Re: [PATCH v7 20/27] arm64/sve: In-kernel vector length availability query interface

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Fri, Mar 29, 2019 at 01:00:45PM +0000, Dave Martin wrote:
> KVM will need to interrogate the set of SVE vector lengths
> available on the system.
> 
> This patch exposes the relevant bits to the kernel, along with a
> sve_vq_available() helper to check whether a particular vector
> length is supported.
> 
> __vq_to_bit() and __bit_to_vq() are not intended for use outside
> these functions: now that these are exposed outside fpsimd.c, they
> are prefixed with __ in order to provide an extra hint that they
> are not intended for general-purpose use.
> 
> Signed-off-by: Dave Martin <Dave.Martin@xxxxxxx>
> Reviewed-by: Alex Bennée <alex.bennee@xxxxxxxxxx>
> Tested-by: zhang.lei <zhang.lei@xxxxxxxxxxxxxx>
> ---
>  arch/arm64/include/asm/fpsimd.h | 29 +++++++++++++++++++++++++++++
>  arch/arm64/kernel/fpsimd.c      | 35 ++++++++---------------------------
>  2 files changed, 37 insertions(+), 27 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
> index df7a143..ad6d2e4 100644
> --- a/arch/arm64/include/asm/fpsimd.h
> +++ b/arch/arm64/include/asm/fpsimd.h
> @@ -24,10 +24,13 @@
>  
>  #ifndef __ASSEMBLY__
>  
> +#include <linux/bitmap.h>
>  #include <linux/build_bug.h>
> +#include <linux/bug.h>
>  #include <linux/cache.h>
>  #include <linux/init.h>
>  #include <linux/stddef.h>
> +#include <linux/types.h>
>  
>  #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
>  /* Masks for extracting the FPSR and FPCR from the FPSCR */
> @@ -89,6 +92,32 @@ extern u64 read_zcr_features(void);
>  
>  extern int __ro_after_init sve_max_vl;
>  extern int __ro_after_init sve_max_virtualisable_vl;
> +/* Set of available vector lengths, as vq_to_bit(vq): */

s/as/for use with/ ?
s/vq_to_bit/__vq_to_bit/

> +extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
> +
> +/*
> + * Helpers to translate bit indices in sve_vq_map to VQ values (and
> + * vice versa).  This allows find_next_bit() to be used to find the
> + * _maximum_ VQ not exceeding a certain value.
> + */
> +static inline unsigned int __vq_to_bit(unsigned int vq)
> +{

Why not have the same WARN_ON and clamping here as we do
in __bit_to_vq. Here a vq > SVE_VQ_MAX will wrap around
to a super high bit.

> +	return SVE_VQ_MAX - vq;
> +}
> +
> +static inline unsigned int __bit_to_vq(unsigned int bit)
> +{
> +	if (WARN_ON(bit >= SVE_VQ_MAX))
> +		bit = SVE_VQ_MAX - 1;
> +
> +	return SVE_VQ_MAX - bit;
> +}
> +
> +/* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */

Are we avoiding putting these tests and WARN_ONs in this function to
keep it fast?

> +static inline bool sve_vq_available(unsigned int vq)
> +{
> +	return test_bit(__vq_to_bit(vq), sve_vq_map);
> +}
>  
>  #ifdef CONFIG_ARM64_SVE
>  
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index 8a93afa..577296b 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -136,7 +136,7 @@ static int sve_default_vl = -1;
>  int __ro_after_init sve_max_vl = SVE_VL_MIN;
>  int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
>  /* Set of available vector lengths, as vq_to_bit(vq): */
> -static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
> +__ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
>  /* Set of vector lengths present on at least one cpu: */
>  static __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
>  static void __percpu *efi_sve_state;
> @@ -270,25 +270,6 @@ void fpsimd_save(void)
>  }
>  
>  /*
> - * Helpers to translate bit indices in sve_vq_map to VQ values (and
> - * vice versa).  This allows find_next_bit() to be used to find the
> - * _maximum_ VQ not exceeding a certain value.
> - */
> -
> -static unsigned int vq_to_bit(unsigned int vq)
> -{
> -	return SVE_VQ_MAX - vq;
> -}
> -
> -static unsigned int bit_to_vq(unsigned int bit)
> -{
> -	if (WARN_ON(bit >= SVE_VQ_MAX))
> -		bit = SVE_VQ_MAX - 1;
> -
> -	return SVE_VQ_MAX - bit;
> -}
> -
> -/*
>   * All vector length selection from userspace comes through here.
>   * We're on a slow path, so some sanity-checks are included.
>   * If things go wrong there's a bug somewhere, but try to fall back to a
> @@ -309,8 +290,8 @@ static unsigned int find_supported_vector_length(unsigned int vl)
>  		vl = max_vl;
>  
>  	bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
> -			    vq_to_bit(sve_vq_from_vl(vl)));
> -	return sve_vl_from_vq(bit_to_vq(bit));
> +			    __vq_to_bit(sve_vq_from_vl(vl)));
> +	return sve_vl_from_vq(__bit_to_vq(bit));
>  }
>  
>  #ifdef CONFIG_SYSCTL
> @@ -648,7 +629,7 @@ static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
>  		write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
>  		vl = sve_get_vl();
>  		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
> -		set_bit(vq_to_bit(vq), map);
> +		set_bit(__vq_to_bit(vq), map);
>  	}
>  }
>  
> @@ -717,7 +698,7 @@ int sve_verify_vq_map(void)
>  	 * Mismatches above sve_max_virtualisable_vl are fine, since
>  	 * no guest is allowed to configure ZCR_EL2.LEN to exceed this:
>  	 */
> -	if (sve_vl_from_vq(bit_to_vq(b)) <= sve_max_virtualisable_vl) {
> +	if (sve_vl_from_vq(__bit_to_vq(b)) <= sve_max_virtualisable_vl) {
>  		pr_warn("SVE: cpu%d: Unsupported vector length(s) present\n",
>  			smp_processor_id());
>  		return -EINVAL;
> @@ -801,8 +782,8 @@ void __init sve_setup(void)
>  	 * so sve_vq_map must have at least SVE_VQ_MIN set.
>  	 * If something went wrong, at least try to patch it up:
>  	 */
> -	if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
> -		set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
> +	if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
> +		set_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map);
>  
>  	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
>  	sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
> @@ -831,7 +812,7 @@ void __init sve_setup(void)
>  		/* No virtualisable VLs?  This is architecturally forbidden. */
>  		sve_max_virtualisable_vl = SVE_VQ_MIN;
>  	else /* b + 1 < SVE_VQ_MAX */
> -		sve_max_virtualisable_vl = sve_vl_from_vq(bit_to_vq(b + 1));
> +		sve_max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));
>  
>  	if (sve_max_virtualisable_vl > sve_max_vl)
>  		sve_max_virtualisable_vl = sve_max_vl;
> -- 
> 2.1.4

Thanks,
drew
_______________________________________________
kvmarm mailing list
kvmarm@xxxxxxxxxxxxxxxxxxxxx
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm




[Index of Archives]     [Linux KVM]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux