Re: [PATCH v2 20/28] arm64/sve: Add prctl controls for userspace vector length management

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

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

> This patch adds two arm64-specific prctls, to permit userspace to
> control its vector length:
>
>  * PR_SVE_SET_VL: set the thread's SVE vector length and vector
>    length inheritance mode.
>
>  * PR_SVE_GET_VL: get the same information.
>
> Although these calls shadow instruction set features in the SVE
> architecture, these prctls provide additional control: the vector
> length inheritance mode is Linux-specific and nothing to do with
> the architecture, and the architecture does not permit EL0 to set
> its own vector length directly.  Both can be used in portable tools
> without requiring the use of SVE instructions.
>
> Signed-off-by: Dave Martin <Dave.Martin@arm.com>

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

> ---
>  arch/arm64/include/asm/fpsimd.h    | 14 ++++++++++++
>  arch/arm64/include/asm/processor.h |  4 ++++
>  arch/arm64/kernel/fpsimd.c         | 46 ++++++++++++++++++++++++++++++++++++++
>  include/uapi/linux/prctl.h         |  4 ++++
>  kernel/sys.c                       | 12 ++++++++++
>  5 files changed, 80 insertions(+)
>
> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
> index 2723cca..d084968 100644
> --- a/arch/arm64/include/asm/fpsimd.h
> +++ b/arch/arm64/include/asm/fpsimd.h
> @@ -17,6 +17,7 @@
>  #define __ASM_FP_H
>
>  #include <asm/ptrace.h>
> +#include <asm/errno.h>
>
>  #ifndef __ASSEMBLY__
>
> @@ -99,6 +100,9 @@ extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
>  extern int sve_set_vector_length(struct task_struct *task,
>  				 unsigned long vl, unsigned long flags);
>
> +extern int sve_set_current_vl(unsigned long arg);
> +extern int sve_get_current_vl(void);
> +
>  extern void __init sve_init_vq_map(void);
>  extern void sve_update_vq_map(void);
>  extern int sve_verify_vq_map(void);
> @@ -114,6 +118,16 @@ static void __maybe_unused sve_sync_to_fpsimd(struct task_struct *task) { }
>  static void __maybe_unused sve_sync_from_fpsimd_zeropad(
>  	struct task_struct *task) { }
>
> +static int __maybe_unused sve_set_current_vl(unsigned long arg)
> +{
> +	return -EINVAL;
> +}
> +
> +static int __maybe_unused sve_get_current_vl(void)
> +{
> +	return -EINVAL;
> +}
> +
>  static void __maybe_unused sve_init_vq_map(void) { }
>  static void __maybe_unused sve_update_vq_map(void) { }
>  static int __maybe_unused sve_verify_vq_map(void) { return 0; }
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index 3faceac..df66452 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -197,4 +197,8 @@ static inline void spin_lock_prefetch(const void *ptr)
>  int cpu_enable_pan(void *__unused);
>  int cpu_enable_cache_maint_trap(void *__unused);
>
> +/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
> +#define SVE_SET_VL(arg)	sve_set_current_vl(arg)
> +#define SVE_GET_VL()	sve_get_current_vl()
> +
>  #endif /* __ASM_PROCESSOR_H */
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index 361c019..42e8331 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -27,6 +27,7 @@
>  #include <linux/kernel.h>
>  #include <linux/init.h>
>  #include <linux/percpu.h>
> +#include <linux/prctl.h>
>  #include <linux/preempt.h>
>  #include <linux/prctl.h>
>  #include <linux/ptrace.h>
> @@ -420,6 +421,51 @@ int sve_set_vector_length(struct task_struct *task,
>  	return 0;
>  }
>
> +/*
> + * Encode the current vector length and flags for return.
> + * This is only required for prctl(): ptrace has separate fields
> + */
> +static int sve_prctl_status(void)
> +{
> +	int ret = current->thread.sve_vl;
> +
> +	if (test_thread_flag(TIF_SVE_VL_INHERIT))
> +		ret |= PR_SVE_VL_INHERIT;
> +
> +	return ret;
> +}
> +
> +/* PR_SVE_SET_VL */
> +int sve_set_current_vl(unsigned long arg)
> +{
> +	unsigned long vl, flags;
> +	int ret;
> +
> +	vl = arg & PR_SVE_VL_LEN_MASK;
> +	flags = arg & ~vl;
> +
> +	if (!system_supports_sve())
> +		return -EINVAL;
> +
> +	preempt_disable();
> +	ret = sve_set_vector_length(current, vl, flags);
> +	preempt_enable();
> +
> +	if (ret)
> +		return ret;
> +
> +	return sve_prctl_status();
> +}
> +
> +/* PR_SVE_GET_VL */
> +int sve_get_current_vl(void)
> +{
> +	if (!system_supports_sve())
> +		return -EINVAL;
> +
> +	return sve_prctl_status();
> +}
> +
>  static unsigned long *sve_alloc_vq_map(void)
>  {
>  	return kzalloc(BITS_TO_LONGS(SVE_VQ_MAX) * sizeof(unsigned long),
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index 1b64901..1ef9370 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/include/uapi/linux/prctl.h
> @@ -198,7 +198,11 @@ struct prctl_mm_map {
>  # define PR_CAP_AMBIENT_CLEAR_ALL	4
>
>  /* arm64 Scalable Vector Extension controls */
> +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
> +#define PR_SVE_SET_VL			48	/* set task vector length */
>  # define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
> +#define PR_SVE_GET_VL			49	/* get task vector length */
> +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
>  # define PR_SVE_VL_LEN_MASK		0xffff
>  # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
>
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 2855ee7..f8215a6 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -110,6 +110,12 @@
>  #ifndef SET_FP_MODE
>  # define SET_FP_MODE(a,b)	(-EINVAL)
>  #endif
> +#ifndef SVE_SET_VL
> +# define SVE_SET_VL(a)		(-EINVAL)
> +#endif
> +#ifndef SVE_GET_VL
> +# define SVE_GET_VL()		(-EINVAL)
> +#endif
>
>  /*
>   * this is where the system-wide overflow UID and GID are defined, for
> @@ -2389,6 +2395,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
>  	case PR_GET_FP_MODE:
>  		error = GET_FP_MODE(me);
>  		break;
> +	case PR_SVE_SET_VL:
> +		error = SVE_SET_VL(arg2);
> +		break;
> +	case PR_SVE_GET_VL:
> +		error = SVE_GET_VL();
> +		break;
>  	default:
>  		error = -EINVAL;
>  		break;