RE: [PATCH v2 19/28] arm64/sve: ptrace and ELF coredump support

Hi Dave,

I am an engineer of the postK computer from Fujitsu.

When I tried to read "max_vl" by ptrace with this patch on our local SVE 
simulator, it was read as zero.
I think the cause of this incident is that "max_vl" is set as "header->vl" 
only on warning case in sve_init_header_from_task().
"max_vl" should be set up also on normal case, like the following patch.


--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -755,6 +755,8 @@ static void sve_init_header_from_task(struct user_sve_header *header,

        if (WARN_ON(!sve_vl_valid(sve_max_vl)))
                header->max_vl = header->vl;
+       else
+               header->max_vl = sve_max_vl;

        header->size = SVE_PT_SIZE(vq, header->flags);
        header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),


Best regards,
Takayuki Okamoto

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Dave Martin
Sent: Friday, September 1, 2017 2:01 AM
To: [email protected]
Cc: Catalin Marinas <[email protected]>; Will Deacon <[email protected]>; Ard Biesheuvel <[email protected]>; Alex Bennée <[email protected]>; Szabolcs Nagy <[email protected]>; Richard Sandiford <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Alan Hayward <[email protected]>; Yao Qi <[email protected]>; Oleg Nesterov <[email protected]>; Alexander Viro <[email protected]>
Subject: [PATCH v2 19/28] arm64/sve: ptrace and ELF coredump support

This patch defines and implements a new regset NT_ARM_SVE, which
describes a thread's SVE register state.  This allows a debugger to
manipulate the SVE state, as well as being included in ELF
coredumps for post-mortem debugging.

Because the regset size and layout are dependent on the thread's
current vector length, it is not possible to define a C struct to
describe the regset contents as is done for existing regsets.
Instead, and for the same reasons, NT_ARM_SVE is based on the
freeform variable-layout approach used for the SVE signal frame.

Additionally, to reduce debug overhead when debugging threads that
might or might not have live SVE register state, NT_ARM_SVE may be
presented in one of two different formats: the old struct
user_fpsimd_state format is embedded for describing the state of a
thread with no live SVE state, whereas a new variable-layout
structure is embedded for describing live SVE state.  This avoids a
debugger needing to poll NT_PRFPREG in addition to NT_ARM_SVE, and
allows existing userspace code to handle the non-SVE case without
too much modification.

For this to work, NT_ARM_SVE is defined with a fixed-format header
of type struct user_sve_header, which the recipient can use to
figure out the content, size and layout of the reset of the regset.
Accessor macros are defined to allow the vector-length-dependent
parts of the regset to be manipulated.

Signed-off-by: Alan Hayward <[email protected]>
Signed-off-by: Dave Martin <[email protected]>
Cc: Alex Bennée <[email protected]>

---

Changes since v1
----------------

Other changes related to Alex Bennée's comments:

* Migrate to SVE_VQ_BYTES instead of magic numbers.

Requested by Alex Bennée:

* Thin out BUG_ON()s:
Redundant BUG_ON()s and ones that just check invariants are removed.
Important sanity-checks are migrated to WARN_ON()s, with some
minimal best-effort patch-up code.

Other:

* [ABI fix] Bail out with -EIO if attempting to set the
SVE regs for an unsupported VL, instead of misparsing the regset data.

* Replace some in-kernel open-coded arithmetic with ALIGN()/
DIV_ROUND_UP().
---
 arch/arm64/include/asm/fpsimd.h      |  13 +-
 arch/arm64/include/uapi/asm/ptrace.h | 135 ++++++++++++++++++
 arch/arm64/kernel/fpsimd.c           |  40 +++++-
 arch/arm64/kernel/ptrace.c           | 270 +++++++++++++++++++++++++++++++++--
 include/uapi/linux/elf.h             |   1 +
 5 files changed, 449 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 6c22624..2723cca 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -38,13 +38,16 @@ struct fpsimd_state {
 			__uint128_t vregs[32];
 			u32 fpsr;
 			u32 fpcr;
+			/*
+			 * For ptrace compatibility, pad to next 128-bit
+			 * boundary here if extending this struct.
+			 */
 		};
 	};
 	/* the id of the last cpu to have restored this state */
 	unsigned int cpu;
 };
 
-
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
 #define VFP_FPSCR_STAT_MASK	0xf800009f
@@ -89,6 +92,10 @@ extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_thread(struct task_struct *task);
 extern void fpsimd_dup_sve(struct task_struct *dst,
 			   struct task_struct const *src);
+extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void sve_sync_to_fpsimd(struct task_struct *task);
+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);
 
@@ -103,6 +110,10 @@ static void __maybe_unused sve_alloc(struct task_struct *task) { }
 static void __maybe_unused fpsimd_release_thread(struct task_struct *task) { }
 static void __maybe_unused fpsimd_dup_sve(struct task_struct *dst,
 					  struct task_struct const *src) { }
+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 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/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index d1ff83d..1915ab0 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 
 #include <asm/hwcap.h>
+#include <asm/sigcontext.h>
 
 
 /*
@@ -63,6 +64,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/prctl.h>
+
 /*
  * User structures for general purpose, floating point and debug registers.
  */
@@ -90,6 +93,138 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
+/* SVE/FP/SIMD state (NT_ARM_SVE) */
+
+struct user_sve_header {
+	__u32 size; /* total meaningful regset content in bytes */
+	__u32 max_size; /* maxmium possible size for this thread */
+	__u16 vl; /* current vector length */
+	__u16 max_vl; /* maximum possible vector length */
+	__u16 flags;
+	__u16 __reserved;
+};
+
+/* Definitions for user_sve_header.flags: */
+#define SVE_PT_REGS_MASK		(1 << 0)
+
+/* Flags: must be kept in sync with prctl interface in <linux/ptrace.h> */
+#define SVE_PT_REGS_FPSIMD		0
+#define SVE_PT_REGS_SVE			SVE_PT_REGS_MASK
+
+#define SVE_PT_VL_INHERIT		(PR_SVE_VL_INHERIT >> 16)
+#define SVE_PT_VL_ONEXEC		(PR_SVE_SET_VL_ONEXEC >> 16)
+
+
+/*
+ * The remainder of the SVE state follows struct user_sve_header.  The
+ * total size of the SVE state (including header) depends on the
+ * metadata in the header:  SVE_PT_SIZE(vq, flags) gives the total size
+ * of the state in bytes, including the header.
+ *
+ * Refer to <asm/sigcontext.h> for details of how to pass the correct
+ * "vq" argument to these macros.
+ */
+
+/* Offset from the start of struct user_sve_header to the register data */
+#define SVE_PT_REGS_OFFSET					\
+	((sizeof(struct sve_context) + (SVE_VQ_BYTES - 1))	\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+
+/*
+ * The register data content and layout depends on the value of the
+ * flags field.
+ */
+
+/*
+ * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD case:
+ *
+ * The payload starts at offset SVE_PT_FPSIMD_OFFSET, and is of type
+ * struct user_fpsimd_state.  Additional data might be appended in the
+ * future: use SVE_PT_FPSIMD_SIZE(vq, flags) to compute the total size.
+ * SVE_PT_FPSIMD_SIZE(vq, flags) will never be less than
+ * sizeof(struct user_fpsimd_state).
+ */
+
+#define SVE_PT_FPSIMD_OFFSET		SVE_PT_REGS_OFFSET
+
+#define SVE_PT_FPSIMD_SIZE(vq, flags)	(sizeof(struct user_fpsimd_state))
+
+/*
+ * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE case:
+ *
+ * The payload starts at offset SVE_PT_SVE_OFFSET, and is of size
+ * SVE_PT_SVE_SIZE(vq, flags).
+ *
+ * Additional macros describe the contents and layout of the payload.
+ * For each, SVE_PT_SVE_x_OFFSET(args) is the start offset relative to
+ * the start of struct user_sve_header, and SVE_PT_SVE_x_SIZE(args) is
+ * the size in bytes:
+ *
+ *	x	type				description
+ *	-	----				-----------
+ *	ZREGS		\
+ *	ZREG		|
+ *	PREGS		| refer to <asm/sigcontext.h>
+ *	PREG		|
+ *	FFR		/
+ *
+ *	FPSR	uint32_t			FPSR
+ *	FPCR	uint32_t			FPCR
+ *
+ * Additional data might be appended in the future.
+ */
+
+#define SVE_PT_SVE_ZREG_SIZE(vq)	SVE_SIG_ZREG_SIZE(vq)
+#define SVE_PT_SVE_PREG_SIZE(vq)	SVE_SIG_PREG_SIZE(vq)
+#define SVE_PT_SVE_FFR_SIZE(vq)		SVE_SIG_FFR_SIZE(vq)
+#define SVE_PT_SVE_FPSR_SIZE		sizeof(__u32)
+#define SVE_PT_SVE_FPCR_SIZE		sizeof(__u32)
+
+#define __SVE_SIG_TO_PT(offset) \
+	((offset) - SVE_SIG_REGS_OFFSET + SVE_PT_REGS_OFFSET)
+
+#define SVE_PT_SVE_OFFSET		SVE_PT_REGS_OFFSET
+
+#define SVE_PT_SVE_ZREGS_OFFSET \
+	__SVE_SIG_TO_PT(SVE_SIG_ZREGS_OFFSET)
+#define SVE_PT_SVE_ZREG_OFFSET(vq, n) \
+	__SVE_SIG_TO_PT(SVE_SIG_ZREG_OFFSET(vq, n))
+#define SVE_PT_SVE_ZREGS_SIZE(vq) \
+	(SVE_PT_SVE_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_PT_SVE_ZREGS_OFFSET)
+
+#define SVE_PT_SVE_PREGS_OFFSET(vq) \
+	__SVE_SIG_TO_PT(SVE_SIG_PREGS_OFFSET(vq))
+#define SVE_PT_SVE_PREG_OFFSET(vq, n) \
+	__SVE_SIG_TO_PT(SVE_SIG_PREG_OFFSET(vq, n))
+#define SVE_PT_SVE_PREGS_SIZE(vq) \
+	(SVE_PT_SVE_PREG_OFFSET(vq, SVE_NUM_PREGS) - \
+		SVE_PT_SVE_PREGS_OFFSET(vq))
+
+#define SVE_PT_SVE_FFR_OFFSET(vq) \
+	__SVE_SIG_TO_PT(SVE_SIG_FFR_OFFSET(vq))
+
+#define SVE_PT_SVE_FPSR_OFFSET(vq)				\
+	((SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq) +	\
+			(SVE_VQ_BYTES - 1))			\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+#define SVE_PT_SVE_FPCR_OFFSET(vq) \
+	(SVE_PT_SVE_FPSR_OFFSET(vq) + SVE_PT_SVE_FPSR_SIZE)
+
+/*
+ * Any future extension appended after FPCR must be aligned to the next
+ * 128-bit boundary.
+ */
+
+#define SVE_PT_SVE_SIZE(vq, flags)					\
+	((SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE		\
+			- SVE_PT_SVE_OFFSET + (SVE_VQ_BYTES - 1))	\
+		/ SVE_VQ_BYTES * SVE_VQ_BYTES)
+
+#define SVE_PT_SIZE(vq, flags)						\
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
+		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index fff9fcf..361c019 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -303,6 +303,37 @@ void sve_alloc(struct task_struct *task)
 	BUG_ON(!task->thread.sve_state);
 }
 
+void fpsimd_sync_to_sve(struct task_struct *task)
+{
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		fpsimd_to_sve(task);
+}
+
+void sve_sync_to_fpsimd(struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SVE))
+		sve_to_fpsimd(task);
+}
+
+void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
+{
+	unsigned int vq;
+	void *sst = task->thread.sve_state;
+	struct fpsimd_state const *fst = &task->thread.fpsimd_state;
+	unsigned int i;
+
+	if (!test_tsk_thread_flag(task, TIF_SVE))
+		return;
+
+	vq = sve_vq_from_vl(task->thread.sve_vl);
+
+	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
+
+	for (i = 0; i < 32; ++i)
+		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
+		       sizeof(fst->vregs[i]));
+}
+
 /*
  * Handle SVE state across fork():
  *
@@ -459,10 +490,17 @@ static void __init sve_efi_setup(void)
 	 * This is evidence of a crippled system and we are returning void,
 	 * so no attempt is made to handle this situation here.
 	 */
-	BUG_ON(!sve_vl_valid(sve_max_vl));
+	if (!sve_vl_valid(sve_max_vl))
+		goto fail;
+
 	efi_sve_state = __alloc_percpu(
 		SVE_SIG_REGS_SIZE(sve_vq_from_vl(sve_max_vl)), SVE_VQ_BYTES);
 	if (!efi_sve_state)
+		goto fail;
+
+	return;
+
+fail:
 		panic("Cannot allocate percpu memory for EFI SVE save/restore");
 }
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 9cbb612..5ef4735b 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
@@ -40,6 +41,7 @@
 #include <linux/elf.h>
 
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/stacktrace.h>
@@ -618,33 +620,66 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
-static int fpr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+static int __fpr_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf, unsigned int start_pos)
 {
 	struct user_fpsimd_state *uregs;
+
+	sve_sync_to_fpsimd(target);
+
 	uregs = &target->thread.fpsimd_state.user_fpsimd;
 
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs,
+				   start_pos, start_pos + sizeof(*uregs));
+}
+
+static int fpr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
 	if (target == current)
 		fpsimd_preserve_current_state();
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1);
+	return __fpr_get(target, regset, pos, count, kbuf, ubuf, 0);
 }
 
-static int fpr_set(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
+static int __fpr_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned int start_pos)
 {
 	int ret;
 	struct user_fpsimd_state newstate =
 		target->thread.fpsimd_state.user_fpsimd;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
+	sve_sync_to_fpsimd(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate,
+				 start_pos, start_pos + sizeof(newstate));
 	if (ret)
 		return ret;
 
 	target->thread.fpsimd_state.user_fpsimd = newstate;
+
+	return ret;
+}
+
+static int fpr_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
+	if (ret)
+		return ret;
+
+	sve_sync_from_fpsimd_zeropad(target);
 	fpsimd_flush_task_state(target);
+
 	return ret;
 }
 
@@ -702,6 +737,210 @@ static int system_call_set(struct task_struct *target,
 	return ret;
 }
 
+#ifdef CONFIG_ARM64_SVE
+
+static void sve_init_header_from_task(struct user_sve_header *header,
+				      struct task_struct *target)
+{
+	unsigned int vq;
+
+	memset(header, 0, sizeof(*header));
+
+	header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
+		SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
+	if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+		header->flags |= SVE_PT_VL_INHERIT;
+
+	header->vl = target->thread.sve_vl;
+	vq = sve_vq_from_vl(header->vl);
+
+	if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+		header->max_vl = header->vl;
+
+	header->size = SVE_PT_SIZE(vq, header->flags);
+	header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
+				      SVE_PT_REGS_SVE);
+}
+
+static unsigned int sve_size_from_header(struct user_sve_header const *header)
+{
+	return ALIGN(header->size, SVE_VQ_BYTES);
+}
+
+static unsigned int sve_get_size(struct task_struct *target,
+				 const struct user_regset *regset)
+{
+	struct user_sve_header header;
+
+	if (!system_supports_sve())
+		return 0;
+
+	sve_init_header_from_task(&header, target);
+	return sve_size_from_header(&header);
+}
+
+static int sve_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	int ret;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	sve_init_header_from_task(&header, target);
+	vq = sve_vq_from_vl(header.vl);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &header,
+				  0, sizeof(header));
+	if (ret)
+		return ret;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+		return __fpr_get(target, regset, pos, count, kbuf, ubuf,
+				 SVE_PT_FPSIMD_OFFSET);
+
+	/* Otherwise: full SVE case */
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  target->thread.sve_state,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+				       start, end);
+	if (ret)
+		return ret;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpsimd_state.fpsr,
+				  start, end);
+	if (ret)
+		return ret;
+
+	start = end;
+	end = sve_size_from_header(&header);
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					start, end);
+}
+
+static int sve_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct user_sve_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	/* Header */
+	if (count < sizeof(header))
+		return -EINVAL;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+				 0, sizeof(header));
+	if (ret)
+		goto out;
+
+	/*
+	 * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by
+	 * sve_set_vector_length(), which will also validate them for us:
+	 */
+	ret = sve_set_vector_length(target, header.vl,
+				    header.flags & ~SVE_PT_REGS_MASK);
+	if (ret)
+		goto out;
+
+	/* Actual VL set may be less than the user asked for: */
+	vq = sve_vq_from_vl(target->thread.sve_vl);
+
+	/* Registers: FPSIMD-only case */
+
+	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
+	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) {
+		sve_sync_to_fpsimd(target);
+
+		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
+				SVE_PT_FPSIMD_OFFSET);
+		clear_tsk_thread_flag(target, TIF_SVE);
+		goto out;
+	}
+
+	/* Otherwise: full SVE case */
+
+	/*
+	 * If setting a different VL from the requested VL and there is
+	 * register data, the data layout will be wrong: don't even
+	 * try to set the registers in this case.
+	 */
+	if (count && vq != sve_vq_from_vl(header.vl)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	sve_alloc(target);
+	fpsimd_sync_to_sve(target);
+	set_tsk_thread_flag(target, TIF_SVE);
+
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+	start = SVE_PT_SVE_OFFSET;
+	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.sve_state,
+				 start, end);
+	if (ret)
+		goto out;
+
+	start = end;
+	end = SVE_PT_SVE_FPSR_OFFSET(vq);
+	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 * Copy fpsr, and fpcr which must follow contiguously in
+	 * struct fpsimd_state:
+	 */
+	start = end;
+	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.fpsimd_state.fpsr,
+				 start, end);
+
+out:
+	fpsimd_flush_task_state(target);
+	return ret;
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -711,6 +950,9 @@ enum aarch64_regset {
 	REGSET_HW_WATCH,
 #endif
 	REGSET_SYSTEM_CALL,
+#ifdef CONFIG_ARM64_SVE
+	REGSET_SVE,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -768,6 +1010,18 @@ static const struct user_regset aarch64_regsets[] = {
 		.get = system_call_get,
 		.set = system_call_set,
 	},
+#ifdef CONFIG_ARM64_SVE
+	[REGSET_SVE] = { /* Scalable Vector Extension */
+		.core_note_type = NT_ARM_SVE,
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+				  SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.get = sve_get,
+		.set = sve_set,
+		.get_size = sve_get_size,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index b5280db..735b8f4 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -416,6 +416,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
 #define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
 #define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
+#define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_METAG_CBUF	0x500		/* Metag catch buffer registers */
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */
-- 
2.1.4