1 files changed, 105 insertions, 25 deletions

diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S
index e7cb4ea3747d..df3846620553 100644
--- a/arch/loongarch/lib/memset.S
+++ b/arch/loongarch/lib/memset.S
@@ -3,12 +3,13 @@
  * 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>
+#include <asm/unwind_hints.h>
 
 .macro fill_to_64 r0
 	bstrins.d \r0, \r0, 15, 8
@@ -16,6 +17,8 @@
 	bstrins.d \r0, \r0, 63, 32
 .endm
 
+.section .noinstr.text, "ax"
+
 SYM_FUNC_START(memset)
 	/*
 	 * Some CPUs support hardware unaligned access
@@ -23,8 +26,13 @@ SYM_FUNC_START(memset)
 	ALTERNATIVE	"b __memset_generic", \
 			"b __memset_fast", CPU_FEATURE_UAL
 SYM_FUNC_END(memset)
+SYM_FUNC_ALIAS(__memset, memset)
 
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
+
+_ASM_NOKPROBE(memset)
+_ASM_NOKPROBE(__memset)
 
 /*
  * void *__memset_generic(void *s, int c, size_t n)
@@ -45,6 +53,7 @@ SYM_FUNC_START(__memset_generic)
 2:	move	a0, a3
 	jr	ra
 SYM_FUNC_END(__memset_generic)
+_ASM_NOKPROBE(__memset_generic)
 
 /*
  * void *__memset_fast(void *s, int c, size_t n)
@@ -54,38 +63,109 @@ SYM_FUNC_END(__memset_generic)
  * a2: n
  */
 SYM_FUNC_START(__memset_fast)
-	move	a3, a0
-	beqz	a2, 3f
-
-	ori	a4, zero, 64
-	blt	a2, a4, 2f
-
 	/* fill a1 to 64 bits */
 	fill_to_64 a1
 
-	/* set 64 bytes at a time */
-1:	st.d	a1, a0, 0
-	st.d	a1, a0, 8
-	st.d	a1, a0, 16
-	st.d	a1, a0, 24
-	st.d	a1, a0, 32
-	st.d	a1, a0, 40
-	st.d	a1, a0, 48
-	st.d	a1, a0, 56
+	sltui	t0, a2, 9
+	bnez	t0, .Lsmall
+
+	add.d	a2, a0, a2
+	st.d	a1, a0, 0
 
-	addi.d	a0, a0, 64
-	addi.d	a2, a2, -64
-	bge	a2, a4, 1b
+	/* align up address */
+	addi.d	a3, a0, 8
+	bstrins.d	a3, zero, 2, 0
 
-	beqz	a2, 3f
+	addi.d	a4, a2, -64
+	bgeu	a3, a4, .Llt64
+
+	/* set 64 bytes at a time */
+.Lloop64:
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	st.d	a1, a3, 16
+	st.d	a1, a3, 24
+	st.d	a1, a3, 32
+	st.d	a1, a3, 40
+	st.d	a1, a3, 48
+	st.d	a1, a3, 56
+	addi.d	a3, a3, 64
+	bltu	a3, a4, .Lloop64
 
 	/* set the remaining bytes */
-2:	st.b	a1, a0, 0
-	addi.d	a0, a0, 1
-	addi.d	a2, a2, -1
-	bgt	a2, zero, 2b
+.Llt64:
+	addi.d	a4, a2, -32
+	bgeu	a3, a4, .Llt32
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	st.d	a1, a3, 16
+	st.d	a1, a3, 24
+	addi.d	a3, a3, 32
+
+.Llt32:
+	addi.d	a4, a2, -16
+	bgeu	a3, a4, .Llt16
+	st.d	a1, a3, 0
+	st.d	a1, a3, 8
+	addi.d	a3, a3, 16
+
+.Llt16:
+	addi.d	a4, a2, -8
+	bgeu	a3, a4, .Llt8
+	st.d	a1, a3, 0
+
+.Llt8:
+	st.d	a1, a2, -8
 
 	/* return */
-3:	move	a0, a3
+	jr	ra
+
+	.align	4
+.Lsmall:
+	pcaddi	t0, 4
+	slli.d	a2, a2, 4
+	add.d	t0, t0, a2
+	jr	t0
+
+	.align	4
+0:	jr	ra
+
+	.align	4
+1:	st.b	a1, a0, 0
+	jr	ra
+
+	.align	4
+2:	st.h	a1, a0, 0
+	jr	ra
+
+	.align	4
+3:	st.h	a1, a0, 0
+	st.b	a1, a0, 2
+	jr	ra
+
+	.align	4
+4:	st.w	a1, a0, 0
+	jr	ra
+
+	.align	4
+5:	st.w	a1, a0, 0
+	st.b	a1, a0, 4
+	jr	ra
+
+	.align	4
+6:	st.w	a1, a0, 0
+	st.h	a1, a0, 4
+	jr	ra
+
+	.align	4
+7:	st.w	a1, a0, 0
+	st.w	a1, a0, 3
+	jr	ra
+
+	.align	4
+8:	st.d	a1, a0, 0
 	jr	ra
 SYM_FUNC_END(__memset_fast)
+_ASM_NOKPROBE(__memset_fast)
+
+STACK_FRAME_NON_STANDARD __memset_fast