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>
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
new file mode 100644
index 0000000..0cdf895
--- /dev/null
+++ b/arch/arm/lib/memset.S
@@ -0,0 +1,126 @@
+/*
+ * linux/arch/arm/lib/memset.S
+ *
+ * Copyright (C) 1995-2000 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.
+ *
+ * ASM optimised string functions
+ */
+#include <asm/assembler.h>
+
+ .text
+ .align 5
+ .word 0
+
+1: subs r2, r2, #4 @ 1 do we have enough
+ blt 5f @ 1 bytes to align with?
+ cmp r3, #2 @ 1
+ strltb r1, [r0], #1 @ 1
+ strleb r1, [r0], #1 @ 1
+ strb r1, [r0], #1 @ 1
+ add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3))
+/*
+ * The pointer is now aligned and the length is adjusted. Try doing the
+ * memset again.
+ */
+
+.globl memset
+memset:
+ ands r3, r0, #3 @ 1 unaligned?
+ bne 1b @ 1
+/*
+ * we know that the pointer in r0 is aligned to a word boundary.
+ */
+ orr r1, r1, r1, lsl #8
+ orr r1, r1, r1, lsl #16
+ mov r3, r1
+ cmp r2, #16
+ blt 4f
+
+#if ! CALGN(1)+0
+
+/*
+ * We need an extra register for this loop - save the return address and
+ * use the LR
+ */
+ str lr, [sp, #-4]!
+ mov ip, r1
+ mov lr, r1
+
+2: subs r2, r2, #64
+ stmgeia r0!, {r1, r3, ip, lr} @ 64 bytes at a time.
+ stmgeia r0!, {r1, r3, ip, lr}
+ stmgeia r0!, {r1, r3, ip, lr}
+ stmgeia r0!, {r1, r3, ip, lr}
+ bgt 2b
+ ldmeqfd sp!, {pc} @ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+ tst r2, #32
+ stmneia r0!, {r1, r3, ip, lr}
+ stmneia r0!, {r1, r3, ip, lr}
+ tst r2, #16
+ stmneia r0!, {r1, r3, ip, lr}
+ ldr lr, [sp], #4
+
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+ stmfd sp!, {r4-r7, lr}
+ mov r4, r1
+ mov r5, r1
+ mov r6, r1
+ mov r7, r1
+ mov ip, r1
+ mov lr, r1
+
+ cmp r2, #96
+ tstgt r0, #31
+ ble 3f
+
+ and ip, r0, #31
+ rsb ip, ip, #32
+ sub r2, r2, ip
+ movs ip, ip, lsl #(32 - 4)
+ stmcsia r0!, {r4, r5, r6, r7}
+ stmmiia r0!, {r4, r5}
+ tst ip, #(1 << 30)
+ mov ip, r1
+ strne r1, [r0], #4
+
+3: subs r2, r2, #64
+ stmgeia r0!, {r1, r3-r7, ip, lr}
+ stmgeia r0!, {r1, r3-r7, ip, lr}
+ bgt 3b
+ ldmeqfd sp!, {r4-r7, pc}
+
+ tst r2, #32
+ stmneia r0!, {r1, r3-r7, ip, lr}
+ tst r2, #16
+ stmneia r0!, {r4-r7}
+ ldmfd sp!, {r4-r7, lr}
+
+#endif
+
+4: tst r2, #8
+ stmneia r0!, {r1, r3}
+ tst r2, #4
+ strne r1, [r0], #4
+/*
+ * When we get here, we've got less than 4 bytes to zero. We
+ * may have an unaligned pointer as well.
+ */
+5: tst r2, #2
+ strneb r1, [r0], #1
+ strneb r1, [r0], #1
+ tst r2, #1
+ strneb r1, [r0], #1
+ mov pc, lr