1/* 2 * linux/arch/arm/lib/copy_template.s 3 * 4 * Code template for optimized memory copy functions 5 * 6 * Author: Nicolas Pitre 7 * Created: Sep 28, 2005 8 * Copyright: MontaVista Software, Inc. 9 * 10 * This program is free software; you can redistribute it and/or modify 11 * it under the terms of the GNU General Public License version 2 as 12 * published by the Free Software Foundation. 13 */ 14 15/* 16 * Theory of operation 17 * ------------------- 18 * 19 * This file provides the core code for a forward memory copy used in 20 * the implementation of memcopy(), copy_to_user() and copy_from_user(). 21 * 22 * The including file must define the following accessor macros 23 * according to the need of the given function: 24 * 25 * ldr1w ptr reg abort 26 * 27 * This loads one word from 'ptr', stores it in 'reg' and increments 28 * 'ptr' to the next word. The 'abort' argument is used for fixup tables. 29 * 30 * ldr4w ptr reg1 reg2 reg3 reg4 abort 31 * ldr8w ptr, reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort 32 * 33 * This loads four or eight words starting from 'ptr', stores them 34 * in provided registers and increments 'ptr' past those words. 35 * The'abort' argument is used for fixup tables. 36 * 37 * ldr1b ptr reg cond abort 38 * 39 * Similar to ldr1w, but it loads a byte and increments 'ptr' one byte. 40 * It also must apply the condition code if provided, otherwise the 41 * "al" condition is assumed by default. 42 * 43 * str1w ptr reg abort 44 * str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort 45 * str1b ptr reg cond abort 46 * 47 * Same as their ldr* counterparts, but data is stored to 'ptr' location 48 * rather than being loaded. 49 * 50 * enter reg1 reg2 51 * 52 * Preserve the provided registers on the stack plus any additional 53 * data as needed by the implementation including this code. Called 54 * upon code entry. 55 * 56 * exit reg1 reg2 57 * 58 * Restore registers with the values previously saved with the 59 * 'preserv' macro. Called upon code termination. 60 * 61 * LDR1W_SHIFT 62 * STR1W_SHIFT 63 * 64 * Correction to be applied to the "ip" register when branching into 65 * the ldr1w or str1w instructions (some of these macros may expand to 66 * than one 32bit instruction in Thumb-2) 67 */ 68 69 70 enter r4, lr 71 72 subs r2, r2, #4 73 blt 8f 74 ands ip, r0, #3 75 PLD( pld [r1, #0] ) 76 bne 9f 77 ands ip, r1, #3 78 bne 10f 79 801: subs r2, r2, #(28) 81 stmfd sp!, {r5 - r8} 82 blt 5f 83 84 CALGN( ands ip, r0, #31 ) 85 CALGN( rsb r3, ip, #32 ) 86 CALGN( sbcnes r4, r3, r2 ) @ C is always set here 87 CALGN( bcs 2f ) 88 CALGN( adr r4, 6f ) 89 CALGN( subs r2, r2, r3 ) @ C gets set 90 CALGN( add pc, r4, ip ) 91 92 PLD( pld [r1, #0] ) 932: PLD( subs r2, r2, #96 ) 94 PLD( pld [r1, #28] ) 95 PLD( blt 4f ) 96 PLD( pld [r1, #60] ) 97 PLD( pld [r1, #92] ) 98 993: PLD( pld [r1, #124] ) 1004: ldr8w r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f 101 subs r2, r2, #32 102 str8w r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f 103 bge 3b 104 PLD( cmn r2, #96 ) 105 PLD( bge 4b ) 106 1075: ands ip, r2, #28 108 rsb ip, ip, #32 109#if LDR1W_SHIFT > 0 110 lsl ip, ip, #LDR1W_SHIFT 111#endif 112 addne pc, pc, ip @ C is always clear here 113 b 7f 1146: 115 .rept (1 << LDR1W_SHIFT) 116 W(nop) 117 .endr 118 ldr1w r1, r3, abort=20f 119 ldr1w r1, r4, abort=20f 120 ldr1w r1, r5, abort=20f 121 ldr1w r1, r6, abort=20f 122 ldr1w r1, r7, abort=20f 123 ldr1w r1, r8, abort=20f 124 ldr1w r1, lr, abort=20f 125 126#if LDR1W_SHIFT < STR1W_SHIFT 127 lsl ip, ip, #STR1W_SHIFT - LDR1W_SHIFT 128#elif LDR1W_SHIFT > STR1W_SHIFT 129 lsr ip, ip, #LDR1W_SHIFT - STR1W_SHIFT 130#endif 131 add pc, pc, ip 132 nop 133 .rept (1 << STR1W_SHIFT) 134 W(nop) 135 .endr 136 str1w r0, r3, abort=20f 137 str1w r0, r4, abort=20f 138 str1w r0, r5, abort=20f 139 str1w r0, r6, abort=20f 140 str1w r0, r7, abort=20f 141 str1w r0, r8, abort=20f 142 str1w r0, lr, abort=20f 143 144 CALGN( bcs 2b ) 145 1467: ldmfd sp!, {r5 - r8} 147 1488: movs r2, r2, lsl #31 149 ldr1b r1, r3, ne, abort=21f 150 ldr1b r1, r4, cs, abort=21f 151 ldr1b r1, ip, cs, abort=21f 152 str1b r0, r3, ne, abort=21f 153 str1b r0, r4, cs, abort=21f 154 str1b r0, ip, cs, abort=21f 155 156 exit r4, pc 157 1589: rsb ip, ip, #4 159 cmp ip, #2 160 ldr1b r1, r3, gt, abort=21f 161 ldr1b r1, r4, ge, abort=21f 162 ldr1b r1, lr, abort=21f 163 str1b r0, r3, gt, abort=21f 164 str1b r0, r4, ge, abort=21f 165 subs r2, r2, ip 166 str1b r0, lr, abort=21f 167 blt 8b 168 ands ip, r1, #3 169 beq 1b 170 17110: bic r1, r1, #3 172 cmp ip, #2 173 ldr1w r1, lr, abort=21f 174 beq 17f 175 bgt 18f 176 177 178 .macro forward_copy_shift pull push 179 180 subs r2, r2, #28 181 blt 14f 182 183 CALGN( ands ip, r0, #31 ) 184 CALGN( rsb ip, ip, #32 ) 185 CALGN( sbcnes r4, ip, r2 ) @ C is always set here 186 CALGN( subcc r2, r2, ip ) 187 CALGN( bcc 15f ) 188 18911: stmfd sp!, {r5 - r9} 190 191 PLD( pld [r1, #0] ) 192 PLD( subs r2, r2, #96 ) 193 PLD( pld [r1, #28] ) 194 PLD( blt 13f ) 195 PLD( pld [r1, #60] ) 196 PLD( pld [r1, #92] ) 197 19812: PLD( pld [r1, #124] ) 19913: ldr4w r1, r4, r5, r6, r7, abort=19f 200 mov r3, lr, lspull #\pull 201 subs r2, r2, #32 202 ldr4w r1, r8, r9, ip, lr, abort=19f 203 orr r3, r3, r4, lspush #\push 204 mov r4, r4, lspull #\pull 205 orr r4, r4, r5, lspush #\push 206 mov r5, r5, lspull #\pull 207 orr r5, r5, r6, lspush #\push 208 mov r6, r6, lspull #\pull 209 orr r6, r6, r7, lspush #\push 210 mov r7, r7, lspull #\pull 211 orr r7, r7, r8, lspush #\push 212 mov r8, r8, lspull #\pull 213 orr r8, r8, r9, lspush #\push 214 mov r9, r9, lspull #\pull 215 orr r9, r9, ip, lspush #\push 216 mov ip, ip, lspull #\pull 217 orr ip, ip, lr, lspush #\push 218 str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f 219 bge 12b 220 PLD( cmn r2, #96 ) 221 PLD( bge 13b ) 222 223 ldmfd sp!, {r5 - r9} 224 22514: ands ip, r2, #28 226 beq 16f 227 22815: mov r3, lr, lspull #\pull 229 ldr1w r1, lr, abort=21f 230 subs ip, ip, #4 231 orr r3, r3, lr, lspush #\push 232 str1w r0, r3, abort=21f 233 bgt 15b 234 CALGN( cmp r2, #0 ) 235 CALGN( bge 11b ) 236 23716: sub r1, r1, #(\push / 8) 238 b 8b 239 240 .endm 241 242 243 forward_copy_shift pull=8 push=24 244 24517: forward_copy_shift pull=16 push=16 246 24718: forward_copy_shift pull=24 push=8 248 249 250/* 251 * Abort preamble and completion macros. 252 * If a fixup handler is required then those macros must surround it. 253 * It is assumed that the fixup code will handle the private part of 254 * the exit macro. 255 */ 256 257 .macro copy_abort_preamble 25819: ldmfd sp!, {r5 - r9} 259 b 21f 26020: ldmfd sp!, {r5 - r8} 26121: 262 .endm 263 264 .macro copy_abort_end 265 ldmfd sp!, {r4, pc} 266 .endm 267 268