summaryrefslogtreecommitdiff
path: root/arch/loongarch/lib/memcpy.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/loongarch/lib/memcpy.S')
-rw-r--r--arch/loongarch/lib/memcpy.S95
1 files changed, 95 insertions, 0 deletions
diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S
new file mode 100644
index 000000000000..7c07d595ee89
--- /dev/null
+++ b/arch/loongarch/lib/memcpy.S
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#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>
+
+SYM_FUNC_START(memcpy)
+ /*
+ * Some CPUs support hardware unaligned access
+ */
+ ALTERNATIVE "b __memcpy_generic", \
+ "b __memcpy_fast", CPU_FEATURE_UAL
+SYM_FUNC_END(memcpy)
+
+EXPORT_SYMBOL(memcpy)
+
+/*
+ * void *__memcpy_generic(void *dst, const void *src, size_t n)
+ *
+ * a0: dst
+ * a1: src
+ * a2: n
+ */
+SYM_FUNC_START(__memcpy_generic)
+ move a3, a0
+ beqz a2, 2f
+
+1: 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, 1b
+
+2: move a0, a3
+ jr ra
+SYM_FUNC_END(__memcpy_generic)
+
+/*
+ * void *__memcpy_fast(void *dst, const void *src, size_t n)
+ *
+ * a0: dst
+ * a1: src
+ * a2: n
+ */
+SYM_FUNC_START(__memcpy_fast)
+ move a3, a0
+ beqz a2, 3f
+
+ ori a4, zero, 64
+ blt a2, a4, 2f
+
+ /* copy 64 bytes at a time */
+1: ld.d t0, a1, 0
+ ld.d t1, a1, 8
+ ld.d t2, a1, 16
+ ld.d t3, a1, 24
+ ld.d t4, a1, 32
+ 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
+
+ /* 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
+
+ /* return */
+3: move a0, a3
+ jr ra
+SYM_FUNC_END(__memcpy_fast)