[PATCH v3 2/3] riscv: optimized memmove

[Matteo Croce <mcroce@linux.microsoft.com>]

From: Matteo Croce <mcroce@microsoft.com>

When the destination buffer is before the source one, or when the
buffers doesn't overlap, it's safe to use memcpy() instead, which is
optimized to use a bigger data size possible.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
 arch/riscv/include/asm/string.h |  6 ++--
 arch/riscv/kernel/riscv_ksyms.c |  2 --
 arch/riscv/lib/Makefile         |  1 -
 arch/riscv/lib/memmove.S        | 64 ---------------------------------
 arch/riscv/lib/string.c         | 23 ++++++++++++
 5 files changed, 26 insertions(+), 70 deletions(-)
 delete mode 100644 arch/riscv/lib/memmove.S

diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 6b5d6fc3eab4..25d9b9078569 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -17,11 +17,11 @@ extern asmlinkage void *__memset(void *, int, size_t);
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *dest, const void *src, size_t count);
 extern void *__memcpy(void *dest, const void *src, size_t count);
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *dest, const void *src, size_t count);
+extern void *__memmove(void *dest, const void *src, size_t count);
 #endif
 
-#define __HAVE_ARCH_MEMMOVE
-extern asmlinkage void *memmove(void *, const void *, size_t);
-extern asmlinkage void *__memmove(void *, const void *, size_t);
 /* For those files which don't want to check by kasan. */
 #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 3f6d512a5b97..361565c4db7e 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -10,6 +10,4 @@
  * Assembly functions that may be used (directly or indirectly) by modules
  */
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memmove);
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 2ffe85d4baee..484f5ff7b508 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
 lib-y			+= memset.o
-lib-y			+= memmove.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
deleted file mode 100644
index 07d1d2152ba5..000000000000
--- a/arch/riscv/lib/memmove.S
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#include <linux/linkage.h>
-#include <asm/asm.h>
-
-ENTRY(__memmove)
-WEAK(memmove)
-        move    t0, a0
-        move    t1, a1
-
-        beq     a0, a1, exit_memcpy
-        beqz    a2, exit_memcpy
-        srli    t2, a2, 0x2
-
-        slt     t3, a0, a1
-        beqz    t3, do_reverse
-
-        andi    a2, a2, 0x3
-        li      t4, 1
-        beqz    t2, byte_copy
-
-word_copy:
-        lw      t3, 0(a1)
-        addi    t2, t2, -1
-        addi    a1, a1, 4
-        sw      t3, 0(a0)
-        addi    a0, a0, 4
-        bnez    t2, word_copy
-        beqz    a2, exit_memcpy
-        j       byte_copy
-
-do_reverse:
-        add     a0, a0, a2
-        add     a1, a1, a2
-        andi    a2, a2, 0x3
-        li      t4, -1
-        beqz    t2, reverse_byte_copy
-
-reverse_word_copy:
-        addi    a1, a1, -4
-        addi    t2, t2, -1
-        lw      t3, 0(a1)
-        addi    a0, a0, -4
-        sw      t3, 0(a0)
-        bnez    t2, reverse_word_copy
-        beqz    a2, exit_memcpy
-
-reverse_byte_copy:
-        addi    a0, a0, -1
-        addi    a1, a1, -1
-
-byte_copy:
-        lb      t3, 0(a1)
-        addi    a2, a2, -1
-        sb      t3, 0(a0)
-        add     a1, a1, t4
-        add     a0, a0, t4
-        bnez    a2, byte_copy
-
-exit_memcpy:
-        move a0, t0
-        move a1, t1
-        ret
-END(__memmove)
diff --git a/arch/riscv/lib/string.c b/arch/riscv/lib/string.c
index e48a79a045d8..9c7009d43c39 100644
--- a/arch/riscv/lib/string.c
+++ b/arch/riscv/lib/string.c
@@ -89,3 +89,26 @@ EXPORT_SYMBOL(__memcpy);
 
 void *memcpy(void *dest, const void *src, size_t count) __weak __alias(__memcpy);
 EXPORT_SYMBOL(memcpy);
+
+/*
+ * Simply check if the buffer overlaps an call memcpy() in case,
+ * otherwise do a simple one byte at time backward copy.
+ */
+void *__memmove(void *dest, const void *src, size_t count)
+{
+	if (dest < src || src + count <= dest)
+		return memcpy(dest, src, count);
+
+	if (dest > src) {
+		const char *s = src + count;
+		char *tmp = dest + count;
+
+		while (count--)
+			*--tmp = *--s;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(__memmove);
+
+void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove);
+EXPORT_SYMBOL(memmove);
-- 
2.31.1