125 lines
2.6 KiB
ArmAsm
125 lines
2.6 KiB
ArmAsm
/*
|
|
* internal version of memcpy(), issued by the compiler to copy blocks of
|
|
* data around. This is really memmove() - it has to be able to deal with
|
|
* possible overlaps, because that ambiguity is when the compiler gives up
|
|
* and calls a function. We have our own, internal version so that we get
|
|
* something we trust, even if the user has redefined the normal symbol.
|
|
*
|
|
* Copyright 2004-2009 Analog Devices Inc.
|
|
*
|
|
* Licensed under the Clear BSD license or the GPL-2 (or later)
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
/* void *memcpy(void *dest, const void *src, size_t n);
|
|
* R0 = To Address (dest) (leave unchanged to form result)
|
|
* R1 = From Address (src)
|
|
* R2 = count
|
|
*
|
|
* Note: Favours word alignment
|
|
*/
|
|
|
|
#ifdef CONFIG_MEMCPY_L1
|
|
.section .l1.text
|
|
#else
|
|
.text
|
|
#endif
|
|
|
|
.align 2
|
|
|
|
ENTRY(_memcpy)
|
|
CC = R2 <= 0; /* length not positive? */
|
|
IF CC JUMP .L_P1L2147483647; /* Nothing to do */
|
|
|
|
P0 = R0 ; /* dst*/
|
|
P1 = R1 ; /* src*/
|
|
P2 = R2 ; /* length */
|
|
|
|
/* check for overlapping data */
|
|
CC = R1 < R0; /* src < dst */
|
|
IF !CC JUMP .Lno_overlap;
|
|
R3 = R1 + R2;
|
|
CC = R0 < R3; /* and dst < src+len */
|
|
IF CC JUMP .Lhas_overlap;
|
|
|
|
.Lno_overlap:
|
|
/* Check for aligned data.*/
|
|
|
|
R3 = R1 | R0;
|
|
R1 = 0x3;
|
|
R3 = R3 & R1;
|
|
CC = R3; /* low bits set on either address? */
|
|
IF CC JUMP .Lnot_aligned;
|
|
|
|
/* Both addresses are word-aligned, so we can copy
|
|
at least part of the data using word copies.*/
|
|
P2 = P2 >> 2;
|
|
CC = P2 <= 2;
|
|
IF !CC JUMP .Lmore_than_seven;
|
|
/* less than eight bytes... */
|
|
P2 = R2;
|
|
LSETUP(.Lthree_start, .Lthree_end) LC0=P2;
|
|
.Lthree_start:
|
|
R3 = B[P1++] (X);
|
|
.Lthree_end:
|
|
B[P0++] = R3;
|
|
|
|
RTS;
|
|
|
|
.Lmore_than_seven:
|
|
/* There's at least eight bytes to copy. */
|
|
P2 += -1; /* because we unroll one iteration */
|
|
LSETUP(.Lword_loops, .Lword_loope) LC0=P2;
|
|
I1 = P1;
|
|
R3 = [I1++];
|
|
#if ANOMALY_05000202
|
|
.Lword_loops:
|
|
[P0++] = R3;
|
|
.Lword_loope:
|
|
R3 = [I1++];
|
|
#else
|
|
.Lword_loops:
|
|
.Lword_loope:
|
|
MNOP || [P0++] = R3 || R3 = [I1++];
|
|
#endif
|
|
[P0++] = R3;
|
|
/* Any remaining bytes to copy? */
|
|
R3 = 0x3;
|
|
R3 = R2 & R3;
|
|
CC = R3 == 0;
|
|
P1 = I1; /* in case there's something left, */
|
|
IF !CC JUMP .Lbytes_left;
|
|
RTS;
|
|
.Lbytes_left: P2 = R3;
|
|
.Lnot_aligned:
|
|
/* From here, we're copying byte-by-byte. */
|
|
LSETUP (.Lbyte_start, .Lbyte_end) LC0=P2;
|
|
.Lbyte_start:
|
|
R1 = B[P1++] (X);
|
|
.Lbyte_end:
|
|
B[P0++] = R1;
|
|
|
|
.L_P1L2147483647:
|
|
RTS;
|
|
|
|
.Lhas_overlap:
|
|
/* Need to reverse the copying, because the
|
|
* dst would clobber the src.
|
|
* Don't bother to work out alignment for
|
|
* the reverse case.
|
|
*/
|
|
P0 = P0 + P2;
|
|
P0 += -1;
|
|
P1 = P1 + P2;
|
|
P1 += -1;
|
|
LSETUP(.Lover_start, .Lover_end) LC0=P2;
|
|
.Lover_start:
|
|
R1 = B[P1--] (X);
|
|
.Lover_end:
|
|
B[P0--] = R1;
|
|
|
|
RTS;
|
|
|
|
ENDPROC(_memcpy)
|