[PATCH 3/4] arm64: copy_template.S: add loop_for_copy_128_bytes macro

[Huang Shijie]

Add the loop_for_copy_128_bytes macro, to make the code clean.
And make preparation for the next patch.

Signed-off-by: Huang Shijie <shijie at os.amperecomputing.com>
---
 arch/arm64/lib/copy_template.S | 58 ++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
index 488df234c49a..79b32569260c 100644
--- a/arch/arm64/lib/copy_template.S
+++ b/arch/arm64/lib/copy_template.S
@@ -10,6 +10,36 @@
  * files/head:/src/aarch64/
  */
 
+.macro loop_for_copy_128_bytes	extra_ops
+	/* pre-get 64 bytes data. */
+	ldp1	A_l, A_h, src, #16
+	ldp1	B_l, B_h, src, #16
+	ldp1	C_l, C_h, src, #16
+	ldp1	D_l, D_h, src, #16
+1:
+	\extra_ops
+	/*
+	* interlace the load of next 64 bytes data block with store of the last
+	* loaded 64 bytes data.
+	*/
+	stp1	A_l, A_h, dst, #16
+	ldp1	A_l, A_h, src, #16
+	stp1	B_l, B_h, dst, #16
+	ldp1	B_l, B_h, src, #16
+	stp1	C_l, C_h, dst, #16
+	ldp1	C_l, C_h, src, #16
+	stp1	D_l, D_h, dst, #16
+	ldp1	D_l, D_h, src, #16
+	subs	count, count, #64
+	b.ge	1b
+	stp1	A_l, A_h, dst, #16
+	stp1	B_l, B_h, dst, #16
+	stp1	C_l, C_h, dst, #16
+	stp1	D_l, D_h, dst, #16
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+.endm
 
 /*
  * Copy a buffer from src to dest (alignment handled by the hardware)
@@ -151,31 +181,5 @@ D_h	.req	x14
 	*/
 	.p2align	L1_CACHE_SHIFT
 .Lcpy_body_large:
-	/* pre-get 64 bytes data. */
-	ldp1	A_l, A_h, src, #16
-	ldp1	B_l, B_h, src, #16
-	ldp1	C_l, C_h, src, #16
-	ldp1	D_l, D_h, src, #16
-1:
-	/*
-	* interlace the load of next 64 bytes data block with store of the last
-	* loaded 64 bytes data.
-	*/
-	stp1	A_l, A_h, dst, #16
-	ldp1	A_l, A_h, src, #16
-	stp1	B_l, B_h, dst, #16
-	ldp1	B_l, B_h, src, #16
-	stp1	C_l, C_h, dst, #16
-	ldp1	C_l, C_h, src, #16
-	stp1	D_l, D_h, dst, #16
-	ldp1	D_l, D_h, src, #16
-	subs	count, count, #64
-	b.ge	1b
-	stp1	A_l, A_h, dst, #16
-	stp1	B_l, B_h, dst, #16
-	stp1	C_l, C_h, dst, #16
-	stp1	D_l, D_h, dst, #16
-
-	tst	count, #0x3f
-	b.ne	.Ltail63
+	loop_for_copy_128_bytes
 .Lexitfunc:
-- 
2.40.1