Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_CMPXCHG_H_ #define _ASM_POWERPC_CMPXCHG_H_ #ifdef __KERNEL__ #include <linux/compiler.h> #include <asm/synch.h> #include <linux/bug.h> #ifdef __BIG_ENDIAN #define BITOFF_CAL(size, off) ((sizeof(u32) - size - off) * BITS_PER_BYTE) #else #define BITOFF_CAL(size, off) (off * BITS_PER_BYTE) #endif #define XCHG_GEN(type, sfx, cl) \ static inline u32 __xchg_##type##sfx(volatile void *p, u32 val) \ { \ unsigned int prev, prev_mask, tmp, bitoff, off; \ \ off = (unsigned long)p % sizeof(u32); \ bitoff = BITOFF_CAL(sizeof(type), off); \ p -= off; \ val <<= bitoff; \ prev_mask = (u32)(type)-1 << bitoff; \ \ __asm__ __volatile__( \ "1: lwarx %0,0,%3\n" \ " andc %1,%0,%5\n" \ " or %1,%1,%4\n" \ " stwcx. %1,0,%3\n" \ " bne- 1b\n" \ : "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p) \ : "r" (p), "r" (val), "r" (prev_mask) \ : "cc", cl); \ \ return prev >> bitoff; \ } #define CMPXCHG_GEN(type, sfx, br, br2, cl) \ static inline \ u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new) \ { \ unsigned int prev, prev_mask, tmp, bitoff, off; \ \ off = (unsigned long)p % sizeof(u32); \ bitoff = BITOFF_CAL(sizeof(type), off); \ p -= off; \ old <<= bitoff; \ new <<= bitoff; \ prev_mask = (u32)(type)-1 << bitoff; \ \ __asm__ __volatile__( \ br \ "1: lwarx %0,0,%3\n" \ " and %1,%0,%6\n" \ " cmpw 0,%1,%4\n" \ " bne- 2f\n" \ " andc %1,%0,%6\n" \ " or %1,%1,%5\n" \ " stwcx. %1,0,%3\n" \ " bne- 1b\n" \ br2 \ "\n" \ "2:" \ : "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p) \ : "r" (p), "r" (old), "r" (new), "r" (prev_mask) \ : "cc", cl); \ \ return prev >> bitoff; \ } /* * Atomic exchange * * Changes the memory location '*p' to be val and returns * the previous value stored there. */ XCHG_GEN(u8, _local, "memory"); XCHG_GEN(u8, _relaxed, "cc"); XCHG_GEN(u16, _local, "memory"); XCHG_GEN(u16, _relaxed, "cc"); static __always_inline unsigned long __xchg_u32_local(volatile void *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( "1: lwarx %0,0,%2 \n" " stwcx. %3,0,%2 \n\ bne- 1b" : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); return prev; } static __always_inline unsigned long __xchg_u32_relaxed(u32 *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( "1: lwarx %0,0,%2\n" " stwcx. %3,0,%2\n" " bne- 1b" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (val) : "cc"); return prev; } #ifdef CONFIG_PPC64 static __always_inline unsigned long __xchg_u64_local(volatile void *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( "1: ldarx %0,0,%2 \n" " stdcx. %3,0,%2 \n\ bne- 1b" : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); return prev; } static __always_inline unsigned long __xchg_u64_relaxed(u64 *p, unsigned long val) { unsigned long prev; __asm__ __volatile__( "1: ldarx %0,0,%2\n" " stdcx. %3,0,%2\n" " bne- 1b" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (val) : "cc"); return prev; } #endif static __always_inline unsigned long __xchg_local(void *ptr, unsigned long x, unsigned int size) { switch (size) { case 1: return __xchg_u8_local(ptr, x); case 2: return __xchg_u16_local(ptr, x); case 4: return __xchg_u32_local(ptr, x); #ifdef CONFIG_PPC64 case 8: return __xchg_u64_local(ptr, x); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg"); return x; } static __always_inline unsigned long __xchg_relaxed(void *ptr, unsigned long x, unsigned int size) { switch (size) { case 1: return __xchg_u8_relaxed(ptr, x); case 2: return __xchg_u16_relaxed(ptr, x); case 4: return __xchg_u32_relaxed(ptr, x); #ifdef CONFIG_PPC64 case 8: return __xchg_u64_relaxed(ptr, x); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); return x; } #define xchg_local(ptr,x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ (__typeof__(*(ptr))) __xchg_local((ptr), \ (unsigned long)_x_, sizeof(*(ptr))); \ }) #define xchg_relaxed(ptr, x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ (__typeof__(*(ptr))) __xchg_relaxed((ptr), \ (unsigned long)_x_, sizeof(*(ptr))); \ }) /* * Compare and exchange - if *p == old, set it to new, * and return the old value of *p. */ CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory"); CMPXCHG_GEN(u8, _local, , , "memory"); CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory"); CMPXCHG_GEN(u8, _relaxed, , , "cc"); CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory"); CMPXCHG_GEN(u16, _local, , , "memory"); CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory"); CMPXCHG_GEN(u16, _relaxed, , , "cc"); static __always_inline unsigned long __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) { unsigned int prev; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" " stwcx. %4,0,%2\n\ bne- 1b" PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } static __always_inline unsigned long __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old, unsigned long new) { unsigned int prev; __asm__ __volatile__ ( "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" " stwcx. %4,0,%2\n\ bne- 1b" "\n\ 2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } static __always_inline unsigned long __cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( "1: lwarx %0,0,%2 # __cmpxchg_u32_relaxed\n" " cmpw 0,%0,%3\n" " bne- 2f\n" " stwcx. %4,0,%2\n" " bne- 1b\n" "2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc"); return prev; } /* * cmpxchg family don't have order guarantee if cmp part fails, therefore we * can avoid superfluous barriers if we use assembly code to implement * cmpxchg() and cmpxchg_acquire(), however we don't do the similar for * cmpxchg_release() because that will result in putting a barrier in the * middle of a ll/sc loop, which is probably a bad idea. For example, this * might cause the conditional store more likely to fail. */ static __always_inline unsigned long __cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( "1: lwarx %0,0,%2 # __cmpxchg_u32_acquire\n" " cmpw 0,%0,%3\n" " bne- 2f\n" " stwcx. %4,0,%2\n" " bne- 1b\n" PPC_ACQUIRE_BARRIER "\n" "2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } #ifdef CONFIG_PPC64 static __always_inline unsigned long __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } static __always_inline unsigned long __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" "\n\ 2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } static __always_inline unsigned long __cmpxchg_u64_relaxed(u64 *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( "1: ldarx %0,0,%2 # __cmpxchg_u64_relaxed\n" " cmpd 0,%0,%3\n" " bne- 2f\n" " stdcx. %4,0,%2\n" " bne- 1b\n" "2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc"); return prev; } static __always_inline unsigned long __cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new) { unsigned long prev; __asm__ __volatile__ ( "1: ldarx %0,0,%2 # __cmpxchg_u64_acquire\n" " cmpd 0,%0,%3\n" " bne- 2f\n" " stdcx. %4,0,%2\n" " bne- 1b\n" PPC_ACQUIRE_BARRIER "\n" "2:" : "=&r" (prev), "+m" (*p) : "r" (p), "r" (old), "r" (new) : "cc", "memory"); return prev; } #endif static __always_inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { case 1: return __cmpxchg_u8(ptr, old, new); case 2: return __cmpxchg_u16(ptr, old, new); case 4: return __cmpxchg_u32(ptr, old, new); #ifdef CONFIG_PPC64 case 8: return __cmpxchg_u64(ptr, old, new); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg"); return old; } static __always_inline unsigned long __cmpxchg_local(void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { case 1: return __cmpxchg_u8_local(ptr, old, new); case 2: return __cmpxchg_u16_local(ptr, old, new); case 4: return __cmpxchg_u32_local(ptr, old, new); #ifdef CONFIG_PPC64 case 8: return __cmpxchg_u64_local(ptr, old, new); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_local"); return old; } static __always_inline unsigned long __cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { case 1: return __cmpxchg_u8_relaxed(ptr, old, new); case 2: return __cmpxchg_u16_relaxed(ptr, old, new); case 4: return __cmpxchg_u32_relaxed(ptr, old, new); #ifdef CONFIG_PPC64 case 8: return __cmpxchg_u64_relaxed(ptr, old, new); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_relaxed"); return old; } static __always_inline unsigned long __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { case 1: return __cmpxchg_u8_acquire(ptr, old, new); case 2: return __cmpxchg_u16_acquire(ptr, old, new); case 4: return __cmpxchg_u32_acquire(ptr, old, new); #ifdef CONFIG_PPC64 case 8: return __cmpxchg_u64_acquire(ptr, old, new); #endif } BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_acquire"); return old; } #define cmpxchg(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_, \ (unsigned long)_n_, sizeof(*(ptr))); \ }) #define cmpxchg_local(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_, \ (unsigned long)_n_, sizeof(*(ptr))); \ }) #define cmpxchg_relaxed(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ (__typeof__(*(ptr))) __cmpxchg_relaxed((ptr), \ (unsigned long)_o_, (unsigned long)_n_, \ sizeof(*(ptr))); \ }) #define cmpxchg_acquire(ptr, o, n) \ ({ \ __typeof__(*(ptr)) _o_ = (o); \ __typeof__(*(ptr)) _n_ = (n); \ (__typeof__(*(ptr))) __cmpxchg_acquire((ptr), \ (unsigned long)_o_, (unsigned long)_n_, \ sizeof(*(ptr))); \ }) #ifdef CONFIG_PPC64 #define cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg((ptr), (o), (n)); \ }) #define cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_local((ptr), (o), (n)); \ }) #define cmpxchg64_relaxed(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_relaxed((ptr), (o), (n)); \ }) #define cmpxchg64_acquire(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_acquire((ptr), (o), (n)); \ }) #else #include <asm-generic/cmpxchg-local.h> #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) #endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_CMPXCHG_H_ */ |