LoongArch: Fix return value underflow in exception path

This patch fixes an underflow issue in the return value within the
exception path, specifically at .Llt8 when the remaining length is less
than 8 bytes.

Cc: stable@vger.kernel.org
Fixes: 8941e93 ("LoongArch: Optimize memory ops (memset/memcpy/memmove)")
Reported-by: Weihao Li <liweihao@loongson.cn>
Signed-off-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

Author: heiher

arch/loongarch/lib/clear_user.S

@@ -108,6 +108,7 @@ SYM_FUNC_START(__clear_user_fast)
 	addi.d	a3, a2, -8
 	bgeu	a0, a3, .Llt8
 15:	st.d	zero, a0, 0
+	addi.d	a0, a0, 8
 
 .Llt8:
 16:	st.d	zero, a2, -8
@@ -188,7 +189,7 @@ SYM_FUNC_START(__clear_user_fast)
 	_asm_extable 13b, .L_fixup_handle_0
 	_asm_extable 14b, .L_fixup_handle_1
 	_asm_extable 15b, .L_fixup_handle_0
-	_asm_extable 16b, .L_fixup_handle_1
+	_asm_extable 16b, .L_fixup_handle_0
 	_asm_extable 17b, .L_fixup_handle_s0
 	_asm_extable 18b, .L_fixup_handle_s0
 	_asm_extable 19b, .L_fixup_handle_s0

arch/loongarch/lib/copy_user.S

@@ -136,6 +136,7 @@ SYM_FUNC_START(__copy_user_fast)
 	bgeu	a1, a4, .Llt8
 30:	ld.d	t0, a1, 0
 31:	st.d	t0, a0, 0
+	addi.d	a0, a0, 8
 
 .Llt8:
 32:	ld.d	t0, a3, -8
@@ -246,7 +247,7 @@ SYM_FUNC_START(__copy_user_fast)
 	_asm_extable 30b, .L_fixup_handle_0
 	_asm_extable 31b, .L_fixup_handle_0
 	_asm_extable 32b, .L_fixup_handle_0
-	_asm_extable 33b, .L_fixup_handle_1
+	_asm_extable 33b, .L_fixup_handle_0
 	_asm_extable 34b, .L_fixup_handle_s0
 	_asm_extable 35b, .L_fixup_handle_s0
 	_asm_extable 36b, .L_fixup_handle_s0