arm: Use optimized memcpy and memset from linux

Using optimized versions of memset and memcpy from linux brings a quite
noticeable speed (x2 or better) improvement for these two functions.

Here are some numbers for test done with jadecpu

                           | HEAD(1)| HEAD(1)| HEAD(2)| HEAD(2)|
                           |        | +patch |        | +patch |
---------------------------+--------+--------+--------+--------+
Reset to prompt            |  438ms |  330ms |  228ms |  120ms |
                           |        |        |        |        |
TFTP a 3MB img             | 4782ms | 3428ms | 3245ms | 2820ms |
                           |        |        |        |        |
FATLOAD USB a 3MB img*     | 8515ms | 8510ms | ------ | ------ |
                           |        |        |        |        |
BOOTM LZO img in RAM       | 3473ms | 3168ms |  592ms |  592ms |
 where CRC is              |  615ms |  615ms |   54ms |   54ms |
 uncompress                | 2460ms | 2462ms |  450ms |  451ms |
 final boot_elf            |  376ms |   68ms |   65ms |   65ms |
                           |        |        |        |        |
BOOTM LZO img in FLASH     | 3207ms | 2902ms | 1050ms | 1050ms |
 where CRC is              |  600ms |  600ms |  135ms |  135ms |
 uncompress                | 2209ms | 2211ms |  828ms |  828ms |
                           |        |        |        |        |
Copy 1.4MB from NOR to RAM |  134ms |   72ms |  120ms |   70ms |

(1) No dcache
(2) dcache enabled in board_init
*Does not work when dcache is on

Size impact:

C version:
   text    data     bss     dec     hex filename
 202862   18912  266456  488230   77326 u-boot

ASM version:
   text    data     bss     dec     hex filename
 203798   18912  266288  488998   77626 u-boot
222712  u-boot.bin

Signed-off-by: Matthias Weisser <weisserm@arcor.de>

1 files changed, 60 insertions, 0 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
new file mode 100644
index 0000000..5e4789b
--- /dev/null
+++ b/arch/arm/include/asm/assembler.h
@@ -0,0 +1,60 @@
+/*
+ *  arch/arm/include/asm/assembler.h
+ *
+ *  Copyright (C) 1996-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This file contains arm architecture specific defines
+ *  for the different processors.
+ *
+ *  Do not include any C declarations in this file - it is included by
+ *  assembler source.
+ */
+
+/*
+ * Endian independent macros for shifting bytes within registers.
+ */
+#ifndef __ARMEB__
+#define pull		lsr
+#define push		lsl
+#define get_byte_0	lsl #0
+#define get_byte_1	lsr #8
+#define get_byte_2	lsr #16
+#define get_byte_3	lsr #24
+#define put_byte_0	lsl #0
+#define put_byte_1	lsl #8
+#define put_byte_2	lsl #16
+#define put_byte_3	lsl #24
+#else
+#define pull		lsl
+#define push		lsr
+#define get_byte_0	lsr #24
+#define get_byte_1	lsr #16
+#define get_byte_2	lsr #8
+#define get_byte_3      lsl #0
+#define put_byte_0	lsl #24
+#define put_byte_1	lsl #16
+#define put_byte_2	lsl #8
+#define put_byte_3      lsl #0
+#endif
+
+/*
+ * Data preload for architectures that support it
+ */
+#if defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__) || \
+	defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || \
+	defined(__ARM_ARCH_6T2__) || defined(__ARM_ARCH_6Z__) || \
+	defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_7A__) || \
+	defined(__ARM_ARCH_7R__)
+#define PLD(code...)	code
+#else
+#define PLD(code...)
+#endif
+
+/*
+ * Cache alligned
+ */
+#define CALGN(code...) code