscv/include/asm/vector.h
> @@ -31,11 +54,72 @@ static __always_inline void riscv_v_disable(void)
>  	csr_clear(CSR_SSTATUS, SR_VS);
>  }
>  
> +static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
> +{
> +	asm volatile (
> +		"csrr	%0, " CSR_STR(CSR_VSTART) "\n\t"
> +		"csrr	%1, " CSR_STR(CSR_VTYPE) "\n\t"
> +		"csrr	%2, " CSR_STR(CSR_VL) "\n\t"
> +		"csrr	%3, " CSR_STR(CSR_VCSR) "\n\t"
> +		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
> +		  "=r" (dest->vcsr) : :);
> +}
> +
> +static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src)
> +{
> +	asm volatile (
> +		"vsetvl	 x0, %2, %1\n\t"
> +		"csrw	" CSR_STR(CSR_VSTART) ", %0\n\t"
> +		"csrw	" CSR_STR(CSR_VCSR) ", %3\n\t"
> +		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl),
> +		    "r" (src->vcsr) :);
> +}
> +
> +static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, void *datap)
> +{
> +	riscv_v_enable();
> +	__vstate_csr_save(save_to);
> +	asm volatile (
> +		"vsetvli	t4, x0, e8, m8, ta, ma\n\t"
> +		"vse8.v		v0, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vse8.v		v8, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vse8.v		v16, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vse8.v		v24, (%0)\n\t"
> +		: : "r" (datap) : "t4", "memory");
> +	riscv_v_disable();
> +}
> +
> +static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_from,
> +				    void *datap)
> +{
> +	riscv_v_enable();
> +	asm volatile (
> +		"vsetvli	t4, x0, e8, m8, ta, ma\n\t"
> +		"vle8.v		v0, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vle8.v		v8, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vle8.v		v16, (%0)\n\t"
> +		"add		%0, %0, t4\n\t"
> +		"vle8.v		v24, (%0)\n\t"
> +		: : "r" (datap) : "t4");

Nit/question: For both enable/disable; Any reason to clobber t4, instead
of using a scratch reg?

Björn