[v4, 5/6] riscv: lib: vectorize copy_to_user/copy_from_user

[Andy Chiu]

This patch utilizes Vector to perform copy_to_user/copy_from_user. If
Vector is available and the size of copy is large enough for Vector to
perform better than scalar, then direct the kernel to do Vector copies
for userspace. Though the best programming practice for users is to
reduce the copy, this provides a faster variant when copies are
inevitable.

The optimal size for using Vector, copy_to_user_thres, is only a
heuristic for now. We can add DT parsing if people feel the need of
customizing it.

The exception fixup code of the __asm_vector_usercopy must fallback to
the scalar one because accessing user pages might fault, and must be
sleepable. Current kernel-mode Vector does not allow tasks to be
preemptible, so we must disactivate Vector and perform a scalar fallback
in such case.

The original implementation of Vector operations comes from
https://github.com/sifive/sifive-libc, which we agree to contribute to
Linux kernel.

Signed-off-by: Andy Chiu <andy.chiu at sifive.com>
---
Changelog v4:
 - new patch since v4
---
 arch/riscv/lib/Makefile          |  2 ++
 arch/riscv/lib/riscv_v_helpers.c | 38 ++++++++++++++++++++++
 arch/riscv/lib/uaccess.S         | 11 +++++++
 arch/riscv/lib/uaccess_vector.S  | 55 ++++++++++++++++++++++++++++++++
 4 files changed, 106 insertions(+)
 create mode 100644 arch/riscv/lib/riscv_v_helpers.c
 create mode 100644 arch/riscv/lib/uaccess_vector.S

diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 494f9cd1a00c..1fe8d797e0f2 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -12,3 +12,5 @@ lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
+lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o
+lib-$(CONFIG_RISCV_ISA_V)	+= uaccess_vector.o
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
new file mode 100644
index 000000000000..d763b9c69fb7
--- /dev/null
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu <andy.chiu at sifive.com>
+ */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#include <asm/vector.h>
+#include <asm/simd.h>
+
+size_t riscv_v_usercopy_thres = 768;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+	size_t remain, copied;
+
+	/* skip has_vector() check because it has been done by the asm  */
+	if (!may_use_simd())
+		goto fallback;
+
+	kernel_vector_begin();
+	remain = __asm_vector_usercopy(dst, src, n);
+	kernel_vector_end();
+
+	if (remain) {
+		copied = n - remain;
+		dst += copied;
+		src += copied;
+		goto fallback;
+	}
+
+	return remain;
+
+fallback:
+	return fallback_scalar_usercopy(dst, src, n);
+}
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 09b47ebacf2e..b43fd189b534 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -3,6 +3,8 @@
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
 
 	.macro fixup op reg addr lbl
 100:
@@ -12,6 +14,14 @@
 
 ENTRY(__asm_copy_to_user)
 ENTRY(__asm_copy_from_user)
+#ifdef CONFIG_RISCV_ISA_V
+	ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+	la	t0, riscv_v_usercopy_thres
+	REG_L	t0, (t0)
+	bltu	a2, t0, fallback_scalar_usercopy
+	tail enter_vector_usercopy
+#endif
+ENTRY(fallback_scalar_usercopy)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,6 +191,7 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	sub a0, t5, a0
 	ret
+ENDPROC(fallback_scalar_usercopy)
 ENDPROC(__asm_copy_to_user)
 ENDPROC(__asm_copy_from_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S
new file mode 100644
index 000000000000..98226f77efbd
--- /dev/null
+++ b/arch/riscv/lib/uaccess_vector.S
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+#define pDstPtr a4
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+ENTRY(__asm_vector_usercopy)
+	/* Enable access to user memory */
+	li t6, SR_SUM
+	csrs CSR_STATUS, t6
+
+	/* Save for return value */
+	mv	t5, a2
+
+	mv pDstPtr, pDst
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	fixup vle8.v vData, (pSrc), 10f
+	fixup vse8.v vData, (pDstPtr), 10f
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	add pDstPtr, pDstPtr, iVL
+	bnez iNum, loop
+
+.Lout_copy_user:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	li	a0, 0
+	ret
+
+	/* Exception fixup code */
+10:
+	/* Disable access to user memory */
+	csrc	CSR_STATUS, t6
+	mv	a0, iNum
+	ret
+ENDPROC(__asm_vector_usercopy)
-- 
2.17.1