diff options
Diffstat (limited to 'arch/arm/lib/memset.S')
| -rw-r--r-- | arch/arm/lib/memset.S | 91 |
1 files changed, 58 insertions, 33 deletions
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 94b0650ea98f..de75ae4d5ab4 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -1,21 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * 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 <linux/linkage.h> #include <asm/assembler.h> +#include <asm/unwind.h> .text .align 5 -ENTRY(memset) +ENTRY(__memset) +ENTRY(mmioset) +WEAK(memset) +UNWIND( .fnstart ) + and r1, r1, #255 @ cast to unsigned char ands r3, r0, #3 @ 1 unaligned? mov ip, r0 @ preserve r0 as return value bne 6f @ 1 @@ -25,34 +27,38 @@ ENTRY(memset) 1: orr r1, r1, r1, lsl #8 orr r1, r1, r1, lsl #16 mov r3, r1 - cmp r2, #16 +7: cmp r2, #16 blt 4f +UNWIND( .fnend ) #if ! CALGN(1)+0 /* * We need 2 extra registers for this loop - use r8 and the LR */ +UNWIND( .fnstart ) +UNWIND( .save {r8, lr} ) stmfd sp!, {r8, lr} mov r8, r1 - mov lr, r1 + mov lr, r3 2: subs r2, r2, #64 - stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time. - stmgeia ip!, {r1, r3, r8, lr} - stmgeia ip!, {r1, r3, r8, lr} - stmgeia ip!, {r1, r3, r8, lr} + stmiage ip!, {r1, r3, r8, lr} @ 64 bytes at a time. + stmiage ip!, {r1, r3, r8, lr} + stmiage ip!, {r1, r3, r8, lr} + stmiage ip!, {r1, r3, r8, lr} bgt 2b - ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go. + ldmfdeq sp!, {r8, pc} @ Now <64 bytes to go. /* * No need to correct the count; we're only testing bits from now on */ tst r2, #32 - stmneia ip!, {r1, r3, r8, lr} - stmneia ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} tst r2, #16 - stmneia ip!, {r1, r3, r8, lr} + stmiane ip!, {r1, r3, r8, lr} ldmfd sp!, {r8, lr} +UNWIND( .fnend ) #else @@ -61,13 +67,15 @@ ENTRY(memset) * whole cache lines at once. */ +UNWIND( .fnstart ) +UNWIND( .save {r4-r8, lr} ) stmfd sp!, {r4-r8, lr} mov r4, r1 - mov r5, r1 + mov r5, r3 mov r6, r1 - mov r7, r1 + mov r7, r3 mov r8, r1 - mov lr, r1 + mov lr, r3 cmp r2, #96 tstgt ip, #31 @@ -77,47 +85,64 @@ ENTRY(memset) rsb r8, r8, #32 sub r2, r2, r8 movs r8, r8, lsl #(32 - 4) - stmcsia ip!, {r4, r5, r6, r7} - stmmiia ip!, {r4, r5} + stmiacs ip!, {r4, r5, r6, r7} + stmiami ip!, {r4, r5} tst r8, #(1 << 30) mov r8, r1 strne r1, [ip], #4 3: subs r2, r2, #64 - stmgeia ip!, {r1, r3-r8, lr} - stmgeia ip!, {r1, r3-r8, lr} + stmiage ip!, {r1, r3-r8, lr} + stmiage ip!, {r1, r3-r8, lr} bgt 3b - ldmeqfd sp!, {r4-r8, pc} + ldmfdeq sp!, {r4-r8, pc} tst r2, #32 - stmneia ip!, {r1, r3-r8, lr} + stmiane ip!, {r1, r3-r8, lr} tst r2, #16 - stmneia ip!, {r4-r7} + stmiane ip!, {r4-r7} ldmfd sp!, {r4-r8, lr} +UNWIND( .fnend ) #endif +UNWIND( .fnstart ) 4: tst r2, #8 - stmneia ip!, {r1, r3} + stmiane ip!, {r1, r3} tst r2, #4 strne r1, [ip], #4 /* - * When we get here, we've got less than 4 bytes to zero. We + * When we get here, we've got less than 4 bytes to set. We * may have an unaligned pointer as well. */ 5: tst r2, #2 - strneb r1, [ip], #1 - strneb r1, [ip], #1 + strbne r1, [ip], #1 + strbne r1, [ip], #1 tst r2, #1 - strneb r1, [ip], #1 - mov pc, lr + strbne r1, [ip], #1 + ret lr 6: subs r2, r2, #4 @ 1 do we have enough blt 5b @ 1 bytes to align with? cmp r3, #2 @ 1 - strltb r1, [ip], #1 @ 1 - strleb r1, [ip], #1 @ 1 + strblt r1, [ip], #1 @ 1 + strble r1, [ip], #1 @ 1 strb r1, [ip], #1 @ 1 add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) b 1b +UNWIND( .fnend ) ENDPROC(memset) +ENDPROC(mmioset) +ENDPROC(__memset) + +ENTRY(__memset32) +UNWIND( .fnstart ) + mov r3, r1 @ copy r1 to r3 and fall into memset64 +UNWIND( .fnend ) +ENDPROC(__memset32) +ENTRY(__memset64) +UNWIND( .fnstart ) + mov ip, r0 @ preserve r0 as return value + b 7b @ jump into the middle of memset +UNWIND( .fnend ) +ENDPROC(__memset64) |