Dave Martin <dave.mar...@arm.com> writes:
> Having read_zcr_features() inline in cpufeature.h results in that
> header requiring #includes which make it hard to include
> <asm/fpsimd.h> elsewhere without triggering header inclusion
> cycles.
>
> This is not a hot-path function and arguably should not be in
> cpufeature.h in the first place, so this patch moves it to
> fpsimd.c, compiled conditionally if CONFIG_ARM64_SVE=y.
>
> This allows some SVE-related #includes to be dropped from
> cpufeature.h, which will ease future maintenance.
>
> A couple of missing #includes of <asm/fpsimd.h> are exposed by this
> change under arch/arm64/. This patch adds the missing #includes as
> necessary.
>
> No functional change.
>
> Signed-off-by: Dave Martin <dave.mar...@arm.com>
> Acked-by: Catalin Marinas <catalin.mari...@arm.com>
> Acked-by: Marc Zyngier <marc.zyng...@arm.com>
Reviewed-by: Alex Bennée <alex.ben...@linaro.org>
> ---
> arch/arm64/include/asm/cpufeature.h | 29 -----------------------------
> arch/arm64/include/asm/fpsimd.h | 2 ++
> arch/arm64/include/asm/processor.h | 1 +
> arch/arm64/kernel/fpsimd.c | 28 ++++++++++++++++++++++++++++
> arch/arm64/kernel/ptrace.c | 1 +
> 5 files changed, 32 insertions(+), 29 deletions(-)
>
> diff --git a/arch/arm64/include/asm/cpufeature.h
> b/arch/arm64/include/asm/cpufeature.h
> index 09b0f2a..0a6b713 100644
> --- a/arch/arm64/include/asm/cpufeature.h
> +++ b/arch/arm64/include/asm/cpufeature.h
> @@ -11,9 +11,7 @@
>
> #include <asm/cpucaps.h>
> #include <asm/cputype.h>
> -#include <asm/fpsimd.h>
> #include <asm/hwcap.h>
> -#include <asm/sigcontext.h>
> #include <asm/sysreg.h>
>
> /*
> @@ -510,33 +508,6 @@ static inline bool system_supports_sve(void)
> cpus_have_const_cap(ARM64_SVE);
> }
>
> -/*
> - * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
> - * vector length.
> - *
> - * Use only if SVE is present.
> - * This function clobbers the SVE vector length.
> - */
> -static inline u64 read_zcr_features(void)
> -{
> - u64 zcr;
> - unsigned int vq_max;
> -
> - /*
> - * Set the maximum possible VL, and write zeroes to all other
> - * bits to see if they stick.
> - */
> - sve_kernel_enable(NULL);
> - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
> -
> - zcr = read_sysreg_s(SYS_ZCR_EL1);
> - zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
> - vq_max = sve_vq_from_vl(sve_get_vl());
> - zcr |= vq_max - 1; /* set LEN field to maximum effective value */
> -
> - return zcr;
> -}
> -
> #endif /* __ASSEMBLY__ */
>
> #endif
> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
> index 3e00f70..fb60b22 100644
> --- a/arch/arm64/include/asm/fpsimd.h
> +++ b/arch/arm64/include/asm/fpsimd.h
> @@ -69,6 +69,8 @@ extern unsigned int sve_get_vl(void);
> struct arm64_cpu_capabilities;
> extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
>
> +extern u64 read_zcr_features(void);
> +
> extern int __ro_after_init sve_max_vl;
>
> #ifdef CONFIG_ARM64_SVE
> diff --git a/arch/arm64/include/asm/processor.h
> b/arch/arm64/include/asm/processor.h
> index 7675989..f902b6d 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -40,6 +40,7 @@
>
> #include <asm/alternative.h>
> #include <asm/cpufeature.h>
> +#include <asm/fpsimd.h>
> #include <asm/hw_breakpoint.h>
> #include <asm/lse.h>
> #include <asm/pgtable-hwdef.h>
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index ded7ffd..5152bbc 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -37,6 +37,7 @@
> #include <linux/sched/task_stack.h>
> #include <linux/signal.h>
> #include <linux/slab.h>
> +#include <linux/stddef.h>
> #include <linux/sysctl.h>
>
> #include <asm/esr.h>
> @@ -754,6 +755,33 @@ void sve_kernel_enable(const struct
> arm64_cpu_capabilities *__always_unused p)
> isb();
> }
>
> +/*
> + * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
> + * vector length.
> + *
> + * Use only if SVE is present.
> + * This function clobbers the SVE vector length.
> + */
> +u64 read_zcr_features(void)
> +{
> + u64 zcr;
> + unsigned int vq_max;
> +
> + /*
> + * Set the maximum possible VL, and write zeroes to all other
> + * bits to see if they stick.
> + */
> + sve_kernel_enable(NULL);
> + write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
> +
> + zcr = read_sysreg_s(SYS_ZCR_EL1);
> + zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
> + vq_max = sve_vq_from_vl(sve_get_vl());
> + zcr |= vq_max - 1; /* set LEN field to maximum effective value */
> +
> + return zcr;
> +}
> +
> void __init sve_setup(void)
> {
> u64 zcr;
> diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
> index 7ff81fe..78889c4 100644
> --- a/arch/arm64/kernel/ptrace.c
> +++ b/arch/arm64/kernel/ptrace.c
> @@ -44,6 +44,7 @@
> #include <asm/compat.h>
> #include <asm/cpufeature.h>
> #include <asm/debug-monitors.h>
> +#include <asm/fpsimd.h>
> #include <asm/pgtable.h>
> #include <asm/stacktrace.h>
> #include <asm/syscall.h>
--
Alex Bennée
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
