[PATCH v2 07/28] arm64/sve: Low-level SVE architectural state manipulation functions

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

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

> Manipulating the SVE architectural state, including the vector and
> predicate registers, first-fault register and the vector length,
> requires the use of dedicated instructions added by SVE.
>
> This patch adds suitable assembly functions for saving and
> restoring the SVE registers and querying the vector length.
> Setting of the vector length is done as part of register restore.
>
> Since people building kernels may not all get an SVE-enabled
> toolchain for a while, this patch uses macros that generate
> explicit opcodes in place of assembler mnemonics.
>
> Signed-off-by: Dave Martin <Dave.Martin@arm.com>
> Cc: Alex Benn?e <alex.bennee@linaro.org>

It took me a while to find a way to properly dissemble the resulting
binaries, in the end needing to run a native objdump in Stretch. I'd
hopped my gdb-multiarch was bleeding edge enough but no ;-)

Reviewed-by: Alex Benn?e <alex.bennee@linaro.org>

>
> ---
>
> Changes since v1
> ----------------
>
> Requested by Alex Benn?e:
>
> * Annotate instruction generation macros with the canonical
> architectural syntax so that people can cross-reference more easily
> against the architectural documentation.
> ---
>  arch/arm64/include/asm/fpsimd.h       |   5 ++
>  arch/arm64/include/asm/fpsimdmacros.h | 148 ++++++++++++++++++++++++++++++++++
>  arch/arm64/kernel/entry-fpsimd.S      |  17 ++++
>  3 files changed, 170 insertions(+)
>
> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
> index 410c481..026a7c7 100644
> --- a/arch/arm64/include/asm/fpsimd.h
> +++ b/arch/arm64/include/asm/fpsimd.h
> @@ -67,6 +67,11 @@ extern void fpsimd_update_current_state(struct fpsimd_state *state);
>
>  extern void fpsimd_flush_task_state(struct task_struct *target);
>
> +extern void sve_save_state(void *state, u32 *pfpsr);
> +extern void sve_load_state(void const *state, u32 const *pfpsr,
> +			   unsigned long vq_minus_1);
> +extern unsigned int sve_get_vl(void);
> +
>  /* For use by EFI runtime services calls only */
>  extern void __efi_fpsimd_begin(void);
>  extern void __efi_fpsimd_end(void);
> diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
> index 0f5fdd3..e050d76 100644
> --- a/arch/arm64/include/asm/fpsimdmacros.h
> +++ b/arch/arm64/include/asm/fpsimdmacros.h
> @@ -75,3 +75,151 @@
>  	ldr	w\tmpnr, [\state, #16 * 2 + 4]
>  	fpsimd_restore_fpcr x\tmpnr, \state
>  .endm
> +
> +/* Sanity-check macros to help avoid encoding garbage instructions */
> +
> +.macro _check_general_reg nr
> +	.if (\nr) < 0 || (\nr) > 30
> +		.error "Bad register number \nr."
> +	.endif
> +.endm
> +
> +.macro _sve_check_zreg znr
> +	.if (\znr) < 0 || (\znr) > 31
> +		.error "Bad Scalable Vector Extension vector register number \znr."
> +	.endif
> +.endm
> +
> +.macro _sve_check_preg pnr
> +	.if (\pnr) < 0 || (\pnr) > 15
> +		.error "Bad Scalable Vector Extension predicate register number \pnr."
> +	.endif
> +.endm
> +
> +.macro _check_num n, min, max
> +	.if (\n) < (\min) || (\n) > (\max)
> +		.error "Number \n out of range [\min,\max]"
> +	.endif
> +.endm
> +
> +/* SVE instruction encodings for non-SVE-capable assemblers */
> +
> +/* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */
> +.macro _sve_str_v nz, nxbase, offset=0
> +	_sve_check_zreg \nz
> +	_check_general_reg \nxbase
> +	_check_num (\offset), -0x100, 0xff
> +	.inst	0xe5804000			\
> +		| (\nz)				\
> +		| ((\nxbase) << 5)		\
> +		| (((\offset) & 7) << 10)	\
> +		| (((\offset) & 0x1f8) << 13)
> +.endm
> +
> +/* LDR (vector): LDR Z\nz, [X\nxbase, #\offset, MUL VL] */
> +.macro _sve_ldr_v nz, nxbase, offset=0
> +	_sve_check_zreg \nz
> +	_check_general_reg \nxbase
> +	_check_num (\offset), -0x100, 0xff
> +	.inst	0x85804000			\
> +		| (\nz)				\
> +		| ((\nxbase) << 5)		\
> +		| (((\offset) & 7) << 10)	\
> +		| (((\offset) & 0x1f8) << 13)
> +.endm
> +
> +/* STR (predicate): STR P\np, [X\nxbase, #\offset, MUL VL] */
> +.macro _sve_str_p np, nxbase, offset=0
> +	_sve_check_preg \np
> +	_check_general_reg \nxbase
> +	_check_num (\offset), -0x100, 0xff
> +	.inst	0xe5800000			\
> +		| (\np)				\
> +		| ((\nxbase) << 5)		\
> +		| (((\offset) & 7) << 10)	\
> +		| (((\offset) & 0x1f8) << 13)
> +.endm
> +
> +/* LDR (predicate): LDR P\np, [X\nxbase, #\offset, MUL VL] */
> +.macro _sve_ldr_p np, nxbase, offset=0
> +	_sve_check_preg \np
> +	_check_general_reg \nxbase
> +	_check_num (\offset), -0x100, 0xff
> +	.inst	0x85800000			\
> +		| (\np)				\
> +		| ((\nxbase) << 5)		\
> +		| (((\offset) & 7) << 10)	\
> +		| (((\offset) & 0x1f8) << 13)
> +.endm
> +
> +/* RDVL X\nx, #\imm */
> +.macro _sve_rdvl nx, imm
> +	_check_general_reg \nx
> +	_check_num (\imm), -0x20, 0x1f
> +	.inst	0x04bf5000			\
> +		| (\nx)				\
> +		| (((\imm) & 0x3f) << 5)
> +.endm
> +
> +/* RDFFR (unpredicated): RDFFR P\np.B */
> +.macro _sve_rdffr np
> +	_sve_check_preg \np
> +	.inst	0x2519f000			\
> +		| (\np)
> +.endm
> +
> +/* WRFFR P\np.B */
> +.macro _sve_wrffr np
> +	_sve_check_preg \np
> +	.inst	0x25289000			\
> +		| ((\np) << 5)
> +.endm
> +
> +.macro __for from:req, to:req
> +	.if (\from) == (\to)
> +		_for__body \from
> +	.else
> +		__for \from, (\from) + ((\to) - (\from)) / 2
> +		__for (\from) + ((\to) - (\from)) / 2 + 1, \to
> +	.endif
> +.endm
> +
> +.macro _for var:req, from:req, to:req, insn:vararg
> +	.macro _for__body \var:req
> +		\insn
> +	.endm
> +
> +	__for \from, \to
> +
> +	.purgem _for__body
> +.endm
> +
> +.macro sve_save nxbase, xpfpsr, nxtmp
> + _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
> + _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
> +		_sve_rdffr	0
> +		_sve_str_p	0, \nxbase
> +		_sve_ldr_p	0, \nxbase, -16
> +
> +		mrs		x\nxtmp, fpsr
> +		str		w\nxtmp, [\xpfpsr]
> +		mrs		x\nxtmp, fpcr
> +		str		w\nxtmp, [\xpfpsr, #4]
> +.endm
> +
> +.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp
> +		mrs_s		x\nxtmp, SYS_ZCR_EL1
> +		bic		x\nxtmp, x\nxtmp, ZCR_ELx_LEN_MASK
> +		orr		x\nxtmp, x\nxtmp, \xvqminus1
> +		msr_s		SYS_ZCR_EL1, x\nxtmp	// self-synchronising
> +
> + _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
> +		_sve_ldr_p	0, \nxbase
> +		_sve_wrffr	0
> + _for n, 0, 15,	_sve_ldr_p	\n, \nxbase, \n - 16
> +
> +		ldr		w\nxtmp, [\xpfpsr]
> +		msr		fpsr, x\nxtmp
> +		ldr		w\nxtmp, [\xpfpsr, #4]
> +		msr		fpcr, x\nxtmp
> +.endm
> diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
> index 6a27cd6..73f17bf 100644
> --- a/arch/arm64/kernel/entry-fpsimd.S
> +++ b/arch/arm64/kernel/entry-fpsimd.S
> @@ -41,3 +41,20 @@ ENTRY(fpsimd_load_state)
>  	fpsimd_restore x0, 8
>  	ret
>  ENDPROC(fpsimd_load_state)
> +
> +#ifdef CONFIG_ARM64_SVE
> +ENTRY(sve_save_state)
> +	sve_save 0, x1, 2
> +	ret
> +ENDPROC(sve_save_state)
> +
> +ENTRY(sve_load_state)
> +	sve_load 0, x1, x2, 3
> +	ret
> +ENDPROC(sve_load_state)
> +
> +ENTRY(sve_get_vl)
> +	_sve_rdvl	0, 1
> +	ret
> +ENDPROC(sve_get_vl)
> +#endif /* CONFIG_ARM64_SVE */


--
Alex Benn?e