1 files changed, 121 insertions, 26 deletions

diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S
index 3b7e1dec7109..39ce6621c704 100644
--- a/arch/loongarch/lib/memcpy.S
+++ b/arch/loongarch/lib/memcpy.S
@@ -44,6 +44,66 @@ SYM_FUNC_START(__memcpy_generic)
 SYM_FUNC_END(__memcpy_generic)
 _ASM_NOKPROBE(__memcpy_generic)
 
+	.align	5
+SYM_FUNC_START_NOALIGN(__memcpy_small)
+	pcaddi	t0, 8
+	slli.d	a2, a2, 5
+	add.d	t0, t0, a2
+	jr	t0
+
+	.align	5
+0:	jr	ra
+
+	.align	5
+1:	ld.b	t0, a1, 0
+	st.b	t0, a0, 0
+	jr	ra
+
+	.align	5
+2:	ld.h	t0, a1, 0
+	st.h	t0, a0, 0
+	jr	ra
+
+	.align	5
+3:	ld.h	t0, a1, 0
+	ld.b	t1, a1, 2
+	st.h	t0, a0, 0
+	st.b	t1, a0, 2
+	jr	ra
+
+	.align	5
+4:	ld.w	t0, a1, 0
+	st.w	t0, a0, 0
+	jr	ra
+
+	.align	5
+5:	ld.w	t0, a1, 0
+	ld.b	t1, a1, 4
+	st.w	t0, a0, 0
+	st.b	t1, a0, 4
+	jr	ra
+
+	.align	5
+6:	ld.w	t0, a1, 0
+	ld.h	t1, a1, 4
+	st.w	t0, a0, 0
+	st.h	t1, a0, 4
+	jr	ra
+
+	.align	5
+7:	ld.w	t0, a1, 0
+	ld.w	t1, a1, 3
+	st.w	t0, a0, 0
+	st.w	t1, a0, 3
+	jr	ra
+
+	.align	5
+8:	ld.d	t0, a1, 0
+	st.d	t0, a0, 0
+	jr	ra
+SYM_FUNC_END(__memcpy_small)
+_ASM_NOKPROBE(__memcpy_small)
+
 /*
  * void *__memcpy_fast(void *dst, const void *src, size_t n)
  *
@@ -52,14 +112,27 @@ _ASM_NOKPROBE(__memcpy_generic)
  * a2: n
  */
 SYM_FUNC_START(__memcpy_fast)
-	move	a3, a0
-	beqz	a2, 3f
+	sltui	t0, a2, 9
+	bnez	t0, __memcpy_small
+
+	add.d	a3, a1, a2
+	add.d	a2, a0, a2
+	ld.d	a6, a1, 0
+	ld.d	a7, a3, -8
+
+	/* align up destination address */
+	andi	t1, a0, 7
+	sub.d	t0, zero, t1
+	addi.d	t0, t0, 8
+	add.d	a1, a1, t0
+	add.d	a5, a0, t0
 
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
+	addi.d	a4, a3, -64
+	bgeu	a1, a4, .Llt64
 
 	/* copy 64 bytes at a time */
-1:	ld.d	t0, a1, 0
+.Lloop64:
+	ld.d	t0, a1, 0
 	ld.d	t1, a1, 8
 	ld.d	t2, a1, 16
 	ld.d	t3, a1, 24
@@ -67,32 +140,54 @@ SYM_FUNC_START(__memcpy_fast)
 	ld.d	t5, a1, 40
 	ld.d	t6, a1, 48
 	ld.d	t7, a1, 56
-	st.d	t0, a0, 0
-	st.d	t1, a0, 8
-	st.d	t2, a0, 16
-	st.d	t3, a0, 24
-	st.d	t4, a0, 32
-	st.d	t5, a0, 40
-	st.d	t6, a0, 48
-	st.d	t7, a0, 56
-
-	addi.d	a0, a0, 64
 	addi.d	a1, a1, 64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
-
-	beqz	a2, 3f
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	st.d	t2, a5, 16
+	st.d	t3, a5, 24
+	st.d	t4, a5, 32
+	st.d	t5, a5, 40
+	st.d	t6, a5, 48
+	st.d	t7, a5, 56
+	addi.d	a5, a5, 64
+	bltu	a1, a4, .Lloop64
 
 	/* copy the remaining bytes */
-2:	ld.b	t0, a1, 0
-	st.b	t0, a0, 0
-	addi.d	a0, a0, 1
-	addi.d	a1, a1, 1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 2b
+.Llt64:
+	addi.d	a4, a3, -32
+	bgeu	a1, a4, .Llt32
+	ld.d	t0, a1, 0
+	ld.d	t1, a1, 8
+	ld.d	t2, a1, 16
+	ld.d	t3, a1, 24
+	addi.d	a1, a1, 32
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	st.d	t2, a5, 16
+	st.d	t3, a5, 24
+	addi.d	a5, a5, 32
+
+.Llt32:
+	addi.d	a4, a3, -16
+	bgeu	a1, a4, .Llt16
+	ld.d	t0, a1, 0
+	ld.d	t1, a1, 8
+	addi.d	a1, a1, 16
+	st.d	t0, a5, 0
+	st.d	t1, a5, 8
+	addi.d	a5, a5, 16
+
+.Llt16:
+	addi.d	a4, a3, -8
+	bgeu	a1, a4, .Llt8
+	ld.d	t0, a1, 0
+	st.d	t0, a5, 0
+
+.Llt8:
+	st.d	a6, a0, 0
+	st.d	a7, a2, -8
 
 	/* return */
-3:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__memcpy_fast)
 _ASM_NOKPROBE(__memcpy_fast)