| xj | b04a402 | 2021-11-25 15:01:52 +0800 | [diff] [blame] | 1 | /* | 
|  | 2 | * This file is subject to the terms and conditions of the GNU General Public | 
|  | 3 | * License.  See the file "COPYING" in the main directory of this archive | 
|  | 4 | * for more details. | 
|  | 5 | * | 
|  | 6 | * Unified implementation of memcpy, memmove and the __copy_user backend. | 
|  | 7 | * | 
|  | 8 | * Copyright (C) 1998, 99, 2000, 01, 2002 Ralf Baechle (ralf@gnu.org) | 
|  | 9 | * Copyright (C) 1999, 2000, 01, 2002 Silicon Graphics, Inc. | 
|  | 10 | * Copyright (C) 2002 Broadcom, Inc. | 
|  | 11 | *   memcpy/copy_user author: Mark Vandevoorde | 
|  | 12 | * Copyright (C) 2007  Maciej W. Rozycki | 
|  | 13 | * Copyright (C) 2014 Imagination Technologies Ltd. | 
|  | 14 | * | 
|  | 15 | * Mnemonic names for arguments to memcpy/__copy_user | 
|  | 16 | */ | 
|  | 17 |  | 
|  | 18 | /* | 
|  | 19 | * Hack to resolve longstanding prefetch issue | 
|  | 20 | * | 
|  | 21 | * Prefetching may be fatal on some systems if we're prefetching beyond the | 
|  | 22 | * end of memory on some systems.  It's also a seriously bad idea on non | 
|  | 23 | * dma-coherent systems. | 
|  | 24 | */ | 
|  | 25 | #ifdef CONFIG_DMA_NONCOHERENT | 
|  | 26 | #undef CONFIG_CPU_HAS_PREFETCH | 
|  | 27 | #endif | 
|  | 28 | #ifdef CONFIG_MIPS_MALTA | 
|  | 29 | #undef CONFIG_CPU_HAS_PREFETCH | 
|  | 30 | #endif | 
|  | 31 | #ifdef CONFIG_CPU_MIPSR6 | 
|  | 32 | #undef CONFIG_CPU_HAS_PREFETCH | 
|  | 33 | #endif | 
|  | 34 |  | 
|  | 35 | #include <asm/asm.h> | 
|  | 36 | #include <asm/asm-offsets.h> | 
|  | 37 | #include <asm/export.h> | 
|  | 38 | #include <asm/regdef.h> | 
|  | 39 |  | 
|  | 40 | #define dst a0 | 
|  | 41 | #define src a1 | 
|  | 42 | #define len a2 | 
|  | 43 |  | 
|  | 44 | /* | 
|  | 45 | * Spec | 
|  | 46 | * | 
|  | 47 | * memcpy copies len bytes from src to dst and sets v0 to dst. | 
|  | 48 | * It assumes that | 
|  | 49 | *   - src and dst don't overlap | 
|  | 50 | *   - src is readable | 
|  | 51 | *   - dst is writable | 
|  | 52 | * memcpy uses the standard calling convention | 
|  | 53 | * | 
|  | 54 | * __copy_user copies up to len bytes from src to dst and sets a2 (len) to | 
|  | 55 | * the number of uncopied bytes due to an exception caused by a read or write. | 
|  | 56 | * __copy_user assumes that src and dst don't overlap, and that the call is | 
|  | 57 | * implementing one of the following: | 
|  | 58 | *   copy_to_user | 
|  | 59 | *     - src is readable  (no exceptions when reading src) | 
|  | 60 | *   copy_from_user | 
|  | 61 | *     - dst is writable  (no exceptions when writing dst) | 
|  | 62 | * __copy_user uses a non-standard calling convention; see | 
|  | 63 | * include/asm-mips/uaccess.h | 
|  | 64 | * | 
|  | 65 | * When an exception happens on a load, the handler must | 
|  | 66 | # ensure that all of the destination buffer is overwritten to prevent | 
|  | 67 | * leaking information to user mode programs. | 
|  | 68 | */ | 
|  | 69 |  | 
|  | 70 | /* | 
|  | 71 | * Implementation | 
|  | 72 | */ | 
|  | 73 |  | 
|  | 74 | /* | 
|  | 75 | * The exception handler for loads requires that: | 
|  | 76 | *  1- AT contain the address of the byte just past the end of the source | 
|  | 77 | *     of the copy, | 
|  | 78 | *  2- src_entry <= src < AT, and | 
|  | 79 | *  3- (dst - src) == (dst_entry - src_entry), | 
|  | 80 | * The _entry suffix denotes values when __copy_user was called. | 
|  | 81 | * | 
|  | 82 | * (1) is set up up by uaccess.h and maintained by not writing AT in copy_user | 
|  | 83 | * (2) is met by incrementing src by the number of bytes copied | 
|  | 84 | * (3) is met by not doing loads between a pair of increments of dst and src | 
|  | 85 | * | 
|  | 86 | * The exception handlers for stores adjust len (if necessary) and return. | 
|  | 87 | * These handlers do not need to overwrite any data. | 
|  | 88 | * | 
|  | 89 | * For __rmemcpy and memmove an exception is always a kernel bug, therefore | 
|  | 90 | * they're not protected. | 
|  | 91 | */ | 
|  | 92 |  | 
|  | 93 | /* Instruction type */ | 
|  | 94 | #define LD_INSN 1 | 
|  | 95 | #define ST_INSN 2 | 
|  | 96 | /* Pretech type */ | 
|  | 97 | #define SRC_PREFETCH 1 | 
|  | 98 | #define DST_PREFETCH 2 | 
|  | 99 | #define LEGACY_MODE 1 | 
|  | 100 | #define EVA_MODE    2 | 
|  | 101 | #define USEROP   1 | 
|  | 102 | #define KERNELOP 2 | 
|  | 103 |  | 
|  | 104 | /* | 
|  | 105 | * Wrapper to add an entry in the exception table | 
|  | 106 | * in case the insn causes a memory exception. | 
|  | 107 | * Arguments: | 
|  | 108 | * insn    : Load/store instruction | 
|  | 109 | * type    : Instruction type | 
|  | 110 | * reg     : Register | 
|  | 111 | * addr    : Address | 
|  | 112 | * handler : Exception handler | 
|  | 113 | */ | 
|  | 114 |  | 
|  | 115 | #define EXC(insn, type, reg, addr, handler)			\ | 
|  | 116 | .if \mode == LEGACY_MODE;				\ | 
|  | 117 | 9:		insn reg, addr;					\ | 
|  | 118 | .section __ex_table,"a";			\ | 
|  | 119 | PTR	9b, handler;				\ | 
|  | 120 | .previous;					\ | 
|  | 121 | /* This is assembled in EVA mode */			\ | 
|  | 122 | .else;							\ | 
|  | 123 | /* If loading from user or storing to user */	\ | 
|  | 124 | .if ((\from == USEROP) && (type == LD_INSN)) || \ | 
|  | 125 | ((\to == USEROP) && (type == ST_INSN));	\ | 
|  | 126 | 9:			__BUILD_EVA_INSN(insn##e, reg, addr);	\ | 
|  | 127 | .section __ex_table,"a";		\ | 
|  | 128 | PTR	9b, handler;			\ | 
|  | 129 | .previous;				\ | 
|  | 130 | .else;						\ | 
|  | 131 | /*					\ | 
|  | 132 | *  Still in EVA, but no need for	\ | 
|  | 133 | * exception handler or EVA insn	\ | 
|  | 134 | */					\ | 
|  | 135 | insn reg, addr;				\ | 
|  | 136 | .endif;						\ | 
|  | 137 | .endif | 
|  | 138 |  | 
|  | 139 | /* | 
|  | 140 | * Only on the 64-bit kernel we can made use of 64-bit registers. | 
|  | 141 | */ | 
|  | 142 | #ifdef CONFIG_64BIT | 
|  | 143 | #define USE_DOUBLE | 
|  | 144 | #endif | 
|  | 145 |  | 
|  | 146 | #ifdef USE_DOUBLE | 
|  | 147 |  | 
|  | 148 | #define LOADK ld /* No exception */ | 
|  | 149 | #define LOAD(reg, addr, handler)	EXC(ld, LD_INSN, reg, addr, handler) | 
|  | 150 | #define LOADL(reg, addr, handler)	EXC(ldl, LD_INSN, reg, addr, handler) | 
|  | 151 | #define LOADR(reg, addr, handler)	EXC(ldr, LD_INSN, reg, addr, handler) | 
|  | 152 | #define STOREL(reg, addr, handler)	EXC(sdl, ST_INSN, reg, addr, handler) | 
|  | 153 | #define STORER(reg, addr, handler)	EXC(sdr, ST_INSN, reg, addr, handler) | 
|  | 154 | #define STORE(reg, addr, handler)	EXC(sd, ST_INSN, reg, addr, handler) | 
|  | 155 | #define ADD    daddu | 
|  | 156 | #define SUB    dsubu | 
|  | 157 | #define SRL    dsrl | 
|  | 158 | #define SRA    dsra | 
|  | 159 | #define SLL    dsll | 
|  | 160 | #define SLLV   dsllv | 
|  | 161 | #define SRLV   dsrlv | 
|  | 162 | #define NBYTES 8 | 
|  | 163 | #define LOG_NBYTES 3 | 
|  | 164 |  | 
|  | 165 | /* | 
|  | 166 | * As we are sharing code base with the mips32 tree (which use the o32 ABI | 
|  | 167 | * register definitions). We need to redefine the register definitions from | 
|  | 168 | * the n64 ABI register naming to the o32 ABI register naming. | 
|  | 169 | */ | 
|  | 170 | #undef t0 | 
|  | 171 | #undef t1 | 
|  | 172 | #undef t2 | 
|  | 173 | #undef t3 | 
|  | 174 | #define t0	$8 | 
|  | 175 | #define t1	$9 | 
|  | 176 | #define t2	$10 | 
|  | 177 | #define t3	$11 | 
|  | 178 | #define t4	$12 | 
|  | 179 | #define t5	$13 | 
|  | 180 | #define t6	$14 | 
|  | 181 | #define t7	$15 | 
|  | 182 |  | 
|  | 183 | #else | 
|  | 184 |  | 
|  | 185 | #define LOADK lw /* No exception */ | 
|  | 186 | #define LOAD(reg, addr, handler)	EXC(lw, LD_INSN, reg, addr, handler) | 
|  | 187 | #define LOADL(reg, addr, handler)	EXC(lwl, LD_INSN, reg, addr, handler) | 
|  | 188 | #define LOADR(reg, addr, handler)	EXC(lwr, LD_INSN, reg, addr, handler) | 
|  | 189 | #define STOREL(reg, addr, handler)	EXC(swl, ST_INSN, reg, addr, handler) | 
|  | 190 | #define STORER(reg, addr, handler)	EXC(swr, ST_INSN, reg, addr, handler) | 
|  | 191 | #define STORE(reg, addr, handler)	EXC(sw, ST_INSN, reg, addr, handler) | 
|  | 192 | #define ADD    addu | 
|  | 193 | #define SUB    subu | 
|  | 194 | #define SRL    srl | 
|  | 195 | #define SLL    sll | 
|  | 196 | #define SRA    sra | 
|  | 197 | #define SLLV   sllv | 
|  | 198 | #define SRLV   srlv | 
|  | 199 | #define NBYTES 4 | 
|  | 200 | #define LOG_NBYTES 2 | 
|  | 201 |  | 
|  | 202 | #endif /* USE_DOUBLE */ | 
|  | 203 |  | 
|  | 204 | #define LOADB(reg, addr, handler)	EXC(lb, LD_INSN, reg, addr, handler) | 
|  | 205 | #define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler) | 
|  | 206 |  | 
|  | 207 | #define _PREF(hint, addr, type)						\ | 
|  | 208 | .if \mode == LEGACY_MODE;					\ | 
|  | 209 | PREF(hint, addr);					\ | 
|  | 210 | .else;								\ | 
|  | 211 | .if ((\from == USEROP) && (type == SRC_PREFETCH)) ||	\ | 
|  | 212 | ((\to == USEROP) && (type == DST_PREFETCH));	\ | 
|  | 213 | /*						\ | 
|  | 214 | * PREFE has only 9 bits for the offset		\ | 
|  | 215 | * compared to PREF which has 16, so it may	\ | 
|  | 216 | * need to use the $at register but this	\ | 
|  | 217 | * register should remain intact because it's	\ | 
|  | 218 | * used later on. Therefore use $v1.		\ | 
|  | 219 | */						\ | 
|  | 220 | .set at=v1;					\ | 
|  | 221 | PREFE(hint, addr);				\ | 
|  | 222 | .set noat;					\ | 
|  | 223 | .else;							\ | 
|  | 224 | PREF(hint, addr);				\ | 
|  | 225 | .endif;							\ | 
|  | 226 | .endif | 
|  | 227 |  | 
|  | 228 | #define PREFS(hint, addr) _PREF(hint, addr, SRC_PREFETCH) | 
|  | 229 | #define PREFD(hint, addr) _PREF(hint, addr, DST_PREFETCH) | 
|  | 230 |  | 
|  | 231 | #ifdef CONFIG_CPU_LITTLE_ENDIAN | 
|  | 232 | #define LDFIRST LOADR | 
|  | 233 | #define LDREST	LOADL | 
|  | 234 | #define STFIRST STORER | 
|  | 235 | #define STREST	STOREL | 
|  | 236 | #define SHIFT_DISCARD SLLV | 
|  | 237 | #else | 
|  | 238 | #define LDFIRST LOADL | 
|  | 239 | #define LDREST	LOADR | 
|  | 240 | #define STFIRST STOREL | 
|  | 241 | #define STREST	STORER | 
|  | 242 | #define SHIFT_DISCARD SRLV | 
|  | 243 | #endif | 
|  | 244 |  | 
|  | 245 | #define FIRST(unit) ((unit)*NBYTES) | 
|  | 246 | #define REST(unit)  (FIRST(unit)+NBYTES-1) | 
|  | 247 | #define UNIT(unit)  FIRST(unit) | 
|  | 248 |  | 
|  | 249 | #define ADDRMASK (NBYTES-1) | 
|  | 250 |  | 
|  | 251 | .text | 
|  | 252 | .set	noreorder | 
|  | 253 | #ifndef CONFIG_CPU_DADDI_WORKAROUNDS | 
|  | 254 | .set	noat | 
|  | 255 | #else | 
|  | 256 | .set	at=v1 | 
|  | 257 | #endif | 
|  | 258 |  | 
|  | 259 | .align	5 | 
|  | 260 |  | 
|  | 261 | /* | 
|  | 262 | * Macro to build the __copy_user common code | 
|  | 263 | * Arguments: | 
|  | 264 | * mode : LEGACY_MODE or EVA_MODE | 
|  | 265 | * from : Source operand. USEROP or KERNELOP | 
|  | 266 | * to   : Destination operand. USEROP or KERNELOP | 
|  | 267 | */ | 
|  | 268 | .macro __BUILD_COPY_USER mode, from, to | 
|  | 269 |  | 
|  | 270 | /* initialize __memcpy if this the first time we execute this macro */ | 
|  | 271 | .ifnotdef __memcpy | 
|  | 272 | .set __memcpy, 1 | 
|  | 273 | .hidden __memcpy /* make sure it does not leak */ | 
|  | 274 | .endif | 
|  | 275 |  | 
|  | 276 | /* | 
|  | 277 | * Note: dst & src may be unaligned, len may be 0 | 
|  | 278 | * Temps | 
|  | 279 | */ | 
|  | 280 | #define rem t8 | 
|  | 281 |  | 
|  | 282 | R10KCBARRIER(0(ra)) | 
|  | 283 | /* | 
|  | 284 | * The "issue break"s below are very approximate. | 
|  | 285 | * Issue delays for dcache fills will perturb the schedule, as will | 
|  | 286 | * load queue full replay traps, etc. | 
|  | 287 | * | 
|  | 288 | * If len < NBYTES use byte operations. | 
|  | 289 | */ | 
|  | 290 | PREFS(	0, 0(src) ) | 
|  | 291 | PREFD(	1, 0(dst) ) | 
|  | 292 | sltu	t2, len, NBYTES | 
|  | 293 | and	t1, dst, ADDRMASK | 
|  | 294 | PREFS(	0, 1*32(src) ) | 
|  | 295 | PREFD(	1, 1*32(dst) ) | 
|  | 296 | bnez	t2, .Lcopy_bytes_checklen\@ | 
|  | 297 | and	t0, src, ADDRMASK | 
|  | 298 | PREFS(	0, 2*32(src) ) | 
|  | 299 | PREFD(	1, 2*32(dst) ) | 
|  | 300 | #ifndef CONFIG_CPU_MIPSR6 | 
|  | 301 | bnez	t1, .Ldst_unaligned\@ | 
|  | 302 | nop | 
|  | 303 | bnez	t0, .Lsrc_unaligned_dst_aligned\@ | 
|  | 304 | #else | 
|  | 305 | or	t0, t0, t1 | 
|  | 306 | bnez	t0, .Lcopy_unaligned_bytes\@ | 
|  | 307 | #endif | 
|  | 308 | /* | 
|  | 309 | * use delay slot for fall-through | 
|  | 310 | * src and dst are aligned; need to compute rem | 
|  | 311 | */ | 
|  | 312 | .Lboth_aligned\@: | 
|  | 313 | SRL	t0, len, LOG_NBYTES+3	 # +3 for 8 units/iter | 
|  | 314 | beqz	t0, .Lcleanup_both_aligned\@ # len < 8*NBYTES | 
|  | 315 | and	rem, len, (8*NBYTES-1)	 # rem = len % (8*NBYTES) | 
|  | 316 | PREFS(	0, 3*32(src) ) | 
|  | 317 | PREFD(	1, 3*32(dst) ) | 
|  | 318 | .align	4 | 
|  | 319 | 1: | 
|  | 320 | R10KCBARRIER(0(ra)) | 
|  | 321 | LOAD(t0, UNIT(0)(src), .Ll_exc\@) | 
|  | 322 | LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@) | 
|  | 323 | LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@) | 
|  | 324 | LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@) | 
|  | 325 | SUB	len, len, 8*NBYTES | 
|  | 326 | LOAD(t4, UNIT(4)(src), .Ll_exc_copy\@) | 
|  | 327 | LOAD(t7, UNIT(5)(src), .Ll_exc_copy\@) | 
|  | 328 | STORE(t0, UNIT(0)(dst),	.Ls_exc_p8u\@) | 
|  | 329 | STORE(t1, UNIT(1)(dst),	.Ls_exc_p7u\@) | 
|  | 330 | LOAD(t0, UNIT(6)(src), .Ll_exc_copy\@) | 
|  | 331 | LOAD(t1, UNIT(7)(src), .Ll_exc_copy\@) | 
|  | 332 | ADD	src, src, 8*NBYTES | 
|  | 333 | ADD	dst, dst, 8*NBYTES | 
|  | 334 | STORE(t2, UNIT(-6)(dst), .Ls_exc_p6u\@) | 
|  | 335 | STORE(t3, UNIT(-5)(dst), .Ls_exc_p5u\@) | 
|  | 336 | STORE(t4, UNIT(-4)(dst), .Ls_exc_p4u\@) | 
|  | 337 | STORE(t7, UNIT(-3)(dst), .Ls_exc_p3u\@) | 
|  | 338 | STORE(t0, UNIT(-2)(dst), .Ls_exc_p2u\@) | 
|  | 339 | STORE(t1, UNIT(-1)(dst), .Ls_exc_p1u\@) | 
|  | 340 | PREFS(	0, 8*32(src) ) | 
|  | 341 | PREFD(	1, 8*32(dst) ) | 
|  | 342 | bne	len, rem, 1b | 
|  | 343 | nop | 
|  | 344 |  | 
|  | 345 | /* | 
|  | 346 | * len == rem == the number of bytes left to copy < 8*NBYTES | 
|  | 347 | */ | 
|  | 348 | .Lcleanup_both_aligned\@: | 
|  | 349 | beqz	len, .Ldone\@ | 
|  | 350 | sltu	t0, len, 4*NBYTES | 
|  | 351 | bnez	t0, .Lless_than_4units\@ | 
|  | 352 | and	rem, len, (NBYTES-1)	# rem = len % NBYTES | 
|  | 353 | /* | 
|  | 354 | * len >= 4*NBYTES | 
|  | 355 | */ | 
|  | 356 | LOAD( t0, UNIT(0)(src),	.Ll_exc\@) | 
|  | 357 | LOAD( t1, UNIT(1)(src),	.Ll_exc_copy\@) | 
|  | 358 | LOAD( t2, UNIT(2)(src),	.Ll_exc_copy\@) | 
|  | 359 | LOAD( t3, UNIT(3)(src),	.Ll_exc_copy\@) | 
|  | 360 | SUB	len, len, 4*NBYTES | 
|  | 361 | ADD	src, src, 4*NBYTES | 
|  | 362 | R10KCBARRIER(0(ra)) | 
|  | 363 | STORE(t0, UNIT(0)(dst),	.Ls_exc_p4u\@) | 
|  | 364 | STORE(t1, UNIT(1)(dst),	.Ls_exc_p3u\@) | 
|  | 365 | STORE(t2, UNIT(2)(dst),	.Ls_exc_p2u\@) | 
|  | 366 | STORE(t3, UNIT(3)(dst),	.Ls_exc_p1u\@) | 
|  | 367 | .set	reorder				/* DADDI_WAR */ | 
|  | 368 | ADD	dst, dst, 4*NBYTES | 
|  | 369 | beqz	len, .Ldone\@ | 
|  | 370 | .set	noreorder | 
|  | 371 | .Lless_than_4units\@: | 
|  | 372 | /* | 
|  | 373 | * rem = len % NBYTES | 
|  | 374 | */ | 
|  | 375 | beq	rem, len, .Lcopy_bytes\@ | 
|  | 376 | nop | 
|  | 377 | 1: | 
|  | 378 | R10KCBARRIER(0(ra)) | 
|  | 379 | LOAD(t0, 0(src), .Ll_exc\@) | 
|  | 380 | ADD	src, src, NBYTES | 
|  | 381 | SUB	len, len, NBYTES | 
|  | 382 | STORE(t0, 0(dst), .Ls_exc_p1u\@) | 
|  | 383 | .set	reorder				/* DADDI_WAR */ | 
|  | 384 | ADD	dst, dst, NBYTES | 
|  | 385 | bne	rem, len, 1b | 
|  | 386 | .set	noreorder | 
|  | 387 |  | 
|  | 388 | #ifndef CONFIG_CPU_MIPSR6 | 
|  | 389 | /* | 
|  | 390 | * src and dst are aligned, need to copy rem bytes (rem < NBYTES) | 
|  | 391 | * A loop would do only a byte at a time with possible branch | 
|  | 392 | * mispredicts.	 Can't do an explicit LOAD dst,mask,or,STORE | 
|  | 393 | * because can't assume read-access to dst.  Instead, use | 
|  | 394 | * STREST dst, which doesn't require read access to dst. | 
|  | 395 | * | 
|  | 396 | * This code should perform better than a simple loop on modern, | 
|  | 397 | * wide-issue mips processors because the code has fewer branches and | 
|  | 398 | * more instruction-level parallelism. | 
|  | 399 | */ | 
|  | 400 | #define bits t2 | 
|  | 401 | beqz	len, .Ldone\@ | 
|  | 402 | ADD	t1, dst, len	# t1 is just past last byte of dst | 
|  | 403 | li	bits, 8*NBYTES | 
|  | 404 | SLL	rem, len, 3	# rem = number of bits to keep | 
|  | 405 | LOAD(t0, 0(src), .Ll_exc\@) | 
|  | 406 | SUB	bits, bits, rem # bits = number of bits to discard | 
|  | 407 | SHIFT_DISCARD t0, t0, bits | 
|  | 408 | STREST(t0, -1(t1), .Ls_exc\@) | 
|  | 409 | jr	ra | 
|  | 410 | move	len, zero | 
|  | 411 | .Ldst_unaligned\@: | 
|  | 412 | /* | 
|  | 413 | * dst is unaligned | 
|  | 414 | * t0 = src & ADDRMASK | 
|  | 415 | * t1 = dst & ADDRMASK; T1 > 0 | 
|  | 416 | * len >= NBYTES | 
|  | 417 | * | 
|  | 418 | * Copy enough bytes to align dst | 
|  | 419 | * Set match = (src and dst have same alignment) | 
|  | 420 | */ | 
|  | 421 | #define match rem | 
|  | 422 | LDFIRST(t3, FIRST(0)(src), .Ll_exc\@) | 
|  | 423 | ADD	t2, zero, NBYTES | 
|  | 424 | LDREST(t3, REST(0)(src), .Ll_exc_copy\@) | 
|  | 425 | SUB	t2, t2, t1	# t2 = number of bytes copied | 
|  | 426 | xor	match, t0, t1 | 
|  | 427 | R10KCBARRIER(0(ra)) | 
|  | 428 | STFIRST(t3, FIRST(0)(dst), .Ls_exc\@) | 
|  | 429 | beq	len, t2, .Ldone\@ | 
|  | 430 | SUB	len, len, t2 | 
|  | 431 | ADD	dst, dst, t2 | 
|  | 432 | beqz	match, .Lboth_aligned\@ | 
|  | 433 | ADD	src, src, t2 | 
|  | 434 |  | 
|  | 435 | .Lsrc_unaligned_dst_aligned\@: | 
|  | 436 | SRL	t0, len, LOG_NBYTES+2	 # +2 for 4 units/iter | 
|  | 437 | PREFS(	0, 3*32(src) ) | 
|  | 438 | beqz	t0, .Lcleanup_src_unaligned\@ | 
|  | 439 | and	rem, len, (4*NBYTES-1)	 # rem = len % 4*NBYTES | 
|  | 440 | PREFD(	1, 3*32(dst) ) | 
|  | 441 | 1: | 
|  | 442 | /* | 
|  | 443 | * Avoid consecutive LD*'s to the same register since some mips | 
|  | 444 | * implementations can't issue them in the same cycle. | 
|  | 445 | * It's OK to load FIRST(N+1) before REST(N) because the two addresses | 
|  | 446 | * are to the same unit (unless src is aligned, but it's not). | 
|  | 447 | */ | 
|  | 448 | R10KCBARRIER(0(ra)) | 
|  | 449 | LDFIRST(t0, FIRST(0)(src), .Ll_exc\@) | 
|  | 450 | LDFIRST(t1, FIRST(1)(src), .Ll_exc_copy\@) | 
|  | 451 | SUB	len, len, 4*NBYTES | 
|  | 452 | LDREST(t0, REST(0)(src), .Ll_exc_copy\@) | 
|  | 453 | LDREST(t1, REST(1)(src), .Ll_exc_copy\@) | 
|  | 454 | LDFIRST(t2, FIRST(2)(src), .Ll_exc_copy\@) | 
|  | 455 | LDFIRST(t3, FIRST(3)(src), .Ll_exc_copy\@) | 
|  | 456 | LDREST(t2, REST(2)(src), .Ll_exc_copy\@) | 
|  | 457 | LDREST(t3, REST(3)(src), .Ll_exc_copy\@) | 
|  | 458 | PREFS(	0, 9*32(src) )		# 0 is PREF_LOAD  (not streamed) | 
|  | 459 | ADD	src, src, 4*NBYTES | 
|  | 460 | #ifdef CONFIG_CPU_SB1 | 
|  | 461 | nop				# improves slotting | 
|  | 462 | #endif | 
|  | 463 | STORE(t0, UNIT(0)(dst),	.Ls_exc_p4u\@) | 
|  | 464 | STORE(t1, UNIT(1)(dst),	.Ls_exc_p3u\@) | 
|  | 465 | STORE(t2, UNIT(2)(dst),	.Ls_exc_p2u\@) | 
|  | 466 | STORE(t3, UNIT(3)(dst),	.Ls_exc_p1u\@) | 
|  | 467 | PREFD(	1, 9*32(dst) )		# 1 is PREF_STORE (not streamed) | 
|  | 468 | .set	reorder				/* DADDI_WAR */ | 
|  | 469 | ADD	dst, dst, 4*NBYTES | 
|  | 470 | bne	len, rem, 1b | 
|  | 471 | .set	noreorder | 
|  | 472 |  | 
|  | 473 | .Lcleanup_src_unaligned\@: | 
|  | 474 | beqz	len, .Ldone\@ | 
|  | 475 | and	rem, len, NBYTES-1  # rem = len % NBYTES | 
|  | 476 | beq	rem, len, .Lcopy_bytes\@ | 
|  | 477 | nop | 
|  | 478 | 1: | 
|  | 479 | R10KCBARRIER(0(ra)) | 
|  | 480 | LDFIRST(t0, FIRST(0)(src), .Ll_exc\@) | 
|  | 481 | LDREST(t0, REST(0)(src), .Ll_exc_copy\@) | 
|  | 482 | ADD	src, src, NBYTES | 
|  | 483 | SUB	len, len, NBYTES | 
|  | 484 | STORE(t0, 0(dst), .Ls_exc_p1u\@) | 
|  | 485 | .set	reorder				/* DADDI_WAR */ | 
|  | 486 | ADD	dst, dst, NBYTES | 
|  | 487 | bne	len, rem, 1b | 
|  | 488 | .set	noreorder | 
|  | 489 |  | 
|  | 490 | #endif /* !CONFIG_CPU_MIPSR6 */ | 
|  | 491 | .Lcopy_bytes_checklen\@: | 
|  | 492 | beqz	len, .Ldone\@ | 
|  | 493 | nop | 
|  | 494 | .Lcopy_bytes\@: | 
|  | 495 | /* 0 < len < NBYTES  */ | 
|  | 496 | R10KCBARRIER(0(ra)) | 
|  | 497 | #define COPY_BYTE(N)			\ | 
|  | 498 | LOADB(t0, N(src), .Ll_exc\@);	\ | 
|  | 499 | SUB	len, len, 1;		\ | 
|  | 500 | beqz	len, .Ldone\@;		\ | 
|  | 501 | STOREB(t0, N(dst), .Ls_exc_p1\@) | 
|  | 502 |  | 
|  | 503 | COPY_BYTE(0) | 
|  | 504 | COPY_BYTE(1) | 
|  | 505 | #ifdef USE_DOUBLE | 
|  | 506 | COPY_BYTE(2) | 
|  | 507 | COPY_BYTE(3) | 
|  | 508 | COPY_BYTE(4) | 
|  | 509 | COPY_BYTE(5) | 
|  | 510 | #endif | 
|  | 511 | LOADB(t0, NBYTES-2(src), .Ll_exc\@) | 
|  | 512 | SUB	len, len, 1 | 
|  | 513 | jr	ra | 
|  | 514 | STOREB(t0, NBYTES-2(dst), .Ls_exc_p1\@) | 
|  | 515 | .Ldone\@: | 
|  | 516 | jr	ra | 
|  | 517 | nop | 
|  | 518 |  | 
|  | 519 | #ifdef CONFIG_CPU_MIPSR6 | 
|  | 520 | .Lcopy_unaligned_bytes\@: | 
|  | 521 | 1: | 
|  | 522 | COPY_BYTE(0) | 
|  | 523 | COPY_BYTE(1) | 
|  | 524 | COPY_BYTE(2) | 
|  | 525 | COPY_BYTE(3) | 
|  | 526 | COPY_BYTE(4) | 
|  | 527 | COPY_BYTE(5) | 
|  | 528 | COPY_BYTE(6) | 
|  | 529 | COPY_BYTE(7) | 
|  | 530 | ADD	src, src, 8 | 
|  | 531 | b	1b | 
|  | 532 | ADD	dst, dst, 8 | 
|  | 533 | #endif /* CONFIG_CPU_MIPSR6 */ | 
|  | 534 | .if __memcpy == 1 | 
|  | 535 | END(memcpy) | 
|  | 536 | .set __memcpy, 0 | 
|  | 537 | .hidden __memcpy | 
|  | 538 | .endif | 
|  | 539 |  | 
|  | 540 | .Ll_exc_copy\@: | 
|  | 541 | /* | 
|  | 542 | * Copy bytes from src until faulting load address (or until a | 
|  | 543 | * lb faults) | 
|  | 544 | * | 
|  | 545 | * When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28) | 
|  | 546 | * may be more than a byte beyond the last address. | 
|  | 547 | * Hence, the lb below may get an exception. | 
|  | 548 | * | 
|  | 549 | * Assumes src < THREAD_BUADDR($28) | 
|  | 550 | */ | 
|  | 551 | LOADK	t0, TI_TASK($28) | 
|  | 552 | nop | 
|  | 553 | LOADK	t0, THREAD_BUADDR(t0) | 
|  | 554 | 1: | 
|  | 555 | LOADB(t1, 0(src), .Ll_exc\@) | 
|  | 556 | ADD	src, src, 1 | 
|  | 557 | sb	t1, 0(dst)	# can't fault -- we're copy_from_user | 
|  | 558 | .set	reorder				/* DADDI_WAR */ | 
|  | 559 | ADD	dst, dst, 1 | 
|  | 560 | bne	src, t0, 1b | 
|  | 561 | .set	noreorder | 
|  | 562 | .Ll_exc\@: | 
|  | 563 | LOADK	t0, TI_TASK($28) | 
|  | 564 | nop | 
|  | 565 | LOADK	t0, THREAD_BUADDR(t0)	# t0 is just past last good address | 
|  | 566 | nop | 
|  | 567 | SUB	len, AT, t0		# len number of uncopied bytes | 
|  | 568 | jr	ra | 
|  | 569 | nop | 
|  | 570 |  | 
|  | 571 | #define SEXC(n)							\ | 
|  | 572 | .set	reorder;			/* DADDI_WAR */ \ | 
|  | 573 | .Ls_exc_p ## n ## u\@:						\ | 
|  | 574 | ADD	len, len, n*NBYTES;				\ | 
|  | 575 | jr	ra;						\ | 
|  | 576 | .set	noreorder | 
|  | 577 |  | 
|  | 578 | SEXC(8) | 
|  | 579 | SEXC(7) | 
|  | 580 | SEXC(6) | 
|  | 581 | SEXC(5) | 
|  | 582 | SEXC(4) | 
|  | 583 | SEXC(3) | 
|  | 584 | SEXC(2) | 
|  | 585 | SEXC(1) | 
|  | 586 |  | 
|  | 587 | .Ls_exc_p1\@: | 
|  | 588 | .set	reorder				/* DADDI_WAR */ | 
|  | 589 | ADD	len, len, 1 | 
|  | 590 | jr	ra | 
|  | 591 | .set	noreorder | 
|  | 592 | .Ls_exc\@: | 
|  | 593 | jr	ra | 
|  | 594 | nop | 
|  | 595 | .endm | 
|  | 596 |  | 
|  | 597 | .align	5 | 
|  | 598 | LEAF(memmove) | 
|  | 599 | EXPORT_SYMBOL(memmove) | 
|  | 600 | ADD	t0, a0, a2 | 
|  | 601 | ADD	t1, a1, a2 | 
|  | 602 | sltu	t0, a1, t0			# dst + len <= src -> memcpy | 
|  | 603 | sltu	t1, a0, t1			# dst >= src + len -> memcpy | 
|  | 604 | and	t0, t1 | 
|  | 605 | beqz	t0, .L__memcpy | 
|  | 606 | move	v0, a0				/* return value */ | 
|  | 607 | beqz	a2, .Lr_out | 
|  | 608 | END(memmove) | 
|  | 609 |  | 
|  | 610 | /* fall through to __rmemcpy */ | 
|  | 611 | LEAF(__rmemcpy)					/* a0=dst a1=src a2=len */ | 
|  | 612 | sltu	t0, a1, a0 | 
|  | 613 | beqz	t0, .Lr_end_bytes_up		# src >= dst | 
|  | 614 | nop | 
|  | 615 | ADD	a0, a2				# dst = dst + len | 
|  | 616 | ADD	a1, a2				# src = src + len | 
|  | 617 |  | 
|  | 618 | .Lr_end_bytes: | 
|  | 619 | R10KCBARRIER(0(ra)) | 
|  | 620 | lb	t0, -1(a1) | 
|  | 621 | SUB	a2, a2, 0x1 | 
|  | 622 | sb	t0, -1(a0) | 
|  | 623 | SUB	a1, a1, 0x1 | 
|  | 624 | .set	reorder				/* DADDI_WAR */ | 
|  | 625 | SUB	a0, a0, 0x1 | 
|  | 626 | bnez	a2, .Lr_end_bytes | 
|  | 627 | .set	noreorder | 
|  | 628 |  | 
|  | 629 | .Lr_out: | 
|  | 630 | jr	ra | 
|  | 631 | move	a2, zero | 
|  | 632 |  | 
|  | 633 | .Lr_end_bytes_up: | 
|  | 634 | R10KCBARRIER(0(ra)) | 
|  | 635 | lb	t0, (a1) | 
|  | 636 | SUB	a2, a2, 0x1 | 
|  | 637 | sb	t0, (a0) | 
|  | 638 | ADD	a1, a1, 0x1 | 
|  | 639 | .set	reorder				/* DADDI_WAR */ | 
|  | 640 | ADD	a0, a0, 0x1 | 
|  | 641 | bnez	a2, .Lr_end_bytes_up | 
|  | 642 | .set	noreorder | 
|  | 643 |  | 
|  | 644 | jr	ra | 
|  | 645 | move	a2, zero | 
|  | 646 | END(__rmemcpy) | 
|  | 647 |  | 
|  | 648 | /* | 
|  | 649 | * A combined memcpy/__copy_user | 
|  | 650 | * __copy_user sets len to 0 for success; else to an upper bound of | 
|  | 651 | * the number of uncopied bytes. | 
|  | 652 | * memcpy sets v0 to dst. | 
|  | 653 | */ | 
|  | 654 | .align	5 | 
|  | 655 | LEAF(memcpy)					/* a0=dst a1=src a2=len */ | 
|  | 656 | EXPORT_SYMBOL(memcpy) | 
|  | 657 | move	v0, dst				/* return value */ | 
|  | 658 | .L__memcpy: | 
|  | 659 | FEXPORT(__copy_user) | 
|  | 660 | EXPORT_SYMBOL(__copy_user) | 
|  | 661 | /* Legacy Mode, user <-> user */ | 
|  | 662 | __BUILD_COPY_USER LEGACY_MODE USEROP USEROP | 
|  | 663 |  | 
|  | 664 | #ifdef CONFIG_EVA | 
|  | 665 |  | 
|  | 666 | /* | 
|  | 667 | * For EVA we need distinct symbols for reading and writing to user space. | 
|  | 668 | * This is because we need to use specific EVA instructions to perform the | 
|  | 669 | * virtual <-> physical translation when a virtual address is actually in user | 
|  | 670 | * space | 
|  | 671 | */ | 
|  | 672 |  | 
|  | 673 | /* | 
|  | 674 | * __copy_from_user (EVA) | 
|  | 675 | */ | 
|  | 676 |  | 
|  | 677 | LEAF(__copy_from_user_eva) | 
|  | 678 | EXPORT_SYMBOL(__copy_from_user_eva) | 
|  | 679 | __BUILD_COPY_USER EVA_MODE USEROP KERNELOP | 
|  | 680 | END(__copy_from_user_eva) | 
|  | 681 |  | 
|  | 682 |  | 
|  | 683 |  | 
|  | 684 | /* | 
|  | 685 | * __copy_to_user (EVA) | 
|  | 686 | */ | 
|  | 687 |  | 
|  | 688 | LEAF(__copy_to_user_eva) | 
|  | 689 | EXPORT_SYMBOL(__copy_to_user_eva) | 
|  | 690 | __BUILD_COPY_USER EVA_MODE KERNELOP USEROP | 
|  | 691 | END(__copy_to_user_eva) | 
|  | 692 |  | 
|  | 693 | /* | 
|  | 694 | * __copy_in_user (EVA) | 
|  | 695 | */ | 
|  | 696 |  | 
|  | 697 | LEAF(__copy_in_user_eva) | 
|  | 698 | EXPORT_SYMBOL(__copy_in_user_eva) | 
|  | 699 | __BUILD_COPY_USER EVA_MODE USEROP USEROP | 
|  | 700 | END(__copy_in_user_eva) | 
|  | 701 |  | 
|  | 702 | #endif |