[PATCH 09/27] arm64/sve: Signal frame and context structure definition

[alex.bennee@linaro.org (Alex Bennée)]

Dave Martin <Dave.Martin@arm.com> writes:

> This patch defines the representation that will be used for the SVE
> register state in the signal frame, and implements support for
> saving and restoring the SVE registers around signals.
>
> The same layout will also be used for the in-kernel task state.
>
> Due to the variability of the SVE vector length, it is not possible
> to define a fixed C struct to describe all the registers.  Instead,
> Macros are defined in sigcontext.h to facilitate access to the
> parts of the structure.
>
> Signed-off-by: Dave Martin <Dave.Martin@arm.com>
> ---
>  arch/arm64/include/uapi/asm/sigcontext.h | 113 ++++++++++++++++++++++++++++++-
>  1 file changed, 112 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
> index f0a76b9..0533bdf 100644
> --- a/arch/arm64/include/uapi/asm/sigcontext.h
> +++ b/arch/arm64/include/uapi/asm/sigcontext.h
> @@ -16,6 +16,8 @@
>  #ifndef _UAPI__ASM_SIGCONTEXT_H
>  #define _UAPI__ASM_SIGCONTEXT_H
>
> +#ifndef __ASSEMBLY__
> +
>  #include <linux/types.h>
>
>  /*
> @@ -41,10 +43,11 @@ struct sigcontext {
>   *
>   *	0x210		fpsimd_context
>   *	 0x10		esr_context
> + *	0x8a0		sve_context (vl <= 64) (optional)
>   *	 0x20		extra_context (optional)
>   *	 0x10		terminator (null _aarch64_ctx)
>   *
> - *	0xdb0		(reserved for future allocation)
> + *	0x510		(reserved for future allocation)
>   *
>   * New records that can exceed this space need to be opt-in for userspace, so
>   * that an expanded signal frame is not generated unexpectedly.  The mechanism
> @@ -116,4 +119,112 @@ struct extra_context {
>  	__u32 __reserved[3];
>  };
>
> +#define SVE_MAGIC	0x53564501
> +
> +struct sve_context {
> +	struct _aarch64_ctx head;
> +	__u16 vl;
> +	__u16 __reserved[3];
> +};
> +
> +#endif /* !__ASSEMBLY__ */
> +
> +/*
> + * The SVE architecture leaves space for future expansion of the
> + * vector length beyond its initial architectural limit of 2048 bits
> + * (16 quadwords).
> + */
> +#define SVE_VQ_MIN		1
> +#define SVE_VQ_MAX		0x200
> +
> +#define SVE_VL_MIN		(SVE_VQ_MIN * 0x10)
> +#define SVE_VL_MAX		(SVE_VQ_MAX * 0x10)
> +
> +#define SVE_NUM_ZREGS		32
> +#define SVE_NUM_PREGS		16
> +
> +#define sve_vl_valid(vl) \
> +	((vl) % 0x10 == 0 && (vl) >= SVE_VL_MIN && (vl) <= SVE_VL_MAX)
> +#define sve_vq_from_vl(vl)	((vl) / 0x10)
> +#define sve_vl_from_vq(vq)	((vq) * 0x10)

I got a little confused first time through over what VQ and VL where.
Maybe it would make sense to expand a little more from first principles?

  /*
   * The SVE architecture defines vector registers as a multiple of 128
   * bit quadwords. The current architectural limit is 2048 bits (16
   * quadwords) but there is room for future expansion beyond that.
    */

  #define SVE_VQ_BITS             128      /* 128 bits in one quadword */
  #define SVE_VQ_BYTES            (SVE_VQ_BITS / 8)

  #define SVE_VQ_MIN		1
  #define SVE_VQ_MAX		0x200    /* see ZCR_ELx[8:0] */

  #define SVE_VL_MIN_BYTES	(SVE_VQ_MIN * SVE_VQ_BYTES)
  #define SVE_VL_MAX_BYTES	(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)


> +
> +/*
> + * If the SVE registers are currently live for the thread at signal delivery,
> + * sve_context.head.size >=
> + *	SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve_context.vl))
> + * and the register data may be accessed using the SVE_SIG_*() macros.
> + *
> + * If sve_context.head.size <
> + *	SVE_SIG_CONTEXT_SIZE(sve_vq_from_vl(sve_context.vl)),
> + * the SVE registers were not live for the thread and no register data
> + * is included: in this case, the SVE_SIG_*() macros should not be
> + * used except for this check.
> + *
> + * The same convention applies when returning from a signal: a caller
> + * will need to remove or resize the sve_context block if it wants to
> + * make the SVE registers live when they were previously non-live or
> + * vice-versa.  This may require the the caller to allocate fresh
> + * memory and/or move other context blocks in the signal frame.
> + *
> + * Changing the vector length during signal return is not permitted:
> + * sve_context.vl must equal the thread's current vector length when
> + * doing a sigreturn.
> + *
> + *
> + * Note: for all these macros, the "vq" argument denotes the SVE
> + * vector length in quadwords (i.e., units of 128 bits).
> + *
> + * The correct way to obtain vq is to use sve_vq_from_vl(vl).  The
> + * result is valid if and only if sve_vl_valid(vl) is true.  This is
> + * guaranteed for a struct sve_context written by the kernel.
> + *
> + *
> + * Additional macros describe the contents and layout of the payload.
> + * For each, SVE_SIG_x_OFFSET(args) is the start offset relative to
> + * the start of struct sve_context, and SVE_SIG_x_SIZE(args) is the
> + * size in bytes:
> + *
> + *	x	type				description
> + *	-	----				-----------
> + *	REGS					the entire SVE context
> + *
> + *	ZREGS	__uint128_t[SVE_NUM_ZREGS][vq]	all Z-registers
> + *	ZREG	__uint128_t[vq]			individual Z-register Zn
> + *
> + *	PREGS	uint16_t[SVE_NUM_PREGS][vq]	all P-registers
> + *	PREG	uint16_t[vq]			individual P-register Pn
> + *
> + *	FFR	uint16_t[vq]			first-fault status register
> + *
> + * Additional data might be appended in the future.
> + */
> +
> +#define SVE_SIG_ZREG_SIZE(vq)	((__u32)(vq) * 16)
> +#define SVE_SIG_PREG_SIZE(vq)	((__u32)(vq) * 2)
> +#define SVE_SIG_FFR_SIZE(vq)	SVE_SIG_PREG_SIZE(vq)
> +
> +#define SVE_SIG_REGS_OFFSET	((sizeof(struct sve_context) + 15) / 16 * 16)
> +
> +#define SVE_SIG_ZREGS_OFFSET	SVE_SIG_REGS_OFFSET
> +#define SVE_SIG_ZREG_OFFSET(vq, n) \
> +	(SVE_SIG_ZREGS_OFFSET + SVE_SIG_ZREG_SIZE(vq) * (n))
> +#define SVE_SIG_ZREGS_SIZE(vq) \
> +	(SVE_SIG_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_SIG_ZREGS_OFFSET)
> +
> +#define SVE_SIG_PREGS_OFFSET(vq) \
> +	(SVE_SIG_ZREGS_OFFSET + SVE_SIG_ZREGS_SIZE(vq))
> +#define SVE_SIG_PREG_OFFSET(vq, n) \
> +	(SVE_SIG_PREGS_OFFSET(vq) + SVE_SIG_PREG_SIZE(vq) * (n))
> +#define SVE_SIG_PREGS_SIZE(vq) \
> +	(SVE_SIG_PREG_OFFSET(vq, SVE_NUM_PREGS) - SVE_SIG_PREGS_OFFSET(vq))
> +
> +#define SVE_SIG_FFR_OFFSET(vq) \
> +	(SVE_SIG_PREGS_OFFSET(vq) + SVE_SIG_PREGS_SIZE(vq))
> +
> +#define SVE_SIG_REGS_SIZE(vq) \
> +	(SVE_SIG_FFR_OFFSET(vq) + SVE_SIG_FFR_SIZE(vq) - SVE_SIG_REGS_OFFSET)
> +
> +#define SVE_SIG_CONTEXT_SIZE(vq) (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))
> +
> +
>  #endif /* _UAPI__ASM_SIGCONTEXT_H */


--
Alex Benn?e