| /* |
| * linux/arch/arm/lib/memzero.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. |
| */ |
| #include <linux/linkage.h> |
| #include <asm/assembler.h> |
| |
| .text |
| .align 5 |
| .word 0 |
| /* |
| * Align the pointer in r0. r3 contains the number of bytes that we are |
| * mis-aligned by, and r1 is the number of bytes. If r1 < 4, then we |
| * don't bother; we use byte stores instead. |
| */ |
| 1: subs r1, r1, #4 @ 1 do we have enough |
| blt 5f @ 1 bytes to align with? |
| cmp r3, #2 @ 1 |
| strltb r2, [r0], #1 @ 1 |
| strleb r2, [r0], #1 @ 1 |
| strb r2, [r0], #1 @ 1 |
| add r1, r1, r3 @ 1 (r1 = r1 - (4 - r3)) |
| /* |
| * The pointer is now aligned and the length is adjusted. Try doing the |
| * memzero again. |
| */ |
| |
| ENTRY(__memzero) |
| mov r2, #0 @ 1 |
| ands r3, r0, #3 @ 1 unaligned? |
| bne 1b @ 1 |
| /* |
| * r3 = 0, and we know that the pointer in r0 is aligned to a word boundary. |
| */ |
| cmp r1, #16 @ 1 we can skip this chunk if we |
| blt 4f @ 1 have < 16 bytes |
| |
| #if ! CALGN(1)+0 |
| |
| /* |
| * We need an extra register for this loop - save the return address and |
| * use the LR |
| */ |
| str lr, [sp, #-4]! @ 1 |
| mov ip, r2 @ 1 |
| mov lr, r2 @ 1 |
| |
| 3: subs r1, r1, #64 @ 1 write 32 bytes out per loop |
| stmgeia r0!, {r2, r3, ip, lr} @ 4 |
| stmgeia r0!, {r2, r3, ip, lr} @ 4 |
| stmgeia r0!, {r2, r3, ip, lr} @ 4 |
| stmgeia r0!, {r2, r3, ip, lr} @ 4 |
| bgt 3b @ 1 |
| ldmeqfd sp!, {pc} @ 1/2 quick exit |
| /* |
| * No need to correct the count; we're only testing bits from now on |
| */ |
| tst r1, #32 @ 1 |
| stmneia r0!, {r2, r3, ip, lr} @ 4 |
| stmneia r0!, {r2, r3, ip, lr} @ 4 |
| tst r1, #16 @ 1 16 bytes or more? |
| stmneia r0!, {r2, r3, ip, lr} @ 4 |
| ldr lr, [sp], #4 @ 1 |
| |
| #else |
| |
| /* |
| * This version aligns the destination pointer in order to write |
| * whole cache lines at once. |
| */ |
| |
| stmfd sp!, {r4-r7, lr} |
| mov r4, r2 |
| mov r5, r2 |
| mov r6, r2 |
| mov r7, r2 |
| mov ip, r2 |
| mov lr, r2 |
| |
| cmp r1, #96 |
| andgts ip, r0, #31 |
| ble 3f |
| |
| rsb ip, ip, #32 |
| sub r1, r1, ip |
| movs ip, ip, lsl #(32 - 4) |
| stmcsia r0!, {r4, r5, r6, r7} |
| stmmiia r0!, {r4, r5} |
| movs ip, ip, lsl #2 |
| strcs r2, [r0], #4 |
| |
| 3: subs r1, r1, #64 |
| stmgeia r0!, {r2-r7, ip, lr} |
| stmgeia r0!, {r2-r7, ip, lr} |
| bgt 3b |
| ldmeqfd sp!, {r4-r7, pc} |
| |
| tst r1, #32 |
| stmneia r0!, {r2-r7, ip, lr} |
| tst r1, #16 |
| stmneia r0!, {r4-r7} |
| ldmfd sp!, {r4-r7, lr} |
| |
| #endif |
| |
| 4: tst r1, #8 @ 1 8 bytes or more? |
| stmneia r0!, {r2, r3} @ 2 |
| tst r1, #4 @ 1 4 bytes or more? |
| strne r2, [r0], #4 @ 1 |
| /* |
| * When we get here, we've got less than 4 bytes to zero. We |
| * may have an unaligned pointer as well. |
| */ |
| 5: tst r1, #2 @ 1 2 bytes or more? |
| strneb r2, [r0], #1 @ 1 |
| strneb r2, [r0], #1 @ 1 |
| tst r1, #1 @ 1 a byte left over |
| strneb r2, [r0], #1 @ 1 |
| mov pc, lr @ 1 |
| ENDPROC(__memzero) |