rjw | 1f88458 | 2022-01-06 17:20:42 +0800 | [diff] [blame^] | 1 | /* |
| 2 | * address space "slices" (meta-segments) support |
| 3 | * |
| 4 | * Copyright (C) 2007 Benjamin Herrenschmidt, IBM Corporation. |
| 5 | * |
| 6 | * Based on hugetlb implementation |
| 7 | * |
| 8 | * Copyright (C) 2003 David Gibson, IBM Corporation. |
| 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 as published by |
| 12 | * the Free Software Foundation; either version 2 of the License, or |
| 13 | * (at your option) any later version. |
| 14 | * |
| 15 | * This program is distributed in the hope that it will be useful, |
| 16 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 17 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 18 | * GNU General Public License for more details. |
| 19 | * |
| 20 | * You should have received a copy of the GNU General Public License |
| 21 | * along with this program; if not, write to the Free Software |
| 22 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
| 23 | */ |
| 24 | |
| 25 | #undef DEBUG |
| 26 | |
| 27 | #include <linux/kernel.h> |
| 28 | #include <linux/mm.h> |
| 29 | #include <linux/pagemap.h> |
| 30 | #include <linux/err.h> |
| 31 | #include <linux/spinlock.h> |
| 32 | #include <linux/export.h> |
| 33 | #include <linux/hugetlb.h> |
| 34 | #include <linux/security.h> |
| 35 | #include <asm/mman.h> |
| 36 | #include <asm/mmu.h> |
| 37 | #include <asm/copro.h> |
| 38 | #include <asm/hugetlb.h> |
| 39 | |
| 40 | static DEFINE_SPINLOCK(slice_convert_lock); |
| 41 | /* |
| 42 | * One bit per slice. We have lower slices which cover 256MB segments |
| 43 | * upto 4G range. That gets us 16 low slices. For the rest we track slices |
| 44 | * in 1TB size. |
| 45 | */ |
| 46 | struct slice_mask { |
| 47 | u64 low_slices; |
| 48 | DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH); |
| 49 | }; |
| 50 | |
| 51 | #ifdef DEBUG |
| 52 | int _slice_debug = 1; |
| 53 | |
| 54 | static void slice_print_mask(const char *label, struct slice_mask mask) |
| 55 | { |
| 56 | if (!_slice_debug) |
| 57 | return; |
| 58 | pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices); |
| 59 | pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices); |
| 60 | } |
| 61 | |
| 62 | #define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0) |
| 63 | |
| 64 | #else |
| 65 | |
| 66 | static void slice_print_mask(const char *label, struct slice_mask mask) {} |
| 67 | #define slice_dbg(fmt...) |
| 68 | |
| 69 | #endif |
| 70 | |
| 71 | static void slice_range_to_mask(unsigned long start, unsigned long len, |
| 72 | struct slice_mask *ret) |
| 73 | { |
| 74 | unsigned long end = start + len - 1; |
| 75 | |
| 76 | ret->low_slices = 0; |
| 77 | if (SLICE_NUM_HIGH) |
| 78 | bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); |
| 79 | |
| 80 | if (start < SLICE_LOW_TOP) { |
| 81 | unsigned long mend = min(end, |
| 82 | (unsigned long)(SLICE_LOW_TOP - 1)); |
| 83 | |
| 84 | ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1)) |
| 85 | - (1u << GET_LOW_SLICE_INDEX(start)); |
| 86 | } |
| 87 | |
| 88 | if ((start + len) > SLICE_LOW_TOP) { |
| 89 | unsigned long start_index = GET_HIGH_SLICE_INDEX(start); |
| 90 | unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT)); |
| 91 | unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index; |
| 92 | |
| 93 | bitmap_set(ret->high_slices, start_index, count); |
| 94 | } |
| 95 | } |
| 96 | |
| 97 | static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, |
| 98 | unsigned long len) |
| 99 | { |
| 100 | struct vm_area_struct *vma; |
| 101 | |
| 102 | if ((mm->context.addr_limit - len) < addr) |
| 103 | return 0; |
| 104 | vma = find_vma(mm, addr); |
| 105 | return (!vma || (addr + len) <= vm_start_gap(vma)); |
| 106 | } |
| 107 | |
| 108 | static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice) |
| 109 | { |
| 110 | return !slice_area_is_free(mm, slice << SLICE_LOW_SHIFT, |
| 111 | 1ul << SLICE_LOW_SHIFT); |
| 112 | } |
| 113 | |
| 114 | static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice) |
| 115 | { |
| 116 | unsigned long start = slice << SLICE_HIGH_SHIFT; |
| 117 | unsigned long end = start + (1ul << SLICE_HIGH_SHIFT); |
| 118 | |
| 119 | #ifdef CONFIG_PPC64 |
| 120 | /* Hack, so that each addresses is controlled by exactly one |
| 121 | * of the high or low area bitmaps, the first high area starts |
| 122 | * at 4GB, not 0 */ |
| 123 | if (start == 0) |
| 124 | start = SLICE_LOW_TOP; |
| 125 | #endif |
| 126 | |
| 127 | return !slice_area_is_free(mm, start, end - start); |
| 128 | } |
| 129 | |
| 130 | static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret) |
| 131 | { |
| 132 | unsigned long i; |
| 133 | |
| 134 | ret->low_slices = 0; |
| 135 | if (SLICE_NUM_HIGH) |
| 136 | bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); |
| 137 | |
| 138 | for (i = 0; i < SLICE_NUM_LOW; i++) |
| 139 | if (!slice_low_has_vma(mm, i)) |
| 140 | ret->low_slices |= 1u << i; |
| 141 | |
| 142 | if (mm->context.addr_limit <= SLICE_LOW_TOP) |
| 143 | return; |
| 144 | |
| 145 | for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) |
| 146 | if (!slice_high_has_vma(mm, i)) |
| 147 | __set_bit(i, ret->high_slices); |
| 148 | } |
| 149 | |
| 150 | static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret) |
| 151 | { |
| 152 | unsigned char *hpsizes; |
| 153 | int index, mask_index; |
| 154 | unsigned long i; |
| 155 | u64 lpsizes; |
| 156 | |
| 157 | ret->low_slices = 0; |
| 158 | if (SLICE_NUM_HIGH) |
| 159 | bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); |
| 160 | |
| 161 | lpsizes = mm->context.low_slices_psize; |
| 162 | for (i = 0; i < SLICE_NUM_LOW; i++) |
| 163 | if (((lpsizes >> (i * 4)) & 0xf) == psize) |
| 164 | ret->low_slices |= 1u << i; |
| 165 | |
| 166 | hpsizes = mm->context.high_slices_psize; |
| 167 | for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) { |
| 168 | mask_index = i & 0x1; |
| 169 | index = i >> 1; |
| 170 | if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize) |
| 171 | __set_bit(i, ret->high_slices); |
| 172 | } |
| 173 | } |
| 174 | |
| 175 | static int slice_check_fit(struct mm_struct *mm, |
| 176 | struct slice_mask mask, struct slice_mask available) |
| 177 | { |
| 178 | DECLARE_BITMAP(result, SLICE_NUM_HIGH); |
| 179 | unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.addr_limit); |
| 180 | |
| 181 | if (!SLICE_NUM_HIGH) |
| 182 | return (mask.low_slices & available.low_slices) == |
| 183 | mask.low_slices; |
| 184 | |
| 185 | bitmap_and(result, mask.high_slices, |
| 186 | available.high_slices, slice_count); |
| 187 | |
| 188 | return (mask.low_slices & available.low_slices) == mask.low_slices && |
| 189 | bitmap_equal(result, mask.high_slices, slice_count); |
| 190 | } |
| 191 | |
| 192 | static void slice_flush_segments(void *parm) |
| 193 | { |
| 194 | #ifdef CONFIG_PPC64 |
| 195 | struct mm_struct *mm = parm; |
| 196 | unsigned long flags; |
| 197 | |
| 198 | if (mm != current->active_mm) |
| 199 | return; |
| 200 | |
| 201 | copy_mm_to_paca(current->active_mm); |
| 202 | |
| 203 | local_irq_save(flags); |
| 204 | slb_flush_and_rebolt(); |
| 205 | local_irq_restore(flags); |
| 206 | #endif |
| 207 | } |
| 208 | |
| 209 | static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize) |
| 210 | { |
| 211 | int index, mask_index; |
| 212 | /* Write the new slice psize bits */ |
| 213 | unsigned char *hpsizes; |
| 214 | u64 lpsizes; |
| 215 | unsigned long i, flags; |
| 216 | |
| 217 | slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize); |
| 218 | slice_print_mask(" mask", mask); |
| 219 | |
| 220 | /* We need to use a spinlock here to protect against |
| 221 | * concurrent 64k -> 4k demotion ... |
| 222 | */ |
| 223 | spin_lock_irqsave(&slice_convert_lock, flags); |
| 224 | |
| 225 | lpsizes = mm->context.low_slices_psize; |
| 226 | for (i = 0; i < SLICE_NUM_LOW; i++) |
| 227 | if (mask.low_slices & (1u << i)) |
| 228 | lpsizes = (lpsizes & ~(0xful << (i * 4))) | |
| 229 | (((unsigned long)psize) << (i * 4)); |
| 230 | |
| 231 | /* Assign the value back */ |
| 232 | mm->context.low_slices_psize = lpsizes; |
| 233 | |
| 234 | hpsizes = mm->context.high_slices_psize; |
| 235 | for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) { |
| 236 | mask_index = i & 0x1; |
| 237 | index = i >> 1; |
| 238 | if (test_bit(i, mask.high_slices)) |
| 239 | hpsizes[index] = (hpsizes[index] & |
| 240 | ~(0xf << (mask_index * 4))) | |
| 241 | (((unsigned long)psize) << (mask_index * 4)); |
| 242 | } |
| 243 | |
| 244 | slice_dbg(" lsps=%lx, hsps=%lx\n", |
| 245 | (unsigned long)mm->context.low_slices_psize, |
| 246 | (unsigned long)mm->context.high_slices_psize); |
| 247 | |
| 248 | spin_unlock_irqrestore(&slice_convert_lock, flags); |
| 249 | |
| 250 | copro_flush_all_slbs(mm); |
| 251 | } |
| 252 | |
| 253 | /* |
| 254 | * Compute which slice addr is part of; |
| 255 | * set *boundary_addr to the start or end boundary of that slice |
| 256 | * (depending on 'end' parameter); |
| 257 | * return boolean indicating if the slice is marked as available in the |
| 258 | * 'available' slice_mark. |
| 259 | */ |
| 260 | static bool slice_scan_available(unsigned long addr, |
| 261 | struct slice_mask available, |
| 262 | int end, |
| 263 | unsigned long *boundary_addr) |
| 264 | { |
| 265 | unsigned long slice; |
| 266 | if (addr < SLICE_LOW_TOP) { |
| 267 | slice = GET_LOW_SLICE_INDEX(addr); |
| 268 | *boundary_addr = (slice + end) << SLICE_LOW_SHIFT; |
| 269 | return !!(available.low_slices & (1u << slice)); |
| 270 | } else { |
| 271 | slice = GET_HIGH_SLICE_INDEX(addr); |
| 272 | *boundary_addr = (slice + end) ? |
| 273 | ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; |
| 274 | return !!test_bit(slice, available.high_slices); |
| 275 | } |
| 276 | } |
| 277 | |
| 278 | static unsigned long slice_find_area_bottomup(struct mm_struct *mm, |
| 279 | unsigned long len, |
| 280 | struct slice_mask available, |
| 281 | int psize, unsigned long high_limit) |
| 282 | { |
| 283 | int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); |
| 284 | unsigned long addr, found, next_end; |
| 285 | struct vm_unmapped_area_info info; |
| 286 | |
| 287 | info.flags = 0; |
| 288 | info.length = len; |
| 289 | info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); |
| 290 | info.align_offset = 0; |
| 291 | |
| 292 | addr = TASK_UNMAPPED_BASE; |
| 293 | /* |
| 294 | * Check till the allow max value for this mmap request |
| 295 | */ |
| 296 | while (addr < high_limit) { |
| 297 | info.low_limit = addr; |
| 298 | if (!slice_scan_available(addr, available, 1, &addr)) |
| 299 | continue; |
| 300 | |
| 301 | next_slice: |
| 302 | /* |
| 303 | * At this point [info.low_limit; addr) covers |
| 304 | * available slices only and ends at a slice boundary. |
| 305 | * Check if we need to reduce the range, or if we can |
| 306 | * extend it to cover the next available slice. |
| 307 | */ |
| 308 | if (addr >= high_limit) |
| 309 | addr = high_limit; |
| 310 | else if (slice_scan_available(addr, available, 1, &next_end)) { |
| 311 | addr = next_end; |
| 312 | goto next_slice; |
| 313 | } |
| 314 | info.high_limit = addr; |
| 315 | |
| 316 | found = vm_unmapped_area(&info); |
| 317 | if (!(found & ~PAGE_MASK)) |
| 318 | return found; |
| 319 | } |
| 320 | |
| 321 | return -ENOMEM; |
| 322 | } |
| 323 | |
| 324 | static unsigned long slice_find_area_topdown(struct mm_struct *mm, |
| 325 | unsigned long len, |
| 326 | struct slice_mask available, |
| 327 | int psize, unsigned long high_limit) |
| 328 | { |
| 329 | int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); |
| 330 | unsigned long addr, found, prev; |
| 331 | struct vm_unmapped_area_info info; |
| 332 | unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr); |
| 333 | |
| 334 | info.flags = VM_UNMAPPED_AREA_TOPDOWN; |
| 335 | info.length = len; |
| 336 | info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); |
| 337 | info.align_offset = 0; |
| 338 | |
| 339 | addr = mm->mmap_base; |
| 340 | /* |
| 341 | * If we are trying to allocate above DEFAULT_MAP_WINDOW |
| 342 | * Add the different to the mmap_base. |
| 343 | * Only for that request for which high_limit is above |
| 344 | * DEFAULT_MAP_WINDOW we should apply this. |
| 345 | */ |
| 346 | if (high_limit > DEFAULT_MAP_WINDOW) |
| 347 | addr += mm->context.addr_limit - DEFAULT_MAP_WINDOW; |
| 348 | |
| 349 | while (addr > min_addr) { |
| 350 | info.high_limit = addr; |
| 351 | if (!slice_scan_available(addr - 1, available, 0, &addr)) |
| 352 | continue; |
| 353 | |
| 354 | prev_slice: |
| 355 | /* |
| 356 | * At this point [addr; info.high_limit) covers |
| 357 | * available slices only and starts at a slice boundary. |
| 358 | * Check if we need to reduce the range, or if we can |
| 359 | * extend it to cover the previous available slice. |
| 360 | */ |
| 361 | if (addr < min_addr) |
| 362 | addr = min_addr; |
| 363 | else if (slice_scan_available(addr - 1, available, 0, &prev)) { |
| 364 | addr = prev; |
| 365 | goto prev_slice; |
| 366 | } |
| 367 | info.low_limit = addr; |
| 368 | |
| 369 | found = vm_unmapped_area(&info); |
| 370 | if (!(found & ~PAGE_MASK)) |
| 371 | return found; |
| 372 | } |
| 373 | |
| 374 | /* |
| 375 | * A failed mmap() very likely causes application failure, |
| 376 | * so fall back to the bottom-up function here. This scenario |
| 377 | * can happen with large stack limits and large mmap() |
| 378 | * allocations. |
| 379 | */ |
| 380 | return slice_find_area_bottomup(mm, len, available, psize, high_limit); |
| 381 | } |
| 382 | |
| 383 | |
| 384 | static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, |
| 385 | struct slice_mask mask, int psize, |
| 386 | int topdown, unsigned long high_limit) |
| 387 | { |
| 388 | if (topdown) |
| 389 | return slice_find_area_topdown(mm, len, mask, psize, high_limit); |
| 390 | else |
| 391 | return slice_find_area_bottomup(mm, len, mask, psize, high_limit); |
| 392 | } |
| 393 | |
| 394 | static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src) |
| 395 | { |
| 396 | dst->low_slices |= src->low_slices; |
| 397 | if (!SLICE_NUM_HIGH) |
| 398 | return; |
| 399 | bitmap_or(dst->high_slices, dst->high_slices, src->high_slices, |
| 400 | SLICE_NUM_HIGH); |
| 401 | } |
| 402 | |
| 403 | static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src) |
| 404 | { |
| 405 | dst->low_slices &= ~src->low_slices; |
| 406 | |
| 407 | if (!SLICE_NUM_HIGH) |
| 408 | return; |
| 409 | bitmap_andnot(dst->high_slices, dst->high_slices, src->high_slices, |
| 410 | SLICE_NUM_HIGH); |
| 411 | } |
| 412 | |
| 413 | #ifdef CONFIG_PPC_64K_PAGES |
| 414 | #define MMU_PAGE_BASE MMU_PAGE_64K |
| 415 | #else |
| 416 | #define MMU_PAGE_BASE MMU_PAGE_4K |
| 417 | #endif |
| 418 | |
| 419 | unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, |
| 420 | unsigned long flags, unsigned int psize, |
| 421 | int topdown) |
| 422 | { |
| 423 | struct slice_mask mask; |
| 424 | struct slice_mask good_mask; |
| 425 | struct slice_mask potential_mask; |
| 426 | struct slice_mask compat_mask; |
| 427 | int fixed = (flags & MAP_FIXED); |
| 428 | int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); |
| 429 | unsigned long page_size = 1UL << pshift; |
| 430 | struct mm_struct *mm = current->mm; |
| 431 | unsigned long newaddr; |
| 432 | unsigned long high_limit; |
| 433 | |
| 434 | high_limit = DEFAULT_MAP_WINDOW; |
| 435 | if (addr >= high_limit || (fixed && (addr + len > high_limit))) |
| 436 | high_limit = TASK_SIZE; |
| 437 | |
| 438 | if (len > high_limit) |
| 439 | return -ENOMEM; |
| 440 | if (len & (page_size - 1)) |
| 441 | return -EINVAL; |
| 442 | if (fixed) { |
| 443 | if (addr & (page_size - 1)) |
| 444 | return -EINVAL; |
| 445 | if (addr > high_limit - len) |
| 446 | return -ENOMEM; |
| 447 | } |
| 448 | |
| 449 | if (high_limit > mm->context.addr_limit) { |
| 450 | mm->context.addr_limit = high_limit; |
| 451 | on_each_cpu(slice_flush_segments, mm, 1); |
| 452 | } |
| 453 | |
| 454 | /* |
| 455 | * init different masks |
| 456 | */ |
| 457 | mask.low_slices = 0; |
| 458 | |
| 459 | /* silence stupid warning */; |
| 460 | potential_mask.low_slices = 0; |
| 461 | |
| 462 | compat_mask.low_slices = 0; |
| 463 | |
| 464 | if (SLICE_NUM_HIGH) { |
| 465 | bitmap_zero(mask.high_slices, SLICE_NUM_HIGH); |
| 466 | bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH); |
| 467 | bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH); |
| 468 | } |
| 469 | |
| 470 | /* Sanity checks */ |
| 471 | BUG_ON(mm->task_size == 0); |
| 472 | BUG_ON(mm->context.addr_limit == 0); |
| 473 | VM_BUG_ON(radix_enabled()); |
| 474 | |
| 475 | slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize); |
| 476 | slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n", |
| 477 | addr, len, flags, topdown); |
| 478 | |
| 479 | /* If hint, make sure it matches our alignment restrictions */ |
| 480 | if (!fixed && addr) { |
| 481 | addr = _ALIGN_UP(addr, page_size); |
| 482 | slice_dbg(" aligned addr=%lx\n", addr); |
| 483 | /* Ignore hint if it's too large or overlaps a VMA */ |
| 484 | if (addr > high_limit - len || addr < mmap_min_addr || |
| 485 | !slice_area_is_free(mm, addr, len)) |
| 486 | addr = 0; |
| 487 | } |
| 488 | |
| 489 | /* First make up a "good" mask of slices that have the right size |
| 490 | * already |
| 491 | */ |
| 492 | slice_mask_for_size(mm, psize, &good_mask); |
| 493 | slice_print_mask(" good_mask", good_mask); |
| 494 | |
| 495 | /* |
| 496 | * Here "good" means slices that are already the right page size, |
| 497 | * "compat" means slices that have a compatible page size (i.e. |
| 498 | * 4k in a 64k pagesize kernel), and "free" means slices without |
| 499 | * any VMAs. |
| 500 | * |
| 501 | * If MAP_FIXED: |
| 502 | * check if fits in good | compat => OK |
| 503 | * check if fits in good | compat | free => convert free |
| 504 | * else bad |
| 505 | * If have hint: |
| 506 | * check if hint fits in good => OK |
| 507 | * check if hint fits in good | free => convert free |
| 508 | * Otherwise: |
| 509 | * search in good, found => OK |
| 510 | * search in good | free, found => convert free |
| 511 | * search in good | compat | free, found => convert free. |
| 512 | */ |
| 513 | |
| 514 | #ifdef CONFIG_PPC_64K_PAGES |
| 515 | /* If we support combo pages, we can allow 64k pages in 4k slices */ |
| 516 | if (psize == MMU_PAGE_64K) { |
| 517 | slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask); |
| 518 | if (fixed) |
| 519 | slice_or_mask(&good_mask, &compat_mask); |
| 520 | } |
| 521 | #endif |
| 522 | |
| 523 | /* First check hint if it's valid or if we have MAP_FIXED */ |
| 524 | if (addr != 0 || fixed) { |
| 525 | /* Build a mask for the requested range */ |
| 526 | slice_range_to_mask(addr, len, &mask); |
| 527 | slice_print_mask(" mask", mask); |
| 528 | |
| 529 | /* Check if we fit in the good mask. If we do, we just return, |
| 530 | * nothing else to do |
| 531 | */ |
| 532 | if (slice_check_fit(mm, mask, good_mask)) { |
| 533 | slice_dbg(" fits good !\n"); |
| 534 | return addr; |
| 535 | } |
| 536 | } else { |
| 537 | /* Now let's see if we can find something in the existing |
| 538 | * slices for that size |
| 539 | */ |
| 540 | newaddr = slice_find_area(mm, len, good_mask, |
| 541 | psize, topdown, high_limit); |
| 542 | if (newaddr != -ENOMEM) { |
| 543 | /* Found within the good mask, we don't have to setup, |
| 544 | * we thus return directly |
| 545 | */ |
| 546 | slice_dbg(" found area at 0x%lx\n", newaddr); |
| 547 | return newaddr; |
| 548 | } |
| 549 | } |
| 550 | |
| 551 | /* We don't fit in the good mask, check what other slices are |
| 552 | * empty and thus can be converted |
| 553 | */ |
| 554 | slice_mask_for_free(mm, &potential_mask); |
| 555 | slice_or_mask(&potential_mask, &good_mask); |
| 556 | slice_print_mask(" potential", potential_mask); |
| 557 | |
| 558 | if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) { |
| 559 | slice_dbg(" fits potential !\n"); |
| 560 | goto convert; |
| 561 | } |
| 562 | |
| 563 | /* If we have MAP_FIXED and failed the above steps, then error out */ |
| 564 | if (fixed) |
| 565 | return -EBUSY; |
| 566 | |
| 567 | slice_dbg(" search...\n"); |
| 568 | |
| 569 | /* If we had a hint that didn't work out, see if we can fit |
| 570 | * anywhere in the good area. |
| 571 | */ |
| 572 | if (addr) { |
| 573 | addr = slice_find_area(mm, len, good_mask, |
| 574 | psize, topdown, high_limit); |
| 575 | if (addr != -ENOMEM) { |
| 576 | slice_dbg(" found area at 0x%lx\n", addr); |
| 577 | return addr; |
| 578 | } |
| 579 | } |
| 580 | |
| 581 | /* Now let's see if we can find something in the existing slices |
| 582 | * for that size plus free slices |
| 583 | */ |
| 584 | addr = slice_find_area(mm, len, potential_mask, |
| 585 | psize, topdown, high_limit); |
| 586 | |
| 587 | #ifdef CONFIG_PPC_64K_PAGES |
| 588 | if (addr == -ENOMEM && psize == MMU_PAGE_64K) { |
| 589 | /* retry the search with 4k-page slices included */ |
| 590 | slice_or_mask(&potential_mask, &compat_mask); |
| 591 | addr = slice_find_area(mm, len, potential_mask, |
| 592 | psize, topdown, high_limit); |
| 593 | } |
| 594 | #endif |
| 595 | |
| 596 | if (addr == -ENOMEM) |
| 597 | return -ENOMEM; |
| 598 | |
| 599 | slice_range_to_mask(addr, len, &mask); |
| 600 | slice_dbg(" found potential area at 0x%lx\n", addr); |
| 601 | slice_print_mask(" mask", mask); |
| 602 | |
| 603 | convert: |
| 604 | slice_andnot_mask(&mask, &good_mask); |
| 605 | slice_andnot_mask(&mask, &compat_mask); |
| 606 | if (mask.low_slices || |
| 607 | (SLICE_NUM_HIGH && |
| 608 | !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH))) { |
| 609 | slice_convert(mm, mask, psize); |
| 610 | if (psize > MMU_PAGE_BASE) |
| 611 | on_each_cpu(slice_flush_segments, mm, 1); |
| 612 | } |
| 613 | return addr; |
| 614 | |
| 615 | } |
| 616 | EXPORT_SYMBOL_GPL(slice_get_unmapped_area); |
| 617 | |
| 618 | unsigned long arch_get_unmapped_area(struct file *filp, |
| 619 | unsigned long addr, |
| 620 | unsigned long len, |
| 621 | unsigned long pgoff, |
| 622 | unsigned long flags) |
| 623 | { |
| 624 | return slice_get_unmapped_area(addr, len, flags, |
| 625 | current->mm->context.user_psize, 0); |
| 626 | } |
| 627 | |
| 628 | unsigned long arch_get_unmapped_area_topdown(struct file *filp, |
| 629 | const unsigned long addr0, |
| 630 | const unsigned long len, |
| 631 | const unsigned long pgoff, |
| 632 | const unsigned long flags) |
| 633 | { |
| 634 | return slice_get_unmapped_area(addr0, len, flags, |
| 635 | current->mm->context.user_psize, 1); |
| 636 | } |
| 637 | |
| 638 | unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) |
| 639 | { |
| 640 | unsigned char *hpsizes; |
| 641 | int index, mask_index; |
| 642 | |
| 643 | /* |
| 644 | * Radix doesn't use slice, but can get enabled along with MMU_SLICE |
| 645 | */ |
| 646 | if (radix_enabled()) { |
| 647 | #ifdef CONFIG_PPC_64K_PAGES |
| 648 | return MMU_PAGE_64K; |
| 649 | #else |
| 650 | return MMU_PAGE_4K; |
| 651 | #endif |
| 652 | } |
| 653 | if (addr < SLICE_LOW_TOP) { |
| 654 | u64 lpsizes; |
| 655 | lpsizes = mm->context.low_slices_psize; |
| 656 | index = GET_LOW_SLICE_INDEX(addr); |
| 657 | return (lpsizes >> (index * 4)) & 0xf; |
| 658 | } |
| 659 | hpsizes = mm->context.high_slices_psize; |
| 660 | index = GET_HIGH_SLICE_INDEX(addr); |
| 661 | mask_index = index & 0x1; |
| 662 | return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xf; |
| 663 | } |
| 664 | EXPORT_SYMBOL_GPL(get_slice_psize); |
| 665 | |
| 666 | /* |
| 667 | * This is called by hash_page when it needs to do a lazy conversion of |
| 668 | * an address space from real 64K pages to combo 4K pages (typically |
| 669 | * when hitting a non cacheable mapping on a processor or hypervisor |
| 670 | * that won't allow them for 64K pages). |
| 671 | * |
| 672 | * This is also called in init_new_context() to change back the user |
| 673 | * psize from whatever the parent context had it set to |
| 674 | * N.B. This may be called before mm->context.id has been set. |
| 675 | * |
| 676 | * This function will only change the content of the {low,high)_slice_psize |
| 677 | * masks, it will not flush SLBs as this shall be handled lazily by the |
| 678 | * caller. |
| 679 | */ |
| 680 | void slice_set_user_psize(struct mm_struct *mm, unsigned int psize) |
| 681 | { |
| 682 | int index, mask_index; |
| 683 | unsigned char *hpsizes; |
| 684 | unsigned long flags, lpsizes; |
| 685 | unsigned int old_psize; |
| 686 | int i; |
| 687 | |
| 688 | slice_dbg("slice_set_user_psize(mm=%p, psize=%d)\n", mm, psize); |
| 689 | |
| 690 | VM_BUG_ON(radix_enabled()); |
| 691 | spin_lock_irqsave(&slice_convert_lock, flags); |
| 692 | |
| 693 | old_psize = mm->context.user_psize; |
| 694 | slice_dbg(" old_psize=%d\n", old_psize); |
| 695 | if (old_psize == psize) |
| 696 | goto bail; |
| 697 | |
| 698 | mm->context.user_psize = psize; |
| 699 | wmb(); |
| 700 | |
| 701 | lpsizes = mm->context.low_slices_psize; |
| 702 | for (i = 0; i < SLICE_NUM_LOW; i++) |
| 703 | if (((lpsizes >> (i * 4)) & 0xf) == old_psize) |
| 704 | lpsizes = (lpsizes & ~(0xful << (i * 4))) | |
| 705 | (((unsigned long)psize) << (i * 4)); |
| 706 | /* Assign the value back */ |
| 707 | mm->context.low_slices_psize = lpsizes; |
| 708 | |
| 709 | hpsizes = mm->context.high_slices_psize; |
| 710 | for (i = 0; i < SLICE_NUM_HIGH; i++) { |
| 711 | mask_index = i & 0x1; |
| 712 | index = i >> 1; |
| 713 | if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == old_psize) |
| 714 | hpsizes[index] = (hpsizes[index] & |
| 715 | ~(0xf << (mask_index * 4))) | |
| 716 | (((unsigned long)psize) << (mask_index * 4)); |
| 717 | } |
| 718 | |
| 719 | |
| 720 | |
| 721 | |
| 722 | slice_dbg(" lsps=%lx, hsps=%lx\n", |
| 723 | (unsigned long)mm->context.low_slices_psize, |
| 724 | (unsigned long)mm->context.high_slices_psize); |
| 725 | |
| 726 | bail: |
| 727 | spin_unlock_irqrestore(&slice_convert_lock, flags); |
| 728 | } |
| 729 | |
| 730 | void slice_set_range_psize(struct mm_struct *mm, unsigned long start, |
| 731 | unsigned long len, unsigned int psize) |
| 732 | { |
| 733 | struct slice_mask mask; |
| 734 | |
| 735 | VM_BUG_ON(radix_enabled()); |
| 736 | |
| 737 | slice_range_to_mask(start, len, &mask); |
| 738 | slice_convert(mm, mask, psize); |
| 739 | } |
| 740 | |
| 741 | #ifdef CONFIG_HUGETLB_PAGE |
| 742 | /* |
| 743 | * is_hugepage_only_range() is used by generic code to verify whether |
| 744 | * a normal mmap mapping (non hugetlbfs) is valid on a given area. |
| 745 | * |
| 746 | * until the generic code provides a more generic hook and/or starts |
| 747 | * calling arch get_unmapped_area for MAP_FIXED (which our implementation |
| 748 | * here knows how to deal with), we hijack it to keep standard mappings |
| 749 | * away from us. |
| 750 | * |
| 751 | * because of that generic code limitation, MAP_FIXED mapping cannot |
| 752 | * "convert" back a slice with no VMAs to the standard page size, only |
| 753 | * get_unmapped_area() can. It would be possible to fix it here but I |
| 754 | * prefer working on fixing the generic code instead. |
| 755 | * |
| 756 | * WARNING: This will not work if hugetlbfs isn't enabled since the |
| 757 | * generic code will redefine that function as 0 in that. This is ok |
| 758 | * for now as we only use slices with hugetlbfs enabled. This should |
| 759 | * be fixed as the generic code gets fixed. |
| 760 | */ |
| 761 | int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, |
| 762 | unsigned long len) |
| 763 | { |
| 764 | struct slice_mask mask, available; |
| 765 | unsigned int psize = mm->context.user_psize; |
| 766 | |
| 767 | if (radix_enabled()) |
| 768 | return 0; |
| 769 | |
| 770 | slice_range_to_mask(addr, len, &mask); |
| 771 | slice_mask_for_size(mm, psize, &available); |
| 772 | #ifdef CONFIG_PPC_64K_PAGES |
| 773 | /* We need to account for 4k slices too */ |
| 774 | if (psize == MMU_PAGE_64K) { |
| 775 | struct slice_mask compat_mask; |
| 776 | slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask); |
| 777 | slice_or_mask(&available, &compat_mask); |
| 778 | } |
| 779 | #endif |
| 780 | |
| 781 | #if 0 /* too verbose */ |
| 782 | slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n", |
| 783 | mm, addr, len); |
| 784 | slice_print_mask(" mask", mask); |
| 785 | slice_print_mask(" available", available); |
| 786 | #endif |
| 787 | return !slice_check_fit(mm, mask, available); |
| 788 | } |
| 789 | #endif |