21eb468e9f
__SVE_VQ_MAX is defined without comment as 512 but the actual architectural maximum is 16, a substantial difference which might not be obvious to readers especially given the several different units used for specifying vector sizes in various contexts and the fact that it's often used via macros. In an effort to minimise surprises for users who might assume the value is the architectural maximum and use it to do things like size allocations add a comment noting the difference, and add a note for SVE_VQ_MAX to aid discoverability. Signed-off-by: Mark Brown <broonie@kernel.org> Acked-by: Dave Martin <Dave.Martin@arm.com> Link: https://lore.kernel.org/r/20240209-arm64-sve-vl-max-comment-v2-1-111b283469ee@kernel.org Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
65 lines
2.0 KiB
C
65 lines
2.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
/* Copyright (C) 2017-2018 ARM Limited */
|
|
|
|
/*
|
|
* For use by other UAPI headers only.
|
|
* Do not make direct use of header or its definitions.
|
|
*/
|
|
|
|
#ifndef _UAPI__ASM_SVE_CONTEXT_H
|
|
#define _UAPI__ASM_SVE_CONTEXT_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
#define __SVE_VQ_BYTES 16 /* number of bytes per quadword */
|
|
|
|
/*
|
|
* Yes, __SVE_VQ_MAX is 512 QUADWORDS.
|
|
*
|
|
* To help ensure forward portability, this is much larger than the
|
|
* current maximum value defined by the SVE architecture. While arrays
|
|
* or static allocations can be sized based on this value, watch out!
|
|
* It will waste a surprisingly large amount of memory.
|
|
*
|
|
* Dynamic sizing based on the actual runtime vector length is likely to
|
|
* be preferable for most purposes.
|
|
*/
|
|
#define __SVE_VQ_MIN 1
|
|
#define __SVE_VQ_MAX 512
|
|
|
|
#define __SVE_VL_MIN (__SVE_VQ_MIN * __SVE_VQ_BYTES)
|
|
#define __SVE_VL_MAX (__SVE_VQ_MAX * __SVE_VQ_BYTES)
|
|
|
|
#define __SVE_NUM_ZREGS 32
|
|
#define __SVE_NUM_PREGS 16
|
|
|
|
#define __sve_vl_valid(vl) \
|
|
((vl) % __SVE_VQ_BYTES == 0 && \
|
|
(vl) >= __SVE_VL_MIN && \
|
|
(vl) <= __SVE_VL_MAX)
|
|
|
|
#define __sve_vq_from_vl(vl) ((vl) / __SVE_VQ_BYTES)
|
|
#define __sve_vl_from_vq(vq) ((vq) * __SVE_VQ_BYTES)
|
|
|
|
#define __SVE_ZREG_SIZE(vq) ((__u32)(vq) * __SVE_VQ_BYTES)
|
|
#define __SVE_PREG_SIZE(vq) ((__u32)(vq) * (__SVE_VQ_BYTES / 8))
|
|
#define __SVE_FFR_SIZE(vq) __SVE_PREG_SIZE(vq)
|
|
|
|
#define __SVE_ZREGS_OFFSET 0
|
|
#define __SVE_ZREG_OFFSET(vq, n) \
|
|
(__SVE_ZREGS_OFFSET + __SVE_ZREG_SIZE(vq) * (n))
|
|
#define __SVE_ZREGS_SIZE(vq) \
|
|
(__SVE_ZREG_OFFSET(vq, __SVE_NUM_ZREGS) - __SVE_ZREGS_OFFSET)
|
|
|
|
#define __SVE_PREGS_OFFSET(vq) \
|
|
(__SVE_ZREGS_OFFSET + __SVE_ZREGS_SIZE(vq))
|
|
#define __SVE_PREG_OFFSET(vq, n) \
|
|
(__SVE_PREGS_OFFSET(vq) + __SVE_PREG_SIZE(vq) * (n))
|
|
#define __SVE_PREGS_SIZE(vq) \
|
|
(__SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - __SVE_PREGS_OFFSET(vq))
|
|
|
|
#define __SVE_FFR_OFFSET(vq) \
|
|
(__SVE_PREGS_OFFSET(vq) + __SVE_PREGS_SIZE(vq))
|
|
|
|
#endif /* ! _UAPI__ASM_SVE_CONTEXT_H */
|