[v5, 6/6] riscv: lib: add vectorized mem* routines

[Andy Chiu]

Provide vectorized memcpy/memset/memmove to accelerate common memory
operations. Also, group them into V_OPT_TEMPLATE3 macro because their
setup/tear-down and fallback logics are the same.

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          |  3 ++
 arch/riscv/lib/memcpy_vector.S   | 29 +++++++++++++++++++
 arch/riscv/lib/memmove_vector.S  | 49 ++++++++++++++++++++++++++++++++
 arch/riscv/lib/memset_vector.S   | 33 +++++++++++++++++++++
 arch/riscv/lib/riscv_v_helpers.c | 21 ++++++++++++++
 5 files changed, 135 insertions(+)
 create mode 100644 arch/riscv/lib/memcpy_vector.S
 create mode 100644 arch/riscv/lib/memmove_vector.S
 create mode 100644 arch/riscv/lib/memset_vector.S

diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 1fe8d797e0f2..3111863afd2e 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -14,3 +14,6 @@ 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
+lib-$(CONFIG_RISCV_ISA_V)	+= memset_vector.o
+lib-$(CONFIG_RISCV_ISA_V)	+= memcpy_vector.o
+lib-$(CONFIG_RISCV_ISA_V)	+= memmove_vector.o
diff --git a/arch/riscv/lib/memcpy_vector.S b/arch/riscv/lib/memcpy_vector.S
new file mode 100644
index 000000000000..4176b6e0a53c
--- /dev/null
+++ b/arch/riscv/lib/memcpy_vector.S
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+#define pDstPtr a4
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+
+/* void *memcpy(void *, const void *, size_t) */
+SYM_FUNC_START(__asm_memcpy_vector)
+	mv pDstPtr, pDst
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	vle8.v vData, (pSrc)
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	vse8.v vData, (pDstPtr)
+	add pDstPtr, pDstPtr, iVL
+	bnez iNum, loop
+	ret
+SYM_FUNC_END(__asm_memcpy_vector)
diff --git a/arch/riscv/lib/memmove_vector.S b/arch/riscv/lib/memmove_vector.S
new file mode 100644
index 000000000000..4cea9d244dc9
--- /dev/null
+++ b/arch/riscv/lib/memmove_vector.S
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+#define pDstPtr a4
+#define pSrcBackwardPtr a5
+#define pDstBackwardPtr a6
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+SYM_FUNC_START(__asm_memmove_vector)
+
+    mv pDstPtr, pDst
+
+    bgeu pSrc, pDst, forward_copy_loop
+    add pSrcBackwardPtr, pSrc, iNum
+    add pDstBackwardPtr, pDst, iNum
+    bltu pDst, pSrcBackwardPtr, backward_copy_loop
+
+forward_copy_loop:
+    vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+
+    vle8.v vData, (pSrc)
+    sub iNum, iNum, iVL
+    add pSrc, pSrc, iVL
+    vse8.v vData, (pDstPtr)
+    add pDstPtr, pDstPtr, iVL
+
+    bnez iNum, forward_copy_loop
+    ret
+
+backward_copy_loop:
+    vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+
+    sub pSrcBackwardPtr, pSrcBackwardPtr, iVL
+    vle8.v vData, (pSrcBackwardPtr)
+    sub iNum, iNum, iVL
+    sub pDstBackwardPtr, pDstBackwardPtr, iVL
+    vse8.v vData, (pDstBackwardPtr)
+    bnez iNum, backward_copy_loop
+    ret
+
+SYM_FUNC_END(__asm_memmove_vector)
diff --git a/arch/riscv/lib/memset_vector.S b/arch/riscv/lib/memset_vector.S
new file mode 100644
index 000000000000..4611feed72ac
--- /dev/null
+++ b/arch/riscv/lib/memset_vector.S
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#define pDst a0
+#define iValue a1
+#define iNum a2
+
+#define iVL a3
+#define iTemp a4
+#define pDstPtr a5
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+/* void *memset(void *, int, size_t) */
+SYM_FUNC_START(__asm_memset_vector)
+
+    mv pDstPtr, pDst
+
+    vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+    vmv.v.x vData, iValue
+
+loop:
+    vse8.v vData, (pDstPtr)
+    sub iNum, iNum, iVL
+    add pDstPtr, pDstPtr, iVL
+    vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+    bnez iNum, loop
+
+    ret
+
+SYM_FUNC_END(__asm_memset_vector)
diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c
index d763b9c69fb7..12e8c5deb013 100644
--- a/arch/riscv/lib/riscv_v_helpers.c
+++ b/arch/riscv/lib/riscv_v_helpers.c
@@ -36,3 +36,24 @@ asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
 fallback:
 	return fallback_scalar_usercopy(dst, src, n);
 }
+
+#define V_OPT_TEMPLATE3(prefix, type_r, type_0, type_1)				\
+extern type_r __asm_##prefix##_vector(type_0, type_1, size_t n);		\
+type_r prefix(type_0 a0, type_1 a1, size_t n)					\
+{										\
+	type_r ret;								\
+	if (has_vector() && may_use_simd() && n > riscv_v_##prefix##_thres) {	\
+		kernel_vector_begin();						\
+		ret = __asm_##prefix##_vector(a0, a1, n);			\
+		kernel_vector_end();						\
+		return ret;							\
+	}									\
+	return __##prefix(a0, a1, n);						\
+}
+
+static size_t riscv_v_memset_thres = 1280;
+V_OPT_TEMPLATE3(memset, void *, void*, int)
+static size_t riscv_v_memcpy_thres = 768;
+V_OPT_TEMPLATE3(memcpy, void *, void*, const void *)
+static size_t riscv_v_memmove_thres = 512;
+V_OPT_TEMPLATE3(memmove, void *, void*, const void *)
-- 
2.17.1