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 <linux/export.h> 36 #include <asm/asm.h> 37 #include <asm/asm-offsets.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_WD 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_WD 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 #ifdef CONFIG_CPU_HAS_PREFETCH 208 # define _PREF(hint, addr, type) \ 209 .if \mode == LEGACY_MODE; \ 210 kernel_pref(hint, addr); \ 211 .else; \ 212 .if ((\from == USEROP) && (type == SRC_PREFETCH)) || \ 213 ((\to == USEROP) && (type == DST_PREFETCH)); \ 214 /* \ 215 * PREFE has only 9 bits for the offset \ 216 * compared to PREF which has 16, so it may \ 217 * need to use the $at register but this \ 218 * register should remain intact because it's \ 219 * used later on. Therefore use $v1. \ 220 */ \ 221 .set at=v1; \ 222 user_pref(hint, addr); \ 223 .set noat; \ 224 .else; \ 225 kernel_pref(hint, addr); \ 226 .endif; \ 227 .endif 228 #else 229 # define _PREF(hint, addr, type) 230 #endif 231 232 #define PREFS(hint, addr) _PREF(hint, addr, SRC_PREFETCH) 233 #define PREFD(hint, addr) _PREF(hint, addr, DST_PREFETCH) 234 235 #ifdef CONFIG_CPU_LITTLE_ENDIAN 236 #define LDFIRST LOADR 237 #define LDREST LOADL 238 #define STFIRST STORER 239 #define STREST STOREL 240 #define SHIFT_DISCARD SLLV 241 #else 242 #define LDFIRST LOADL 243 #define LDREST LOADR 244 #define STFIRST STOREL 245 #define STREST STORER 246 #define SHIFT_DISCARD SRLV 247 #endif 248 249 #define FIRST(unit) ((unit)*NBYTES) 250 #define REST(unit) (FIRST(unit)+NBYTES-1) 251 #define UNIT(unit) FIRST(unit) 252 253 #define ADDRMASK (NBYTES-1) 254 255 .text 256 .set noreorder 257 #ifndef CONFIG_CPU_DADDI_WORKAROUNDS 258 .set noat 259 #else 260 .set at=v1 261 #endif 262 263 .align 5 264 265 /* 266 * Macro to build the __copy_user common code 267 * Arguments: 268 * mode : LEGACY_MODE or EVA_MODE 269 * from : Source operand. USEROP or KERNELOP 270 * to : Destination operand. USEROP or KERNELOP 271 */ 272 .macro __BUILD_COPY_USER mode, from, to 273 274 /* initialize __memcpy if this the first time we execute this macro */ 275 .ifnotdef __memcpy 276 .set __memcpy, 1 277 .hidden __memcpy /* make sure it does not leak */ 278 .endif 279 280 /* 281 * Note: dst & src may be unaligned, len may be 0 282 * Temps 283 */ 284 #define rem t8 285 286 R10KCBARRIER(0(ra)) 287 /* 288 * The "issue break"s below are very approximate. 289 * Issue delays for dcache fills will perturb the schedule, as will 290 * load queue full replay traps, etc. 291 * 292 * If len < NBYTES use byte operations. 293 */ 294 PREFS( 0, 0(src) ) 295 PREFD( 1, 0(dst) ) 296 sltu t2, len, NBYTES 297 and t1, dst, ADDRMASK 298 PREFS( 0, 1*32(src) ) 299 PREFD( 1, 1*32(dst) ) 300 bnez t2, .Lcopy_bytes_checklen\@ 301 and t0, src, ADDRMASK 302 PREFS( 0, 2*32(src) ) 303 PREFD( 1, 2*32(dst) ) 304 #ifndef CONFIG_CPU_NO_LOAD_STORE_LR 305 bnez t1, .Ldst_unaligned\@ 306 nop 307 bnez t0, .Lsrc_unaligned_dst_aligned\@ 308 #else /* CONFIG_CPU_NO_LOAD_STORE_LR */ 309 or t0, t0, t1 310 bnez t0, .Lcopy_unaligned_bytes\@ 311 #endif /* CONFIG_CPU_NO_LOAD_STORE_LR */ 312 /* 313 * use delay slot for fall-through 314 * src and dst are aligned; need to compute rem 315 */ 316 .Lboth_aligned\@: 317 SRL t0, len, LOG_NBYTES+3 # +3 for 8 units/iter 318 beqz t0, .Lcleanup_both_aligned\@ # len < 8*NBYTES 319 and rem, len, (8*NBYTES-1) # rem = len % (8*NBYTES) 320 PREFS( 0, 3*32(src) ) 321 PREFD( 1, 3*32(dst) ) 322 .align 4 323 1: 324 R10KCBARRIER(0(ra)) 325 LOAD(t0, UNIT(0)(src), .Ll_exc\@) 326 LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@) 327 LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@) 328 LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@) 329 SUB len, len, 8*NBYTES 330 LOAD(t4, UNIT(4)(src), .Ll_exc_copy\@) 331 LOAD(t7, UNIT(5)(src), .Ll_exc_copy\@) 332 STORE(t0, UNIT(0)(dst), .Ls_exc_p8u\@) 333 STORE(t1, UNIT(1)(dst), .Ls_exc_p7u\@) 334 LOAD(t0, UNIT(6)(src), .Ll_exc_copy\@) 335 LOAD(t1, UNIT(7)(src), .Ll_exc_copy\@) 336 ADD src, src, 8*NBYTES 337 ADD dst, dst, 8*NBYTES 338 STORE(t2, UNIT(-6)(dst), .Ls_exc_p6u\@) 339 STORE(t3, UNIT(-5)(dst), .Ls_exc_p5u\@) 340 STORE(t4, UNIT(-4)(dst), .Ls_exc_p4u\@) 341 STORE(t7, UNIT(-3)(dst), .Ls_exc_p3u\@) 342 STORE(t0, UNIT(-2)(dst), .Ls_exc_p2u\@) 343 STORE(t1, UNIT(-1)(dst), .Ls_exc_p1u\@) 344 PREFS( 0, 8*32(src) ) 345 PREFD( 1, 8*32(dst) ) 346 bne len, rem, 1b 347 nop 348 349 /* 350 * len == rem == the number of bytes left to copy < 8*NBYTES 351 */ 352 .Lcleanup_both_aligned\@: 353 beqz len, .Ldone\@ 354 sltu t0, len, 4*NBYTES 355 bnez t0, .Lless_than_4units\@ 356 and rem, len, (NBYTES-1) # rem = len % NBYTES 357 /* 358 * len >= 4*NBYTES 359 */ 360 LOAD( t0, UNIT(0)(src), .Ll_exc\@) 361 LOAD( t1, UNIT(1)(src), .Ll_exc_copy\@) 362 LOAD( t2, UNIT(2)(src), .Ll_exc_copy\@) 363 LOAD( t3, UNIT(3)(src), .Ll_exc_copy\@) 364 SUB len, len, 4*NBYTES 365 ADD src, src, 4*NBYTES 366 R10KCBARRIER(0(ra)) 367 STORE(t0, UNIT(0)(dst), .Ls_exc_p4u\@) 368 STORE(t1, UNIT(1)(dst), .Ls_exc_p3u\@) 369 STORE(t2, UNIT(2)(dst), .Ls_exc_p2u\@) 370 STORE(t3, UNIT(3)(dst), .Ls_exc_p1u\@) 371 .set reorder /* DADDI_WAR */ 372 ADD dst, dst, 4*NBYTES 373 beqz len, .Ldone\@ 374 .set noreorder 375 .Lless_than_4units\@: 376 /* 377 * rem = len % NBYTES 378 */ 379 beq rem, len, .Lcopy_bytes\@ 380 nop 381 1: 382 R10KCBARRIER(0(ra)) 383 LOAD(t0, 0(src), .Ll_exc\@) 384 ADD src, src, NBYTES 385 SUB len, len, NBYTES 386 STORE(t0, 0(dst), .Ls_exc_p1u\@) 387 .set reorder /* DADDI_WAR */ 388 ADD dst, dst, NBYTES 389 bne rem, len, 1b 390 .set noreorder 391 392 #ifndef CONFIG_CPU_NO_LOAD_STORE_LR 393 /* 394 * src and dst are aligned, need to copy rem bytes (rem < NBYTES) 395 * A loop would do only a byte at a time with possible branch 396 * mispredicts. Can't do an explicit LOAD dst,mask,or,STORE 397 * because can't assume read-access to dst. Instead, use 398 * STREST dst, which doesn't require read access to dst. 399 * 400 * This code should perform better than a simple loop on modern, 401 * wide-issue mips processors because the code has fewer branches and 402 * more instruction-level parallelism. 403 */ 404 #define bits t2 405 beqz len, .Ldone\@ 406 ADD t1, dst, len # t1 is just past last byte of dst 407 li bits, 8*NBYTES 408 SLL rem, len, 3 # rem = number of bits to keep 409 LOAD(t0, 0(src), .Ll_exc\@) 410 SUB bits, bits, rem # bits = number of bits to discard 411 SHIFT_DISCARD t0, t0, bits 412 STREST(t0, -1(t1), .Ls_exc\@) 413 jr ra 414 move len, zero 415 .Ldst_unaligned\@: 416 /* 417 * dst is unaligned 418 * t0 = src & ADDRMASK 419 * t1 = dst & ADDRMASK; T1 > 0 420 * len >= NBYTES 421 * 422 * Copy enough bytes to align dst 423 * Set match = (src and dst have same alignment) 424 */ 425 #define match rem 426 LDFIRST(t3, FIRST(0)(src), .Ll_exc\@) 427 ADD t2, zero, NBYTES 428 LDREST(t3, REST(0)(src), .Ll_exc_copy\@) 429 SUB t2, t2, t1 # t2 = number of bytes copied 430 xor match, t0, t1 431 R10KCBARRIER(0(ra)) 432 STFIRST(t3, FIRST(0)(dst), .Ls_exc\@) 433 beq len, t2, .Ldone\@ 434 SUB len, len, t2 435 ADD dst, dst, t2 436 beqz match, .Lboth_aligned\@ 437 ADD src, src, t2 438 439 .Lsrc_unaligned_dst_aligned\@: 440 SRL t0, len, LOG_NBYTES+2 # +2 for 4 units/iter 441 PREFS( 0, 3*32(src) ) 442 beqz t0, .Lcleanup_src_unaligned\@ 443 and rem, len, (4*NBYTES-1) # rem = len % 4*NBYTES 444 PREFD( 1, 3*32(dst) ) 445 1: 446 /* 447 * Avoid consecutive LD*'s to the same register since some mips 448 * implementations can't issue them in the same cycle. 449 * It's OK to load FIRST(N+1) before REST(N) because the two addresses 450 * are to the same unit (unless src is aligned, but it's not). 451 */ 452 R10KCBARRIER(0(ra)) 453 LDFIRST(t0, FIRST(0)(src), .Ll_exc\@) 454 LDFIRST(t1, FIRST(1)(src), .Ll_exc_copy\@) 455 SUB len, len, 4*NBYTES 456 LDREST(t0, REST(0)(src), .Ll_exc_copy\@) 457 LDREST(t1, REST(1)(src), .Ll_exc_copy\@) 458 LDFIRST(t2, FIRST(2)(src), .Ll_exc_copy\@) 459 LDFIRST(t3, FIRST(3)(src), .Ll_exc_copy\@) 460 LDREST(t2, REST(2)(src), .Ll_exc_copy\@) 461 LDREST(t3, REST(3)(src), .Ll_exc_copy\@) 462 PREFS( 0, 9*32(src) ) # 0 is PREF_LOAD (not streamed) 463 ADD src, src, 4*NBYTES 464 #ifdef CONFIG_CPU_SB1 465 nop # improves slotting 466 #endif 467 STORE(t0, UNIT(0)(dst), .Ls_exc_p4u\@) 468 STORE(t1, UNIT(1)(dst), .Ls_exc_p3u\@) 469 STORE(t2, UNIT(2)(dst), .Ls_exc_p2u\@) 470 STORE(t3, UNIT(3)(dst), .Ls_exc_p1u\@) 471 PREFD( 1, 9*32(dst) ) # 1 is PREF_STORE (not streamed) 472 .set reorder /* DADDI_WAR */ 473 ADD dst, dst, 4*NBYTES 474 bne len, rem, 1b 475 .set noreorder 476 477 .Lcleanup_src_unaligned\@: 478 beqz len, .Ldone\@ 479 and rem, len, NBYTES-1 # rem = len % NBYTES 480 beq rem, len, .Lcopy_bytes\@ 481 nop 482 1: 483 R10KCBARRIER(0(ra)) 484 LDFIRST(t0, FIRST(0)(src), .Ll_exc\@) 485 LDREST(t0, REST(0)(src), .Ll_exc_copy\@) 486 ADD src, src, NBYTES 487 SUB len, len, NBYTES 488 STORE(t0, 0(dst), .Ls_exc_p1u\@) 489 .set reorder /* DADDI_WAR */ 490 ADD dst, dst, NBYTES 491 bne len, rem, 1b 492 .set noreorder 493 494 #endif /* !CONFIG_CPU_NO_LOAD_STORE_LR */ 495 .Lcopy_bytes_checklen\@: 496 beqz len, .Ldone\@ 497 nop 498 .Lcopy_bytes\@: 499 /* 0 < len < NBYTES */ 500 R10KCBARRIER(0(ra)) 501 #define COPY_BYTE(N) \ 502 LOADB(t0, N(src), .Ll_exc\@); \ 503 SUB len, len, 1; \ 504 beqz len, .Ldone\@; \ 505 STOREB(t0, N(dst), .Ls_exc_p1\@) 506 507 COPY_BYTE(0) 508 COPY_BYTE(1) 509 #ifdef USE_DOUBLE 510 COPY_BYTE(2) 511 COPY_BYTE(3) 512 COPY_BYTE(4) 513 COPY_BYTE(5) 514 #endif 515 LOADB(t0, NBYTES-2(src), .Ll_exc\@) 516 SUB len, len, 1 517 jr ra 518 STOREB(t0, NBYTES-2(dst), .Ls_exc_p1\@) 519 .Ldone\@: 520 jr ra 521 nop 522 523 #ifdef CONFIG_CPU_NO_LOAD_STORE_LR 524 .Lcopy_unaligned_bytes\@: 525 1: 526 COPY_BYTE(0) 527 COPY_BYTE(1) 528 COPY_BYTE(2) 529 COPY_BYTE(3) 530 COPY_BYTE(4) 531 COPY_BYTE(5) 532 COPY_BYTE(6) 533 COPY_BYTE(7) 534 ADD src, src, 8 535 b 1b 536 ADD dst, dst, 8 537 #endif /* CONFIG_CPU_NO_LOAD_STORE_LR */ 538 .if __memcpy == 1 539 END(memcpy) 540 .set __memcpy, 0 541 .hidden __memcpy 542 .endif 543 544 .Ll_exc_copy\@: 545 /* 546 * Copy bytes from src until faulting load address (or until a 547 * lb faults) 548 * 549 * When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28) 550 * may be more than a byte beyond the last address. 551 * Hence, the lb below may get an exception. 552 * 553 * Assumes src < THREAD_BUADDR($28) 554 */ 555 LOADK t0, TI_TASK($28) 556 nop 557 LOADK t0, THREAD_BUADDR(t0) 558 1: 559 LOADB(t1, 0(src), .Ll_exc\@) 560 ADD src, src, 1 561 sb t1, 0(dst) # can't fault -- we're copy_from_user 562 .set reorder /* DADDI_WAR */ 563 ADD dst, dst, 1 564 bne src, t0, 1b 565 .set noreorder 566 .Ll_exc\@: 567 LOADK t0, TI_TASK($28) 568 nop 569 LOADK t0, THREAD_BUADDR(t0) # t0 is just past last good address 570 nop 571 SUB len, AT, t0 # len number of uncopied bytes 572 jr ra 573 nop 574 575 #define SEXC(n) \ 576 .set reorder; /* DADDI_WAR */ \ 577 .Ls_exc_p ## n ## u\@: \ 578 ADD len, len, n*NBYTES; \ 579 jr ra; \ 580 .set noreorder 581 582 SEXC(8) 583 SEXC(7) 584 SEXC(6) 585 SEXC(5) 586 SEXC(4) 587 SEXC(3) 588 SEXC(2) 589 SEXC(1) 590 591 .Ls_exc_p1\@: 592 .set reorder /* DADDI_WAR */ 593 ADD len, len, 1 594 jr ra 595 .set noreorder 596 .Ls_exc\@: 597 jr ra 598 nop 599 .endm 600 601 #ifndef CONFIG_HAVE_PLAT_MEMCPY 602 .align 5 603 LEAF(memmove) 604 EXPORT_SYMBOL(memmove) 605 ADD t0, a0, a2 606 ADD t1, a1, a2 607 sltu t0, a1, t0 # dst + len <= src -> memcpy 608 sltu t1, a0, t1 # dst >= src + len -> memcpy 609 and t0, t1 610 beqz t0, .L__memcpy 611 move v0, a0 /* return value */ 612 beqz a2, .Lr_out 613 END(memmove) 614 615 /* fall through to __rmemcpy */ 616 LEAF(__rmemcpy) /* a0=dst a1=src a2=len */ 617 sltu t0, a1, a0 618 beqz t0, .Lr_end_bytes_up # src >= dst 619 nop 620 ADD a0, a2 # dst = dst + len 621 ADD a1, a2 # src = src + len 622 623 .Lr_end_bytes: 624 R10KCBARRIER(0(ra)) 625 lb t0, -1(a1) 626 SUB a2, a2, 0x1 627 sb t0, -1(a0) 628 SUB a1, a1, 0x1 629 .set reorder /* DADDI_WAR */ 630 SUB a0, a0, 0x1 631 bnez a2, .Lr_end_bytes 632 .set noreorder 633 634 .Lr_out: 635 jr ra 636 move a2, zero 637 638 .Lr_end_bytes_up: 639 R10KCBARRIER(0(ra)) 640 lb t0, (a1) 641 SUB a2, a2, 0x1 642 sb t0, (a0) 643 ADD a1, a1, 0x1 644 .set reorder /* DADDI_WAR */ 645 ADD a0, a0, 0x1 646 bnez a2, .Lr_end_bytes_up 647 .set noreorder 648 649 jr ra 650 move a2, zero 651 END(__rmemcpy) 652 653 /* 654 * A combined memcpy/__copy_user 655 * __copy_user sets len to 0 for success; else to an upper bound of 656 * the number of uncopied bytes. 657 * memcpy sets v0 to dst. 658 */ 659 .align 5 660 LEAF(memcpy) /* a0=dst a1=src a2=len */ 661 EXPORT_SYMBOL(memcpy) 662 move v0, dst /* return value */ 663 .L__memcpy: 664 #ifndef CONFIG_EVA 665 FEXPORT(__raw_copy_from_user) 666 EXPORT_SYMBOL(__raw_copy_from_user) 667 FEXPORT(__raw_copy_to_user) 668 EXPORT_SYMBOL(__raw_copy_to_user) 669 #endif 670 /* Legacy Mode, user <-> user */ 671 __BUILD_COPY_USER LEGACY_MODE USEROP USEROP 672 673 #endif 674 675 #ifdef CONFIG_EVA 676 677 /* 678 * For EVA we need distinct symbols for reading and writing to user space. 679 * This is because we need to use specific EVA instructions to perform the 680 * virtual <-> physical translation when a virtual address is actually in user 681 * space 682 */ 683 684 /* 685 * __copy_from_user (EVA) 686 */ 687 688 LEAF(__raw_copy_from_user) 689 EXPORT_SYMBOL(__raw_copy_from_user) 690 __BUILD_COPY_USER EVA_MODE USEROP KERNELOP 691 END(__raw_copy_from_user) 692 693 694 695 /* 696 * __copy_to_user (EVA) 697 */ 698 699 LEAF(__raw_copy_to_user) 700 EXPORT_SYMBOL(__raw_copy_to_user) 701 __BUILD_COPY_USER EVA_MODE KERNELOP USEROP 702 END(__raw_copy_to_user) 703 704 #endif 705