Re: [PATCH v2 12/28] arm64/sve: Support vector length resetting for new processes

["Alex Bennée" <alex.bennee@linaro.org>]

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

> It's desirable to be able to reset the vector length to some sane
> default for new processes, since the new binary and its libraries
> processes may or may not be SVE-aware.
>
> This patch tracks the desired post-exec vector length (if any) in a
> new thread member sve_vl_onexec, and adds a new thread flag
> TIF_SVE_VL_INHERIT to control whether to inherit or reset the
> vector length.  Currently these are inactive.  Subsequent patches
> will provide the capability to configure them.
>
> Signed-off-by: Dave Martin <Dave.Martin@arm.com>
> Cc: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

>
> ---
>
> Changes since v1
> ----------------
>
> Requested by Alex Bennée:
>
> * Make sve_vl_onexec an unsigned int: that's the type used virtually
> everywhere else, and the memory saving is too minor to be interesting.
> ---
>  arch/arm64/include/asm/processor.h   |  1 +
>  arch/arm64/include/asm/thread_info.h |  1 +
>  arch/arm64/kernel/fpsimd.c           | 16 ++++++++++++----
>  3 files changed, 14 insertions(+), 4 deletions(-)
>
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index 4831d28..3faceac 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -87,6 +87,7 @@ struct thread_struct {
>  	struct fpsimd_state	fpsimd_state;
>  	void			*sve_state;	/* SVE registers, if any */
>  	unsigned int		sve_vl;		/* SVE vector length */
> +	unsigned int		sve_vl_onexec;	/* SVE vl after next exec */
>  	unsigned long		fault_address;	/* fault info */
>  	unsigned long		fault_code;	/* ESR_EL1 value */
>  	struct debug_info	debug;		/* debugging */
> diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
> index f0880fc..d3568ab 100644
> --- a/arch/arm64/include/asm/thread_info.h
> +++ b/arch/arm64/include/asm/thread_info.h
> @@ -92,6 +92,7 @@ void arch_setup_new_exec(void);
>  #define TIF_SINGLESTEP		21
>  #define TIF_32BIT		22	/* 32bit process */
>  #define TIF_SVE			23	/* Scalable Vector Extension in use */
> +#define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
>
>  #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
>  #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index 9b1ebd7..e20b44d 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -106,6 +106,9 @@
>   */
>  static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
>
> +/* Default VL for tasks that don't set it explicitly: */
> +static int sve_default_vl = SVE_VL_MIN;
> +
>  static void sve_free(struct task_struct *task)
>  {
>  	kfree(task->thread.sve_state);
> @@ -380,15 +383,20 @@ void fpsimd_flush_thread(void)
>  		 * If a bug causes this to go wrong, we make some noise and
>  		 * try to fudge thread.sve_vl to a safe value here.
>  		 */
> -		vl = current->thread.sve_vl;
> -
> -		if (vl == 0)
> -			vl = SVE_VL_MIN;
> +		vl = current->thread.sve_vl_onexec ?
> +			current->thread.sve_vl_onexec : sve_default_vl;
>
>  		if (WARN_ON(!sve_vl_valid(vl)))
>  			vl = SVE_VL_MIN;
>
>  		current->thread.sve_vl = vl;
> +
> +		/*
> +		 * If the task is not set to inherit, ensure that the vector
> +		 * length will be reset by a subsequent exec:
> +		 */
> +		if (!test_thread_flag(TIF_SVE_VL_INHERIT))
> +			current->thread.sve_vl_onexec = 0;
>  	}
>
>  	set_thread_flag(TIF_FOREIGN_FPSTATE);