1 files changed, 82 insertions, 56 deletions

diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S
index 6ffdb46da78f..82dae062fec8 100644
--- a/arch/loongarch/lib/memmove.S
+++ b/arch/loongarch/lib/memmove.S
@@ -3,42 +3,36 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 
+#include <linux/export.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/cpu.h>
-#include <asm/export.h>
 #include <asm/regdef.h>
 
+.section .noinstr.text, "ax"
+
 SYM_FUNC_START(memmove)
-	blt	a0, a1, 1f	/* dst < src, memcpy */
-	blt	a1, a0, 3f	/* src < dst, rmemcpy */
-	jr	ra		/* dst == src, return */
-
-	/* if (src - dst) < 64, copy 1 byte at a time */
-1:	ori	a3, zero, 64
-	sub.d	t0, a1, a0
-	blt	t0, a3, 2f
-	b	memcpy
-2:	b	__memcpy_generic
-
-	/* if (dst - src) < 64, copy 1 byte at a time */
-3:	ori	a3, zero, 64
-	sub.d	t0, a0, a1
-	blt	t0, a3, 4f
-	b	rmemcpy
-4:	b	__rmemcpy_generic
+	blt	a0, a1, __memcpy	/* dst < src, memcpy */
+	blt	a1, a0, __rmemcpy	/* src < dst, rmemcpy */
+	jr	ra			/* dst == src, return */
 SYM_FUNC_END(memmove)
+SYM_FUNC_ALIAS(__memmove, memmove)
 
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL(__memmove)
+
+_ASM_NOKPROBE(memmove)
+_ASM_NOKPROBE(__memmove)
 
-SYM_FUNC_START(rmemcpy)
+SYM_FUNC_START(__rmemcpy)
 	/*
 	 * Some CPUs support hardware unaligned access
 	 */
 	ALTERNATIVE	"b __rmemcpy_generic", \
 			"b __rmemcpy_fast", CPU_FEATURE_UAL
-SYM_FUNC_END(rmemcpy)
+SYM_FUNC_END(__rmemcpy)
+_ASM_NOKPROBE(__rmemcpy)
 
 /*
  * void *__rmemcpy_generic(void *dst, const void *src, size_t n)
@@ -64,6 +58,7 @@ SYM_FUNC_START(__rmemcpy_generic)
 2:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__rmemcpy_generic)
+_ASM_NOKPROBE(__rmemcpy_generic)
 
 /*
  * void *__rmemcpy_fast(void *dst, const void *src, size_t n)
@@ -73,49 +68,80 @@ SYM_FUNC_END(__rmemcpy_generic)
  * a2: n
  */
 SYM_FUNC_START(__rmemcpy_fast)
-	move	a3, a0
-	beqz	a2, 3f
+	sltui	t0, a2, 9
+	bnez	t0, __memcpy_small
 
-	add.d	a0, a0, a2
-	add.d	a1, a1, a2
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+	ld.d	a6, a1, 0
+	ld.d	a7, a3, -8
 
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
+	/* align up destination address */
+	andi	t1, a2, 7
+	sub.d	a3, a3, t1
+	sub.d	a5, a2, t1
+
+	addi.d	a4, a1, 64
+	bgeu	a4, a3, .Llt64
 
 	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, -8
-	ld.d	t1, a1, -16
-	ld.d	t2, a1, -24
-	ld.d	t3, a1, -32
-	ld.d	t4, a1, -40
-	ld.d	t5, a1, -48
-	ld.d	t6, a1, -56
-	ld.d	t7, a1, -64
-	st.d	t0, a0, -8
-	st.d	t1, a0, -16
-	st.d	t2, a0, -24
-	st.d	t3, a0, -32
-	st.d	t4, a0, -40
-	st.d	t5, a0, -48
-	st.d	t6, a0, -56
-	st.d	t7, a0, -64
-
-	addi.d	a0, a0, -64
-	addi.d	a1, a1, -64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
-
-	beqz	a2, 3f
+.Lloop64:
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	ld.d	t4, a3, -40
+	ld.d	t5, a3, -48
+	ld.d	t6, a3, -56
+	ld.d	t7, a3, -64
+	addi.d	a3, a3, -64
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	st.d	t4, a5, -40
+	st.d	t5, a5, -48
+	st.d	t6, a5, -56
+	st.d	t7, a5, -64
+	addi.d	a5, a5, -64
+	bltu	a4, a3, .Lloop64
 
 	/* copy the remaining bytes */
-2:	ld.b	t0, a1, -1
-	st.b	t0, a0, -1
-	addi.d	a0, a0, -1
-	addi.d	a1, a1, -1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 2b
+.Llt64:
+	addi.d	a4, a1, 32
+	bgeu	a4, a3, .Llt32
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	ld.d	t2, a3, -24
+	ld.d	t3, a3, -32
+	addi.d	a3, a3, -32
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	st.d	t2, a5, -24
+	st.d	t3, a5, -32
+	addi.d	a5, a5, -32
+
+.Llt32:
+	addi.d	a4, a1, 16
+	bgeu	a4, a3, .Llt16
+	ld.d	t0, a3, -8
+	ld.d	t1, a3, -16
+	addi.d	a3, a3, -16
+	st.d	t0, a5, -8
+	st.d	t1, a5, -16
+	addi.d	a5, a5, -16
+
+.Llt16:
+	addi.d	a4, a1, 8
+	bgeu	a4, a3, .Llt8
+	ld.d	t0, a3, -8
+	st.d	t0, a5, -8
+
+.Llt8:
+	st.d	a6, a0, 0
+	st.d	a7, a2, -8
 
 	/* return */
-3:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__rmemcpy_fast)
+_ASM_NOKPROBE(__rmemcpy_fast)