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 <alan.hayward@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alex Bennée <alex.bennee@linaro.org>
Cc: Okamoto Takayuki <tokamoto@jp.fujitsu.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

2 files changed, 149 insertions, 1 deletions

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index d8e0dc9f65a1..d754e5a6949c 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
@@ -88,6 +91,10 @@ extern size_t sve_state_size(struct task_struct const *task);
 
 extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
+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);
 
@@ -104,6 +111,9 @@ extern void __init sve_setup(void);
 
 static inline void sve_alloc(struct task_struct *task) { }
 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 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/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 3697d95ba0a1..e7085589f81c 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>
 
 
 /*
@@ -62,6 +63,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/prctl.h>
+
 /*
  * User structures for general purpose, floating point and debug registers.
  */
@@ -89,6 +92,141 @@ 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)
+
+#define SVE_PT_REGS_FPSIMD		0
+#define SVE_PT_REGS_SVE			SVE_PT_REGS_MASK
+
+/*
+ * Common SVE_PT_* flags:
+ * These must be kept in sync with prctl interface in <linux/ptrace.h>
+ */
+#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 */