[v4,20/28] arm64/sve: Add prctl controls for userspace vector length management

Message ID 1509101470-7881-21-git-send-email-Dave.Martin@arm.com
State New
Headers show
Series
  • ARM Scalable Vector Extension (SVE)
Related show

Commit Message

Dave Martin Oct. 27, 2017, 10:51 a.m.
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 prctls resemble instruction set features in the SVE
architecture, they 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: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alex Bennée <alex.bennee@linaro.org>

---

**Dropped at v3** Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
due to non-trivial changes/fixes after v2.

Changes since v3
----------------

Requested by Catalin Marinas:

 * Replace static __maybe_unused functions with static inlines.

   (Retaining Catalin's Reviewed-by with his approval.)
---
 arch/arm64/include/asm/fpsimd.h    | 14 +++++++++++
 arch/arm64/include/asm/processor.h |  4 +++
 arch/arm64/kernel/fpsimd.c         | 50 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h         |  4 +++
 kernel/sys.c                       | 12 +++++++++
 5 files changed, 84 insertions(+)

Comments

Alex Bennée Oct. 27, 2017, 5:52 p.m. | #1
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 prctls resemble instruction set features in the SVE
> architecture, they 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: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Alex Bennée <alex.bennee@linaro.org>

FYI there is a minor conflict applying this on current master.

>
> ---
>
> **Dropped at v3** Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
> due to non-trivial changes/fixes after v2.
>
> Changes since v3
> ----------------
>
> Requested by Catalin Marinas:
>
>  * Replace static __maybe_unused functions with static inlines.
>
>    (Retaining Catalin's Reviewed-by with his approval.)
> ---
>  arch/arm64/include/asm/fpsimd.h    | 14 +++++++++++
>  arch/arm64/include/asm/processor.h |  4 +++
>  arch/arm64/kernel/fpsimd.c         | 50 ++++++++++++++++++++++++++++++++++++++
>  include/uapi/linux/prctl.h         |  4 +++
>  kernel/sys.c                       | 12 +++++++++
>  5 files changed, 84 insertions(+)
>
> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
> index d754e5a..b868412 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__
>
> @@ -98,6 +99,9 @@ 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);
> +
>  /*
>   * Probing and setup functions.
>   * Calls to these functions must be serialised with one another.
> @@ -114,6 +118,16 @@ static inline void fpsimd_release_task(struct task_struct *task) { }
>  static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
>  static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
>
> +static inline int sve_set_current_vl(unsigned long arg)
> +{
> +	return -EINVAL;
> +}
> +
> +static inline int sve_get_current_vl(void)
> +{
> +	return -EINVAL;
> +}
> +
>  static inline void sve_init_vq_map(void) { }
>  static inline void sve_update_vq_map(void) { }
>  static inline int sve_verify_vq_map(void) { return 0; }
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index c6fddb0..023cacb 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -217,5 +217,9 @@ 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 /* __ASSEMBLY__ */
>  #endif /* __ASM_PROCESSOR_H */
> diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
> index a47ce44..7465622 100644
> --- a/arch/arm64/kernel/fpsimd.c
> +++ b/arch/arm64/kernel/fpsimd.c
> @@ -28,6 +28,7 @@
>  #include <linux/irqflags.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>
> @@ -557,6 +558,55 @@ int sve_set_vector_length(struct task_struct *task,
>  }
>
>  /*
> + * Encode the current vector length and flags for return.
> + * This is only required for prctl(): ptrace has separate fields
> + *
> + * flags are as for sve_set_vector_length().
> + */
> +static int sve_prctl_status(unsigned long flags)
> +{
> +	int ret;
> +
> +	if (flags & PR_SVE_SET_VL_ONEXEC)
> +		ret = current->thread.sve_vl_onexec;
> +	else
> +		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;
> +
> +	ret = sve_set_vector_length(current, vl, flags);
> +	if (ret)
> +		return ret;
> +
> +	return sve_prctl_status(flags);
> +}
> +
> +/* PR_SVE_GET_VL */
> +int sve_get_current_vl(void)
> +{
> +	if (!system_supports_sve())
> +		return -EINVAL;
> +
> +	return sve_prctl_status(0);
> +}
> +
> +/*
>   * Bitmap for temporary storage of the per-CPU set of supported vector lengths
>   * during secondary boot.
>   */
> 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 9aebc29..c541916 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
> @@ -2385,6 +2391,12 @@ 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;


--
Alex Bennée
Dave Martin Oct. 28, 2017, 4:05 p.m. | #2
On Fri, Oct 27, 2017 at 06:52:50PM +0100, Alex Bennée wrote:
> 
> 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 prctls resemble instruction set features in the SVE
> > architecture, they 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: Catalin Marinas <catalin.marinas@arm.com>
> > Cc: Alex Bennée <alex.bennee@linaro.org>
> 
> FYI there is a minor conflict applying this on current master.

There are some trivial conflicts with one or two patches that already
went into arm64/for-next/core, so I based on that for this posting, not
torvalds/master.

There's a note in the cover letter giving the precise commit I based
on, though the branch doesn't seem to have moved yet since I posted.

Otherwise, I don't see any conflict -- can you give details?

Cheers
---Dave
Alex Bennée Oct. 30, 2017, 4:12 p.m. | #3
Dave Martin <Dave.Martin@arm.com> writes:

> On Fri, Oct 27, 2017 at 06:52:50PM +0100, Alex Bennée wrote:
>>
>> 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 prctls resemble instruction set features in the SVE
>> > architecture, they 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: Catalin Marinas <catalin.marinas@arm.com>
>> > Cc: Alex Bennée <alex.bennee@linaro.org>
>>
>> FYI there is a minor conflict applying this on current master.
>
> There are some trivial conflicts with one or two patches that already
> went into arm64/for-next/core, so I based on that for this posting, not
> torvalds/master.
>
> There's a note in the cover letter giving the precise commit I based
> on, though the branch doesn't seem to have moved yet since I posted.

Ahh probably those. It was only a few header file shuffles. I was
rushing to apply before my flight back I failed to note the change in
base commit.

>
> Otherwise, I don't see any conflict -- can you give details?

Only that #endif _ASM_ had been dropped from the header file.

>
> Cheers
> ---Dave


--
Alex Bennée
Dave Martin Oct. 30, 2017, 4:17 p.m. | #4
On Mon, Oct 30, 2017 at 04:12:13PM +0000, Alex Bennée wrote:
> 
> Dave Martin <Dave.Martin@arm.com> writes:
> 
> > On Fri, Oct 27, 2017 at 06:52:50PM +0100, Alex Bennée wrote:
> >>
> >> 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 prctls resemble instruction set features in the SVE
> >> > architecture, they 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: Catalin Marinas <catalin.marinas@arm.com>
> >> > Cc: Alex Bennée <alex.bennee@linaro.org>
> >>
> >> FYI there is a minor conflict applying this on current master.
> >
> > There are some trivial conflicts with one or two patches that already
> > went into arm64/for-next/core, so I based on that for this posting, not
> > torvalds/master.
> >
> > There's a note in the cover letter giving the precise commit I based
> > on, though the branch doesn't seem to have moved yet since I posted.
> 
> Ahh probably those. It was only a few header file shuffles. I was
> rushing to apply before my flight back I failed to note the change in
> base commit.
> 
> >
> > Otherwise, I don't see any conflict -- can you give details?
> 
> Only that #endif _ASM_ had been dropped from the header file.

The #ifndef __ASSEMBLY__ ... #endif is added by another in-flight patch,
so it depends on whether that patch (from arm64/for-next/core) is already
applied.

Cheers
---Dave

Patch

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index d754e5a..b868412 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__
 
@@ -98,6 +99,9 @@  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);
+
 /*
  * Probing and setup functions.
  * Calls to these functions must be serialised with one another.
@@ -114,6 +118,16 @@  static inline void fpsimd_release_task(struct task_struct *task) { }
 static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
 static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
 
+static inline int sve_set_current_vl(unsigned long arg)
+{
+	return -EINVAL;
+}
+
+static inline int sve_get_current_vl(void)
+{
+	return -EINVAL;
+}
+
 static inline void sve_init_vq_map(void) { }
 static inline void sve_update_vq_map(void) { }
 static inline int sve_verify_vq_map(void) { return 0; }
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index c6fddb0..023cacb 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -217,5 +217,9 @@  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 /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a47ce44..7465622 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -28,6 +28,7 @@ 
 #include <linux/irqflags.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>
@@ -557,6 +558,55 @@  int sve_set_vector_length(struct task_struct *task,
 }
 
 /*
+ * Encode the current vector length and flags for return.
+ * This is only required for prctl(): ptrace has separate fields
+ *
+ * flags are as for sve_set_vector_length().
+ */
+static int sve_prctl_status(unsigned long flags)
+{
+	int ret;
+
+	if (flags & PR_SVE_SET_VL_ONEXEC)
+		ret = current->thread.sve_vl_onexec;
+	else
+		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;
+
+	ret = sve_set_vector_length(current, vl, flags);
+	if (ret)
+		return ret;
+
+	return sve_prctl_status(flags);
+}
+
+/* PR_SVE_GET_VL */
+int sve_get_current_vl(void)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_prctl_status(0);
+}
+
+/*
  * Bitmap for temporary storage of the per-CPU set of supported vector lengths
  * during secondary boot.
  */
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 9aebc29..c541916 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
@@ -2385,6 +2391,12 @@  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;