| 387 430 429 318 171 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; unsigned nr_demoted; }; /* Stat data for system wide items */ enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_PER_VMA_LOCK_STATS #define count_vm_vma_lock_event(x) count_vm_event(x) #else #define count_vm_vma_lock_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { __mod_zone_page_state(folio_zone(folio), item, nr); } static inline void __zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void __zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { mod_zone_page_state(folio_zone(folio), item, nr); } static inline void zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void __node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { __mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void __node_stat_add_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void __node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } static inline void node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void node_stat_add_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #ifdef CONFIG_MEMCG void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val); static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __lruvec_stat_mod_folio(folio, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { lruvec_stat_mod_folio(page_folio(page), idx, val); } #else static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { __mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void __lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void __lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } static inline void lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } void memmap_boot_pages_add(long delta); void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ |
| 39 7 7 10 10 10 1 355 356 356 146 248 119 119 119 129 103 18 104 73 73 212 213 131 131 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <kunit/visibility.h> #include "internal.h" #include "swap.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated. * @s: The data to copy * @len: The size of the data, not including the NUL terminator * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; /* '+1' for the NUL terminator */ buf = kmalloc_track_caller(len + 1, gfp); if (!buf) return NULL; memcpy(buf, s, len); /* Ensure the buf is always NUL-terminated, regardless of @s. */ buf[len] = '\0'; return buf; } /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ noinline char *kstrdup(const char *s, gfp_t gfp) { return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup_noprof); /** * kmemdup_array - duplicate a given array. * * @src: array to duplicate. * @count: number of elements to duplicate from array. * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } EXPORT_SYMBOL(kmemdup_array); /** * kvmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result may be not physically contiguous. Use kvfree() to free. */ void *kvmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kvmalloc(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kvmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { return s ? __kmemdup_nul(s, len, gfp) : NULL; } EXPORT_SYMBOL(kmemdup_nul); static kmem_buckets *user_buckets __ro_after_init; static int __init init_user_buckets(void) { user_buckets = kmem_buckets_create("memdup_user", 0, 0, INT_MAX, NULL); return 0; } subsys_initcall(init_user_buckets); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_alloc_track_caller(user_buckets, len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_valloc(user_buckets, len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } /* * Change backing file, only valid to use during initial VMA setup. */ void vma_set_file(struct vm_area_struct *vma, struct file *file) { /* Changing an anonymous vma with this is illegal */ get_file(file); swap(vma->vm_file, file); fput(file); } EXPORT_SYMBOL(vma_set_file); #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long __weak arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; /* On parisc the stack always grows up - so a unlimited stack should * not be an indicator to use the legacy memory layout. */ if (rlim_stack->rlim_cur == RLIM_INFINITY && !IS_ENABLED(CONFIG_STACK_GROWSUP)) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { #ifdef CONFIG_STACK_GROWSUP /* * For an upwards growing stack the calculation is much simpler. * Memory for the maximum stack size is reserved at the top of the * task. mmap_base starts directly below the stack and grows * downwards. */ return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); #else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); #endif } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); set_bit(MMF_TOPDOWN, &mm->flags); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; clear_bit(MMF_TOPDOWN, &mm->flags); } #endif #ifdef CONFIG_MMU EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } /* * Perform a userland memory mapping into the current process address space. See * the comment for do_mmap() for more details on this operation in general. * * This differs from do_mmap() in that: * * a. An offset parameter is provided rather than pgoff, which is both checked * for overflow and page alignment. * b. mmap locking is performed on the caller's behalf. * c. Userfaultfd unmap events and memory population are handled. * * This means that this function performs essentially the same work as if * userland were invoking mmap (2). * * Returns either an error, or the address at which the requested mapping has * been performed. */ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size) { /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. * However make sure that larger requests are not too disruptive - no * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { flags |= __GFP_NOWARN; if (!(flags & __GFP_RETRY_MAYFAIL)) flags |= __GFP_NORETRY; /* nofail semantic is implemented by the vmalloc fallback */ flags &= ~__GFP_NOFAIL; } return flags; } /** * __kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. * @size: size of the request. * @b: which set of kmalloc buckets to allocate from. * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. * @node: numa node to allocate from * * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Return: pointer to the allocated memory of %NULL in case of failure */ void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) { void *ret; /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ ret = __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, b), kmalloc_gfp_adjust(flags, size), node); if (ret || size <= PAGE_SIZE) return ret; /* non-sleeping allocations are not supported by vmalloc */ if (!gfpflags_allow_blocking(flags)) return NULL; /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } /* * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, * since the callers already cannot assume anything * about the resulting pointer, and cannot play * protection games. */ return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, node, __builtin_return_address(0)); } EXPORT_SYMBOL(__kvmalloc_node_noprof); /** * kvfree() - Free memory. * @addr: Pointer to allocated memory. * * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); /** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. * * Use the special memzero_explicit() function to clear the content of a * kvmalloc'ed object containing sensitive data to make sure that the * compiler won't optimize out the data clearing. */ void kvfree_sensitive(const void *addr, size_t len) { if (likely(!ZERO_OR_NULL_PTR(addr))) { memzero_explicit((void *)addr, len); kvfree(addr); } } EXPORT_SYMBOL(kvfree_sensitive); /** * kvrealloc - reallocate memory; contents remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @flags: the flags for the page level allocator * * If @p is %NULL, kvrealloc() behaves exactly like kvmalloc(). If @size is 0 * and @p is not a %NULL pointer, the object pointed to is freed. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or kvfree() for the * same memory allocation. * * Return: pointer to the allocated memory or %NULL in case of error */ void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) { void *n; if (is_vmalloc_addr(p)) return vrealloc_noprof(p, size, flags); n = krealloc_noprof(p, size, kmalloc_gfp_adjust(flags, size)); if (!n) { /* We failed to krealloc(), fall back to kvmalloc(). */ n = kvmalloc_noprof(size, flags); if (!n) return NULL; if (p) { /* We already know that `p` is not a vmalloc address. */ kasan_disable_current(); memcpy(n, kasan_reset_tag(p), ksize(p)); kasan_enable_current(); kfree(p); } } return n; } EXPORT_SYMBOL(kvrealloc_noprof); /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc_noprof(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array_noprof); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array_noprof); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc_noprof); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc_noprof); struct anon_vma *folio_anon_vma(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; return (void *)(mapping - PAGE_MAPPING_ANON); } /** * folio_mapping - Find the mapping where this folio is stored. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the swap mapping * this page is stored in (which is different from the mapping for the * swap file or swap device where the data is stored). * * You can call this for folios which aren't in the swap cache or page * cache and it will return NULL. */ struct address_space *folio_mapping(struct folio *folio) { struct address_space *mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(folio_test_slab(folio))) return NULL; if (unlikely(folio_test_swapcache(folio))) return swap_address_space(folio->swap); mapping = folio->mapping; if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; return mapping; } EXPORT_SYMBOL(folio_mapping); /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. * @src: Folio to copy from. * * The bytes in the folio represented by @src are copied to @dst. * Assumes the caller has validated that @dst is at least as large as @src. * Can be called in atomic context for order-0 folios, but if the folio is * larger, it may sleep. */ void folio_copy(struct folio *dst, struct folio *src) { long i = 0; long nr = folio_nr_pages(src); for (;;) { copy_highpage(folio_page(dst, i), folio_page(src, i)); if (++i == nr) break; cond_resched(); } } EXPORT_SYMBOL(folio_copy); int folio_mc_copy(struct folio *dst, struct folio *src) { long nr = folio_nr_pages(src); long i = 0; for (;;) { if (copy_mc_highpage(folio_page(dst, i), folio_page(src, i))) return -EHWPOISON; if (++i == nr) break; cond_resched(); } return 0; } EXPORT_SYMBOL(folio_mc_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condition (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; unsigned long bytes_failed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: bytes_failed = pages << PAGE_SHIFT; pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n", __func__, current->pid, current->comm, bytes_failed); vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_local_page(page1); addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_local(addr2); kunmap_local(addr1); return ret; } #ifdef CONFIG_PRINTK /** * mem_dump_obj - Print available provenance information * @object: object for which to find provenance information. * * This function uses pr_cont(), so that the caller is expected to have * printed out whatever preamble is appropriate. The provenance information * depends on the type of object and on how much debugging is enabled. * For example, for a slab-cache object, the slab name is printed, and, * if available, the return address and stack trace from the allocation * and last free path of that object. */ void mem_dump_obj(void *object) { const char *type; if (kmem_dump_obj(object)) return; if (vmalloc_dump_obj(object)) return; if (is_vmalloc_addr(object)) type = "vmalloc memory"; else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; else if (object == ZERO_SIZE_PTR) type = "zero-size pointer"; else type = "non-paged memory"; pr_cont(" %s\n", type); } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif /* * A driver might set a page logically offline -- PageOffline() -- and * turn the page inaccessible in the hypervisor; after that, access to page * content can be fatal. * * Some special PFN walkers -- i.e., /proc/kcore -- read content of random * pages after checking PageOffline(); however, these PFN walkers can race * with drivers that set PageOffline(). * * page_offline_freeze()/page_offline_thaw() allows for a subsystem to * synchronize with such drivers, achieving that a page cannot be set * PageOffline() while frozen. * * page_offline_begin()/page_offline_end() is used by drivers that care about * such races when setting a page PageOffline(). */ static DECLARE_RWSEM(page_offline_rwsem); void page_offline_freeze(void) { down_read(&page_offline_rwsem); } void page_offline_thaw(void) { up_read(&page_offline_rwsem); } void page_offline_begin(void) { down_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_begin); void page_offline_end(void) { up_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_end); #ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio) { long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) flush_dcache_page(folio_page(folio, i)); } EXPORT_SYMBOL(flush_dcache_folio); #endif |
| 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 | // SPDX-License-Identifier: GPL-2.0-only /* * VXLAN: Virtual eXtensible Local Area Network * * Copyright (c) 2012-2013 Vyatta Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/if_ether.h> #include <linux/ethtool.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tun_proto.h> #include <net/vxlan.h> #include <net/nexthop.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif #include "vxlan_private.h" #define VXLAN_VERSION "0.1" #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 * for compatibility with early adopters. */ static unsigned short vxlan_port __read_mostly = 8472; module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); unsigned int vxlan_net_id; const u8 all_zeros_mac[ETH_ALEN + 2]; static struct rtnl_link_ops vxlan_link_ops; static int vxlan_sock_add(struct vxlan_dev *vxlan); static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); /* salt for hash table */ static u32 vxlan_salt __read_mostly; static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) { return vs->flags & VXLAN_F_COLLECT_METADATA || ip_tunnel_collect_metadata(); } /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). */ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; flags &= VXLAN_F_RCV_FLAGS; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { if (inet_sk(vs->sock->sk)->inet_sport == port && vxlan_get_sk_family(vs) == family && vs->flags == flags && vs->sock->sk->sk_bound_dev_if == ifindex) return vs; } return NULL; } static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni, struct vxlan_vni_node **vninode) { struct vxlan_vni_node *vnode; struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA && !(vs->flags & VXLAN_F_VNIFILTER)) vni = 0; hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { if (!node->vxlan) continue; vnode = NULL; if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { vnode = vxlan_vnifilter_lookup(node->vxlan, vni); if (!vnode) continue; } else if (node->vxlan->default_dst.remote_vni != vni) { continue; } if (IS_ENABLED(CONFIG_IPV6)) { const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } if (vninode) *vninode = vnode; return node->vxlan; } return NULL; } /* Look up VNI in a per net namespace table */ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, __be32 vni, sa_family_t family, __be16 port, u32 flags) { struct vxlan_sock *vs; vs = vxlan_find_sock(net, family, port, flags, ifindex); if (!vs) return NULL; return vxlan_vs_find_vni(vs, ifindex, vni, NULL); } /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, u32 portid, u32 seq, int type, unsigned int flags, const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; bool send_ip, send_eth; struct nlmsghdr *nlh; struct nexthop *nh; struct ndmsg *ndm; int nh_family; u32 nh_id; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); memset(ndm, 0, sizeof(*ndm)); send_eth = send_ip = true; rcu_read_lock(); nh = rcu_dereference(fdb->nh); if (nh) { nh_family = nexthop_get_family(nh); nh_id = nh->id; } rcu_read_unlock(); if (type == RTM_GETNEIGH) { if (rdst) { send_ip = !vxlan_addr_any(&rdst->remote_ip); ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else if (nh) { ndm->ndm_family = nh_family; } send_eth = !is_zero_ether_addr(fdb->eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; if (!net_eq(dev_net(vxlan->dev), vxlan->net) && nla_put_s32(skb, NDA_LINK_NETNSID, peernet2id(dev_net(vxlan->dev), vxlan->net))) goto nla_put_failure; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; if (nh) { if (nla_put_u32(skb, NDA_NH_ID, nh_id)) goto nla_put_failure; } else if (rdst) { if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; } if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */ + nla_total_size(sizeof(struct nda_cacheinfo)); } static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; fdb_info->remote_ifindex = rd->remote_ifindex; memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN); fdb_info->vni = fdb->vni; fdb_info->offloaded = rd->offloaded; fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; } static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, bool adding, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; int ret; if (WARN_ON(!rd)) return 0; notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info, extack); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type, bool swdev_notify, struct netlink_ext_ack *extack) { int err; if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false, extack); break; } } __vxlan_fdb_notify(vxlan, fdb, rd, type); return 0; } static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { }; memcpy(f.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Hash Ethernet address */ static u32 eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, FDB_HASH_BITS); } u32 eth_vni_hash(const unsigned char *addr, __be32 vni) { /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(addr + 2)); return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); } u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) return eth_vni_hash(mac, vni); else return eth_hash(mac); } /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { if (ether_addr_equal(mac, f->eth_addr)) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (vni == f->vni) return f; } else { return f; } } } return NULL; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); if (f && f->used != jiffies) f->used = jiffies; return f; } /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; list_for_each_entry(rd, &f->remotes, list) { if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return rd; } return NULL; } int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); u8 eth_addr[ETH_ALEN + 2] = { 0 }; struct vxlan_rdst *rdst; struct vxlan_fdb *f; int rc = 0; if (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)) return -EINVAL; ether_addr_copy(eth_addr, mac); rcu_read_lock(); f = __vxlan_find_mac(vxlan, eth_addr, vni); if (!f) { rc = -ENOENT; goto out; } rdst = first_remote_rcu(f); vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, const struct vxlan_rdst *rdst, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; int rc = 0; if (!netif_is_vxlan(dev)) return -EINVAL; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst, extack); if (rc) goto unlock; } } } spin_unlock_bh(&vxlan->hash_lock[h]); } return 0; unlock: spin_unlock_bh(&vxlan->hash_lock[h]); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; if (!netif_is_vxlan(dev)) return; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) if (f->vni == vni) list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; spin_unlock_bh(&vxlan->hash_lock[h]); } } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst *oldrd) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; *oldrd = *rd; dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; rd->offloaded = false; return 1; } /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); return -ENOMEM; } rd->remote_ip = *ip; rd->remote_port = port; rd->offloaded = false; rd->remote_vni = vni; rd->remote_ifindex = ifindex; list_add_tail_rcu(&rd->list, &f->remotes); *rdp = rd; return 1; } static bool vxlan_parse_gpe_proto(const struct vxlanhdr *hdr, __be16 *protocol) { const struct vxlanhdr_gpe *gpe = (const struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) return false; /* "The initial version is 0. If a receiver does not support the * version indicated it MUST drop the packet. */ if (gpe->version != 0) return false; /* "When the O bit is set to 1, the packet is an OAM packet and OAM * processing MUST occur." However, we don't implement OAM * processing, thus drop the packet. */ if (gpe->oam_flag) return false; *protocol = tun_p_to_eth_p(gpe->next_protocol); if (!*protocol) return false; return true; } static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, __be32 vni_field, struct gro_remcsum *grc, bool nopartial) { size_t start, offset; if (skb->remcsum_offload) return vh; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; start = vxlan_rco_start(vni_field); offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return vh; } static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb, struct gro_remcsum *grc) { struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; skb_gro_remcsum_init(grc); off_vx = skb_gro_offset(skb); hlen = off_vx + sizeof(*vh); vh = skb_gro_header(skb, hlen, off_vx); if (unlikely(!vh)) return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; vh2 = (struct vxlanhdr *)(p->data + off_vx); if (vh->vx_flags != vh2->vx_flags || vh->vx_vni != vh2->vx_vni) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } return vh; } static struct sk_buff *vxlan_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct gro_remcsum grc; int flush = 1; if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; } skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; struct sk_buff *pp = NULL; struct gro_remcsum grc; struct vxlanhdr *vh; __be16 protocol; int flush = 1; vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); if (vh) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto out; ptype = gro_find_receive_by_type(protocol); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; } out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { /* Sets 'skb->inner_mac_header' since we are always called with * 'skb->encapsulation' set. */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); const struct packet_offload *ptype; int err = -ENOSYS; __be16 protocol; if (!vxlan_parse_gpe_proto(vh, &protocol)) return err; ptype = gro_find_complete_by_type(protocol); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); return err; } static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, __u16 state, __be32 src_vni, __u16 ndm_flags) { struct vxlan_fdb *f; f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return NULL; f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; f->vni = src_vni; f->nh = NULL; RCU_INIT_POINTER(f->vdev, vxlan); INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); return f; } static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, __be32 src_vni, struct vxlan_fdb *f) { ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac, src_vni)); } static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, u32 nhid, struct netlink_ext_ack *extack) { struct nexthop *old_nh = rtnl_dereference(fdb->nh); struct nexthop *nh; int err = -EINVAL; if (old_nh && old_nh->id == nhid) return 0; nh = nexthop_find_by_id(vxlan->net, nhid); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); nh = NULL; goto err_inval; } if (!nexthop_is_fdb(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); goto err_inval; } if (!nexthop_is_multipath(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); goto err_inval; } /* check nexthop group family */ switch (vxlan->default_dst.remote_ip.sa.sa_family) { case AF_INET: if (!nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } break; case AF_INET6: if (nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } } if (old_nh) { list_del_rcu(&fdb->nh_list); nexthop_put(old_nh); } rcu_assign_pointer(fdb->nh, nh); list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); return 1; err_inval: if (nh) nexthop_put(nh); return err; } int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, struct vxlan_fdb **fdb, struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int rc; if (vxlan->cfg.addrmax && vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); if (!f) return -ENOMEM; if (nhid) rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); else rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) goto errout; *fdb = f; return 0; errout: kfree(f); return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; struct nexthop *nh; nh = rcu_dereference_raw(f->nh); if (nh) { rcu_assign_pointer(f->nh, NULL); rcu_assign_pointer(f->vdev, NULL); nexthop_put(nh); } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); kfree(rd); } kfree(f); } static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); __vxlan_fdb_free(f); } static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { struct vxlan_rdst *rd; netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; if (do_notify) { if (rcu_access_pointer(f->nh)) vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); else list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); } hlist_del_rcu(&f->hlist); list_del_rcu(&f->nh_list); call_rcu(&f->rcu, vxlan_fdb_free); } static void vxlan_dst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; struct vxlan_rdst oldrd; int notify = 0; int rc = 0; int err; if (nhid && !rcu_access_pointer(f->nh)) { NL_SET_ERR_MSG(extack, "Cannot replace an existing non nexthop fdb with a nexthop"); return -EOPNOTSUPP; } if (nhid && (flags & NLM_F_APPEND)) { NL_SET_ERR_MSG(extack, "Cannot append to a nexthop fdb"); return -EOPNOTSUPP; } /* Do not allow an externally learned entry to take over an entry added * by the user. */ if (!(fdb_flags & NTF_EXT_LEARNED) || !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; f->updated = jiffies; notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; f->updated = jiffies; notify = 1; } } if ((flags & NLM_F_REPLACE)) { /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { if (nhid) { rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); if (rc < 0) return rc; } else { rc = vxlan_fdb_replace(f, ip, port, vni, ifindex, &oldrd); } notify |= rc; } else { NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; notify |= rc; } if (ndm_flags & NTF_USE) f->used = jiffies; if (notify) { if (rd == NULL) rd = first_remote_rtnl(f); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify, extack); if (err) goto err_notify; } return 0; err_notify: if (nhid) return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); call_rcu(&rd->rcu, vxlan_dst_free); } return err; } static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; int rc; /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; vxlan_fdb_insert(vxlan, mac, src_vni, f); rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) goto err_notify; return 0; err_notify: vxlan_fdb_destroy(vxlan, f, false, false); return rc; } /* Add new entry to forwarding table -- assumes lock held */ int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, "lost race to create %pM\n", mac); return -EEXIST; } return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, ndm_flags, nhid, swdev_notify, extack); } } static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, __be32 *vni, u32 *ifindex, u32 *nhid, struct netlink_ext_ack *extack) { struct net *net = dev_net(vxlan->dev); int err; if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); return -EINVAL; } if (tb[NDA_DST]) { err = vxlan_nla_get_addr(ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG(extack, "Unsupported address family"); return err; } } else { union vxlan_addr *remote = &vxlan->default_dst.remote_ip; if (remote->sa.sa_family == AF_INET) { ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); ip->sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { ip->sin6.sin6_addr = in6addr_any; ip->sa.sa_family = AF_INET6; #endif } } if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { NL_SET_ERR_MSG(extack, "Invalid vxlan port"); return -EINVAL; } *port = nla_get_be16(tb[NDA_PORT]); } else { *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid vni"); return -EINVAL; } *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } if (tb[NDA_SRC_VNI]) { if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid src vni"); return -EINVAL; } *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); } else { *src_vni = vxlan->default_dst.remote_vni; } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid ifindex"); return -EINVAL; } *ifindex = nla_get_u32(tb[NDA_IFINDEX]); tdev = __dev_get_by_index(net, *ifindex); if (!tdev) { NL_SET_ERR_MSG(extack, "Device not found"); return -EADDRNOTAVAIL; } } else { *ifindex = 0; } *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int err = -ENOENT; f = vxlan_find_mac(vxlan, addr, src_vni); if (!f) return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); if (!rd) goto out; } /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ if (rd && !list_is_singular(&f->remotes)) { vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); goto out; } vxlan_fdb_destroy(vxlan, f, true, swdev_notify); out: return 0; } /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; __be16 port; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } /* Dump forwarding table */ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; int err = 0; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { if (*idx < ctx->fdb_idx) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); if (err < 0) { rcu_read_unlock(); goto out; } skip_nh: *idx += 1; continue; } list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < ctx->fdb_idx) goto skip; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) { rcu_read_unlock(); goto out; } skip: *idx += 1; } } rcu_read_unlock(); } out: return err; } static int vxlan_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; __be32 vni; int err; if (tb[NDA_VNI]) vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); else vni = vxlan->default_dst.remote_vni; rcu_read_lock(); f = __vxlan_find_mac(vxlan, addr, vni); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = vxlan_fdb_info(skb, vxlan, f, portid, seq, RTM_NEWNEIGH, 0, first_remote_rcu(f)); errout: rcu_read_unlock(); return err; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. */ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, union vxlan_addr *src_ip, const u8 *src_mac, u32 src_ifindex, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 ifindex = 0; /* Ignore packets from invalid src-address */ if (!is_valid_ether_addr(src_mac)) return SKB_DROP_REASON_MAC_INVALID_SOURCE; #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) ifindex = src_ifindex; #endif f = vxlan_find_mac(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; /* Don't migrate static entries, drop packets */ if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; /* Don't override an fdb with nexthop with a learnt entry */ if (rcu_access_pointer(f->nh)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; f->updated = jiffies; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { u32 hash_index = fdb_head_index(vxlan, src_mac, vni); /* learned new entry */ spin_lock(&vxlan->hash_lock[hash_index]); /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock[hash_index]); } return SKB_NOT_DROPPED_YET; } static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { struct vxlan_net *vn; if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); return true; } static void vxlan_sock_release(struct vxlan_dev *vxlan) { struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); RCU_INIT_POINTER(vxlan->vn6_sock, NULL); #endif RCU_INIT_POINTER(vxlan->vn4_sock, NULL); synchronize_net(); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vs_del_vnigrp(vxlan); else vxlan_vs_del_dev(vxlan); if (__vxlan_sock_release_prep(sock4)) { udp_tunnel_sock_release(sock4->sock); kfree(sock4); } #if IS_ENABLED(CONFIG_IPV6) if (__vxlan_sock_release_prep(sock6)) { udp_tunnel_sock_release(sock6->sock); kfree(sock6); } #endif } static enum skb_drop_reason vxlan_remcsum(struct sk_buff *skb, u32 vxflags) { const struct vxlanhdr *vh = vxlan_hdr(skb); enum skb_drop_reason reason; size_t start, offset; if (!(vh->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) return SKB_NOT_DROPPED_YET; start = vxlan_rco_start(vh->vx_vni); offset = start + vxlan_rco_offset(vh->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) return reason; skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); return SKB_NOT_DROPPED_YET; } static void vxlan_parse_gbp_hdr(struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { const struct vxlanhdr *vh = vxlan_hdr(skb); const struct vxlanhdr_gbp *gbp; struct metadata_dst *tun_dst; gbp = (const struct vxlanhdr_gbp *)vh; if (!(vh->vx_flags & VXLAN_HF_GBP)) return; md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) md->gbp |= VXLAN_GBP_POLICY_APPLIED; /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; u32 ifindex = skb->dev->ifindex; skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return SKB_DROP_REASON_LOCAL_MAC; /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET6; #endif } if (!(vxlan->cfg.flags & VXLAN_F_LEARN)) return SKB_NOT_DROPPED_YET; return vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni); } static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, struct sk_buff *skb) { int err = 0; if (vxlan_get_sk_family(vs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err) && log_ecn_error) { if (vxlan_get_sk_family(vs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } return err <= 1; } /* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; const struct vxlanhdr *vh; struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); enum skb_drop_reason reason; bool raw_proto = false; void *oiph; __be32 vni = 0; int nh; /* Need UDP and VXLAN header to be present */ reason = pskb_may_pull_reason(skb, VXLAN_HLEN); if (reason) goto drop; vh = vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(vh->vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", ntohl(vh->vx_flags), ntohl(vh->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; vni = vxlan_vni(vh->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { reason = SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND; goto drop; } if (vh->vx_flags & vxlan->cfg.reserved_bits.vx_flags || vh->vx_vni & vxlan->cfg.reserved_bits.vx_vni) { /* If the header uses bits besides those enabled by the * netdevice configuration, treat this as a malformed packet. * This behavior diverges from VXLAN RFC (RFC7348) which * stipulates that bits in reserved in reserved fields are to be * ignored. The approach here maintains compatibility with * previous stack code, and also is more robust and provides a * little more security in adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } if (vxlan->cfg.flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto drop; raw_proto = true; } if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, !net_eq(vxlan->net, dev_net(vxlan->dev)))) { reason = SKB_DROP_REASON_NOMEM; goto drop; } if (vxlan->cfg.flags & VXLAN_F_REMCSUM_RX) { reason = vxlan_remcsum(skb, vxlan->cfg.flags); if (unlikely(reason)) goto drop; } if (vxlan_collect_metadata(vs)) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; __set_bit(IP_TUNNEL_KEY_BIT, flags); tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) { reason = SKB_DROP_REASON_NOMEM; goto drop; } md = ip_tunnel_info_opts(&tun_dst->u.tun_info); skb_dst_set(skb, (struct dst_entry *)tun_dst); } else { memset(md, 0, sizeof(*md)); } if (vxlan->cfg.flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(skb, vxlan->cfg.flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) goto drop; } else { skb_reset_mac_header(skb); skb->dev = vxlan->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); reason = pskb_inet_may_pull_reason(skb); if (reason) { DEV_STATS_INC(vxlan->dev, rx_length_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { reason = SKB_DROP_REASON_IP_TUNNEL_ECN; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } rcu_read_lock(); if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); dev_dstats_rx_dropped(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } dev_dstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); rcu_read_unlock(); return 0; drop: reason = reason ?: SKB_DROP_REASON_NOT_SPECIFIED; /* Consume bad packet */ kfree_skb_reason(skb, reason); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */ static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) { struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr *hdr; __be32 vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) return -EINVAL; hdr = vxlan_hdr(skb); if (!(hdr->vx_flags & VXLAN_HF_VNI)) return -EINVAL; vs = rcu_dereference_sk_user_data(sk); if (!vs) return -ENOENT; vni = vxlan_vni(hdr->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); if (!vxlan) return -ENOENT; return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; struct neighbour *n; if (dev->flags & IFF_NOARP) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); if ((parp->ar_hrd != htons(ARPHRD_ETHER) && parp->ar_hrd != htons(ARPHRD_IEEE802)) || parp->ar_pro != htons(ETH_P_IP) || parp->ar_op != htons(ARPOP_REQUEST) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) goto out; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, n->ha, sha); neigh_release(n); if (reply == NULL) goto out; skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); } out: consume_skb(skb); return NETDEV_TX_OK; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *vxlan_na_create(struct sk_buff *request, struct neighbour *n, bool isrouter) { struct net_device *dev = request->dev; struct sk_buff *reply; struct nd_msg *ns, *na; struct ipv6hdr *pip6; u8 *daddr; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; if (dev == NULL || !pskb_may_pull(request, request->len)) return NULL; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (reply == NULL) return NULL; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); skb_push(reply, sizeof(struct ethhdr)); skb_reset_mac_header(reply); ns = (struct nd_msg *)(ipv6_hdr(request) + 1); daddr = eth_hdr(request)->h_source; ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { if (!ns->opt[i + 1]) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } /* Ethernet header */ ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_reset_network_header(reply); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_reset_transport_header(reply); /* Neighbor Advertisement */ na = skb_put_zero(reply, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = isrouter; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na)+na_olen, 0)); pip6->payload_len = htons(sizeof(*na)+na_olen); skb_push(reply, sizeof(struct ipv6hdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; return reply; } static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); const struct in6_addr *daddr; const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; struct neighbour *n; struct nd_msg *msg; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; msg = (struct nd_msg *)(iphdr + 1); if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) goto out; n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0)); neigh_release(n); if (reply == NULL) goto out; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); } out: rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } #endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: { struct iphdr *pip; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: { struct ipv6hdr *pip6; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #endif default: return false; } if (n) { bool diff; diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); } neigh_release(n); return diff; } return false; } static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; gpe->next_protocol = tun_p_from_eth_p(protocol); if (!gpe->next_protocol) return -EPFNOSUPPORT; return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int iphdr_len, __be32 vni, struct vxlan_metadata *md, u32 vxflags, bool udp_sum) { struct vxlanhdr *vxh; int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 inner_protocol = htons(ETH_P_TEB); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { int csum_start = skb_checksum_start_offset(skb); if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; /* Need space for new headers (invalidates iph ptr) */ err = skb_cow_head(skb, min_headroom); if (unlikely(err)) return err; err = iptunnel_handle_offloads(skb, type); if (err) return err; vxh = __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { unsigned int start; start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } } if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); if (vxflags & VXLAN_F_GPE) { err = vxlan_build_gpe_hdr(vxh, skb->protocol); if (err < 0) return err; inner_protocol = skb->protocol; } skb_set_inner_protocol(skb, inner_protocol); return 0; } /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; unsigned int len = skb->len; struct net_device *dev; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); if (remote_ip->sa.sa_family == AF_INET) { loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); loopback.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { loopback.sin6.sin6_addr = in6addr_loopback; loopback.sa.sa_family = AF_INET6; #endif } rcu_read_lock(); dev = skb->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); goto drop; } if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); dev_dstats_tx_add(src_vxlan->dev, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { dev_dstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) { #if IS_ENABLED(CONFIG_IPV6) /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. */ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND); return -ENOENT; } vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); return 1; } return 0; } void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; int addr_family; __u8 tos, ttl; int ifindex; int err; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); enum skb_drop_reason reason; bool no_eth_encap; __be32 vni = 0; no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); reason = skb_vlan_inet_prepare(skb, no_eth_encap); if (reason) goto drop; reason = SKB_DROP_REASON_NOT_SPECIFIED; old_iph = ip_hdr(skb); info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { memset(&key, 0, sizeof(key)); pkey = &key; if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, default_vni, true); return; } goto drop; } addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr; key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr; } dst_cache = &rdst->dst_cache; md->gbp = skb->mark; if (flags & VXLAN_F_TTL_INHERIT) { ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) switch (vxlan->cfg.label_policy) { case VXLAN_LABEL_FIXED: key.label = vxlan->cfg.label; break; case VXLAN_LABEL_INHERIT: key.label = ip_tunnel_get_flowlabel(old_iph, skb); break; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } #endif } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", dev->name); goto drop; } pkey = &info->key; addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; __be16 df = 0; __be32 saddr; if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(rt)) { err = PTR_ERR(rt); reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) goto out_unlock; if (vxlan->cfg.df == VXLAN_DF_SET) { df = htons(IP_DF); } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6 || (ntohs(eth->h_proto) == ETH_P_IP && old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) { df = htons(IP_DF); } ndst = &rt->dst; err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv4.src = pkey->u.ipv4.dst; unclone->key.u.ipv4.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) goto out_unlock; } err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv6.src = pkey->u.ipv6.dst; unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, pkey->label, src_port, dst_port, !udp_sum); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); out_unlock: rcu_read_unlock(); return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; tx_error: rcu_read_unlock(); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, reason); } static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, struct vxlan_fdb *f, __be32 vni, bool did_rsc) { struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = rcu_dereference(f->nh); if (!nh) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); else goto drop; return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); } static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, u32 nhid, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = nexthop_find_by_id(dev_net(dev), nhid); if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) goto drop; if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); else goto drop; return NETDEV_TX_OK; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return NETDEV_TX_OK; } /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. * Outer UDP destination is the VXLAN assigned port. * source port is based on hash of flow */ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; bool did_rsc; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); nhid = info->key.nhid; } else { if (info && info->mode & IP_TUNNEL_INFO_TX) vxlan_xmit_one(skb, dev, vni, NULL, false); else kfree_skb_reason(skb, SKB_DROP_REASON_TUNNEL_TXINFO); return NETDEV_TX_OK; } } if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); if (m->icmph.icmp6_code == 0 && m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif } if (nhid) return vxlan_xmit_nhid(skb, dev, nhid, vni); if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; rcu_read_lock(); mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); if (mdb_entry) { netdev_tx_t ret; ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); rcu_read_unlock(); return ret; } rcu_read_unlock(); } eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac(vxlan, eth->h_dest, vni); } if (f == NULL) { f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); return NETDEV_TX_OK; } } if (rcu_access_pointer(f->nh)) { vxlan_xmit_nh(skb, dev, f, (vni ? : vxlan->default_dst.remote_vni), did_rsc); } else { list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; if (!fdst) { fdst = rdst; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); } return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ static void vxlan_cleanup(struct timer_list *t) { struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; unsigned int h; if (!netif_running(vxlan->dev)) return; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; if (f->flags & NTF_EXT_LEARNED) continue; timeout = f->used + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; vxlan_fdb_destroy(vxlan, f, true, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } spin_unlock(&vxlan->hash_lock[h]); } mod_timer(&vxlan->age_timer, next_timer); } static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif spin_unlock(&vn->sock_lock); } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; node->vxlan = vxlan; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int err; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_init(vxlan); err = gro_cells_init(&vxlan->gro_cells, dev); if (err) goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) goto err_gro_cells_destroy; netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); return err; } static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f, true, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); vxlan_mdb_fini(vxlan); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); gro_cells_destroy(&vxlan->gro_cells); vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); } /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int ret; ret = vxlan_sock_add(vxlan); if (ret < 0) return ret; ret = vxlan_multicast_join(vxlan); if (ret) { vxlan_sock_release(vxlan); return ret; } if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; } struct vxlan_fdb_flush_desc { bool ignore_default_entry; unsigned long state; unsigned long state_mask; unsigned long flags; unsigned long flags_mask; __be32 src_vni; u32 nhid; __be32 vni; __be16 port; union vxlan_addr dst_ip; }; static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan) { return is_zero_ether_addr(f->eth_addr) && f->vni == vxlan->cfg.vni; } static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid) { struct nexthop *nh = rtnl_dereference(f->nh); return nh && nh->id == nhid; } static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { if (desc->state_mask && (f->state & desc->state_mask) != desc->state) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan)) return false; if (desc->src_vni && f->vni != desc->src_vni) return false; if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid)) return false; return true; } static bool vxlan_fdb_flush_should_match_remotes(const struct vxlan_fdb_flush_desc *desc) { return desc->vni || desc->port || desc->dst_ip.sa.sa_family; } static bool vxlan_fdb_flush_remote_matches(const struct vxlan_fdb_flush_desc *desc, const struct vxlan_rdst *rd) { if (desc->vni && rd->remote_vni != desc->vni) return false; if (desc->port && rd->remote_port != desc->port) return false; if (desc->dst_ip.sa.sa_family && !vxlan_addr_equal(&rd->remote_ip, &desc->dst_ip)) return false; return true; } static void vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; vxlan_fdb_dst_destroy(vxlan, f, rd, true); remotes_flushed = true; } *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc); unsigned int h; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); if (!vxlan_fdb_flush_matches(f, vxlan, desc)) continue; if (match_remotes) { bool destroy_fdb = false; vxlan_fdb_flush_match_remotes(f, vxlan, desc, &destroy_fdb); if (!destroy_fdb) continue; } vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } } static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = { [NDA_SRC_VNI] = { .type = NLA_U32 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; #define VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_EXT_LEARNED | NTF_OFFLOADED | \ NTF_ROUTER) static int vxlan_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct nlattr *tb[NDA_MAX + 1]; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, vxlan_del_bulk_policy, extack); if (err) return err; if (ndm_flags & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.state = ndm->ndm_state; desc.flags = ndm_flags; if (tb[NDA_NDM_STATE_MASK]) desc.state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); if (tb[NDA_NDM_FLAGS_MASK]) desc.flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); if (tb[NDA_SRC_VNI]) desc.src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); if (tb[NDA_NH_ID]) desc.nhid = nla_get_u32(tb[NDA_NH_ID]); if (tb[NDA_VNI]) desc.vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); if (tb[NDA_PORT]) desc.port = nla_get_be16(tb[NDA_PORT]); if (tb[NDA_DST]) { union vxlan_addr ip; err = vxlan_nla_get_addr(&ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG_ATTR(extack, tb[NDA_DST], "Unsupported address family"); return err; } desc.dst_ip = ip; } vxlan_flush(vxlan, &desc); return 0; } /* Cleanup timer and forwarding table on shutdown */ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, .state = 0, .state_mask = NUD_PERMANENT | NUD_NOARP, }; vxlan_multicast_leave(vxlan); del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan, &desc); vxlan_sock_release(vxlan); return 0; } /* Stub, nothing needs to be done. */ static void vxlan_set_multicast_list(struct net_device *dev) { } static int vxlan_change_mtu(struct net_device *dev, int new_mtu) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); /* This check is different than dev->max_mtu, because it looks at * the lowerdev->mtu, rather than the static dev->max_mtu */ if (lowerdev) { int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct ip_tunnel_info *info = skb_tunnel_info(skb); __be16 sport, dport; sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; if (ip_tunnel_info_af(info) == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; if (!sock4) return -EIO; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0, &info->key.u.ipv4.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); } else { #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; if (!sock6) return -EIO; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, 0, &info->key.u.ipv6.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); #else /* !CONFIG_IPV6 */ return -EPFNOSUPPORT; #endif } info->key.tp_src = sport; info->key.tp_dst = dport; return 0; } static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_del_bulk = vxlan_fdb_delete_bulk, .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_mdb_add = vxlan_mdb_add, .ndo_mdb_del = vxlan_mdb_del, .ndo_mdb_del_bulk = vxlan_mdb_del_bulk, .ndo_mdb_dump = vxlan_mdb_dump, .ndo_mdb_get = vxlan_mdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type vxlan_type = { .name = "vxlan", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening VXLAN udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) { struct vxlan_sock *vs; struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) type = UDP_TUNNEL_TYPE_VXLAN_GPE; else type = UDP_TUNNEL_TYPE_VXLAN; if (push) udp_tunnel_push_rx_port(dev, vs->sock, type); else udp_tunnel_drop_rx_port(dev, vs->sock, type); } } spin_unlock(&vn->sock_lock); } /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; eth_hw_addr_random(dev); ether_setup(dev); dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } } static void vxlan_ether_setup(struct net_device *dev) { dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->netdev_ops = &vxlan_netdev_ether_ops; } static void vxlan_raw_setup(struct net_device *dev) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &vxlan_netdev_raw_ops; } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "MTU must be between 68 and 65535"); return -EINVAL; } } if (!data) { NL_SET_ERR_MSG(extack, "Required attributes not provided to perform the operation"); return -EINVAL; } if (data[IFLA_VXLAN_ID]) { u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } if (data[IFLA_VXLAN_DF]) { enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static void vxlan_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); } static int vxlan_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); if (!lowerdev) { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; return 0; } return __ethtool_get_link_ksettings(lowerdev, cmd); } static const struct ethtool_ops vxlan_ethtool_ops = { .get_drvinfo = vxlan_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = vxlan_get_link_ksettings, }; static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.use_udp6_rx_checksums = !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; } udp_conf.local_udp_port = port; udp_conf.bind_ifindex = ifindex; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vs->vni_list[h]); sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); if (IS_ERR(sock)) { kfree(vs); return ERR_CAST(sock); } vs->sock = sock; refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = vs; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; if (vs->flags & VXLAN_F_GPE) { tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; } else { tunnel_cfg.gro_receive = vxlan_gro_receive; tunnel_cfg.gro_complete = vxlan_gro_complete; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); return vs; } static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { spin_unlock(&vn->sock_lock); return -EBUSY; } spin_unlock(&vn->sock_lock); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); node = &vxlan->hlist6; } else #endif { rcu_assign_pointer(vxlan->vn4_sock, vs); node = &vxlan->hlist4; } if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) vxlan_vs_add_vnigrp(vxlan, vs, ipv6); else vxlan_vs_add_dev(vs, vxlan, node); return 0; } static int vxlan_sock_add(struct vxlan_dev *vxlan) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; RCU_INIT_POINTER(vxlan->vn4_sock, NULL); #if IS_ENABLED(CONFIG_IPV6) RCU_INIT_POINTER(vxlan->vn6_sock, NULL); if (ipv6) { ret = __vxlan_sock_add(vxlan, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = __vxlan_sock_add(vxlan, false); if (ret < 0) vxlan_sock_release(vxlan); return ret; } int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, struct vxlan_config *conf, __be32 vni) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *tmp; list_for_each_entry(tmp, &vn->vxlan_list, next) { if (tmp == vxlan) continue; if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { if (!vxlan_vnifilter_lookup(tmp, vni)) continue; } else if (tmp->cfg.vni != vni) { continue; } if (tmp->cfg.dst_port != conf->dst_port) continue; if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) continue; if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && tmp->cfg.remote_ifindex != conf->remote_ifindex) continue; return -EEXIST; } return 0; } static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, struct net_device **lower, struct vxlan_dev *old, struct netlink_ext_ack *extack) { bool use_ipv6 = false; if (conf->flags & VXLAN_F_GPE) { /* For now, allow GPE only together with * COLLECT_METADATA. This can be relaxed later; in such * case, the other side of the PtP link will have to be * provided. */ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG(extack, "VXLAN GPE does not support this combination of attributes"); return -EINVAL; } } if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { /* Unless IPv6 is explicitly requested, assume IPv4 */ conf->remote_ip.sa.sa_family = AF_INET; conf->saddr.sa.sa_family = AF_INET; } else if (!conf->remote_ip.sa.sa_family) { conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; } else if (!conf->saddr.sa.sa_family) { conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; } if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { NL_SET_ERR_MSG(extack, "Local and remote address must be from the same family"); return -EINVAL; } if (vxlan_addr_multicast(&conf->saddr)) { NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); return -EINVAL; } if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { int local_type = ipv6_addr_type(&conf->saddr.sin6.sin6_addr); int remote_type = ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); if (local_type & IPV6_ADDR_LINKLOCAL) { if (!(remote_type & IPV6_ADDR_LINKLOCAL) && (remote_type != IPV6_ADDR_ANY)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags |= VXLAN_F_IPV6_LINKLOCAL; } else { if (remote_type == (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; } } } if (conf->label && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label attribute only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->label_policy && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label policy only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->remote_ifindex) { struct net_device *lowerdev; lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); if (!lowerdev) { NL_SET_ERR_MSG(extack, "Invalid local interface, device not found"); return -ENODEV; } #if IS_ENABLED(CONFIG_IPV6) if (use_ipv6) { struct inet6_dev *idev = __in6_dev_get(lowerdev); if (idev && idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 support disabled by administrator"); return -EPERM; } } #endif *lower = lowerdev; } else { if (vxlan_addr_multicast(&conf->remote_ip)) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote destination"); return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { NL_SET_ERR_MSG(extack, "Local interface required for link-local local/remote addresses"); return -EINVAL; } #endif *lower = NULL; } if (!conf->dst_port) { if (conf->flags & VXLAN_F_GPE) conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); else conf->dst_port = htons(vxlan_port); } if (!conf->age_interval) conf->age_interval = FDB_AGE_DEFAULT; if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { NL_SET_ERR_MSG(extack, "A VXLAN device with the specified VNI already exists"); return -EEXIST; } return 0; } static void vxlan_config_apply(struct net_device *dev, struct vxlan_config *conf, struct net_device *lowerdev, struct net *src_net, bool changelink) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int max_mtu = ETH_MAX_MTU; u32 flags = conf->flags; if (!changelink) { if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); if (conf->mtu) dev->mtu = conf->mtu; vxlan->net = src_net; } dst->remote_vni = conf->vni; memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; netif_inherit_tso_max(dev, lowerdev); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; if (!changelink && !conf->mtu) dev->mtu = max_mtu; } if (dev->mtu > max_mtu) dev->mtu = max_mtu; if (flags & VXLAN_F_COLLECT_METADATA) flags |= VXLAN_F_IPV6; needed_headroom += vxlan_headroom(flags); dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; int ret; ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); if (ret) return ret; vxlan_config_apply(dev, conf, lowerdev, src_net, changelink); return 0; } static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, false, extack); if (err) return err; dev->ethtool_ops = &vxlan_ethtool_ops; /* create an fdb entry for a valid default destination */ if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, NTF_SELF, 0, &f, extack); if (err) return err; } err = register_netdevice(dev); if (err) goto errout; unregister = true; if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); if (!remote_dev) { err = -ENODEV; goto errout; } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) goto errout; } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; if (f) { vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } } list_add(&vxlan->next, &vn->vxlan_list); if (remote_dev) dst->remote_dev = remote_dev; return 0; unlink: if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so * destroy the entry by hand here. */ if (f) __vxlan_fdb_free(f); unregister: if (unregister) unregister_netdevice(dev); return err; } /* Set/clear flags based on attribute */ static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], int attrtype, unsigned long mask, bool changelink, bool changelink_supported, struct netlink_ext_ack *extack) { unsigned long flags; if (!tb[attrtype]) return 0; if (changelink && !changelink_supported) { vxlan_flag_attr_error(attrtype, extack); return -EOPNOTSUPP; } if (vxlan_policy[attrtype].type == NLA_FLAG) flags = conf->flags | mask; else if (nla_get_u8(tb[attrtype])) flags = conf->flags | mask; else flags = conf->flags & ~mask; conf->flags = flags; return 0; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlanhdr used_bits = { .vx_flags = VXLAN_HF_VNI, .vx_vni = VXLAN_VNI_MASK, }; struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; memset(conf, 0, sizeof(*conf)); /* if changelink operation, start with old existing cfg */ if (changelink) memcpy(conf, &vxlan->cfg, sizeof(*conf)); if (data[IFLA_VXLAN_ID]) { __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (changelink && (vni != conf->vni)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); } if (data[IFLA_VXLAN_GROUP]) { if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); conf->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); conf->remote_ip.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); return -EOPNOTSUPP; } conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); conf->saddr.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_LOCAL6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); return -EOPNOTSUPP; } /* TODO: respect scope id */ conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); conf->saddr.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LINK]) conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); if (data[IFLA_VXLAN_TOS]) conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (data[IFLA_VXLAN_TTL_INHERIT]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, VXLAN_F_TTL_INHERIT, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LABEL_POLICY]) conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, VXLAN_F_LEARN, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; } if (data[IFLA_VXLAN_AGEING]) conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, VXLAN_F_PROXY, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_RSC]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, VXLAN_F_RSC, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L2MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, VXLAN_F_L2MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L3MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, VXLAN_F_L3MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LIMIT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], "Cannot change limit"); return -EOPNOTSUPP; } conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); } if (data[IFLA_VXLAN_COLLECT_METADATA]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, VXLAN_F_COLLECT_METADATA, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_PORT_RANGE]) { if (!changelink) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); conf->port_min = ntohs(p->low); conf->port_max = ntohs(p->high); } else { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], "Cannot change port range"); return -EOPNOTSUPP; } } if (data[IFLA_VXLAN_PORT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], "Cannot change port"); return -EOPNOTSUPP; } conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); } if (data[IFLA_VXLAN_UDP_CSUM]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], "Cannot change UDP_CSUM flag"); return -EOPNOTSUPP; } if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } if (data[IFLA_VXLAN_LOCALBYPASS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, VXLAN_F_LOCALBYPASS, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to local bypass on a new device */ conf->flags |= VXLAN_F_LOCALBYPASS; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, VXLAN_F_REMCSUM_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, VXLAN_F_REMCSUM_RX, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_HF_RCO; used_bits.vx_vni |= ~VXLAN_VNI_MASK; } if (data[IFLA_VXLAN_GBP]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, VXLAN_F_GBP, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GBP_USED_BITS; } if (data[IFLA_VXLAN_GPE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, VXLAN_F_GPE, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GPE_USED_BITS; } if (data[IFLA_VXLAN_RESERVED_BITS]) { struct vxlanhdr reserved_bits; if (changelink) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_RESERVED_BITS], "Cannot change reserved_bits"); return -EOPNOTSUPP; } nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS], sizeof(reserved_bits)); if (used_bits.vx_flags & reserved_bits.vx_flags || used_bits.vx_vni & reserved_bits.vx_vni) { __be64 ub_be64, rb_be64; memcpy(&ub_be64, &used_bits, sizeof(ub_be64)); memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64)); NL_SET_ERR_MSG_ATTR_FMT(extack, data[IFLA_VXLAN_RESERVED_BITS], "Used bits %#018llx cannot overlap reserved bits %#018llx", be64_to_cpu(ub_be64), be64_to_cpu(rb_be64)); return -EINVAL; } conf->reserved_bits = reserved_bits; } else { /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ conf->reserved_bits = (struct vxlanhdr) { .vx_flags = ~used_bits.vx_flags, .vx_vni = ~used_bits.vx_vni, }; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, false, extack); if (err) return err; } if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "Cannot change mtu"); return -EOPNOTSUPP; } conf->mtu = nla_get_u32(tb[IFLA_MTU]); } if (data[IFLA_VXLAN_DF]) conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); if (data[IFLA_VXLAN_VNIFILTER]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, VXLAN_F_VNIFILTER, changelink, false, extack); if (err) return err; if ((conf->flags & VXLAN_F_VNIFILTER) && !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], "vxlan vnifilter only valid in collect metadata mode"); return -EINVAL; } } return 0; } static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_config conf; int err; err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); if (err) return err; return __vxlan_dev_create(src_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, vxlan, extack); if (err) return err; if (dst->remote_dev == lowerdev) lowerdev = NULL; err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, extack); if (err) return err; /* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } if (!vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, dst->remote_ip, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); /* If vni filtering device, also update fdb entries of * all vnis that were using default remote ip */ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, &conf.remote_ip, extack); if (err) { netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } } if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); return 0; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, }; vxlan_flush(vxlan, &desc); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); if (vxlan->default_dst.remote_dev) netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ /* IFLA_VXLAN_PORT_RANGE */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + nla_total_size(0) + /* IFLA_VXLAN_GBP */ nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ /* IFLA_VXLAN_RESERVED_BITS */ nla_total_size(sizeof(struct vxlanhdr)) + 0; } static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { .low = htons(vxlan->cfg.port_min), .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { if (dst->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP, dst->remote_ip.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6, &dst->remote_ip.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; if (!vxlan_addr_any(&vxlan->cfg.saddr)) { if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS, sizeof(vxlan->cfg.reserved_bits), &vxlan->cfg.reserved_bits)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *vxlan_get_link_net(const struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); return READ_ONCE(vxlan->net); } static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .kind = "vxlan", .maxtype = IFLA_VXLAN_MAX, .policy = vxlan_policy, .priv_size = sizeof(struct vxlan_dev), .setup = vxlan_setup, .validate = vxlan_validate, .newlink = vxlan_newlink, .changelink = vxlan_changelink, .dellink = vxlan_dellink, .get_size = vxlan_get_size, .fill_info = vxlan_fill_info, .get_link_net = vxlan_get_link_net, }; struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &vxlan_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; err = __vxlan_dev_create(net, dev, conf, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); vxlan_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } return dev; } EXPORT_SYMBOL_GPL(vxlan_dev_create); static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { struct vxlan_dev *vxlan, *next; LIST_HEAD(list_kill); list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { struct vxlan_rdst *dst = &vxlan->default_dst; /* In case we created vxlan device with carrier * and we loose the carrier due to module unload * we also need to remove vxlan device. In other * cases, it's not necessary and remote_ifindex * is 0 here, so no matches. */ if (dst->remote_ifindex == dev->ifindex) vxlan_dellink(vxlan->dev, &list_kill); } unregister_netdevice_many(&list_kill); } static int vxlan_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) vxlan_handle_lowerdev_unregister(vn, dev); else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) vxlan_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) vxlan_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block vxlan_notifier_block __read_mostly = { .notifier_call = vxlan_netdevice_event, }; static void vxlan_fdb_offloaded_set(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; u32 hash_index; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) goto out; rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, fdb_info->remote_port, fdb_info->remote_vni, fdb_info->remote_ifindex); if (!rdst) goto out; rdst->offloaded = fdb_info->offloaded; out: spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static int vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; u32 hash_index; int err; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); extack = switchdev_notifier_info_to_extack(&fdb_info->info); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, 0, false, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_fdb_external_learn_del(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 hash_index; int err = 0; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) err = -ENOENT; else if (f->flags & NTF_EXT_LEARNED) err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, fdb_info->remote_ip, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_vxlan_fdb_info *fdb_info; int err = 0; switch (event) { case SWITCHDEV_VXLAN_FDB_OFFLOADED: vxlan_fdb_offloaded_set(dev, ptr); break; case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_add(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = true; vxlan_fdb_offloaded_set(dev, fdb_info); break; case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_del(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = false; vxlan_fdb_offloaded_set(dev, fdb_info); break; } return err; } static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { .notifier_call = vxlan_switchdev_event, }; static void vxlan_fdb_nh_flush(struct nexthop *nh) { struct vxlan_fdb *fdb; struct vxlan_dev *vxlan; u32 hash_index; rcu_read_lock(); list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { vxlan = rcu_dereference(fdb->vdev); WARN_ON(!vxlan); hash_index = fdb_head_index(vxlan, fdb->eth_addr, vxlan->default_dst.remote_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!hlist_unhashed(&fdb->hlist)) vxlan_fdb_destroy(vxlan, fdb, false, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } rcu_read_unlock(); } static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct nh_notifier_info *info = ptr; struct nexthop *nh; if (event != NEXTHOP_EVENT_DEL) return NOTIFY_DONE; nh = nexthop_find_by_id(info->net, info->id); if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); return NOTIFY_DONE; } static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); spin_lock_init(&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); return register_nexthop_notifier(net, &vn->nexthop_notifier_block, NULL); } static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn, struct list_head *dev_to_kill) { struct vxlan_dev *vxlan, *next; list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) vxlan_dellink(vxlan->dev, dev_to_kill); } static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); __unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); vxlan_destroy_tunnels(vn, dev_to_kill); } } static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; for (h = 0; h < PORT_HASH_SIZE; ++h) WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static struct pernet_operations vxlan_net_ops = { .init = vxlan_init_net, .exit_batch_rtnl = vxlan_exit_batch_rtnl, .exit = vxlan_exit_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), }; static int __init vxlan_init_module(void) { int rc; get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); if (rc) goto out3; rc = rtnl_link_register(&vxlan_link_ops); if (rc) goto out4; rc = vxlan_vnifilter_init(); if (rc) goto out5; return 0; out5: rtnl_link_unregister(&vxlan_link_ops); out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: unregister_netdevice_notifier(&vxlan_notifier_block); out2: unregister_pernet_subsys(&vxlan_net_ops); out1: return rc; } late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); unregister_netdevice_notifier(&vxlan_notifier_block); unregister_pernet_subsys(&vxlan_net_ops); /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |
| 247 247 247 247 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * generic net pointers */ #ifndef __NET_GENERIC_H__ #define __NET_GENERIC_H__ #include <linux/bug.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> /* * Generic net pointers are to be used by modules to put some private * stuff on the struct net without explicit struct net modification * * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. * 2. set pernet_operations->size to have the code allocate and free * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * * After accomplishing all of the above, the private pointer can be * accessed with the net_generic() call. */ struct net_generic { union { struct { unsigned int len; struct rcu_head rcu; } s; DECLARE_FLEX_ARRAY(void *, ptr); }; }; static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; } #endif |
| 19 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Authors: Thiébaud Weksteen <tweek@google.com> * Peter Enderborg <Peter.Enderborg@sony.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM avc #if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SELINUX_H #include <linux/tracepoint.h> TRACE_EVENT(selinux_audited, TP_PROTO(struct selinux_audit_data *sad, char *scontext, char *tcontext, const char *tclass ), TP_ARGS(sad, scontext, tcontext, tclass), TP_STRUCT__entry( __field(u32, requested) __field(u32, denied) __field(u32, audited) __field(int, result) __string(scontext, scontext) __string(tcontext, tcontext) __string(tclass, tclass) ), TP_fast_assign( __entry->requested = sad->requested; __entry->denied = sad->denied; __entry->audited = sad->audited; __entry->result = sad->result; __assign_str(tcontext); __assign_str(scontext); __assign_str(tclass); ), TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s", __entry->requested, __entry->denied, __entry->audited, __entry->result, __get_str(scontext), __get_str(tcontext), __get_str(tclass) ) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * Forwarding Information Database * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Changes: * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/bpf.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; bool skip_notify; }; #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else #define FWS_INIT FWS_L #endif static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the * affected subtree. This allows for cached routes to be asynchronously * tested when modifications are made to the destination cache as a * result of redirects, path MTU changes, etc. */ static void fib6_gc_timer_cb(struct timer_list *t); #define FOR_WALKERS(net, w) \ list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) static void fib6_walker_link(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_add(&w->lh, &net->ipv6.fib6_walkers); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) { int new, old = atomic_read(&net->ipv6.fib6_sernum); do { new = old < INT_MAX ? old + 1 : 1; } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); return new; } enum { FIB6_NO_SERNUM_CHANGE = 0, }; void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { struct fib6_node *fn; fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* * Auxiliary address test functions for the radix tree. * * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ #if defined(__LITTLE_ENDIAN) # define BITOP_BE32_SWIZZLE (0x1F & ~7) #else # define BITOP_BE32_SWIZZLE 0 #endif static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; size_t sz = sizeof(*f6i); if (with_fib6_nh) sz += sizeof(struct fib6_nh); f6i = kzalloc(sz, gfp_flags); if (!f6i) return NULL; /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); INIT_HLIST_NODE(&f6i->gc_link); return f6i; } void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); WARN_ON(f6i->fib6_node); if (f6i->nh) nexthop_put(f6i->nh); else fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); if (fn) net->ipv6.rt6_stats->fib_nodes++; return fn; } static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); net->ipv6.rt6_stats->fib_nodes--; } static void node_free(struct net *net, struct fib6_node *fn) { kfree_rcu(fn, rcu); net->ipv6.rt6_stats->fib_nodes--; } static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); kfree(table); } static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; /* * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation * operation, tables never disappear once they exist. */ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) { struct fib6_table *table; table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; } struct fib6_table *fib6_new_table(struct net *net, u32 id) { struct fib6_table *tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; tb = fib6_alloc_table(net, id); if (tb) fib6_link_table(net, tb); return tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT6_TABLE_MAIN; h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; } } rcu_read_unlock(); return NULL; } EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); } #else struct fib6_table *fib6_new_table(struct net *net, u32 id) { return fib6_get_table(net, id); } struct fib6_table *fib6_get_table(struct net *net, u32 id) { return net->ipv6.fib6_main_tbl; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } return &rt->dst; } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } #endif unsigned int fib6_tables_seq_read(const struct net *net) { unsigned int h, fib_seq = 0; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { const struct hlist_head *head = &net->ipv6.fib_table_hash[h]; const struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += READ_ONCE(tb->fib_seq); } rcu_read_unlock(); return fib_seq; } static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; return call_fib6_notifier(nb, event_type, &info.info); } static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, .nsiblings = rt->fib6_nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); } struct fib6_dump_arg { struct net *net; struct notifier_block *nb; struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; if (rt->fib6_nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, rt->fib6_nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, arg->extack); return err; } static int fib6_node_dump(struct fib6_walker *w) { int err; err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } static int fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { int err; w->root = &tb->tb6_root; spin_lock_bh(&tb->tb6_lock); err = fib6_walk(net, w); spin_unlock_bh(&tb->tb6_lock); return err; } /* Called with rcu_read_lock() */ int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; unsigned int h; int err = 0; w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_node_dump; arg.net = net; arg.nb = nb; arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); if (err) goto out; } } out: kfree(w); /* The tree traversal function should never return a positive value. */ return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) { int res; struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args, w->skip_in_node); if (res >= 0) { /* Frame is full, suspend walking */ w->leaf = rt; /* We'll restart from this node, so if some routes were * already dumped, skip them next time. */ w->skip_in_node += res; return 1; } w->skip_in_node = 0; /* Multipath routes are dumped in one route with the * RTA_MULTIPATH attribute. Jump 'rt' to point to the * last sibling of this route (no need to dump the * sibling routes again) */ if (rt->fib6_nsiblings) rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); } w->leaf = NULL; return 0; } static void fib6_dump_end(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); } cb->done = (void *)cb->args[3]; cb->args[1] = 3; } static int fib6_dump_done(struct netlink_callback *cb) { fib6_dump_end(cb); return cb->done ? cb->done(cb) : 0; } static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; w = (void *)cb->args[2]; w->root = &table->tb6_root; if (cb->args[4] == 0) { w->count = 0; w->skip = 0; w->skip_in_node = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { int sernum = READ_ONCE(w->root->fn_sernum); if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; w->skip_in_node = 0; } else w->skip = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; } } return res; } static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int e = 0, s_e; struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; unsigned int h, s_h; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); if (rtm->rtm_flags & RTM_F_PREFIX) arg.filter.flags = RTM_F_PREFIX; } w = (void *)cb->args[2]; if (!w) { /* New dump: * * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) { err = -ENOMEM; goto unlock; } w->func = fib6_dump_node; cb->args[2] = (long)w; /* 2. hook callback destructor. */ cb->args[3] = (long)cb->done; cb->done = fib6_dump_done; } arg.skb = skb; arg.cb = cb; arg.net = net; w->args = &arg; if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); err = -ENOENT; goto unlock; } if (!cb->args[0]) { err = fib6_dump_table(tb, skb, cb); if (!err) cb->args[0] = 1; } goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; err = fib6_dump_table(tb, skb, cb); if (err != 0) goto out; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); if (err <= 0) fib6_dump_end(cb); return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { if (!f6i) return; if (f6i->fib6_metrics == &dst_default_metrics) { struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); if (!p) return; refcount_set(&p->refcnt, 1); f6i->fib6_metrics = p; } f6i->fib6_metrics->metrics[metric - 1] = val; } /* * Routing Table * * return the appropriate node for a routing tree "add" operation * by either creating and inserting or by returning an existing * node. */ static struct fib6_node *fib6_add_1(struct net *net, struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; /* insert node in tree */ fn = root; do { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } /* * Exact match ? */ if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } return fn; } /* * We have more bits to go */ /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)) : rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { /* We should not create new node because * NLM_F_REPLACE was specified without NLM_F_CREATE * I assume it is safe to require NLM_F_CREATE when * REPLACE flag is used! Later we may want to remove the * check for replace_required, because according * to netlink specification, NLM_F_CREATE * MUST be specified if new route is created. * That would keep IPv6 consistent with IPv4 */ if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. * Create new leaf node without children. */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); return ln; insert_above: /* * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create * and the current */ pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(net); ln = node_alloc(net); if (!in || !ln) { if (in) node_free_immediate(net, in); if (ln) node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } /* * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes * in the other branch */ in->fn_bit = bit; RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; fib6_info_hold(rcu_dereference_protected(in->leaf, lockdep_is_held(&table->tb6_lock))); /* update parent pointer */ if (dir) rcu_assign_pointer(pn->right, in); else rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, in); rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { rcu_assign_pointer(in->right, ln); rcu_assign_pointer(in->left, fn); } else { rcu_assign_pointer(in->left, ln); rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) RCU_INIT_POINTER(ln->right, fn); else RCU_INIT_POINTER(ln->left, fn); rcu_assign_pointer(fn->parent, ln); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); } return ln; } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, const struct fib6_info *match, const struct fib6_table *table) { int cpu; if (!fib6_nh->rt6i_pcpu) return; rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ for_each_possible_cpu(cpu) { struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); /* Paired with xchg() in rt6_get_pcpu_route() */ pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes * from a fib6_info to NULL (ip6_dst_destroy); it can never * change from one fib6_info reference to another */ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } rcu_read_unlock(); } struct fib6_nh_pcpu_arg { struct fib6_info *from; const struct fib6_table *table; }; static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_nh_pcpu_arg *arg = _arg; __fib6_drop_pcpu_from(nh, arg->from, arg->table); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i, const struct fib6_table *table) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. */ f6i->fib6_destroying = 1; mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { struct fib6_nh_pcpu_arg arg = { .from = f6i, .table = table }; nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i, table); } } static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); fib6_drop_pcpu_from(rt, table); if (rt->nh && !list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes * and replace dummy references to this route with references * to still alive ones. */ while (fn) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); fib6_info_hold(new_leaf); rcu_assign_pointer(fn->leaf, new_leaf); fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } } fib6_clean_expires(rt); fib6_remove_gc_list(rt); } /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; break; } fallback_ins = fallback_ins ?: ins; goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); fib6_remove_gc_list(iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, * but not the same gateway, then the route we try to * add is sibling to this route, increment our counter * of siblings, and later we will add our route to the * list. * Only static routes (which don't have flag * RTF_EXPIRES) are used for ECMPv6. * * To avoid long list, we only had siblings if the * route have a gateway. */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; next_iter: ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No matching route with same ecmp-able-ness found, replace * first matching route */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ if (rt->fib6_nsiblings) { unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { list_add_tail_rcu(&rt->fib6_siblings, &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rt6_multipath_rebalance(temp_sibling); } /* * insert node */ if (!replace) { if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; /* The route should only be notified if it is the first * route in the node or if it is added as a sibling * route to the first route in the node. */ if (!info->skip_notify_kernel && (notify_sibling_rt || ins == &fn->leaf)) { enum fib_event_type fib_event; if (notify_sibling_rt) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, fib_event, rt, extack); if (err) { struct fib6_info *sibling, *next_sibling; /* If the route has siblings, then it first * needs to be unlinked from them. */ if (!rt->fib6_nsiblings) return err; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } } rcu_assign_pointer(rt->fib6_next, iter); fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } } else { int nsiblings; if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; } fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->fib6_nsiblings; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->fib6_next; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } } return 0; } static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { if (!timer_pending(&net->ipv6.ip6_fib_timer)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } } void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } /* allow ipv4 to update sernum via ipv6_stub */ void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum_upto_root(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); } /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; struct fib6_node *fn; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node *pn = NULL; #endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; if (info->nlh->nlmsg_flags & NLM_F_REPLACE) replace_required = 1; } if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, &rt->fib6_dst.addr, rt->fib6_dst.plen, offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; goto out; } #ifdef CONFIG_IPV6_SUBTREES pn = fn; if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* * Create subtree. * * fn[main tree] * | * sfn[subtree root] * \ * sn[new leaf node] */ /* Create subtree root node */ sfn = node_alloc(info->nl_net); if (!sfn) goto failure; fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); rcu_assign_pointer(sfn->leaf, info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); goto failure; } } if (!rcu_access_pointer(fn->leaf)) { if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, info->nl_net->ipv6.fib6_null_entry); } else { fib6_info_hold(rt); rcu_assign_pointer(fn->leaf, rt); } } fn = sn; } #endif err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); if (rt->fib6_flags & RTF_EXPIRES) fib6_add_gc_list(rt); fib6_start_gc(info->nl_net, rt); } out: if (err) { #ifdef CONFIG_IPV6_SUBTREES /* * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } #endif goto failure; } else if (fib6_requires_src(rt)) { fib6_routes_require_src_inc(info->nl_net); } return err; failure: /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: * 1. fn is an intermediate node and we failed to add the new * route to it in both subtree creation failure and fib6_add_rt2node() * failure case. * 2. fn is the root node in the table and we fail to add the first * default route to it. */ if (fn && (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); return err; } /* * Routing tree lookup * */ struct lookup_args { int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, struct lookup_args *args) { struct fib6_node *fn; __be32 dir; if (unlikely(args->offset == 0)) return NULL; /* * Descend on a tree */ fn = root; for (;;) { struct fib6_node *next; dir = addr_bit_set(args->addr, fn->fn_bit); next = dir ? rcu_dereference(fn->right) : rcu_dereference(fn->left); if (next) { fn = next; continue; } break; } while (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) goto backtrack; key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; sfn = fib6_node_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; } #endif if (fn->fn_flags & RTN_RTINFO) return fn; } } backtrack: if (fn->fn_flags & RTN_ROOT) break; fn = rcu_dereference(fn->parent); } return NULL; } /* called with rcu_read_lock() held */ struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif { .offset = 0, /* sentinel */ } }; fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; } /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) * exact_match == true means we try to find fn with exact match of * the passed in prefix addr * exact_match == false means we try to find fn with longest prefix * match of the passed in prefix addr. This is useful for finding fn * for cached route as it will be stored in the exception table under * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, int plen, int offset, bool exact_match) { struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ if (!leaf) { if (plen <= fn->fn_bit) goto out; else goto next; } key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) goto out; if (plen == fn->fn_bit) return fn; if (fn->fn_flags & RTN_RTINFO) prev = fn; next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) fn = rcu_dereference(fn->right); else fn = rcu_dereference(fn->left); } out: if (exact_match) return NULL; else return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct fib6_info, fib6_src), exact_match); } } } #endif if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; } /* * Deletion * */ static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); child_right = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); if (child_left) return rcu_dereference_protected(child_left->leaf, lockdep_is_held(&table->tb6_lock)); if (child_right) return rcu_dereference_protected(child_right->leaf, lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } return NULL; } /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn) { int children; int nstate; struct fib6_node *child; struct fib6_walker *w; int iter = 0; /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } for (;;) { struct fib6_node *fn_r = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *fn_l = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_r = rcu_dereference_protected(pn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); WARN_ON(fn_leaf); children = 0; child = NULL; if (fn_r) { child = fn_r; children |= 1; } if (fn_l) { child = fn_l; children |= 2; } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags & RTN_ROOT) #endif ) { new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); new_fn_leaf = net->ipv6.fib6_null_entry; } #endif fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn_r == fn) rcu_assign_pointer(pn->right, child); else if (pn_l == fn) rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } #endif read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { if (w->node == fn) { w->node = child; if (children&2) { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } } read_unlock(&net->ipv6.fib6_walker_lock); node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; bool notify_del = false; /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. */ leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); if (leaf == rt && !rt->fib6_nsiblings) { if (rcu_access_pointer(rt->fib6_next)) replace_rt = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); else notify_del = true; } /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; /* The route is deleted from a multipath route. If this * multipath route is the first route in the node, then we need * to emit a delete notification. Otherwise, we need to skip * the notification. */ if (rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf)) notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } /* Adjust walkers */ read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); /* If it was last route, call fib6_repair_tree() to: * 1. For root node, put back null_entry as how the table was created. * 2. For other nodes, expunge its radix tree node. */ if (!rcu_access_pointer(fn->leaf)) { if (!(fn->fn_flags & RTN_TL_ROOT)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; } fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); if (!info->skip_notify_kernel) { if (notify_del) call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); else if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); fib6_info_release(rt); } /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; struct fib6_table *table; struct fib6_node *fn; if (rt == net->ipv6.fib6_null_entry) return -ENOENT; table = rt->fib6_table; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { if (fib6_requires_src(cur)) fib6_routes_require_src_dec(info->nl_net); fib6_del_route(table, fn, rtp, info); return 0; } rtp_next = &cur->fib6_next; } return -ENOENT; } /* * Tree traversal function. * * Certainly, it is not interrupt safe. * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. * * Callback function w->func may return: * 0 -> continue walking. * positive value -> walking is suspended (used by tree dumps, * and probably by gc, if it will be split to several slices) * negative value -> terminate walking. * * The function itself returns: * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. * * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: if (FIB6_SUBTREE(fn)) { w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; fallthrough; #endif case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->skip) { w->skip--; goto skip; } err = w->func(w); if (err) return err; w->count++; continue; } skip: w->state = FWS_U; fallthrough; case FWS_U: if (fn == w->root) return 0; pn = rcu_dereference_protected(fn->parent, 1); left = rcu_dereference_protected(pn->left, 1); right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } #endif if (left == fn) { w->state = FWS_R; continue; } if (right == fn) { w->state = FWS_C; w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 WARN_ON(1); #endif } } } static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) fib6_walker_unlink(net, w); return res; } static int fib6_clean_node(struct fib6_walker *w) { int res; struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, .skip_notify = c->skip_notify, }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && READ_ONCE(w->node->fn_sernum) != c->sernum) WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); w->leaf = NULL; return 0; } for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { if (WARN_ON(!rt->fib6_nsiblings)) continue; rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); } w->leaf = rt; return 0; } /* * Convenient frontend to tree walker. * * func is called on each route. * It may return -2 -> skip multipath route. * -1 -> delete this route. * 0 -> continue walking */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct fib6_info *, void *arg), int sernum, void *arg, bool skip_notify) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; c.w.count = 0; c.w.skip = 0; c.w.skip_in_node = 0; c.func = func; c.sernum = sernum; c.arg = arg; c.net = net; c.skip_notify = skip_notify; fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), int sernum, void *arg, bool skip_notify) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg, skip_notify); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); } void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); } static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); __fib6_clean_all(net, NULL, new_sernum, NULL, false); } /* * Garbage collection */ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { unsigned long now = jiffies; /* * check addrconf expiration here. * Routes are expired even if they are in use. */ if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; } /* Also age clones in the exception table. * Note, that clones are aged out * only if they are not in use now. */ rt6_age_exceptions(rt, gc_args, now); return 0; } static void fib6_gc_table(struct net *net, struct fib6_table *tb6, struct fib6_gc_args *gc_args) { struct fib6_info *rt; struct hlist_node *n; struct nl_info info = { .nl_net = net, .skip_notify = false, }; hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) if (fib6_age(rt, gc_args) == -1) fib6_del(rt, &info); } static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_gc_table(net, table, gc_args); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; unsigned long now; if (force) { spin_lock_bh(&net->ipv6.fib6_gc_lock); } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(struct timer_list *t) { struct net *arg = from_timer(arg, t, ipv6.ip6_fib_timer); fib6_run_gc(0, arg, true); } static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; int err; err = fib6_notifier_init(net); if (err) return err; /* Default to 3-tuple */ net->ipv6.sysctl.multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), GFP_KERNEL); if (!net->ipv6.fib6_main_tbl) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), GFP_KERNEL); if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: kfree(net->ipv6.fib6_main_tbl); #endif out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); out_notifier: fib6_notifier_exit(net); return -ENOMEM; } static void fib6_net_exit(struct net *net) { unsigned int i; del_timer_sync(&net->ipv6.ip6_fib_timer); for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { struct hlist_head *head = &net->ipv6.fib_table_hash[i]; struct hlist_node *tmp; struct fib6_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { hlist_del(&tb->tb6_hlist); fib6_free_table(tb); } } kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, }; static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .dumpit = inet6_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; int __init fib6_init(void) { int ret = -ENOMEM; fib6_node_kmem = KMEM_CACHE(fib6_node, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; ret = register_pernet_subsys(&fib6_net_ops); if (ret) goto out_kmem_cache_create; ret = rtnl_register_many(fib6_rtnl_msg_handlers); if (ret) goto out_unregister_subsys; __fib6_flush_trees = fib6_flush_trees; out: return ret; out_unregister_subsys: unregister_pernet_subsys(&fib6_net_ops); out_kmem_cache_create: kmem_cache_destroy(fib6_node_kmem); goto out; } void fib6_gc_cleanup(void) { unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } #ifdef CONFIG_PROC_FS static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; if (rt->nh) fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } static int ipv6_route_yield(struct fib6_walker *w) { struct ipv6_route_iter *iter = w->args; if (!iter->skip) return 1; do { iter->w.leaf = rcu_dereference_protected( iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; } while (iter->w.leaf); return 0; } static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; iter->w.root = &iter->tbl->tb6_root; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, struct net *net) { unsigned int h; struct hlist_node *node; if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); } static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { int sernum = READ_ONCE(iter->w.root->fn_sernum); if (iter->sernum != sernum) { iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); iter->w.skip = iter->w.count; } } static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; ++(*pos); if (!v) goto iter_table; n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; iter_table: ipv6_route_check_sernum(iter); spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); return NULL; } fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; ipv6_route_seq_setup_walk(iter, net); goto iter_table; } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; if (iter->tbl) { loff_t p = 0; ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } } static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; return w->node && !(w->state == FWS_U && w->node == w->root); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) static int ipv6_route_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__ipv6_route ctx; ctx.meta = meta; ctx.rt = v; return bpf_iter_run_prog(prog, &ctx); } static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct ipv6_route_iter *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return ipv6_route_native_seq_show(seq, v); ret = ipv6_route_prog_seq_show(prog, &meta, v); iter->w.leaf = NULL; return ret; } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)ipv6_route_prog_seq_show(prog, &meta, v); } ipv6_route_native_seq_stop(seq, v); } #else static int ipv6_route_seq_show(struct seq_file *seq, void *v) { return ipv6_route_native_seq_show(seq, v); } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { ipv6_route_native_seq_stop(seq, v); } #endif const struct seq_operations ipv6_route_seq_ops = { .start = ipv6_route_seq_start, .next = ipv6_route_seq_next, .stop = ipv6_route_seq_stop, .show = ipv6_route_seq_show }; #endif /* CONFIG_PROC_FS */ |
| 22 22 22 22 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <linux/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) { int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(u32 *state, u8 *stream, int nrounds) { u32 x[16]; int i; memcpy(x, state, 64); chacha_permute(x, nrounds); for (i = 0; i < ARRAY_SIZE(x); i++) put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); state[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) { u32 x[16]; memcpy(x, state, 64); chacha_permute(x, nrounds); memcpy(&stream[0], &x[0], 16); memcpy(&stream[4], &x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 3 3 3 3 3 3 3 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/hashtable.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> #include <rdma/rdma_counter.h> #include "core_priv.h" #include "restrack.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("core kernel InfiniBand API"); MODULE_LICENSE("Dual BSD/GPL"); struct workqueue_struct *ib_comp_wq; struct workqueue_struct *ib_comp_unbound_wq; struct workqueue_struct *ib_wq; EXPORT_SYMBOL_GPL(ib_wq); static struct workqueue_struct *ib_unreg_wq; /* * Each of the three rwsem locks (devices, clients, client_data) protects the * xarray of the same name. Specifically it allows the caller to assert that * the MARK will/will not be changing under the lock, and for devices and * clients, that the value in the xarray is still a valid pointer. Change of * the MARK is linked to the object state, so holding the lock and testing the * MARK also asserts that the contained object is in a certain state. * * This is used to build a two stage register/unregister flow where objects * can continue to be in the xarray even though they are still in progress to * register/unregister. * * The xarray itself provides additional locking, and restartable iteration, * which is also relied on. * * Locks should not be nested, with the exception of client_data, which is * allowed to nest under the read side of the other two locks. * * The devices_rwsem also protects the device name list, any change or * assignment of device name must also hold the write side to guarantee unique * names. */ /* * devices contains devices that have had their names assigned. The * devices may not be registered. Users that care about the registration * status need to call ib_device_try_get() on the device to ensure it is * registered, and keep it registered, for the required duration. * */ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); static void ib_client_put(struct ib_client *client) { if (refcount_dec_and_test(&client->uses)) complete(&client->uses_zero); } /* * If client_data is registered then the corresponding client must also still * be registered. */ #define CLIENT_DATA_REGISTERED XA_MARK_1 unsigned int rdma_dev_net_id; /* * A list of net namespaces is maintained in an xarray. This is necessary * because we can't get the locking right using the existing net ns list. We * would require a init_net callback after the list is updated. */ static DEFINE_XARRAY_FLAGS(rdma_nets, XA_FLAGS_ALLOC); /* * rwsem to protect accessing the rdma_nets xarray entries. */ static DECLARE_RWSEM(rdma_nets_rwsem); bool ib_devices_shared_netns = true; module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444); MODULE_PARM_DESC(netns_mode, "Share device among net namespaces; default=1 (shared)"); /** * rdma_dev_access_netns() - Return whether an rdma device can be accessed * from a specified net namespace or not. * @dev: Pointer to rdma device which needs to be checked * @net: Pointer to net namesapce for which access to be checked * * When the rdma device is in shared mode, it ignores the net namespace. * When the rdma device is exclusive to a net namespace, rdma device net * namespace is checked against the specified one. */ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net) { return (ib_devices_shared_netns || net_eq(read_pnet(&dev->coredev.rdma_net), net)); } EXPORT_SYMBOL(rdma_dev_access_netns); /* * xarray has this behavior where it won't iterate over NULL values stored in * allocated arrays. So we need our own iterator to see all values stored in * the array. This does the same thing as xa_for_each except that it also * returns NULL valued entries if the array is allocating. Simplified to only * work on simple xarrays. */ static void *xan_find_marked(struct xarray *xa, unsigned long *indexp, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { entry = xas_find_marked(&xas, ULONG_MAX, filter); if (xa_is_zero(entry)) break; } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) { *indexp = xas.xa_index; if (xa_is_zero(entry)) return NULL; return entry; } return XA_ERROR(-ENOENT); } #define xan_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xan_find_marked(xa, &(index), filter); \ !xa_is_err(entry); \ (index)++, entry = xan_find_marked(xa, &(index), filter)) /* RCU hash table mapping netdevice pointers to struct ib_port_data */ static DEFINE_SPINLOCK(ndev_hash_lock); static DECLARE_HASHTABLE(ndev_hash, 5); static void free_netdevs(struct ib_device *ib_dev); static void ib_unregister_work(struct work_struct *work); static void __ib_unregister_device(struct ib_device *device); static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data); static void ib_policy_change_task(struct work_struct *work); static DECLARE_WORK(ib_policy_change_work, ib_policy_change_task); static void __ibdev_printk(const char *level, const struct ib_device *ibdev, struct va_format *vaf) { if (ibdev && ibdev->dev.parent) dev_printk_emit(level[1] - '0', ibdev->dev.parent, "%s %s %s: %pV", dev_driver_string(ibdev->dev.parent), dev_name(ibdev->dev.parent), dev_name(&ibdev->dev), vaf); else if (ibdev) printk("%s%s: %pV", level, dev_name(&ibdev->dev), vaf); else printk("%s(NULL ib_device): %pV", level, vaf); } #define define_ibdev_printk_level(func, level) \ void func(const struct ib_device *ibdev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __ibdev_printk(level, ibdev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_ibdev_printk_level(ibdev_emerg, KERN_EMERG); define_ibdev_printk_level(ibdev_alert, KERN_ALERT); define_ibdev_printk_level(ibdev_crit, KERN_CRIT); define_ibdev_printk_level(ibdev_err, KERN_ERR); define_ibdev_printk_level(ibdev_warn, KERN_WARNING); define_ibdev_printk_level(ibdev_notice, KERN_NOTICE); define_ibdev_printk_level(ibdev_info, KERN_INFO); static struct notifier_block ibdev_lsm_nb = { .notifier_call = ib_security_change, }; static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net); /* Pointer to the RCU head at the start of the ib_port_data array */ struct ib_port_data_rcu { struct rcu_head rcu_head; struct ib_port_data pdata[]; }; static void ib_device_check_mandatory(struct ib_device *device) { #define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device_ops, x), #x } static const struct { size_t offset; char *name; } mandatory_table[] = { IB_MANDATORY_FUNC(query_device), IB_MANDATORY_FUNC(query_port), IB_MANDATORY_FUNC(alloc_pd), IB_MANDATORY_FUNC(dealloc_pd), IB_MANDATORY_FUNC(create_qp), IB_MANDATORY_FUNC(modify_qp), IB_MANDATORY_FUNC(destroy_qp), IB_MANDATORY_FUNC(post_send), IB_MANDATORY_FUNC(post_recv), IB_MANDATORY_FUNC(create_cq), IB_MANDATORY_FUNC(destroy_cq), IB_MANDATORY_FUNC(poll_cq), IB_MANDATORY_FUNC(req_notify_cq), IB_MANDATORY_FUNC(get_dma_mr), IB_MANDATORY_FUNC(reg_user_mr), IB_MANDATORY_FUNC(dereg_mr), IB_MANDATORY_FUNC(get_port_immutable) }; int i; device->kverbs_provider = true; for (i = 0; i < ARRAY_SIZE(mandatory_table); ++i) { if (!*(void **) ((void *) &device->ops + mandatory_table[i].offset)) { device->kverbs_provider = false; break; } } } /* * Caller must perform ib_device_put() to return the device reference count * when ib_device_get_by_index() returns valid device pointer. */ struct ib_device *ib_device_get_by_index(const struct net *net, u32 index) { struct ib_device *device; down_read(&devices_rwsem); device = xa_load(&devices, index); if (device) { if (!rdma_dev_access_netns(device, net)) { device = NULL; goto out; } if (!ib_device_try_get(device)) device = NULL; } out: up_read(&devices_rwsem); return device; } /** * ib_device_put - Release IB device reference * @device: device whose reference to be released * * ib_device_put() releases reference to the IB device to allow it to be * unregistered and eventually free. */ void ib_device_put(struct ib_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->unreg_completion); } EXPORT_SYMBOL(ib_device_put); static struct ib_device *__ib_device_get_by_name(const char *name) { struct ib_device *device; unsigned long index; xa_for_each (&devices, index, device) if (!strcmp(name, dev_name(&device->dev))) return device; return NULL; } /** * ib_device_get_by_name - Find an IB device by name * @name: The name to look for * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device by its name. The caller must call * ib_device_put() on the returned pointer. */ struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id) { struct ib_device *device; down_read(&devices_rwsem); device = __ib_device_get_by_name(name); if (device && driver_id != RDMA_DRIVER_UNKNOWN && device->ops.driver_id != driver_id) device = NULL; if (device) { if (!ib_device_try_get(device)) device = NULL; } up_read(&devices_rwsem); return device; } EXPORT_SYMBOL(ib_device_get_by_name); static int rename_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; int ret = 0; mutex_lock(&device->compat_devs_mutex); xa_for_each (&device->compat_devs, index, cdev) { ret = device_rename(&cdev->dev, dev_name(&device->dev)); if (ret) { dev_warn(&cdev->dev, "Fail to rename compatdev to new name %s\n", dev_name(&device->dev)); break; } } mutex_unlock(&device->compat_devs_mutex); return ret; } int ib_device_rename(struct ib_device *ibdev, const char *name) { unsigned long index; void *client_data; int ret; down_write(&devices_rwsem); if (!strcmp(name, dev_name(&ibdev->dev))) { up_write(&devices_rwsem); return 0; } if (__ib_device_get_by_name(name)) { up_write(&devices_rwsem); return -EEXIST; } ret = device_rename(&ibdev->dev, name); if (ret) { up_write(&devices_rwsem); return ret; } strscpy(ibdev->name, name, IB_DEVICE_NAME_MAX); ret = rename_compat_devs(ibdev); downgrade_write(&devices_rwsem); down_read(&ibdev->client_data_rwsem); xan_for_each_marked(&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->rename) continue; client->rename(ibdev, client_data); } up_read(&ibdev->client_data_rwsem); rdma_nl_notify_event(ibdev, 0, RDMA_RENAME_EVENT); up_read(&devices_rwsem); return 0; } int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim) { if (use_dim > 1) return -EINVAL; ibdev->use_cq_dim = use_dim; return 0; } static int alloc_name(struct ib_device *ibdev, const char *name) { struct ib_device *device; unsigned long index; struct ida inuse; int rc; int i; lockdep_assert_held_write(&devices_rwsem); ida_init(&inuse); xa_for_each (&devices, index, device) { char buf[IB_DEVICE_NAME_MAX]; if (sscanf(dev_name(&device->dev), name, &i) != 1) continue; if (i < 0 || i >= INT_MAX) continue; snprintf(buf, sizeof buf, name, i); if (strcmp(buf, dev_name(&device->dev)) != 0) continue; rc = ida_alloc_range(&inuse, i, i, GFP_KERNEL); if (rc < 0) goto out; } rc = ida_alloc(&inuse, GFP_KERNEL); if (rc < 0) goto out; rc = dev_set_name(&ibdev->dev, name, rc); out: ida_destroy(&inuse); return rc; } static void ib_device_release(struct device *device) { struct ib_device *dev = container_of(device, struct ib_device, dev); free_netdevs(dev); WARN_ON(refcount_read(&dev->refcount)); if (dev->hw_stats_data) ib_device_release_hw_stats(dev->hw_stats_data); if (dev->port_data) { ib_cache_release_one(dev); ib_security_release_port_pkey_list(dev); rdma_counter_release(dev); kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu, pdata[0]), rcu_head); } mutex_destroy(&dev->subdev_lock); mutex_destroy(&dev->unregistration_lock); mutex_destroy(&dev->compat_devs_mutex); xa_destroy(&dev->compat_devs); xa_destroy(&dev->client_data); kfree_rcu(dev, rcu_head); } static int ib_device_uevent(const struct device *device, struct kobj_uevent_env *env) { if (add_uevent_var(env, "NAME=%s", dev_name(device))) return -ENOMEM; /* * It would be nice to pass the node GUID with the event... */ return 0; } static const void *net_namespace(const struct device *d) { const struct ib_core_device *coredev = container_of(d, struct ib_core_device, dev); return read_pnet(&coredev->rdma_net); } static struct class ib_class = { .name = "infiniband", .dev_release = ib_device_release, .dev_uevent = ib_device_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; static void rdma_init_coredev(struct ib_core_device *coredev, struct ib_device *dev, struct net *net) { /* This BUILD_BUG_ON is intended to catch layout change * of union of ib_core_device and device. * dev must be the first element as ib_core and providers * driver uses it. Adding anything in ib_core_device before * device will break this assumption. */ BUILD_BUG_ON(offsetof(struct ib_device, coredev.dev) != offsetof(struct ib_device, dev)); coredev->dev.class = &ib_class; coredev->dev.groups = dev->groups; device_initialize(&coredev->dev); coredev->owner = dev; INIT_LIST_HEAD(&coredev->port_list); write_pnet(&coredev->rdma_net, net); } /** * _ib_alloc_device - allocate an IB device struct * @size:size of structure to allocate * * Low-level drivers should use ib_alloc_device() to allocate &struct * ib_device. @size is the size of the structure to be allocated, * including any private data used by the low-level driver. * ib_dealloc_device() must be used to free structures allocated with * ib_alloc_device(). */ struct ib_device *_ib_alloc_device(size_t size) { struct ib_device *device; unsigned int i; if (WARN_ON(size < sizeof(struct ib_device))) return NULL; device = kzalloc(size, GFP_KERNEL); if (!device) return NULL; if (rdma_restrack_init(device)) { kfree(device); return NULL; } rdma_init_coredev(&device->coredev, device, &init_net); INIT_LIST_HEAD(&device->event_handler_list); spin_lock_init(&device->qp_open_list_lock); init_rwsem(&device->event_handler_rwsem); mutex_init(&device->unregistration_lock); /* * client_data needs to be alloc because we don't want our mark to be * destroyed if the user stores NULL in the client data. */ xa_init_flags(&device->client_data, XA_FLAGS_ALLOC); init_rwsem(&device->client_data_rwsem); xa_init_flags(&device->compat_devs, XA_FLAGS_ALLOC); mutex_init(&device->compat_devs_mutex); init_completion(&device->unreg_completion); INIT_WORK(&device->unregistration_work, ib_unregister_work); spin_lock_init(&device->cq_pools_lock); for (i = 0; i < ARRAY_SIZE(device->cq_pools); i++) INIT_LIST_HEAD(&device->cq_pools[i]); rwlock_init(&device->cache_lock); device->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_CLOSE_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_AH) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_CQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_QP) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_XSRQ) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_DEREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_CQ) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_QP) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_QP) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_QP) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_QP) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_REG_MR) | BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ); mutex_init(&device->subdev_lock); INIT_LIST_HEAD(&device->subdev_list_head); INIT_LIST_HEAD(&device->subdev_list); return device; } EXPORT_SYMBOL(_ib_alloc_device); /** * ib_dealloc_device - free an IB device struct * @device:structure to free * * Free a structure allocated with ib_alloc_device(). */ void ib_dealloc_device(struct ib_device *device) { if (device->ops.dealloc_driver) device->ops.dealloc_driver(device); /* * ib_unregister_driver() requires all devices to remain in the xarray * while their ops are callable. The last op we call is dealloc_driver * above. This is needed to create a fence on op callbacks prior to * allowing the driver module to unload. */ down_write(&devices_rwsem); if (xa_load(&devices, device->index) == device) xa_erase(&devices, device->index); up_write(&devices_rwsem); /* Expedite releasing netdev references */ free_netdevs(device); WARN_ON(!xa_empty(&device->compat_devs)); WARN_ON(!xa_empty(&device->client_data)); WARN_ON(refcount_read(&device->refcount)); rdma_restrack_clean(device); /* Balances with device_initialize */ put_device(&device->dev); } EXPORT_SYMBOL(ib_dealloc_device); /* * add_client_context() and remove_client_context() must be safe against * parallel calls on the same device - registration/unregistration of both the * device and client can be occurring in parallel. * * The routines need to be a fence, any caller must not return until the add * or remove is fully completed. */ static int add_client_context(struct ib_device *device, struct ib_client *client) { int ret = 0; if (!device->kverbs_provider && !client->no_kverbs_req) return 0; down_write(&device->client_data_rwsem); /* * So long as the client is registered hold both the client and device * unregistration locks. */ if (!refcount_inc_not_zero(&client->uses)) goto out_unlock; refcount_inc(&device->refcount); /* * Another caller to add_client_context got here first and has already * completely initialized context. */ if (xa_get_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED)) goto out; ret = xa_err(xa_store(&device->client_data, client->client_id, NULL, GFP_KERNEL)); if (ret) goto out; downgrade_write(&device->client_data_rwsem); if (client->add) { if (client->add(device)) { /* * If a client fails to add then the error code is * ignored, but we won't call any more ops on this * client. */ xa_erase(&device->client_data, client->client_id); up_read(&device->client_data_rwsem); ib_device_put(device); ib_client_put(client); return 0; } } /* Readers shall not see a client until add has been completed */ xa_set_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED); up_read(&device->client_data_rwsem); return 0; out: ib_device_put(device); ib_client_put(client); out_unlock: up_write(&device->client_data_rwsem); return ret; } static void remove_client_context(struct ib_device *device, unsigned int client_id) { struct ib_client *client; void *client_data; down_write(&device->client_data_rwsem); if (!xa_get_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED)) { up_write(&device->client_data_rwsem); return; } client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the * remove callback as the remove callback can recurse back into any * public functions in this module and thus try for any locks those * functions take. * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); ib_device_put(device); ib_client_put(client); } static int alloc_port_data(struct ib_device *device) { struct ib_port_data_rcu *pdata_rcu; u32 port; if (device->port_data) return 0; /* This can only be called once the physical port range is defined */ if (WARN_ON(!device->phys_port_cnt)) return -EINVAL; /* Reserve U32_MAX so the logic to go over all the ports is sane */ if (WARN_ON(device->phys_port_cnt == U32_MAX)) return -EINVAL; /* * device->port_data is indexed directly by the port number to make * access to this data as efficient as possible. * * Therefore port_data is declared as a 1 based array with potential * empty slots at the beginning. */ pdata_rcu = kzalloc(struct_size(pdata_rcu, pdata, size_add(rdma_end_port(device), 1)), GFP_KERNEL); if (!pdata_rcu) return -ENOMEM; /* * The rcu_head is put in front of the port data array and the stored * pointer is adjusted since we never need to see that member until * kfree_rcu. */ device->port_data = pdata_rcu->pdata; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; pdata->ib_dev = device; spin_lock_init(&pdata->pkey_list_lock); INIT_LIST_HEAD(&pdata->pkey_list); spin_lock_init(&pdata->netdev_lock); INIT_HLIST_NODE(&pdata->ndev_hash_link); } return 0; } static int verify_immutable(const struct ib_device *dev, u32 port) { return WARN_ON(!rdma_cap_ib_mad(dev, port) && rdma_max_mad_size(dev, port) != 0); } static int setup_port_data(struct ib_device *device) { u32 port; int ret; ret = alloc_port_data(device); if (ret) return ret; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; ret = device->ops.get_port_immutable(device, port, &pdata->immutable); if (ret) return ret; if (verify_immutable(device, port)) return -EINVAL; } return 0; } /** * ib_port_immutable_read() - Read rdma port's immutable data * @dev: IB device * @port: port number whose immutable data to read. It starts with index 1 and * valid upto including rdma_end_port(). */ const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port) { WARN_ON(!rdma_is_port_valid(dev, port)); return &dev->port_data[port].immutable; } EXPORT_SYMBOL(ib_port_immutable_read); void ib_get_device_fw_str(struct ib_device *dev, char *str) { if (dev->ops.get_dev_fw_str) dev->ops.get_dev_fw_str(dev, str); else str[0] = '\0'; } EXPORT_SYMBOL(ib_get_device_fw_str); static void ib_policy_change_task(struct work_struct *work) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned int i; rdma_for_each_port (dev, i) { u64 sp; ib_get_cached_subnet_prefix(dev, i, &sp); ib_security_cache_change(dev, i, sp); } } up_read(&devices_rwsem); } static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data) { if (event != LSM_POLICY_CHANGE) return NOTIFY_DONE; schedule_work(&ib_policy_change_work); ib_mad_agent_security_change(); return NOTIFY_OK; } static void compatdev_release(struct device *dev) { struct ib_core_device *cdev = container_of(dev, struct ib_core_device, dev); kfree(cdev); } static int add_one_compat_dev(struct ib_device *device, struct rdma_dev_net *rnet) { struct ib_core_device *cdev; int ret; lockdep_assert_held(&rdma_nets_rwsem); if (!ib_devices_shared_netns) return 0; /* * Create and add compat device in all namespaces other than where it * is currently bound to. */ if (net_eq(read_pnet(&rnet->net), read_pnet(&device->coredev.rdma_net))) return 0; /* * The first of init_net() or ib_register_device() to take the * compat_devs_mutex wins and gets to add the device. Others will wait * for completion here. */ mutex_lock(&device->compat_devs_mutex); cdev = xa_load(&device->compat_devs, rnet->id); if (cdev) { ret = 0; goto done; } ret = xa_reserve(&device->compat_devs, rnet->id, GFP_KERNEL); if (ret) goto done; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) { ret = -ENOMEM; goto cdev_err; } cdev->dev.parent = device->dev.parent; rdma_init_coredev(cdev, device, read_pnet(&rnet->net)); cdev->dev.release = compatdev_release; ret = dev_set_name(&cdev->dev, "%s", dev_name(&device->dev)); if (ret) goto add_err; ret = device_add(&cdev->dev); if (ret) goto add_err; ret = ib_setup_port_attrs(cdev); if (ret) goto port_err; ret = xa_err(xa_store(&device->compat_devs, rnet->id, cdev, GFP_KERNEL)); if (ret) goto insert_err; mutex_unlock(&device->compat_devs_mutex); return 0; insert_err: ib_free_port_attrs(cdev); port_err: device_del(&cdev->dev); add_err: put_device(&cdev->dev); cdev_err: xa_release(&device->compat_devs, rnet->id); done: mutex_unlock(&device->compat_devs_mutex); return ret; } static void remove_one_compat_dev(struct ib_device *device, u32 id) { struct ib_core_device *cdev; mutex_lock(&device->compat_devs_mutex); cdev = xa_erase(&device->compat_devs, id); mutex_unlock(&device->compat_devs_mutex); if (cdev) { ib_free_port_attrs(cdev); device_del(&cdev->dev); put_device(&cdev->dev); } } static void remove_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; xa_for_each (&device->compat_devs, index, cdev) remove_one_compat_dev(device, index); } static int add_compat_devs(struct ib_device *device) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; lockdep_assert_held(&devices_rwsem); down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, index, rnet) { ret = add_one_compat_dev(device, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); return ret; } static void remove_all_compat_devs(void) { struct ib_compat_device *cdev; struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { unsigned long c_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&dev->compat_devs, c_index, cdev) remove_one_compat_dev(dev, c_index); up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); } static int add_all_compat_devs(void) { struct rdma_dev_net *rnet; struct ib_device *dev; unsigned long index; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned long net_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, net_index, rnet) { ret = add_one_compat_dev(dev, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); if (ret) remove_all_compat_devs(); return ret; } int rdma_compatdev_set(u8 enable) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; down_write(&rdma_nets_rwsem); if (ib_devices_shared_netns == enable) { up_write(&rdma_nets_rwsem); return 0; } /* enable/disable of compat devices is not supported * when more than default init_net exists. */ xa_for_each (&rdma_nets, index, rnet) { ret++; break; } if (!ret) ib_devices_shared_netns = enable; up_write(&rdma_nets_rwsem); if (ret) return -EBUSY; if (enable) ret = add_all_compat_devs(); else remove_all_compat_devs(); return ret; } static void rdma_dev_exit_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); struct ib_device *dev; unsigned long index; int ret; down_write(&rdma_nets_rwsem); /* * Prevent the ID from being re-used and hide the id from xa_for_each. */ ret = xa_err(xa_store(&rdma_nets, rnet->id, NULL, GFP_KERNEL)); WARN_ON(ret); up_write(&rdma_nets_rwsem); down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { get_device(&dev->dev); /* * Release the devices_rwsem so that pontentially blocking * device_del, doesn't hold the devices_rwsem for too long. */ up_read(&devices_rwsem); remove_one_compat_dev(dev, rnet->id); /* * If the real device is in the NS then move it back to init. */ rdma_dev_change_netns(dev, net, &init_net); put_device(&dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); rdma_nl_net_exit(rnet); xa_erase(&rdma_nets, rnet->id); } static __net_init int rdma_dev_init_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); unsigned long index; struct ib_device *dev; int ret; write_pnet(&rnet->net, net); ret = rdma_nl_net_init(rnet); if (ret) return ret; /* No need to create any compat devices in default init_net. */ if (net_eq(net, &init_net)) return 0; ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL); if (ret) { rdma_nl_net_exit(rnet); return ret; } down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { /* Hold nets_rwsem so that netlink command cannot change * system configuration for device sharing mode. */ down_read(&rdma_nets_rwsem); ret = add_one_compat_dev(dev, rnet); up_read(&rdma_nets_rwsem); if (ret) break; } up_read(&devices_rwsem); if (ret) rdma_dev_exit_net(net); return ret; } /* * Assign the unique string device name and the unique device index. This is * undone by ib_dealloc_device. */ static int assign_name(struct ib_device *device, const char *name) { static u32 last_id; int ret; down_write(&devices_rwsem); /* Assign a unique name to the device */ if (strchr(name, '%')) ret = alloc_name(device, name); else ret = dev_set_name(&device->dev, name); if (ret) goto out; if (__ib_device_get_by_name(dev_name(&device->dev))) { ret = -ENFILE; goto out; } strscpy(device->name, dev_name(&device->dev), IB_DEVICE_NAME_MAX); ret = xa_alloc_cyclic(&devices, &device->index, device, xa_limit_31b, &last_id, GFP_KERNEL); if (ret > 0) ret = 0; out: up_write(&devices_rwsem); return ret; } /* * setup_device() allocates memory and sets up data that requires calling the * device ops, this is the only reason these actions are not done during * ib_alloc_device. It is undone by ib_dealloc_device(). */ static int setup_device(struct ib_device *device) { struct ib_udata uhw = {.outlen = 0, .inlen = 0}; int ret; ib_device_check_mandatory(device); ret = setup_port_data(device); if (ret) { dev_warn(&device->dev, "Couldn't create per-port data\n"); return ret; } memset(&device->attrs, 0, sizeof(device->attrs)); ret = device->ops.query_device(device, &device->attrs, &uhw); if (ret) { dev_warn(&device->dev, "Couldn't query the device attributes\n"); return ret; } return 0; } static void disable_device(struct ib_device *device) { u32 cid; WARN_ON(!refcount_read(&device->refcount)); down_write(&devices_rwsem); xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); /* * Remove clients in LIFO order, see assign_client_id. This could be * more efficient if xarray learns to reverse iterate. Since no new * clients can be added to this ib_device past this point we only need * the maximum possible client_id value here. */ down_read(&clients_rwsem); cid = highest_client_id; up_read(&clients_rwsem); while (cid) { cid--; remove_client_context(device, cid); } ib_cq_pool_cleanup(device); /* Pairs with refcount_set in enable_device */ ib_device_put(device); wait_for_completion(&device->unreg_completion); /* * compat devices must be removed after device refcount drops to zero. * Otherwise init_net() may add more compatdevs after removing compat * devices and before device is disabled. */ remove_compat_devs(device); } /* * An enabled device is visible to all clients and to all the public facing * APIs that return a device pointer. This always returns with a new get, even * if it fails. */ static int enable_device_and_get(struct ib_device *device) { struct ib_client *client; unsigned long index; int ret = 0; /* * One ref belongs to the xa and the other belongs to this * thread. This is needed to guard against parallel unregistration. */ refcount_set(&device->refcount, 2); down_write(&devices_rwsem); xa_set_mark(&devices, device->index, DEVICE_REGISTERED); /* * By using downgrade_write() we ensure that no other thread can clear * DEVICE_REGISTERED while we are completing the client setup. */ downgrade_write(&devices_rwsem); if (device->ops.enable_driver) { ret = device->ops.enable_driver(device); if (ret) goto out; } down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { ret = add_client_context(device, client); if (ret) break; } up_read(&clients_rwsem); if (!ret) ret = add_compat_devs(device); out: up_read(&devices_rwsem); return ret; } static void prevent_dealloc_device(struct ib_device *ib_dev) { } static void ib_device_notify_register(struct ib_device *device) { struct net_device *netdev; u32 port; int ret; ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT); if (ret) return; rdma_for_each_port(device, port) { netdev = ib_device_get_netdev(device, port); if (!netdev) continue; ret = rdma_nl_notify_event(device, port, RDMA_NETDEV_ATTACH_EVENT); dev_put(netdev); if (ret) return; } } /** * ib_register_device - Register an IB device with IB core * @device: Device to register * @name: unique string device name. This may include a '%' which will * cause a unique index to be added to the passed device name. * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB * device will be used. In this case the caller should fully * setup the ibdev for DMA. This usually means using dma_virt_ops. * * Low-level drivers use ib_register_device() to register their * devices with the IB core. All registered clients will receive a * callback for each device that is added. @device must be allocated * with ib_alloc_device(). * * If the driver uses ops.dealloc_driver and calls any ib_unregister_device() * asynchronously then the device pointer may become freed as soon as this * function returns. */ int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device) { int ret; ret = assign_name(device, name); if (ret) return ret; /* * If the caller does not provide a DMA capable device then the IB core * will set up ib_sge and scatterlist structures that stash the kernel * virtual address into the address field. */ WARN_ON(dma_device && !dma_device->dma_parms); device->dma_device = dma_device; ret = setup_device(device); if (ret) return ret; ret = ib_cache_setup_one(device); if (ret) { dev_warn(&device->dev, "Couldn't set up InfiniBand P_Key/GID cache\n"); return ret; } device->groups[0] = &ib_dev_attr_group; device->groups[1] = device->ops.device_group; ret = ib_setup_device_attrs(device); if (ret) goto cache_cleanup; ib_device_register_rdmacg(device); rdma_counter_init(device); /* * Ensure that ADD uevent is not fired because it * is too early amd device is not initialized yet. */ dev_set_uevent_suppress(&device->dev, true); ret = device_add(&device->dev); if (ret) goto cg_cleanup; ret = ib_setup_port_attrs(&device->coredev); if (ret) { dev_warn(&device->dev, "Couldn't register device with driver model\n"); goto dev_cleanup; } ret = enable_device_and_get(device); if (ret) { void (*dealloc_fn)(struct ib_device *); /* * If we hit this error flow then we don't want to * automatically dealloc the device since the caller is * expected to call ib_dealloc_device() after * ib_register_device() fails. This is tricky due to the * possibility for a parallel unregistration along with this * error flow. Since we have a refcount here we know any * parallel flow is stopped in disable_device and will see the * special dealloc_driver pointer, causing the responsibility to * ib_dealloc_device() to revert back to this thread. */ dealloc_fn = device->ops.dealloc_driver; device->ops.dealloc_driver = prevent_dealloc_device; ib_device_put(device); __ib_unregister_device(device); device->ops.dealloc_driver = dealloc_fn; dev_set_uevent_suppress(&device->dev, false); return ret; } dev_set_uevent_suppress(&device->dev, false); /* Mark for userspace that device is ready */ kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_notify_register(device); ib_device_put(device); return 0; dev_cleanup: device_del(&device->dev); cg_cleanup: dev_set_uevent_suppress(&device->dev, false); ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); return ret; } EXPORT_SYMBOL(ib_register_device); /* Callers must hold a get on the device. */ static void __ib_unregister_device(struct ib_device *ib_dev) { struct ib_device *sub, *tmp; mutex_lock(&ib_dev->subdev_lock); list_for_each_entry_safe_reverse(sub, tmp, &ib_dev->subdev_list_head, subdev_list) { list_del(&sub->subdev_list); ib_dev->ops.del_sub_dev(sub); ib_device_put(ib_dev); } mutex_unlock(&ib_dev->subdev_lock); /* * We have a registration lock so that all the calls to unregister are * fully fenced, once any unregister returns the device is truely * unregistered even if multiple callers are unregistering it at the * same time. This also interacts with the registration flow and * provides sane semantics if register and unregister are racing. */ mutex_lock(&ib_dev->unregistration_lock); if (!refcount_read(&ib_dev->refcount)) goto out; disable_device(ib_dev); rdma_nl_notify_event(ib_dev, 0, RDMA_UNREGISTER_EVENT); /* Expedite removing unregistered pointers from the hash table */ free_netdevs(ib_dev); ib_free_port_attrs(&ib_dev->coredev); device_del(&ib_dev->dev); ib_device_unregister_rdmacg(ib_dev); ib_cache_cleanup_one(ib_dev); /* * Drivers using the new flow may not call ib_dealloc_device except * in error unwind prior to registration success. */ if (ib_dev->ops.dealloc_driver && ib_dev->ops.dealloc_driver != prevent_dealloc_device) { WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1); ib_dealloc_device(ib_dev); } out: mutex_unlock(&ib_dev->unregistration_lock); } /** * ib_unregister_device - Unregister an IB device * @ib_dev: The device to unregister * * Unregister an IB device. All clients will receive a remove callback. * * Callers should call this routine only once, and protect against races with * registration. Typically it should only be called as part of a remove * callback in an implementation of driver core's struct device_driver and * related. * * If ops.dealloc_driver is used then ib_dev will be freed upon return from * this function. */ void ib_unregister_device(struct ib_device *ib_dev) { get_device(&ib_dev->dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device); /** * ib_unregister_device_and_put - Unregister a device while holding a 'get' * @ib_dev: The device to unregister * * This is the same as ib_unregister_device(), except it includes an internal * ib_device_put() that should match a 'get' obtained by the caller. * * It is safe to call this routine concurrently from multiple threads while * holding the 'get'. When the function returns the device is fully * unregistered. * * Drivers using this flow MUST use the driver_unregister callback to clean up * their resources associated with the device and dealloc it. */ void ib_unregister_device_and_put(struct ib_device *ib_dev) { WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); ib_device_put(ib_dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_and_put); /** * ib_unregister_driver - Unregister all IB devices for a driver * @driver_id: The driver to unregister * * This implements a fence for device unregistration. It only returns once all * devices associated with the driver_id have fully completed their * unregistration and returned from ib_unregister_device*(). * * If device's are not yet unregistered it goes ahead and starts unregistering * them. * * This does not block creation of new devices with the given driver_id, that * is the responsibility of the caller. */ void ib_unregister_driver(enum rdma_driver_id driver_id) { struct ib_device *ib_dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, ib_dev) { if (ib_dev->ops.driver_id != driver_id) continue; get_device(&ib_dev->dev); up_read(&devices_rwsem); WARN_ON(!ib_dev->ops.dealloc_driver); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); } EXPORT_SYMBOL(ib_unregister_driver); static void ib_unregister_work(struct work_struct *work) { struct ib_device *ib_dev = container_of(work, struct ib_device, unregistration_work); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } /** * ib_unregister_device_queued - Unregister a device using a work queue * @ib_dev: The device to unregister * * This schedules an asynchronous unregistration using a WQ for the device. A * driver should use this to avoid holding locks while doing unregistration, * such as holding the RTNL lock. * * Drivers using this API must use ib_unregister_driver before module unload * to ensure that all scheduled unregistrations have completed. */ void ib_unregister_device_queued(struct ib_device *ib_dev) { WARN_ON(!refcount_read(&ib_dev->refcount)); WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); if (!queue_work(ib_unreg_wq, &ib_dev->unregistration_work)) put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_queued); /* * The caller must pass in a device that has the kref held and the refcount * released. If the device is in cur_net and still registered then it is moved * into net. */ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net) { int ret2 = -EINVAL; int ret; mutex_lock(&device->unregistration_lock); /* * If a device not under ib_device_get() or if the unregistration_lock * is not held, the namespace can be changed, or it can be unregistered. * Check again under the lock. */ if (refcount_read(&device->refcount) == 0 || !net_eq(cur_net, read_pnet(&device->coredev.rdma_net))) { ret = -ENODEV; goto out; } kobject_uevent(&device->dev.kobj, KOBJ_REMOVE); disable_device(device); /* * At this point no one can be using the device, so it is safe to * change the namespace. */ write_pnet(&device->coredev.rdma_net, net); down_read(&devices_rwsem); /* * Currently rdma devices are system wide unique. So the device name * is guaranteed free in the new namespace. Publish the new namespace * at the sysfs level. */ ret = device_rename(&device->dev, dev_name(&device->dev)); up_read(&devices_rwsem); if (ret) { dev_warn(&device->dev, "%s: Couldn't rename device after namespace change\n", __func__); /* Try and put things back and re-enable the device */ write_pnet(&device->coredev.rdma_net, cur_net); } ret2 = enable_device_and_get(device); if (ret2) { /* * This shouldn't really happen, but if it does, let the user * retry at later point. So don't disable the device. */ dev_warn(&device->dev, "%s: Couldn't re-enable device after namespace change\n", __func__); } kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_put(device); out: mutex_unlock(&device->unregistration_lock); if (ret) return ret; return ret2; } int ib_device_set_netns_put(struct sk_buff *skb, struct ib_device *dev, u32 ns_fd) { struct net *net; int ret; net = get_net_ns_by_fd(ns_fd); if (IS_ERR(net)) { ret = PTR_ERR(net); goto net_err; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; goto ns_err; } /* * All the ib_clients, including uverbs, are reset when the namespace is * changed and this cannot be blocked waiting for userspace to do * something, so disassociation is mandatory. */ if (!dev->ops.disassociate_ucontext || ib_devices_shared_netns) { ret = -EOPNOTSUPP; goto ns_err; } get_device(&dev->dev); ib_device_put(dev); ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net); put_device(&dev->dev); put_net(net); return ret; ns_err: put_net(net); net_err: ib_device_put(dev); return ret; } static struct pernet_operations rdma_dev_net_ops = { .init = rdma_dev_init_net, .exit = rdma_dev_exit_net, .id = &rdma_dev_net_id, .size = sizeof(struct rdma_dev_net), }; static int assign_client_id(struct ib_client *client) { int ret; lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in * registration order. */ client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); return 0; } static void remove_client_id(struct ib_client *client) { down_write(&clients_rwsem); xa_erase(&clients, client->client_id); for (; highest_client_id; highest_client_id--) if (xa_load(&clients, highest_client_id - 1)) break; up_write(&clients_rwsem); } /** * ib_register_client - Register an IB client * @client:Client to register * * Upper level users of the IB drivers can use ib_register_client() to * register callbacks for IB device addition and removal. When an IB * device is added, each registered client's add method will be called * (in the order the clients were registered), and when a device is * removed, each client's remove method will be called (in the reverse * order that clients were registered). In addition, when * ib_register_client() is called, the client will receive an add * callback for all devices already registered. */ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); /* * The devices_rwsem is held in write mode to ensure that a racing * ib_register_device() sees a consisent view of clients and devices. */ down_write(&devices_rwsem); down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) goto out; need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); if (ret) goto out; } ret = 0; out: up_write(&clients_rwsem); up_write(&devices_rwsem); if (need_unreg && ret) ib_unregister_client(client); return ret; } EXPORT_SYMBOL(ib_register_client); /** * ib_unregister_client - Unregister an IB client * @client:Client to unregister * * Upper level users use ib_unregister_client() to remove their client * registration. When ib_unregister_client() is called, the client * will receive a remove callback for each IB device still registered. * * This is a full fence, once it returns no client callbacks will be called, * or are running in another thread. */ void ib_unregister_client(struct ib_client *client) { struct ib_device *device; unsigned long index; down_write(&clients_rwsem); ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); /* We do not want to have locks while calling client->remove() */ rcu_read_lock(); xa_for_each (&devices, index, device) { if (!ib_device_try_get(device)) continue; rcu_read_unlock(); remove_client_context(device, client->client_id); ib_device_put(device); rcu_read_lock(); } rcu_read_unlock(); /* * remove_client_context() is not a fence, it can return even though a * removal is ongoing. Wait until all removals are completed. */ wait_for_completion(&client->uses_zero); remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); static int __ib_get_global_client_nl_info(const char *client_name, struct ib_client_nl_info *res) { struct ib_client *client; unsigned long index; int ret = -ENOENT; down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { if (strcmp(client->name, client_name) != 0) continue; if (!client->get_global_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_global_nl_info(res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&clients_rwsem); return ret; } static int __ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { unsigned long index; void *client_data; int ret = -ENOENT; down_read(&ibdev->client_data_rwsem); xan_for_each_marked (&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || strcmp(client->name, client_name) != 0) continue; if (!client->get_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_nl_info(ibdev, client_data, res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; /* * The cdev is guaranteed valid as long as we are inside the * client_data_rwsem as remove_one can't be called. Keep it * valid for the caller. */ if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&ibdev->client_data_rwsem); return ret; } /** * ib_get_client_nl_info - Fetch the nl_info from a client * @ibdev: IB device * @client_name: Name of the client * @res: Result of the query */ int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { int ret; if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); #ifdef CONFIG_MODULES if (ret == -ENOENT) { request_module("rdma-client-%s", client_name); if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); } #endif if (ret) { if (ret == -ENOENT) return -EOPNOTSUPP; return ret; } if (WARN_ON(!res->cdev)) return -EINVAL; return 0; } /** * ib_set_client_data - Set IB client context * @device:Device to set context for * @client:Client to set context for * @data:Context to set * * ib_set_client_data() sets client context data that can be retrieved with * ib_get_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data) { void *rc; if (WARN_ON(IS_ERR(data))) data = NULL; rc = xa_store(&device->client_data, client->client_id, data, GFP_KERNEL); WARN_ON(xa_is_err(rc)); } EXPORT_SYMBOL(ib_set_client_data); /** * ib_register_event_handler - Register an IB event handler * @event_handler:Handler to register * * ib_register_event_handler() registers an event handler that will be * called back when asynchronous IB events occur (as defined in * chapter 11 of the InfiniBand Architecture Specification). This * callback occurs in workqueue context. */ void ib_register_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_add_tail(&event_handler->list, &event_handler->device->event_handler_list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_register_event_handler); /** * ib_unregister_event_handler - Unregister an event handler * @event_handler:Handler to unregister * * Unregister an event handler registered with * ib_register_event_handler(). */ void ib_unregister_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_del(&event_handler->list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_unregister_event_handler); void ib_dispatch_event_clients(struct ib_event *event) { struct ib_event_handler *handler; down_read(&event->device->event_handler_rwsem); list_for_each_entry(handler, &event->device->event_handler_list, list) handler->handler(handler, event); up_read(&event->device->event_handler_rwsem); } static int iw_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { struct in_device *inetdev; struct net_device *netdev; memset(port_attr, 0, sizeof(*port_attr)); netdev = ib_device_get_netdev(device, port_num); if (!netdev) return -ENODEV; port_attr->max_mtu = IB_MTU_4096; port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu); if (!netif_carrier_ok(netdev)) { port_attr->state = IB_PORT_DOWN; port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; } else { rcu_read_lock(); inetdev = __in_dev_get_rcu(netdev); if (inetdev && inetdev->ifa_list) { port_attr->state = IB_PORT_ACTIVE; port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; } else { port_attr->state = IB_PORT_INIT; port_attr->phys_state = IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING; } rcu_read_unlock(); } dev_put(netdev); return device->ops.query_port(device, port_num, port_attr); } static int __ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { int err; memset(port_attr, 0, sizeof(*port_attr)); err = device->ops.query_port(device, port_num, port_attr); if (err || port_attr->subnet_prefix) return err; if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) return 0; ib_get_cached_subnet_prefix(device, port_num, &port_attr->subnet_prefix); return 0; } /** * ib_query_port - Query IB port attributes * @device:Device to query * @port_num:Port number to query * @port_attr:Port attributes * * ib_query_port() returns the attributes of a port through the * @port_attr pointer. */ int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (rdma_protocol_iwarp(device, port_num)) return iw_query_port(device, port_num, port_attr); else return __ib_query_port(device, port_num, port_attr); } EXPORT_SYMBOL(ib_query_port); static void add_ndev_hash(struct ib_port_data *pdata) { unsigned long flags; might_sleep(); spin_lock_irqsave(&ndev_hash_lock, flags); if (hash_hashed(&pdata->ndev_hash_link)) { hash_del_rcu(&pdata->ndev_hash_link); spin_unlock_irqrestore(&ndev_hash_lock, flags); /* * We cannot do hash_add_rcu after a hash_del_rcu until the * grace period */ synchronize_rcu(); spin_lock_irqsave(&ndev_hash_lock, flags); } if (pdata->netdev) hash_add_rcu(ndev_hash, &pdata->ndev_hash_link, (uintptr_t)pdata->netdev); spin_unlock_irqrestore(&ndev_hash_lock, flags); } /** * ib_device_set_netdev - Associate the ib_dev with an underlying net_device * @ib_dev: Device to modify * @ndev: net_device to affiliate, may be NULL * @port: IB port the net_device is connected to * * Drivers should use this to link the ib_device to a netdev so the netdev * shows up in interfaces like ib_enum_roce_netdev. Only one netdev may be * affiliated with any port. * * The caller must ensure that the given ndev is not unregistered or * unregistering, and that either the ib_device is unregistered or * ib_device_set_netdev() is called with NULL when the ndev sends a * NETDEV_UNREGISTER event. */ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, u32 port) { enum rdma_nl_notify_event_type etype; struct net_device *old_ndev; struct ib_port_data *pdata; unsigned long flags; int ret; if (!rdma_is_port_valid(ib_dev, port)) return -EINVAL; /* * Drivers wish to call this before ib_register_driver, so we have to * setup the port data early. */ ret = alloc_port_data(ib_dev); if (ret) return ret; pdata = &ib_dev->port_data[port]; spin_lock_irqsave(&pdata->netdev_lock, flags); old_ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (old_ndev == ndev) { spin_unlock_irqrestore(&pdata->netdev_lock, flags); return 0; } rcu_assign_pointer(pdata->netdev, ndev); netdev_put(old_ndev, &pdata->netdev_tracker); netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC); spin_unlock_irqrestore(&pdata->netdev_lock, flags); add_ndev_hash(pdata); /* Make sure that the device is registered before we send events */ if (xa_load(&devices, ib_dev->index) != ib_dev) return 0; etype = ndev ? RDMA_NETDEV_ATTACH_EVENT : RDMA_NETDEV_DETACH_EVENT; rdma_nl_notify_event(ib_dev, port, etype); return 0; } EXPORT_SYMBOL(ib_device_set_netdev); static void free_netdevs(struct ib_device *ib_dev) { unsigned long flags; u32 port; if (!ib_dev->port_data) return; rdma_for_each_port (ib_dev, port) { struct ib_port_data *pdata = &ib_dev->port_data[port]; struct net_device *ndev; spin_lock_irqsave(&pdata->netdev_lock, flags); ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (ndev) { spin_lock(&ndev_hash_lock); hash_del_rcu(&pdata->ndev_hash_link); spin_unlock(&ndev_hash_lock); /* * If this is the last dev_put there is still a * synchronize_rcu before the netdev is kfreed, so we * can continue to rely on unlocked pointer * comparisons after the put */ rcu_assign_pointer(pdata->netdev, NULL); netdev_put(ndev, &pdata->netdev_tracker); } spin_unlock_irqrestore(&pdata->netdev_lock, flags); } } struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port) { struct ib_port_data *pdata; struct net_device *res; if (!rdma_is_port_valid(ib_dev, port)) return NULL; if (!ib_dev->port_data) return NULL; pdata = &ib_dev->port_data[port]; /* * New drivers should use ib_device_set_netdev() not the legacy * get_netdev(). */ if (ib_dev->ops.get_netdev) res = ib_dev->ops.get_netdev(ib_dev, port); else { spin_lock(&pdata->netdev_lock); res = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); dev_hold(res); spin_unlock(&pdata->netdev_lock); } return res; } EXPORT_SYMBOL(ib_device_get_netdev); /** * ib_query_netdev_port - Query the port number of a net_device * associated with an ibdev * @ibdev: IB device * @ndev: Network device * @port: IB port the net_device is connected to */ int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, u32 *port) { struct net_device *ib_ndev; u32 port_num; rdma_for_each_port(ibdev, port_num) { ib_ndev = ib_device_get_netdev(ibdev, port_num); if (ndev == ib_ndev) { *port = port_num; dev_put(ib_ndev); return 0; } dev_put(ib_ndev); } return -ENOENT; } EXPORT_SYMBOL(ib_query_netdev_port); /** * ib_device_get_by_netdev - Find an IB device associated with a netdev * @ndev: netdev to locate * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device that is associated with a netdev via * ib_device_set_netdev(). The caller must call ib_device_put() on the * returned pointer. */ struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id) { struct ib_device *res = NULL; struct ib_port_data *cur; rcu_read_lock(); hash_for_each_possible_rcu (ndev_hash, cur, ndev_hash_link, (uintptr_t)ndev) { if (rcu_access_pointer(cur->netdev) == ndev && (driver_id == RDMA_DRIVER_UNKNOWN || cur->ib_dev->ops.driver_id == driver_id) && ib_device_try_get(cur->ib_dev)) { res = cur->ib_dev; break; } } rcu_read_unlock(); return res; } EXPORT_SYMBOL(ib_device_get_by_netdev); /** * ib_enum_roce_netdev - enumerate all RoCE ports * @ib_dev : IB device we want to query * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all of the physical RoCE ports of ib_dev * which are related to netdevice and calls callback() on each * device for which filter() function returns non zero. */ void ib_enum_roce_netdev(struct ib_device *ib_dev, roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { u32 port; rdma_for_each_port (ib_dev, port) if (rdma_protocol_roce(ib_dev, port)) { struct net_device *idev = ib_device_get_netdev(ib_dev, port); if (filter(ib_dev, port, idev, filter_cookie)) cb(ib_dev, port, idev, cookie); dev_put(idev); } } /** * ib_enum_all_roce_netdevs - enumerate all RoCE devices * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all RoCE devices' physical ports which are related * to netdevices and calls callback() on each device for which * filter() function returns non zero. */ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie); up_read(&devices_rwsem); } /* * ib_enum_all_devs - enumerate all ib_devices * @cb: Callback to call for each found ib_device * * Enumerates all ib_devices and calls callback() on each device. */ int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, struct netlink_callback *cb) { unsigned long index; struct ib_device *dev; unsigned int idx = 0; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { if (!rdma_dev_access_netns(dev, sock_net(skb->sk))) continue; ret = nldev_cb(dev, skb, cb, idx); if (ret) break; idx++; } up_read(&devices_rwsem); return ret; } /** * ib_query_pkey - Get P_Key table entry * @device:Device to query * @port_num:Port number to query * @index:P_Key table index to query * @pkey:Returned P_Key * * ib_query_pkey() fetches the specified P_Key table entry. */ int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (!device->ops.query_pkey) return -EOPNOTSUPP; return device->ops.query_pkey(device, port_num, index, pkey); } EXPORT_SYMBOL(ib_query_pkey); /** * ib_modify_device - Change IB device attributes * @device:Device to modify * @device_modify_mask:Mask of attributes to change * @device_modify:New attribute values * * ib_modify_device() changes a device's attributes as specified by * the @device_modify_mask and @device_modify structure. */ int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify) { if (!device->ops.modify_device) return -EOPNOTSUPP; return device->ops.modify_device(device, device_modify_mask, device_modify); } EXPORT_SYMBOL(ib_modify_device); /** * ib_modify_port - Modifies the attributes for the specified port. * @device: The device to modify. * @port_num: The number of the port to modify. * @port_modify_mask: Mask used to specify which attributes of the port * to change. * @port_modify: New attribute values for the port. * * ib_modify_port() changes a port's attributes as specified by the * @port_modify_mask and @port_modify structure. */ int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify) { int rc; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (device->ops.modify_port) rc = device->ops.modify_port(device, port_num, port_modify_mask, port_modify); else if (rdma_protocol_roce(device, port_num) && ((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 || (port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0)) rc = 0; else rc = -EOPNOTSUPP; return rc; } EXPORT_SYMBOL(ib_modify_port); /** * ib_find_gid - Returns the port number and GID table index where * a specified GID value occurs. Its searches only for IB link layer. * @device: The device to query. * @gid: The GID value to search for. * @port_num: The port number of the device where the GID value was found. * @index: The index into the GID table where the GID was found. This * parameter may be NULL. */ int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index) { union ib_gid tmp_gid; u32 port; int ret, i; rdma_for_each_port (device, port) { if (!rdma_protocol_ib(device, port)) continue; for (i = 0; i < device->port_data[port].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(device, port, i, &tmp_gid); if (ret) continue; if (!memcmp(&tmp_gid, gid, sizeof *gid)) { *port_num = port; if (index) *index = i; return 0; } } } return -ENOENT; } EXPORT_SYMBOL(ib_find_gid); /** * ib_find_pkey - Returns the PKey table index where a specified * PKey value occurs. * @device: The device to query. * @port_num: The port number of the device to search for the PKey. * @pkey: The PKey value to search for. * @index: The index into the PKey table where the PKey was found. */ int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { int ret, i; u16 tmp_pkey; int partial_ix = -1; for (i = 0; i < device->port_data[port_num].immutable.pkey_tbl_len; ++i) { ret = ib_query_pkey(device, port_num, i, &tmp_pkey); if (ret) return ret; if ((pkey & 0x7fff) == (tmp_pkey & 0x7fff)) { /* if there is full-member pkey take it.*/ if (tmp_pkey & 0x8000) { *index = i; return 0; } if (partial_ix < 0) partial_ix = i; } } /*no full-member, if exists take the limited*/ if (partial_ix >= 0) { *index = partial_ix; return 0; } return -ENOENT; } EXPORT_SYMBOL(ib_find_pkey); /** * ib_get_net_dev_by_params() - Return the appropriate net_dev * for a received CM request * @dev: An RDMA device on which the request has been received. * @port: Port number on the RDMA device. * @pkey: The Pkey the request came on. * @gid: A GID that the net_dev uses to communicate. * @addr: Contains the IP address that the request specified as its * destination. * */ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr) { struct net_device *net_dev = NULL; unsigned long index; void *client_data; if (!rdma_protocol_ib(dev, port)) return NULL; /* * Holding the read side guarantees that the client will not become * unregistered while we are calling get_net_dev_by_params() */ down_read(&dev->client_data_rwsem); xan_for_each_marked (&dev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->get_net_dev_by_params) continue; net_dev = client->get_net_dev_by_params(dev, port, pkey, gid, addr, client_data); if (net_dev) break; } up_read(&dev->client_data_rwsem); return net_dev; } EXPORT_SYMBOL(ib_get_net_dev_by_params); void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) { struct ib_device_ops *dev_ops = &dev->ops; #define SET_DEVICE_OP(ptr, name) \ do { \ if (ops->name) \ if (!((ptr)->name)) \ (ptr)->name = ops->name; \ } while (0) #define SET_OBJ_SIZE(ptr, name) SET_DEVICE_OP(ptr, size_##name) if (ops->driver_id != RDMA_DRIVER_UNKNOWN) { WARN_ON(dev_ops->driver_id != RDMA_DRIVER_UNKNOWN && dev_ops->driver_id != ops->driver_id); dev_ops->driver_id = ops->driver_id; } if (ops->owner) { WARN_ON(dev_ops->owner && dev_ops->owner != ops->owner); dev_ops->owner = ops->owner; } if (ops->uverbs_abi_ver) dev_ops->uverbs_abi_ver = ops->uverbs_abi_ver; dev_ops->uverbs_no_driver_id_binding |= ops->uverbs_no_driver_id_binding; SET_DEVICE_OP(dev_ops, add_gid); SET_DEVICE_OP(dev_ops, add_sub_dev); SET_DEVICE_OP(dev_ops, advise_mr); SET_DEVICE_OP(dev_ops, alloc_dm); SET_DEVICE_OP(dev_ops, alloc_hw_device_stats); SET_DEVICE_OP(dev_ops, alloc_hw_port_stats); SET_DEVICE_OP(dev_ops, alloc_mr); SET_DEVICE_OP(dev_ops, alloc_mr_integrity); SET_DEVICE_OP(dev_ops, alloc_mw); SET_DEVICE_OP(dev_ops, alloc_pd); SET_DEVICE_OP(dev_ops, alloc_rdma_netdev); SET_DEVICE_OP(dev_ops, alloc_ucontext); SET_DEVICE_OP(dev_ops, alloc_xrcd); SET_DEVICE_OP(dev_ops, attach_mcast); SET_DEVICE_OP(dev_ops, check_mr_status); SET_DEVICE_OP(dev_ops, counter_alloc_stats); SET_DEVICE_OP(dev_ops, counter_bind_qp); SET_DEVICE_OP(dev_ops, counter_dealloc); SET_DEVICE_OP(dev_ops, counter_unbind_qp); SET_DEVICE_OP(dev_ops, counter_update_stats); SET_DEVICE_OP(dev_ops, create_ah); SET_DEVICE_OP(dev_ops, create_counters); SET_DEVICE_OP(dev_ops, create_cq); SET_DEVICE_OP(dev_ops, create_flow); SET_DEVICE_OP(dev_ops, create_qp); SET_DEVICE_OP(dev_ops, create_rwq_ind_table); SET_DEVICE_OP(dev_ops, create_srq); SET_DEVICE_OP(dev_ops, create_user_ah); SET_DEVICE_OP(dev_ops, create_wq); SET_DEVICE_OP(dev_ops, dealloc_dm); SET_DEVICE_OP(dev_ops, dealloc_driver); SET_DEVICE_OP(dev_ops, dealloc_mw); SET_DEVICE_OP(dev_ops, dealloc_pd); SET_DEVICE_OP(dev_ops, dealloc_ucontext); SET_DEVICE_OP(dev_ops, dealloc_xrcd); SET_DEVICE_OP(dev_ops, del_gid); SET_DEVICE_OP(dev_ops, del_sub_dev); SET_DEVICE_OP(dev_ops, dereg_mr); SET_DEVICE_OP(dev_ops, destroy_ah); SET_DEVICE_OP(dev_ops, destroy_counters); SET_DEVICE_OP(dev_ops, destroy_cq); SET_DEVICE_OP(dev_ops, destroy_flow); SET_DEVICE_OP(dev_ops, destroy_flow_action); SET_DEVICE_OP(dev_ops, destroy_qp); SET_DEVICE_OP(dev_ops, destroy_rwq_ind_table); SET_DEVICE_OP(dev_ops, destroy_srq); SET_DEVICE_OP(dev_ops, destroy_wq); SET_DEVICE_OP(dev_ops, device_group); SET_DEVICE_OP(dev_ops, detach_mcast); SET_DEVICE_OP(dev_ops, disassociate_ucontext); SET_DEVICE_OP(dev_ops, drain_rq); SET_DEVICE_OP(dev_ops, drain_sq); SET_DEVICE_OP(dev_ops, enable_driver); SET_DEVICE_OP(dev_ops, fill_res_cm_id_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_mr_entry); SET_DEVICE_OP(dev_ops, fill_res_mr_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_qp_entry); SET_DEVICE_OP(dev_ops, fill_res_qp_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_srq_entry); SET_DEVICE_OP(dev_ops, fill_res_srq_entry_raw); SET_DEVICE_OP(dev_ops, fill_stat_mr_entry); SET_DEVICE_OP(dev_ops, get_dev_fw_str); SET_DEVICE_OP(dev_ops, get_dma_mr); SET_DEVICE_OP(dev_ops, get_hw_stats); SET_DEVICE_OP(dev_ops, get_link_layer); SET_DEVICE_OP(dev_ops, get_netdev); SET_DEVICE_OP(dev_ops, get_numa_node); SET_DEVICE_OP(dev_ops, get_port_immutable); SET_DEVICE_OP(dev_ops, get_vector_affinity); SET_DEVICE_OP(dev_ops, get_vf_config); SET_DEVICE_OP(dev_ops, get_vf_guid); SET_DEVICE_OP(dev_ops, get_vf_stats); SET_DEVICE_OP(dev_ops, iw_accept); SET_DEVICE_OP(dev_ops, iw_add_ref); SET_DEVICE_OP(dev_ops, iw_connect); SET_DEVICE_OP(dev_ops, iw_create_listen); SET_DEVICE_OP(dev_ops, iw_destroy_listen); SET_DEVICE_OP(dev_ops, iw_get_qp); SET_DEVICE_OP(dev_ops, iw_reject); SET_DEVICE_OP(dev_ops, iw_rem_ref); SET_DEVICE_OP(dev_ops, map_mr_sg); SET_DEVICE_OP(dev_ops, map_mr_sg_pi); SET_DEVICE_OP(dev_ops, mmap); SET_DEVICE_OP(dev_ops, mmap_free); SET_DEVICE_OP(dev_ops, modify_ah); SET_DEVICE_OP(dev_ops, modify_cq); SET_DEVICE_OP(dev_ops, modify_device); SET_DEVICE_OP(dev_ops, modify_hw_stat); SET_DEVICE_OP(dev_ops, modify_port); SET_DEVICE_OP(dev_ops, modify_qp); SET_DEVICE_OP(dev_ops, modify_srq); SET_DEVICE_OP(dev_ops, modify_wq); SET_DEVICE_OP(dev_ops, peek_cq); SET_DEVICE_OP(dev_ops, poll_cq); SET_DEVICE_OP(dev_ops, port_groups); SET_DEVICE_OP(dev_ops, post_recv); SET_DEVICE_OP(dev_ops, post_send); SET_DEVICE_OP(dev_ops, post_srq_recv); SET_DEVICE_OP(dev_ops, process_mad); SET_DEVICE_OP(dev_ops, query_ah); SET_DEVICE_OP(dev_ops, query_device); SET_DEVICE_OP(dev_ops, query_gid); SET_DEVICE_OP(dev_ops, query_pkey); SET_DEVICE_OP(dev_ops, query_port); SET_DEVICE_OP(dev_ops, query_qp); SET_DEVICE_OP(dev_ops, query_srq); SET_DEVICE_OP(dev_ops, query_ucontext); SET_DEVICE_OP(dev_ops, rdma_netdev_get_params); SET_DEVICE_OP(dev_ops, read_counters); SET_DEVICE_OP(dev_ops, reg_dm_mr); SET_DEVICE_OP(dev_ops, reg_user_mr); SET_DEVICE_OP(dev_ops, reg_user_mr_dmabuf); SET_DEVICE_OP(dev_ops, req_notify_cq); SET_DEVICE_OP(dev_ops, rereg_user_mr); SET_DEVICE_OP(dev_ops, resize_cq); SET_DEVICE_OP(dev_ops, set_vf_guid); SET_DEVICE_OP(dev_ops, set_vf_link_state); SET_DEVICE_OP(dev_ops, ufile_hw_cleanup); SET_DEVICE_OP(dev_ops, report_port_event); SET_OBJ_SIZE(dev_ops, ib_ah); SET_OBJ_SIZE(dev_ops, ib_counters); SET_OBJ_SIZE(dev_ops, ib_cq); SET_OBJ_SIZE(dev_ops, ib_mw); SET_OBJ_SIZE(dev_ops, ib_pd); SET_OBJ_SIZE(dev_ops, ib_qp); SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table); SET_OBJ_SIZE(dev_ops, ib_srq); SET_OBJ_SIZE(dev_ops, ib_ucontext); SET_OBJ_SIZE(dev_ops, ib_xrcd); } EXPORT_SYMBOL(ib_set_device_ops); int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name) { struct ib_device *sub; int ret = 0; if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev) return -EOPNOTSUPP; if (!ib_device_try_get(parent)) return -EINVAL; sub = parent->ops.add_sub_dev(parent, type, name); if (IS_ERR(sub)) { ib_device_put(parent); return PTR_ERR(sub); } sub->type = type; sub->parent = parent; mutex_lock(&parent->subdev_lock); list_add_tail(&parent->subdev_list_head, &sub->subdev_list); mutex_unlock(&parent->subdev_lock); return ret; } EXPORT_SYMBOL(ib_add_sub_device); int ib_del_sub_device_and_put(struct ib_device *sub) { struct ib_device *parent = sub->parent; if (!parent) return -EOPNOTSUPP; mutex_lock(&parent->subdev_lock); list_del(&sub->subdev_list); mutex_unlock(&parent->subdev_lock); ib_device_put(sub); parent->ops.del_sub_dev(sub); ib_device_put(parent); return 0; } EXPORT_SYMBOL(ib_del_sub_device_and_put); #ifdef CONFIG_INFINIBAND_VIRT_DMA int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents) { struct scatterlist *s; int i; for_each_sg(sg, s, nents, i) { sg_dma_address(s) = (uintptr_t)sg_virt(s); sg_dma_len(s) = s->length; } return nents; } EXPORT_SYMBOL(ib_dma_virt_map_sg); #endif /* CONFIG_INFINIBAND_VIRT_DMA */ static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { [RDMA_NL_LS_OP_RESOLVE] = { .doit = ib_nl_handle_resolve_resp, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_SET_TIMEOUT] = { .doit = ib_nl_handle_set_timeout, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_IP_RESOLVE] = { .doit = ib_nl_handle_ip_res_resp, .flags = RDMA_NL_ADMIN_PERM, }, }; void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev) { enum ib_port_state curr_state; struct ib_event ibevent = {}; u32 port; if (ib_query_netdev_port(ibdev, ndev, &port)) return; curr_state = ib_get_curr_port_state(ndev); write_lock_irq(&ibdev->cache_lock); if (ibdev->port_data[port].cache.last_port_state == curr_state) { write_unlock_irq(&ibdev->cache_lock); return; } ibdev->port_data[port].cache.last_port_state = curr_state; write_unlock_irq(&ibdev->cache_lock); ibevent.event = (curr_state == IB_PORT_DOWN) ? IB_EVENT_PORT_ERR : IB_EVENT_PORT_ACTIVE; ibevent.device = ibdev; ibevent.element.port_num = port; ib_dispatch_event(&ibevent); } EXPORT_SYMBOL(ib_dispatch_port_state_event); static void handle_port_event(struct net_device *ndev, unsigned long event) { struct ib_device *ibdev; /* Currently, link events in bonding scenarios are still * reported by drivers that support bonding. */ if (netif_is_lag_master(ndev) || netif_is_lag_port(ndev)) return; ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN); if (!ibdev) return; if (ibdev->ops.report_port_event) { ibdev->ops.report_port_event(ibdev, ndev, event); goto put_ibdev; } ib_dispatch_port_state_event(ibdev, ndev); put_ibdev: ib_device_put(ibdev); }; static int ib_netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct ib_device *ibdev; u32 port; switch (event) { case NETDEV_CHANGENAME: ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN); if (!ibdev) return NOTIFY_DONE; if (ib_query_netdev_port(ibdev, ndev, &port)) { ib_device_put(ibdev); break; } rdma_nl_notify_event(ibdev, port, RDMA_NETDEV_RENAME_EVENT); ib_device_put(ibdev); break; case NETDEV_UP: case NETDEV_CHANGE: case NETDEV_DOWN: handle_port_event(ndev, event); break; default: break; } return NOTIFY_DONE; } static struct notifier_block nb_netdevice = { .notifier_call = ib_netdevice_event, }; static int __init ib_core_init(void) { int ret = -ENOMEM; ib_wq = alloc_workqueue("infiniband", 0, 0); if (!ib_wq) return -ENOMEM; ib_unreg_wq = alloc_workqueue("ib-unreg-wq", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); if (!ib_unreg_wq) goto err; ib_comp_wq = alloc_workqueue("ib-comp-wq", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0); if (!ib_comp_wq) goto err_unbound; ib_comp_unbound_wq = alloc_workqueue("ib-comp-unb-wq", WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, WQ_UNBOUND_MAX_ACTIVE); if (!ib_comp_unbound_wq) goto err_comp; ret = class_register(&ib_class); if (ret) { pr_warn("Couldn't create InfiniBand device class\n"); goto err_comp_unbound; } rdma_nl_init(); ret = addr_init(); if (ret) { pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } ret = ib_mad_init(); if (ret) { pr_warn("Couldn't init IB MAD\n"); goto err_addr; } ret = ib_sa_init(); if (ret) { pr_warn("Couldn't init SA\n"); goto err_mad; } ret = register_blocking_lsm_notifier(&ibdev_lsm_nb); if (ret) { pr_warn("Couldn't register LSM notifier. ret %d\n", ret); goto err_sa; } ret = register_pernet_device(&rdma_dev_net_ops); if (ret) { pr_warn("Couldn't init compat dev. ret %d\n", ret); goto err_compat; } nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); ret = roce_gid_mgmt_init(); if (ret) { pr_warn("Couldn't init RoCE GID management\n"); goto err_parent; } register_netdevice_notifier(&nb_netdevice); return 0; err_parent: rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: ib_sa_cleanup(); err_mad: ib_mad_cleanup(); err_addr: addr_cleanup(); err_ibnl: class_unregister(&ib_class); err_comp_unbound: destroy_workqueue(ib_comp_unbound_wq); err_comp: destroy_workqueue(ib_comp_wq); err_unbound: destroy_workqueue(ib_unreg_wq); err: destroy_workqueue(ib_wq); return ret; } static void __exit ib_core_cleanup(void) { unregister_netdevice_notifier(&nb_netdevice); roce_gid_mgmt_cleanup(); rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); unregister_blocking_lsm_notifier(&ibdev_lsm_nb); ib_sa_cleanup(); ib_mad_cleanup(); addr_cleanup(); rdma_nl_exit(); class_unregister(&ib_class); destroy_workqueue(ib_comp_unbound_wq); destroy_workqueue(ib_comp_wq); /* Make sure that any pending umem accounting work is done. */ destroy_workqueue(ib_wq); destroy_workqueue(ib_unreg_wq); WARN_ON(!xa_empty(&clients)); WARN_ON(!xa_empty(&devices)); } MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4); /* ib core relies on netdev stack to first register net_ns_type_operations * ns kobject type before ib_core initialization. */ fs_initcall(ib_core_init); module_exit(ib_core_cleanup); |
| 12 2 12 24 15 24 24 24 24 23 6 108 369 108 368 107 108 108 12 108 108 360 73 73 56 73 73 369 369 369 369 368 369 368 369 367 368 368 368 | 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 | #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/swap.h> #include <linux/rmap.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #ifndef CONFIG_MMU_GATHER_NO_GATHER static bool tlb_next_batch(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; /* Limit batching if we have delayed rmaps pending */ if (tlb->delayed_rmap && tlb->active != &tlb->local) return false; batch = tlb->active; if (batch->next) { tlb->active = batch->next; return true; } if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) return false; batch = (void *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (!batch) return false; tlb->batch_count++; batch->next = NULL; batch->nr = 0; batch->max = MAX_GATHER_BATCH; tlb->active->next = batch; tlb->active = batch; return true; } #ifdef CONFIG_SMP static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_struct *vma) { struct encoded_page **pages = batch->encoded_pages; for (int i = 0; i < batch->nr; i++) { struct encoded_page *enc = pages[i]; if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) { struct page *page = encoded_page_ptr(enc); unsigned int nr_pages = 1; if (unlikely(encoded_page_flags(enc) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr_pages = encoded_nr_pages(pages[++i]); folio_remove_rmap_ptes(page_folio(page), page, nr_pages, vma); } } } /** * tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB * @tlb: the current mmu_gather * @vma: The memory area from which the pages are being removed. * * Note that because of how tlb_next_batch() above works, we will * never start multiple new batches with pending delayed rmaps, so * we only need to walk through the current active batch and the * original local one. */ void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (!tlb->delayed_rmap) return; tlb_flush_rmap_batch(&tlb->local, vma); if (tlb->active != &tlb->local) tlb_flush_rmap_batch(tlb->active, vma); tlb->delayed_rmap = 0; } #endif /* * We might end up freeing a lot of pages. Reschedule on a regular * basis to avoid soft lockups in configurations without full * preemption enabled. The magic number of 512 folios seems to work. */ #define MAX_NR_FOLIOS_PER_FREE 512 static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch) { struct encoded_page **pages = batch->encoded_pages; unsigned int nr, nr_pages; while (batch->nr) { if (!page_poisoning_enabled_static() && !want_init_on_free()) { nr = min(MAX_NR_FOLIOS_PER_FREE, batch->nr); /* * Make sure we cover page + nr_pages, and don't leave * nr_pages behind when capping the number of entries. */ if (unlikely(encoded_page_flags(pages[nr - 1]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr++; } else { /* * With page poisoning and init_on_free, the time it * takes to free memory grows proportionally with the * actual memory size. Therefore, limit based on the * actual memory size and not the number of involved * folios. */ for (nr = 0, nr_pages = 0; nr < batch->nr && nr_pages < MAX_NR_FOLIOS_PER_FREE; nr++) { if (unlikely(encoded_page_flags(pages[nr]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr_pages += encoded_nr_pages(pages[++nr]); else nr_pages++; } } free_pages_and_swap_cache(pages, nr); pages += nr; batch->nr -= nr; cond_resched(); } } static void tlb_batch_pages_flush(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; for (batch = &tlb->local; batch && batch->nr; batch = batch->next) __tlb_batch_free_encoded_pages(batch); tlb->active = &tlb->local; } static void tlb_batch_list_free(struct mmu_gather *tlb) { struct mmu_gather_batch *batch, *next; for (batch = tlb->local.next; batch; batch = next) { next = batch->next; free_pages((unsigned long)batch, 0); } tlb->local.next = NULL; } static bool __tlb_remove_folio_pages_size(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap, int page_size) { int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0; struct mmu_gather_batch *batch; VM_BUG_ON(!tlb->end); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE VM_WARN_ON(tlb->page_size != page_size); VM_WARN_ON_ONCE(nr_pages != 1 && page_size != PAGE_SIZE); VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1)); #endif batch = tlb->active; /* * Add the page and check if we are full. If so * force a flush. */ if (likely(nr_pages == 1)) { batch->encoded_pages[batch->nr++] = encode_page(page, flags); } else { flags |= ENCODED_PAGE_BIT_NR_PAGES_NEXT; batch->encoded_pages[batch->nr++] = encode_page(page, flags); batch->encoded_pages[batch->nr++] = encode_nr_pages(nr_pages); } /* * Make sure that we can always add another "page" + "nr_pages", * requiring two entries instead of only a single one. */ if (batch->nr >= batch->max - 1) { if (!tlb_next_batch(tlb)) return true; batch = tlb->active; } VM_BUG_ON_PAGE(batch->nr > batch->max - 1, page); return false; } bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap) { return __tlb_remove_folio_pages_size(tlb, page, nr_pages, delay_rmap, PAGE_SIZE); } bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, bool delay_rmap, int page_size) { return __tlb_remove_folio_pages_size(tlb, page, 1, delay_rmap, page_size); } #endif /* MMU_GATHER_NO_GATHER */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE static void __tlb_remove_table_free(struct mmu_table_batch *batch) { int i; for (i = 0; i < batch->nr; i++) __tlb_remove_table(batch->tables[i]); free_page((unsigned long)batch); } #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * Semi RCU freeing of the page directories. * * This is needed by some architectures to implement software pagetable walkers. * * gup_fast() and other software pagetable walkers do a lockless page-table * walk and therefore needs some synchronization with the freeing of the page * directories. The chosen means to accomplish that is by disabling IRQs over * the walk. * * Architectures that use IPIs to flush TLBs will then automagically DTRT, * since we unlink the page, flush TLBs, free the page. Since the disabling of * IRQs delays the completion of the TLB flush we can never observe an already * freed page. * * Architectures that do not have this (PPC) need to delay the freeing by some * other means, this is that means. * * What we do is batch the freed directory pages (tables) and RCU free them. * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling * holds off grace periods. * * However, in order to batch these pages we need to allocate storage, this * allocation is deep inside the MM code and can thus easily fail on memory * pressure. To guarantee progress we fall back to single table freeing, see * the implementation of tlb_remove_table_one(). * */ static void tlb_remove_table_smp_sync(void *arg) { /* Simply deliver the interrupt */ } void tlb_remove_table_sync_one(void) { /* * This isn't an RCU grace period and hence the page-tables cannot be * assumed to be actually RCU-freed. * * It is however sufficient for software page-table walkers that rely on * IRQ disabling. */ smp_call_function(tlb_remove_table_smp_sync, NULL, 1); } static void tlb_remove_table_rcu(struct rcu_head *head) { __tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu)); } static void tlb_remove_table_free(struct mmu_table_batch *batch) { call_rcu(&batch->rcu, tlb_remove_table_rcu); } #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ static void tlb_remove_table_free(struct mmu_table_batch *batch) { __tlb_remove_table_free(batch); } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ /* * If we want tlb_remove_table() to imply TLB invalidates. */ static inline void tlb_table_invalidate(struct mmu_gather *tlb) { if (tlb_needs_table_invalidate()) { /* * Invalidate page-table caches used by hardware walkers. Then * we still need to RCU-sched wait while freeing the pages * because software walkers can still be in-flight. */ tlb_flush_mmu_tlbonly(tlb); } } #ifdef CONFIG_PT_RECLAIM static inline void __tlb_remove_table_one_rcu(struct rcu_head *head) { struct ptdesc *ptdesc; ptdesc = container_of(head, struct ptdesc, pt_rcu_head); __tlb_remove_table(ptdesc); } static inline void __tlb_remove_table_one(void *table) { struct ptdesc *ptdesc; ptdesc = table; call_rcu(&ptdesc->pt_rcu_head, __tlb_remove_table_one_rcu); } #else static inline void __tlb_remove_table_one(void *table) { tlb_remove_table_sync_one(); __tlb_remove_table(table); } #endif /* CONFIG_PT_RECLAIM */ static void tlb_remove_table_one(void *table) { __tlb_remove_table_one(table); } static void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; if (*batch) { tlb_table_invalidate(tlb); tlb_remove_table_free(*batch); *batch = NULL; } } void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; if (*batch == NULL) { *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { tlb_table_invalidate(tlb); tlb_remove_table_one(table); return; } (*batch)->nr = 0; } (*batch)->tables[(*batch)->nr++] = table; if ((*batch)->nr == MAX_TABLE_BATCH) tlb_table_flush(tlb); } static inline void tlb_table_init(struct mmu_gather *tlb) { tlb->batch = NULL; } #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_table_flush(struct mmu_gather *tlb) { } static inline void tlb_table_init(struct mmu_gather *tlb) { } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ static void tlb_flush_mmu_free(struct mmu_gather *tlb) { tlb_table_flush(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_pages_flush(tlb); #endif } void tlb_flush_mmu(struct mmu_gather *tlb) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_mmu_free(tlb); } static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { tlb->mm = mm; tlb->fullmm = fullmm; #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb->need_flush_all = 0; tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); tlb->active = &tlb->local; tlb->batch_count = 0; #endif tlb->delayed_rmap = 0; tlb_table_init(tlb); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE tlb->page_size = 0; #endif __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } /** * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, false); } /** * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * In this case, @mm is without users and we're going to destroy the * full address space (exit/execve). * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, true); } /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish * * Called at the end of the shootdown operation to free up any resources that * were required. */ void tlb_finish_mmu(struct mmu_gather *tlb) { /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB * flush by batching, one thread may end up seeing inconsistent PTEs * and result in having stale TLB entries. So flush TLB forcefully * if we detect parallel PTE batching threads. * * However, some syscalls, e.g. munmap(), may free page tables, this * needs force flush everything in the given range. Otherwise this * may result in having stale TLB entries for some architectures, * e.g. aarch64, that could specify flush what level TLB. */ if (mm_tlb_flush_nested(tlb->mm)) { /* * The aarch64 yields better performance with fullmm by * avoiding multiple CPUs spamming TLBI messages at the * same time. * * On x86 non-fullmm doesn't yield significant difference * against fullmm. */ tlb->fullmm = 1; __tlb_reset_range(tlb); tlb->freed_tables = 1; } tlb_flush_mmu(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_list_free(tlb); #endif dec_tlb_flush_pending(tlb->mm); } |
| 3 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 14 253 244 244 231 231 253 253 1 253 253 253 1 253 253 231 231 16 16 16 16 16 16 231 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | // SPDX-License-Identifier: GPL-2.0 /* * inode.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ #define pr_fmt(fmt) "debugfs: " fmt #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/fsnotify.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/security.h> #include "internal.h" #define DEBUGFS_DEFAULT_MODE 0700 static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; /* * Don't allow access attributes to be changed whilst the kernel is locked down * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret) return ret; } return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_dir_inode_operations = { .lookup = simple_lookup, .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = debugfs_setattr, }; static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); } return inode; } struct debugfs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; /* Opt_* bitfield. */ unsigned int opts; }; enum { Opt_uid, Opt_gid, Opt_mode, Opt_source, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_uid ("uid", Opt_uid), fsparam_string ("source", Opt_source), {} }; static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct debugfs_fs_info *opts = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; but * traditionally debugfs has ignored all mount options */ if (opt == -ENOPARAM) return 0; return opt; } switch (opt) { case Opt_uid: opts->uid = result.uid; break; case Opt_gid: opts->gid = result.gid; break; case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); fc->source = param->string; param->string = NULL; break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options */ } opts->opts |= BIT(opt); return 0; } static void _debugfs_apply_options(struct super_block *sb, bool remount) { struct debugfs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); /* * On remount, only reset mode/uid/gid if they were provided as mount * options. */ if (!remount || fsi->opts & BIT(Opt_mode)) { inode->i_mode &= ~S_IALLUGO; inode->i_mode |= fsi->mode; } if (!remount || fsi->opts & BIT(Opt_uid)) inode->i_uid = fsi->uid; if (!remount || fsi->opts & BIT(Opt_gid)) inode->i_gid = fsi->gid; } static void debugfs_apply_options(struct super_block *sb) { _debugfs_apply_options(sb, false); } static void debugfs_apply_options_remount(struct super_block *sb) { _debugfs_apply_options(sb, true); } static int debugfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; debugfs_apply_options_remount(sb); return 0; } static int debugfs_show_options(struct seq_file *m, struct dentry *root) { struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, fsi->uid)); if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, fsi->gid)); if (fsi->mode != DEBUGFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mode); return 0; } static struct kmem_cache *debugfs_inode_cachep __ro_after_init; static void init_once(void *foo) { struct debugfs_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static struct inode *debugfs_alloc_inode(struct super_block *sb) { struct debugfs_inode_info *info; info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, .alloc_inode = debugfs_alloc_inode, .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; if (fsd) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { struct inode *inode = path->dentry->d_inode; return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); } static const struct dentry_operations debugfs_dops = { .d_delete = always_delete_dentry, .d_release = debugfs_release_dentry, .d_automount = debugfs_automount, }; static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr debug_files[] = {{""}}; int err; err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); if (err) return err; sb->s_op = &debugfs_super_operations; sb->s_d_op = &debugfs_dops; debugfs_apply_options(sb); return 0; } static int debugfs_get_tree(struct fs_context *fc) { if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return -EPERM; return get_tree_single(fc, debugfs_fill_super); } static void debugfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations debugfs_context_ops = { .free = debugfs_free_fc, .parse_param = debugfs_parse_param, .get_tree = debugfs_get_tree, .reconfigure = debugfs_reconfigure, }; static int debugfs_init_fs_context(struct fs_context *fc) { struct debugfs_fs_info *fsi; fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->mode = DEBUGFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &debugfs_context_ops; return 0; } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", .init_fs_context = debugfs_init_fs_context, .parameters = debugfs_param_specs, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("debugfs"); /** * debugfs_lookup() - look up an existing debugfs file * @name: a pointer to a string containing the name of the file to look up. * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file * doesn't exist or an error occurs, %NULL will be returned. The returned * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) { struct dentry *dentry; if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); static struct dentry *start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; int error; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return ERR_PTR(-EPERM); if (!debugfs_initialized()) return ERR_PTR(-ENOENT); pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) { pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super * block. A pointer to that is in the struct vfsmount that we * have around. */ if (!parent) parent = debugfs_mount->mnt_root; inode_lock(d_inode(parent)); if (unlikely(IS_DEADDIR(d_inode(parent)))) dentry = ERR_PTR(-ENOENT); else dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry)) pr_err("Directory '%s' with parent '%s' already present!\n", name, parent->d_name.name); else pr_err("File '%s' in directory '%s' already present!\n", name, parent->d_name.name); dput(dentry); dentry = ERR_PTR(-EEXIST); } if (IS_ERR(dentry)) { inode_unlock(d_inode(parent)); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } return dentry; } static struct dentry *failed_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); return dentry; } static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *proxy_fops, const void *real_fops) { struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); dentry = start_creating(name, parent); if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); return failed_creating(dentry); } inode->i_mode = mode; inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; if (!real_fops) proxy_fops = &debugfs_noop_file_operations; inode->i_fop = proxy_fops; DEBUGFS_I(inode)->raw = real_fops; DEBUGFS_I(inode)->aux = aux; d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_full); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct debugfs_short_fops *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_short_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); /** * debugfs_create_file_unsafe - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * debugfs_create_file_unsafe() is completely analogous to * debugfs_create_file(), the only difference being that the fops * handed it will not get protected against file removals by the * debugfs core. * * It is your responsibility to protect your struct file_operation * methods against file removals by means of debugfs_file_get() * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and * thus, may be used here. */ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, NULL, &debugfs_open_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); /** * debugfs_create_file_size - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * @file_size: initial file size * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) */ void debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, loff_t file_size) { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); /** * debugfs_create_dir - create a directory in the debugfs filesystem * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * directory will be created in the root of the debugfs filesystem. * * This function creates a directory in debugfs with the given name. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); return failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_create_automount - create automount point in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @f: function to be called when pathname resolution steps on that one. * @data: opaque argument to pass to f(). * * @f should return what ->d_automount() would. */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; DEBUGFS_I(inode)->automount = f; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); /** * debugfs_create_symlink- create a symbolic link in the debugfs filesystem * @name: a pointer to a string containing the name of the symbolic link to * create. * @parent: a pointer to the parent dentry for this symbolic link. This * should be a directory dentry if set. If this parameter is NULL, * then the symbolic link will be created in the root of the debugfs * filesystem. * @target: a pointer to a string containing the path to the target of the * symbolic link. * * This function creates a symbolic link with the given name in debugfs that * links to the given target path. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target) { struct dentry *dentry; struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); return dentry; } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); return failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either * debugfs_file_get() must see a dead dentry or we must see a * debugfs_fsdata instance at ->d_fsdata here (or both). */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); if (!fsd) return; /* if this was the last reference, we're done */ if (refcount_dec_and_test(&fsd->active_users)) return; /* * If there's still a reference, the code that obtained it can * be in different states: * - The common case of not using cancellations, or already * after debugfs_leave_cancellation(), where we just need * to wait for debugfs_file_put() which signals the completion; * - inside a cancellation section, i.e. between * debugfs_enter_cancellation() and debugfs_leave_cancellation(), * in which case we need to trigger the ->cancel() function, * and then wait for debugfs_file_put() just like in the * previous case; * - before debugfs_enter_cancellation() (but obviously after * debugfs_file_get()), in which case we may not see the * cancellation in the list on the first round of the loop, * but debugfs_enter_cancellation() signals the completion * after adding it, so this code gets woken up to call the * ->cancel() function. */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; /* * Lock the cancellations. Note that the cancellations * structs are meant to be on the stack, so we need to * ensure we either use them here or don't touch them, * and debugfs_leave_cancellation() will wait for this * to be finished processing before exiting one. It may * of course win and remove the cancellation, but then * chances are we never even got into this bit, we only * do if the refcount isn't zero already. */ mutex_lock(&fsd->cancellations_mtx); while ((c = list_first_entry_or_null(&fsd->cancellations, typeof(*c), list))) { list_del_init(&c->list); c->cancel(dentry, c->cancel_data); } mutex_unlock(&fsd->cancellations_mtx); wait_for_completion(&fsd->active_users_drained); } } static void remove_one(struct dentry *victim) { if (d_is_reg(victim)) __debugfs_file_removed(victim); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } /** * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function * (like debugfs_create_file() or variants thereof.) * * This function is required to be called in order for the file to be * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ void debugfs_remove(struct dentry *dentry) { if (IS_ERR_OR_NULL(dentry)) return; simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); simple_recursive_removal(dentry, remove_one); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it * @name: a pointer to a string containing the name of the item to look up. * @parent: a pointer to the parent dentry of the item. * * This is the equlivant of doing something like * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting * handled for the directory being looked up. */ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) { struct dentry *dentry; dentry = debugfs_lookup(name, parent); if (!dentry) return; debugfs_remove(dentry); dput(dentry); } EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** * debugfs_change_name - rename a file/directory in the debugfs filesystem * @dentry: dentry of an object to be renamed. * @fmt: format for new name * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * * This function will return 0 on success and -E... on failure. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) { int error = 0; const char *new_name; struct name_snapshot old_name; struct dentry *parent, *target; struct inode *dir; va_list ap; if (IS_ERR_OR_NULL(dentry)) return 0; va_start(ap, fmt); new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); va_end(ap); if (!new_name) return -ENOMEM; parent = dget_parent(dentry); dir = d_inode(parent); inode_lock(dir); take_dentry_name_snapshot(&old_name, dentry); if (WARN_ON_ONCE(dentry->d_parent != parent)) { error = -EINVAL; goto out; } if (strcmp(old_name.name.name, new_name) == 0) goto out; target = lookup_one_len(new_name, parent, strlen(new_name)); if (IS_ERR(target)) { error = PTR_ERR(target); goto out; } if (d_really_is_positive(target)) { dput(target); error = -EINVAL; goto out; } simple_rename_timestamp(dir, dentry, dir, target); d_move(dentry, target); dput(target); fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); out: release_dentry_name_snapshot(&old_name); inode_unlock(dir); dput(parent); kfree_const(new_name); return error; } EXPORT_SYMBOL_GPL(debugfs_change_name); /** * debugfs_initialized - Tells whether debugfs has been registered */ bool debugfs_initialized(void) { return debugfs_registered; } EXPORT_SYMBOL_GPL(debugfs_initialized); static int __init debugfs_kernel(char *str) { if (str) { if (!strcmp(str, "on")) debugfs_allow = DEBUGFS_ALLOW_API | DEBUGFS_ALLOW_MOUNT; else if (!strcmp(str, "no-mount")) debugfs_allow = DEBUGFS_ALLOW_API; else if (!strcmp(str, "off")) debugfs_allow = 0; } return 0; } early_param("debugfs", debugfs_kernel); static int __init debugfs_init(void) { int retval; if (!(debugfs_allow & DEBUGFS_ALLOW_MOUNT)) return -EPERM; retval = sysfs_create_mount_point(kernel_kobj, "debug"); if (retval) return retval; debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", sizeof(struct debugfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, init_once); if (debugfs_inode_cachep == NULL) { sysfs_remove_mount_point(kernel_kobj, "debug"); return -ENOMEM; } retval = register_filesystem(&debug_fs_type); if (retval) { // Really not going to happen sysfs_remove_mount_point(kernel_kobj, "debug"); kmem_cache_destroy(debugfs_inode_cachep); return retval; } debugfs_registered = true; return 0; } core_initcall(debugfs_init); |
| 61 853 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/bitops.h> #include <asm/types.h> /** * hweightN - returns the hamming weight of a N-bit word * @x: the word to weigh * * The Hamming Weight of a number is the total number of bits set in it. */ unsigned int __sw_hweight32(unsigned int w) { #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; w = (w & 0x33333333) + ((w >> 2) & 0x33333333); w = (w + (w >> 4)) & 0x0f0f0f0f; return (w * 0x01010101) >> 24; #else unsigned int res = w - ((w >> 1) & 0x55555555); res = (res & 0x33333333) + ((res >> 2) & 0x33333333); res = (res + (res >> 4)) & 0x0F0F0F0F; res = res + (res >> 8); return (res + (res >> 16)) & 0x000000FF; #endif } EXPORT_SYMBOL(__sw_hweight32); unsigned int __sw_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } EXPORT_SYMBOL(__sw_hweight16); unsigned int __sw_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } EXPORT_SYMBOL(__sw_hweight8); unsigned long __sw_hweight64(__u64 w) { #if BITS_PER_LONG == 32 return __sw_hweight32((unsigned int)(w >> 32)) + __sw_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul); w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful; return (w * 0x0101010101010101ul) >> 56; #else __u64 res = w - ((w >> 1) & 0x5555555555555555ul); res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; res = res + (res >> 8); res = res + (res >> 16); return (res + (res >> 32)) & 0x00000000000000FFul; #endif #endif } EXPORT_SYMBOL(__sw_hweight64); |
| 272 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM capability #if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CAPABILITY_H #include <linux/cred.h> #include <linux/tracepoint.h> #include <linux/user_namespace.h> /** * cap_capable - called after it's determined if a task has a particular * effective capability * * @cred: The credentials used * @target_ns: The user namespace of the resource being accessed * @capable_ns: The user namespace in which the credential provides the * capability to access the targeted resource. * This will be NULL if ret is not 0. * @cap: The capability to check for * @ret: The return value of the check: 0 if it does, -ve if it does not * * Allows to trace calls to cap_capable in commoncap.c */ TRACE_EVENT(cap_capable, TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *capable_ns, int cap, int ret), TP_ARGS(cred, target_ns, capable_ns, cap, ret), TP_STRUCT__entry( __field(const struct cred *, cred) __field(struct user_namespace *, target_ns) __field(const struct user_namespace *, capable_ns) __field(int, cap) __field(int, ret) ), TP_fast_assign( __entry->cred = cred; __entry->target_ns = target_ns; __entry->capable_ns = ret == 0 ? capable_ns : NULL; __entry->cap = cap; __entry->ret = ret; ), TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, __entry->ret) ); #endif /* _TRACE_CAPABILITY_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 336 332 335 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/mmap.c * * Copyright (C) 2012 ARM Ltd. */ #include <linux/io.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/types.h> #include <asm/cpufeature.h> #include <asm/page.h> static pgprot_t protection_map[16] __ro_after_init = { [VM_NONE] = PAGE_NONE, [VM_READ] = PAGE_READONLY, [VM_WRITE] = PAGE_READONLY, [VM_WRITE | VM_READ] = PAGE_READONLY, /* PAGE_EXECONLY if Enhanced PAN */ [VM_EXEC] = PAGE_READONLY_EXEC, [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, [VM_EXEC | VM_WRITE] = PAGE_READONLY_EXEC, [VM_EXEC | VM_WRITE | VM_READ] = PAGE_READONLY_EXEC, [VM_SHARED] = PAGE_NONE, [VM_SHARED | VM_READ] = PAGE_READONLY, [VM_SHARED | VM_WRITE] = PAGE_SHARED, [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, /* PAGE_EXECONLY if Enhanced PAN */ [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC }; /* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. */ int valid_phys_addr_range(phys_addr_t addr, size_t size) { /* * Check whether addr is covered by a memory region without the * MEMBLOCK_NOMAP attribute, and whether that region covers the * entire range. In theory, this could lead to false negatives * if the range is covered by distinct but adjacent memory regions * that only differ in other attributes. However, few of such * attributes have been defined, and it is debatable whether it * follows that /dev/mem read() calls should be able traverse * such boundaries. */ return memblock_is_region_memory(addr, size) && memblock_is_map_memory(addr); } /* * Do not allow /dev/mem mappings beyond the supported physical range. */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK); } static int __init adjust_protection_map(void) { /* * With Enhanced PAN we can honour the execute-only permissions as * there is no PAN override with such mappings. */ if (cpus_have_cap(ARM64_HAS_EPAN)) { protection_map[VM_EXEC] = PAGE_EXECONLY; protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } if (lpa2_is_enabled()) for (int i = 0; i < ARRAY_SIZE(protection_map); i++) pgprot_val(protection_map[i]) &= ~PTE_SHARED; return 0; } arch_initcall(adjust_protection_map); pgprot_t vm_get_page_prot(unsigned long vm_flags) { pteval_t prot; /* Short circuit GCS to avoid bloating the table. */ if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { prot = _PAGE_GCS_RO; } else { prot = pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); } if (vm_flags & VM_ARM64_BTI) prot |= PTE_GP; /* * There are two conditions required for returning a Normal Tagged * memory type: (1) the user requested it via PROT_MTE passed to * mmap() or mprotect() and (2) the corresponding vma supports MTE. We * register (1) as VM_MTE in the vma->vm_flags and (2) as * VM_MTE_ALLOWED. Note that the latter can only be set during the * mmap() call since mprotect() does not accept MAP_* flags. * Checking for VM_MTE only is sufficient since arch_validate_flags() * does not permit (VM_MTE & !VM_MTE_ALLOWED). */ if (vm_flags & VM_MTE) prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); #ifdef CONFIG_ARCH_HAS_PKEYS if (system_supports_poe()) { if (vm_flags & VM_PKEY_BIT0) prot |= PTE_PO_IDX_0; if (vm_flags & VM_PKEY_BIT1) prot |= PTE_PO_IDX_1; if (vm_flags & VM_PKEY_BIT2) prot |= PTE_PO_IDX_2; } #endif return __pgprot(prot); } EXPORT_SYMBOL(vm_get_page_prot); |
| 359 224 223 221 3 222 219 2 2 360 4 153 224 223 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/vmalloc.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> #include "slab.h" /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: within the current stack (when can't frame-check exactly) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; /* Finally, check stack depth if possible. */ #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER if (IS_ENABLED(CONFIG_STACK_GROWSUP)) { if ((void *)current_stack_pointer < obj + len) return BAD_STACK; } else { if (obj < (void *)current_stack_pointer) return BAD_STACK; } #endif return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { unsigned long addr = (unsigned long)ptr; unsigned long offset; struct folio *folio; if (is_kmap_addr(ptr)) { offset = offset_in_page(ptr); if (n > PAGE_SIZE - offset) usercopy_abort("kmap", NULL, to_user, offset, n); return; } if (is_vmalloc_addr(ptr) && !pagefault_disabled()) { struct vmap_area *area = find_vmap_area(addr); if (!area) usercopy_abort("vmalloc", "no area", to_user, 0, n); if (n > area->va_end - addr) { offset = addr - area->va_start; usercopy_abort("vmalloc", NULL, to_user, offset, n); } return; } if (!virt_addr_valid(ptr)) return; folio = virt_to_folio(ptr); if (folio_test_slab(folio)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, folio_slab(folio), to_user); } else if (folio_test_large(folio)) { offset = ptr - folio_address(folio); if (n > folio_size(folio) - offset) usercopy_abort("page alloc", NULL, to_user, offset, n); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER IS_ENABLED(CONFIG_STACK_GROWSUP) ? ptr - (void *)current_stack_pointer : (void *)current_stack_pointer - ptr, #else 0, #endif n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (kstrtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 3 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 | // SPDX-License-Identifier: GPL-1.0+ /* * originally based on the dummy device. * * Copyright 1999, Thomas Davis, tadavis@lbl.gov. * Based on dummy.c, and eql.c devices. * * bonding.c: an Ethernet Bonding driver * * This is useful to talk to a Cisco EtherChannel compatible equipment: * Cisco 5500 * Sun Trunking (Solaris) * Alteon AceDirector Trunks * Linux Bonding * and probably many L2 switches ... * * How it works: * ifconfig bond0 ipaddress netmask up * will setup a network device, with an ip address. No mac address * will be assigned at this time. The hw mac address will come from * the first slave bonded to the channel. All slaves will then use * this hw mac address. * * ifconfig bond0 down * will release all slaves, marking them as down. * * ifenslave bond0 eth0 * will attach eth0 to bond0 as a slave. eth0 hw mac address will either * a: be used as initial mac address * b: if a hw mac address already is there, eth0's hw mac address * will then be set from bond0. * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/filter.h> #include <linux/interrupt.h> #include <linux/ptrace.h> #include <linux/ioport.h> #include <linux/in.h> #include <net/ip.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <linux/timer.h> #include <linux/socket.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/bitops.h> #include <linux/io.h> #include <asm/dma.h> #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/smp.h> #include <linux/if_ether.h> #include <net/arp.h> #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/if_bonding.h> #include <linux/phy.h> #include <linux/jiffies.h> #include <linux/preempt.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_sched.h> #include <linux/rculist.h> #include <net/flow_dissector.h> #include <net/xfrm.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #if IS_ENABLED(CONFIG_TLS_DEVICE) #include <net/tls.h> #endif #include <net/ip6_route.h> #include <net/xdp.h> #include "bonding_priv.h" /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int tx_queues = BOND_DEFAULT_TX_QUEUES; static int num_peer_notif = 1; static int miimon; static int updelay; static int downdelay; static int use_carrier = 1; static char *mode; static char *primary; static char *primary_reselect; static char *lacp_rate; static int min_links; static char *ad_select; static char *xmit_hash_policy; static int arp_interval; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; static char *arp_all_targets; static char *fail_over_mac; static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; static int packets_per_slave = 1; static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(tx_queues, int, 0); MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); module_param_named(num_grat_arp, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on " "failover event (alias of num_unsol_na)"); module_param_named(num_unsol_na, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on " "failover event (alias of num_grat_arp)"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds"); module_param(downdelay, int, 0); MODULE_PARM_DESC(downdelay, "Delay before considering link down, " "in milliseconds"); module_param(use_carrier, int, 0); MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " "0 for off, 1 for on (default)"); module_param(mode, charp, 0); MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, " "1 for active-backup, 2 for balance-xor, " "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, " "6 for balance-alb"); module_param(primary, charp, 0); MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(primary_reselect, charp, 0); MODULE_PARM_DESC(primary_reselect, "Reselect primary slave " "once it comes up; " "0 for always (default), " "1 for only if speed of primary is " "better, " "2 for only on active slave " "failure"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " "0 for slow, 1 for fast"); module_param(ad_select, charp, 0); MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); module_param(min_links, int, 0); MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " "2 for layer 2+3, 3 for encap layer 2+3, " "4 for encap layer 3+4, 5 for vlan+srcmac"); module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form"); module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " "0 for none (default), 1 for active, " "2 for backup, 3 for all"); module_param(arp_all_targets, charp, 0); MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all"); module_param(fail_over_mac, charp, 0); MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to " "the same MAC; 0 for none (default), " "1 for active, 2 for follow"); module_param(all_slaves_active, int, 0); MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface " "by setting active flag for all slaves; " "0 for never (default), 1 for always."); module_param(resend_igmp, int, 0); MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on " "link failure"); module_param(packets_per_slave, int, 0); MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr " "mode; 0 for a random slave, 1 packet per " "slave (default), >1 packets per slave."); module_param(lp_interval, uint, 0); MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where " "the bonding driver sends learning packets to " "each slaves peer switch. The default is 1."); /*----------------------------- Global variables ----------------------------*/ #ifdef CONFIG_NET_POLL_CONTROLLER atomic_t netpoll_block_tx = ATOMIC_INIT(0); #endif unsigned int bond_net_id __read_mostly; static const struct flow_dissector_key flow_keys_bonding_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_ICMP, .offset = offsetof(struct flow_keys, icmp), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static struct flow_dissector flow_keys_bonding __read_mostly; /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); static void bond_uninit(struct net_device *bond_dev); static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod); static void bond_netdev_notify_work(struct work_struct *work); /*---------------------------- General routines -----------------------------*/ const char *bond_mode_name(int mode) { static const char *names[] = { [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)", [BOND_MODE_XOR] = "load balancing (xor)", [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)", [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation", [BOND_MODE_TLB] = "transmit load balancing", [BOND_MODE_ALB] = "adaptive load balancing", }; if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; } /** * bond_dev_queue_xmit - Prepare skb for xmit. * * @bond: bond device that got this skb for tx. * @skb: hw accel VLAN tagged skb to transmit * @slave_dev: slave that is supposed to xmit this skbuff */ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; BUILD_BUG_ON(sizeof(skb->queue_mapping) != sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); if (unlikely(netpoll_tx_running(bond->dev))) return bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); return dev_queue_xmit(skb); } static bool bond_sk_check(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: case BOND_MODE_XOR: if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) return true; fallthrough; default: return false; } } static bool bond_xdp_check(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: case BOND_MODE_ACTIVEBACKUP: return true; case BOND_MODE_8023AD: case BOND_MODE_XOR: /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: return false; } } /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, * We don't protect the slave list iteration with a lock because: * a. This operation is performed in IOCTL context, * b. The operation is protected by the RTNL semaphore in the 8021q code, * c. Holding a lock with BH disabled while directly calling a base driver * entry point is generally a BAD idea. * * The design of synchronization/protection for this operation in the 8021q * module is good for one or more VLAN devices over a single physical device * and cannot be extended for a teaming solution like bonding, so there is a * potential race condition here where a net device from the vlan group might * be referenced (either by a base driver or the 8021q code) while it is being * removed from the system. However, it turns out we're not making matters * worse, and if it works for regular VLAN usage it will work here too. */ /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res; bond_for_each_slave(bond, slave, iter) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } return 0; unwind: /* unwind to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { if (rollback_slave == slave) break; vlan_vid_del(rollback_slave->dev, proto, vid); } return res; } /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) vlan_vid_del(slave->dev, proto, vid); if (bond_is_lb(bond)) bond_alb_clear_vlan(bond, vid); return 0; } /*---------------------------------- XFRM -----------------------------------*/ #ifdef CONFIG_XFRM_OFFLOAD /** * bond_ipsec_dev - Get active device for IPsec offload * @xs: pointer to transformer state struct * * Context: caller must hold rcu_read_lock. * * Return: the device for ipsec offload, or NULL if not exist. **/ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; if (!bond_dev) return NULL; bond = netdev_priv(bond_dev); if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return NULL; slave = rcu_dereference(bond->curr_active_slave); if (!slave) return NULL; if (!xs->xso.real_dev) return NULL; if (xs->xso.real_dev != slave->dev) pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n", bond_dev->name, slave->dev->name, xs->xso.real_dev->name); return slave->dev; } /** * bond_ipsec_add_sa - program device with a security association * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ static int bond_ipsec_add_sa(struct xfrm_state *xs, struct netlink_ext_ack *extack) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; int err; if (!bond_dev) return -EINVAL; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!real_dev) { err = -ENODEV; goto out; } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload"); err = -EINVAL; goto out; } ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL); if (!ipsec) { err = -ENOMEM; goto out; } xs->xso.real_dev = real_dev; err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack); if (!err) { ipsec->xs = xs; INIT_LIST_HEAD(&ipsec->list); mutex_lock(&bond->ipsec_lock); list_add(&ipsec->list, &bond->ipsec_list); mutex_unlock(&bond->ipsec_lock); } else { kfree(ipsec); } out: netdev_put(real_dev, &tracker); return err; } static void bond_ipsec_add_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { if (!list_empty(&bond->ipsec_list)) slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_add\n", __func__); goto out; } list_for_each_entry(ipsec, &bond->ipsec_list, list) { /* If new state is added before ipsec_lock acquired */ if (ipsec->xs->xso.real_dev == real_dev) continue; ipsec->xs->xso.real_dev = real_dev; if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); ipsec->xs->xso.real_dev = NULL; } } out: mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_del_sa - clear out this specific SA * @xs: pointer to transformer state struct **/ static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; if (!bond_dev) return; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != real_dev); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: netdev_put(real_dev, &tracker); mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (ipsec->xs == xs) { list_del(&ipsec->list); kfree(ipsec); break; } } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_del_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (!ipsec->xs->xso.real_dev) continue; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); } else { real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); if (real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs); } } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bonding *bond; struct slave *slave; if (!bond_dev) return; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != real_dev); if (real_dev && real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(xs); out: netdev_put(real_dev, &tracker); } /** * bond_ipsec_offload_ok - can this packet use the xfrm hw offload * @skb: current data packet * @xs: pointer to transformer state struct **/ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *real_dev; bool ok = false; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || netif_is_bond_master(real_dev)) goto out; ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); out: rcu_read_unlock(); return ok; } /** * bond_advance_esn_state - ESN support for IPSec HW offload * @xs: pointer to transformer state struct **/ static void bond_advance_esn_state(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs); out: rcu_read_unlock(); } /** * bond_xfrm_update_stats - Update xfrm state * @xs: pointer to transformer state struct **/ static void bond_xfrm_update_stats(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs); out: rcu_read_unlock(); } static const struct xfrmdev_ops bond_xfrmdev_ops = { .xdo_dev_state_add = bond_ipsec_add_sa, .xdo_dev_state_delete = bond_ipsec_del_sa, .xdo_dev_state_free = bond_ipsec_free_sa, .xdo_dev_offload_ok = bond_ipsec_offload_ok, .xdo_dev_state_advance_esn = bond_advance_esn_state, .xdo_dev_state_update_stats = bond_xfrm_update_stats, }; #endif /* CONFIG_XFRM_OFFLOAD */ /*------------------------------- Link status -------------------------------*/ /* Set the carrier state for the master according to the state of its * slaves. If any slaves are up, the master is up. In 802.3ad mode, * do special 802.3ad magic. * * Returns zero if carrier state does not change, nonzero if it does. */ int bond_set_carrier(struct bonding *bond) { struct list_head *iter; struct slave *slave; if (!bond_has_slaves(bond)) goto down; if (BOND_MODE(bond) == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); return 1; } return 0; } } down: if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); return 1; } return 0; } /* Get link speed and duplex from the slave's base driver * using ethtool. If for some reason the call fails or the * values are invalid, set speed and duplex to -1, * and return. Return 1 if speed or duplex settings are * UNKNOWN; 0 otherwise. */ static int bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; struct ethtool_link_ksettings ecmd; int res; slave->speed = SPEED_UNKNOWN; slave->duplex = DUPLEX_UNKNOWN; res = __ethtool_get_link_ksettings(slave_dev, &ecmd); if (res < 0) return 1; if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1)) return 1; switch (ecmd.base.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: return 1; } slave->speed = ecmd.base.speed; slave->duplex = ecmd.base.duplex; return 0; } const char *bond_slave_link_status(s8 link) { switch (link) { case BOND_LINK_UP: return "up"; case BOND_LINK_FAIL: return "going down"; case BOND_LINK_DOWN: return "down"; case BOND_LINK_BACK: return "going back"; default: return "unknown"; } } /* if <dev> supports MII link status reporting, check its link status. * * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), * depending upon the setting of the use_carrier parameter. * * Return either BMSR_LSTATUS, meaning that the link is up (or we * can't tell and just pretend it is), or 0, meaning that the link is * down. * * If reporting is non-zero, instead of faking link up, return -1 if * both ETHTOOL and MII ioctls fail (meaning the device does not * support them). If use_carrier is set, return whatever it says. * It'd be nice if there was a good way to tell if a driver supports * netif_carrier, but there really isn't. */ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting) { const struct net_device_ops *slave_ops = slave_dev->netdev_ops; int (*ioctl)(struct net_device *, struct ifreq *, int); struct ifreq ifr; struct mii_ioctl_data *mii; if (!reporting && !netif_running(slave_dev)) return 0; if (bond->params.use_carrier) return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; /* Try to get link status using Ethtool first. */ if (slave_dev->ethtool_ops->get_link) return slave_dev->ethtool_ops->get_link(slave_dev) ? BMSR_LSTATUS : 0; /* Ethtool can't be used, fallback to MII ioctls. */ ioctl = slave_ops->ndo_eth_ioctl; if (ioctl) { /* TODO: set pointer to correct ioctl on a per team member * bases to make this more efficient. that is, once * we determine the correct ioctl, we will always * call it and not the others for that team * member. */ /* We cannot assume that SIOCGMIIPHY will also read a * register; not all network drivers (e.g., e100) * support that. */ /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; if (ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) return mii->val_out & BMSR_LSTATUS; } } /* If reporting, report that either there's no ndo_eth_ioctl, * or both SIOCGMIIREG and get_link failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. */ return reporting ? -1 : BMSR_LSTATUS; } /*----------------------------- Multicast list ------------------------------*/ /* Push the promiscuity flag down to appropriate slaves */ static int bond_set_promiscuity(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_promiscuity(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; } } return err; } /* Push the allmulti flag down to all slaves */ static int bond_set_allmulti(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_allmulti(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; } } return err; } /* Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active * slave. */ static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mcast_work.work); if (!rtnl_trylock()) { queue_delayed_work(bond->wq, &bond->mcast_work, 1); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); if (bond->igmp_retrans > 1) { bond->igmp_retrans--; queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } rtnl_unlock(); } /* Flush bond's hardware addresses from slave */ static void bond_hw_addr_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); dev_uc_unsync(slave_dev, bond_dev); dev_mc_unsync(slave_dev, bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_del(slave_dev, lacpdu_mcast_addr); } /*--------------------------- Active slave change ---------------------------*/ /* Update the hardware address list and promisc/allmulti for the new and * old active slaves (if any). Modes that are not using primary keep all * slaves up date at all times; only the modes that use primary need to call * this function to swap these settings during a failover. */ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { if (old_active) { if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); if (bond->dev->flags & IFF_UP) bond_hw_addr_flush(bond->dev, old_active->dev); bond_slave_ns_maddrs_add(bond, old_active); } if (new_active) { /* FIXME: Signal errors upstream. */ if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(new_active->dev, 1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); if (bond->dev->flags & IFF_UP) { netif_addr_lock_bh(bond->dev); dev_uc_sync(new_active->dev, bond->dev); dev_mc_sync(new_active->dev, bond->dev); netif_addr_unlock_bh(bond->dev); } bond_slave_ns_maddrs_del(bond, new_active); } } /** * bond_set_dev_addr - clone slave's address to bond * @bond_dev: bond net device * @slave_dev: slave net device * * Should be called with RTNL held. */ static int bond_set_dev_addr(struct net_device *bond_dev, struct net_device *slave_dev) { int err; slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", bond_dev, slave_dev, slave_dev->addr_len); err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; __dev_addr_set(bond_dev, slave_dev->dev_addr, slave_dev->addr_len); bond_dev->addr_assign_type = NET_ADDR_STOLEN; call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); return 0; } static struct slave *bond_get_old_active(struct bonding *bond, struct slave *new_active) { struct slave *slave; struct list_head *iter; bond_for_each_slave(bond, slave, iter) { if (slave == new_active) continue; if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr)) return slave; } return NULL; } /* bond_do_fail_over_mac * * Perform special MAC address swapping for fail_over_mac settings * * Called with RTNL */ static void bond_do_fail_over_mac(struct bonding *bond, struct slave *new_active, struct slave *old_active) { u8 tmp_mac[MAX_ADDR_LEN]; struct sockaddr_storage ss; int rv; switch (bond->params.fail_over_mac) { case BOND_FOM_ACTIVE: if (new_active) { rv = bond_set_dev_addr(bond->dev, new_active->dev); if (rv) slave_err(bond->dev, new_active->dev, "Error %d setting bond MAC from slave\n", -rv); } break; case BOND_FOM_FOLLOW: /* if new_active && old_active, swap them * if just old_active, do nothing (going to no active slave) * if just new_active, set new_active to bond's MAC */ if (!new_active) return; if (!old_active) old_active = bond_get_old_active(bond, new_active); if (old_active) { bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr, new_active->dev->addr_len); bond_hw_addr_copy(ss.__data, old_active->dev->dev_addr, old_active->dev->addr_len); ss.ss_family = new_active->dev->type; } else { bond_hw_addr_copy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len); ss.ss_family = bond->dev->type; } rv = dev_set_mac_address(new_active->dev, (struct sockaddr *)&ss, NULL); if (rv) { slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n", -rv); goto out; } if (!old_active) goto out; bond_hw_addr_copy(ss.__data, tmp_mac, new_active->dev->addr_len); ss.ss_family = old_active->dev->type; rv = dev_set_mac_address(old_active->dev, (struct sockaddr *)&ss, NULL); if (rv) slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n", -rv); out: break; default: netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n", bond->params.fail_over_mac); break; } } /** * bond_choose_primary_or_current - select the primary or high priority slave * @bond: our bonding struct * * - Check if there is a primary link. If the primary link was set and is up, * go on and do link reselection. * * - If primary link is not set or down, find the highest priority link. * If the highest priority link is not current slave, set it as primary * link and do link reselection. */ static struct slave *bond_choose_primary_or_current(struct bonding *bond) { struct slave *prim = rtnl_dereference(bond->primary_slave); struct slave *curr = rtnl_dereference(bond->curr_active_slave); struct slave *slave, *hprio = NULL; struct list_head *iter; if (!prim || prim->link != BOND_LINK_UP) { bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { hprio = hprio ?: slave; if (slave->prio > hprio->prio) hprio = slave; } } if (hprio && hprio != curr) { prim = hprio; goto link_reselect; } if (!curr || curr->link != BOND_LINK_UP) return NULL; return curr; } if (bond->force_primary) { bond->force_primary = false; return prim; } link_reselect: if (!curr || curr->link != BOND_LINK_UP) return prim; /* At this point, prim and curr are both up */ switch (bond->params.primary_reselect) { case BOND_PRI_RESELECT_ALWAYS: return prim; case BOND_PRI_RESELECT_BETTER: if (prim->speed < curr->speed) return curr; if (prim->speed == curr->speed && prim->duplex <= curr->duplex) return curr; return prim; case BOND_PRI_RESELECT_FAILURE: return curr; default: netdev_err(bond->dev, "impossible primary_reselect %d\n", bond->params.primary_reselect); return curr; } } /** * bond_find_best_slave - select the best available slave to be the active one * @bond: our bonding struct */ static struct slave *bond_find_best_slave(struct bonding *bond) { struct slave *slave, *bestslave = NULL; struct list_head *iter; int mintime = bond->params.updelay; slave = bond_choose_primary_or_current(bond); if (slave) return slave; bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) return slave; if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) && slave->delay < mintime) { mintime = slave->delay; bestslave = slave; } } return bestslave; } /* must be called in RCU critical section or with RTNL held */ static bool bond_should_notify_peers(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); if (!slave || !bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", slave ? slave->dev->name : "NULL"); return true; } /** * bond_change_active_slave - change the active slave into the specified one * @bond: our bonding struct * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. * Setting include flags, mc-list, promiscuity, allmulti, etc. * * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP, * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * * Caller must hold RTNL. */ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) { struct slave *old_active; ASSERT_RTNL(); old_active = rtnl_dereference(bond->curr_active_slave); if (old_active == new_active) return; #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_del_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ if (new_active) { new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { if (bond_uses_primary(bond)) { slave_info(bond->dev, new_active->dev, "making interface the new active one %d ms earlier\n", (bond->params.updelay - new_active->delay) * bond->params.miimon); } new_active->delay = 0; bond_set_slave_link_state(new_active, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { if (bond_uses_primary(bond)) slave_info(bond->dev, new_active->dev, "making interface the new active one\n"); } } if (bond_uses_primary(bond)) bond_hw_addr_swap(bond, new_active, old_active); if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); } else { rcu_assign_pointer(bond->curr_active_slave, new_active); } if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, old_active); if (netif_running(bond->dev)) { bond->send_peer_notif = bond->params.num_peer_notif * max(1, bond->params.peer_notif_delay); should_notify_peers = bond_should_notify_peers(bond); } call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } } } #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_add_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave. * resend only if bond is brought up with the affected * bonding modes and the retransmission is enabled */ if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) && ((bond_uses_primary(bond) && new_active) || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } /** * bond_select_active_slave - select a new active slave, if needed * @bond: our bonding struct * * This functions should be called when one of the following occurs: * - The old curr_active_slave has been released or lost its link. * - The primary_slave has got its link back. * - A slave has got its link back and there's no old curr_active_slave. * * Caller must hold RTNL. */ void bond_select_active_slave(struct bonding *bond) { struct slave *best_slave; int rv; ASSERT_RTNL(); best_slave = bond_find_best_slave(bond); if (best_slave != rtnl_dereference(bond->curr_active_slave)) { bond_change_active_slave(bond, best_slave); rv = bond_set_carrier(bond); if (!rv) return; if (netif_carrier_ok(bond->dev)) netdev_info(bond->dev, "active interface up!\n"); else netdev_info(bond->dev, "now running without any active interface!\n"); } } #ifdef CONFIG_NET_POLL_CONTROLLER static inline int slave_enable_netpoll(struct slave *slave) { struct netpoll *np; int err = 0; np = kzalloc(sizeof(*np), GFP_KERNEL); err = -ENOMEM; if (!np) goto out; err = __netpoll_setup(np, slave->dev); if (err) { kfree(np); goto out; } slave->np = np; out: return err; } static inline void slave_disable_netpoll(struct slave *slave) { struct netpoll *np = slave->np; if (!np) return; slave->np = NULL; __netpoll_free(np); } static void bond_poll_controller(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; struct ad_info ad_info; if (BOND_MODE(bond) == BOND_MODE_8023AD) if (bond_3ad_get_active_agg_info(bond, &ad_info)) return; bond_for_each_slave_rcu(bond, slave, iter) { if (!bond_slave_is_up(slave)) continue; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg && agg->aggregator_identifier != ad_info.aggregator_id) continue; } netpoll_poll_dev(slave->dev); } } static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) if (bond_slave_is_up(slave)) slave_disable_netpoll(slave); } static int bond_netpoll_setup(struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave; int err = 0; bond_for_each_slave(bond, slave, iter) { err = slave_enable_netpoll(slave); if (err) { bond_netpoll_cleanup(dev); break; } } return err; } #else static inline int slave_enable_netpoll(struct slave *slave) { return 0; } static inline void slave_disable_netpoll(struct slave *slave) { } static void bond_netpoll_cleanup(struct net_device *bond_dev) { } #endif /*---------------------------------- IOCTL ----------------------------------*/ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t features) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; netdev_features_t mask; struct slave *slave; mask = features; features = netdev_base_features(features); bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, slave->dev->features, mask); } features = netdev_add_tso_features(features, mask); return features; } #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_PARTIAL) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) #define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) static void bond_compute_features(struct bonding *bond) { netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD netdev_features_t xfrm_features = BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ netdev_features_t mpls_features = BOND_MPLS_FEATURES; struct net_device *bond_dev = bond->dev; struct list_head *iter; struct slave *slave; unsigned short max_hard_header_len = ETH_HLEN; unsigned int tso_max_size = TSO_MAX_SIZE; u16 tso_max_segs = TSO_MAX_SEGS; if (!bond_has_slaves(bond)) goto done; vlan_features = netdev_base_features(vlan_features); mpls_features = netdev_base_features(mpls_features); bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, slave->dev->hw_enc_features, BOND_ENC_FEATURES); #ifdef CONFIG_XFRM_OFFLOAD xfrm_features = netdev_increment_features(xfrm_features, slave->dev->hw_enc_features, BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ gso_partial_features = netdev_increment_features(gso_partial_features, slave->dev->gso_partial_features, BOND_GSO_PARTIAL_FEATURES); mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, BOND_MPLS_FEATURES); dst_release_flag &= slave->dev->priv_flags; if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; tso_max_size = min(tso_max_size, slave->dev->tso_max_size); tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs); } bond_dev->hard_header_len = max_hard_header_len; done: bond_dev->gso_partial_features = gso_partial_features; bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_enc_features |= xfrm_features; #endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->mpls_features = mpls_features; netif_set_tso_max_segs(bond_dev, tso_max_segs); netif_set_tso_max_size(bond_dev, tso_max_size); bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE; netdev_change_features(bond_dev); } static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { bool was_up = !!(bond_dev->flags & IFF_UP); dev_close(bond_dev); bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, slave_dev->addr_len); if (slave_dev->flags & IFF_POINTOPOINT) { bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } if (was_up) dev_open(bond_dev, NULL); } /* On bonding slaves other than the currently active slave, suppress * duplicates except for alb non-mcast/bcast. */ static bool bond_should_deliver_exact_match(struct sk_buff *skb, struct slave *slave, struct bonding *bond) { if (bond_is_slave_inactive(slave)) { if (BOND_MODE(bond) == BOND_MODE_ALB && skb->pkt_type != PACKET_BROADCAST && skb->pkt_type != PACKET_MULTICAST) return false; return true; } return false; } static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); int ret = RX_HANDLER_ANOTHER; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return RX_HANDLER_CONSUMED; *pskb = skb; slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; recv_probe = READ_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); if (ret == RX_HANDLER_CONSUMED) { consume_skb(skb); return ret; } } /* * For packets determined by bond_should_deliver_exact_match() call to * be suppressed we want to make an exception for link-local packets. * This is necessary for e.g. LLDP daemons to be able to monitor * inactive slave links without being forced to bind to them * explicitly. * * At the same time, packets that are passed to the bonding master * (including link-local ones) can have their originating interface * determined via PACKET_ORIGDEV socket option. */ if (bond_should_deliver_exact_match(skb, slave, bond)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) return RX_HANDLER_PASS; return RX_HANDLER_EXACT; } skb->dev = bond->dev; if (BOND_MODE(bond) == BOND_MODE_ALB && netif_is_bridge_port(bond->dev) && skb->pkt_type == PACKET_HOST) { if (unlikely(skb_cow_head(skb, skb->data - skb_mac_header(skb)))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, bond->dev->addr_len); } return ret; } static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return NETDEV_LAG_TX_TYPE_ROUNDROBIN; case BOND_MODE_ACTIVEBACKUP: return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; case BOND_MODE_BROADCAST: return NETDEV_LAG_TX_TYPE_BROADCAST; case BOND_MODE_XOR: case BOND_MODE_8023AD: return NETDEV_LAG_TX_TYPE_HASH; default: return NETDEV_LAG_TX_TYPE_UNKNOWN; } } static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond, enum netdev_lag_tx_type type) { if (type != NETDEV_LAG_TX_TYPE_HASH) return NETDEV_LAG_HASH_NONE; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_LAYER2: return NETDEV_LAG_HASH_L2; case BOND_XMIT_POLICY_LAYER34: return NETDEV_LAG_HASH_L34; case BOND_XMIT_POLICY_LAYER23: return NETDEV_LAG_HASH_L23; case BOND_XMIT_POLICY_ENCAP23: return NETDEV_LAG_HASH_E23; case BOND_XMIT_POLICY_ENCAP34: return NETDEV_LAG_HASH_E34; case BOND_XMIT_POLICY_VLAN_SRCMAC: return NETDEV_LAG_HASH_VLAN_SRCMAC; default: return NETDEV_LAG_HASH_UNKNOWN; } } static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; enum netdev_lag_tx_type type; int err; type = bond_lag_tx_type(bond); lag_upper_info.tx_type = type; lag_upper_info.hash_type = bond_lag_hash_type(bond, type); err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, &lag_upper_info, extack); if (err) return err; slave->dev->flags |= IFF_SLAVE; return 0; } static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) { netdev_upper_dev_unlink(slave->dev, bond->dev); slave->dev->flags &= ~IFF_SLAVE; } static void slave_kobj_release(struct kobject *kobj) { struct slave *slave = to_slave(kobj); struct bonding *bond = bond_get_bond_by_slave(slave); cancel_delayed_work_sync(&slave->notify_work); if (BOND_MODE(bond) == BOND_MODE_8023AD) kfree(SLAVE_AD_INFO(slave)); kfree(slave); } static struct kobj_type slave_ktype = { .release = slave_kobj_release, #ifdef CONFIG_SYSFS .sysfs_ops = &slave_sysfs_ops, #endif }; static int bond_kobj_init(struct slave *slave) { int err; err = kobject_init_and_add(&slave->kobj, &slave_ktype, &(slave->dev->dev.kobj), "bonding_slave"); if (err) kobject_put(&slave->kobj); return err; } static struct slave *bond_alloc_slave(struct bonding *bond, struct net_device *slave_dev) { struct slave *slave = NULL; slave = kzalloc(sizeof(*slave), GFP_KERNEL); if (!slave) return NULL; slave->bond = bond; slave->dev = slave_dev; INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { kobject_put(&slave->kobj); return NULL; } } return slave; } static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); info->miimon = bond->params.miimon; info->num_slaves = bond->slave_cnt; } static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) { strcpy(info->slave_name, slave->dev->name); info->link = slave->link; info->state = bond_slave_state(slave); info->link_failure_count = slave->link_failure_count; } static void bond_netdev_notify_work(struct work_struct *_work) { struct slave *slave = container_of(_work, struct slave, notify_work.work); if (rtnl_trylock()) { struct netdev_bonding_info binfo; bond_fill_ifslave(slave, &binfo.slave); bond_fill_ifbond(slave->bond, &binfo.master); netdev_bonding_info_change(slave->dev, &binfo); rtnl_unlock(); } else { queue_delayed_work(slave->bond->wq, &slave->notify_work, 1); } } void bond_queue_slave_event(struct slave *slave) { queue_delayed_work(slave->bond->wq, &slave->notify_work, 0); } void bond_lower_state_changed(struct slave *slave) { struct netdev_lag_lower_state_info info; info.link_up = slave->link == BOND_LINK_UP || slave->link == BOND_LINK_FAIL; info.tx_enabled = bond_is_active_slave(slave); netdev_lower_state_changed(slave->dev, &info); } #define BOND_NL_ERR(bond_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ netdev_err(bond_dev, "Error: %s\n", errmsg); \ } while (0) #define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \ } while (0) /* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); ether_setup(bond_dev); bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } void bond_xdp_set_features(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); xdp_features_t val = NETDEV_XDP_ACT_MASK; struct list_head *iter; struct slave *slave; ASSERT_RTNL(); if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } bond_for_each_slave(bond, slave, iter) val &= slave->dev->xdp_features; val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY; xdp_set_features_flag(bond_dev, val); } /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL, *prev_slave; struct sockaddr_storage ss; int link_reporting; int res = 0, i; if (slave_dev->flags & IFF_MASTER && !netif_is_bond_master(slave_dev)) { BOND_NL_ERR(bond_dev, extack, "Device type (master device) cannot be enslaved"); return -EPERM; } if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_eth_ioctl == NULL) { slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); } /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device is in use and cannot be enslaved"); return -EBUSY; } if (bond_dev == slave_dev) { BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself."); return -EPERM; } /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n"); if (vlan_uses_dev(bond_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); return -EPERM; } else { slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n"); } } else { slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n"); } if (slave_dev->features & NETIF_F_HW_ESP) slave_dbg(bond_dev, slave_dev, "is esp-hw-offload capable\n"); /* Old ifenslave binaries are no longer supported. These can * be identified with moderate accuracy by the state of the slave: * the current ifenslave will set the interface down prior to * enslaving it; the old ifenslave will not. */ if (slave_dev->flags & IFF_UP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device can not be enslaved while up"); return -EPERM; } /* set bonding device ether type by slave - bonding netdevices are * created with ether_setup, so when the slave type is not ARPHRD_ETHER * there is a need to override some of the type dependent attribs/funcs. * * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, bond_dev); res = notifier_to_errno(res); if (res) { slave_err(bond_dev, slave_dev, "refused to change device type\n"); return -EBUSY; } /* Flush unicast and multicast addresses */ dev_uc_flush(bond_dev); dev_mc_flush(bond_dev); if (slave_dev->type != ARPHRD_ETHER) bond_setup_by_slave(bond_dev, slave_dev); else bond_ether_setup(bond_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, bond_dev); } } else if (bond_dev->type != slave_dev->type) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device type is different from other slaves"); return -EINVAL; } if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Only active-backup mode is supported for infiniband slaves"); res = -EOPNOTSUPP; goto err_undo_flags; } if (!slave_ops->ndo_set_mac_address || slave_dev->type == ARPHRD_INFINIBAND) { slave_warn(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address\n"); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac != BOND_FOM_ACTIVE) { if (!bond_has_slaves(bond)) { bond->params.fail_over_mac = BOND_FOM_ACTIVE; slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); res = -EOPNOTSUPP; goto err_undo_flags; } } } call_netdevice_notifiers(NETDEV_JOIN, slave_dev); /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ if (!bond_has_slaves(bond) && bond->dev->addr_assign_type == NET_ADDR_RANDOM) { res = bond_set_dev_addr(bond->dev, slave_dev); if (res) goto err_undo_flags; } new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ new_slave->queue_id = 0; /* Save slave's original mtu and then set it to match the bond */ new_slave->original_mtu = slave_dev->mtu; res = dev_set_mtu(slave_dev, bond->dev->mtu); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling dev_set_mtu\n", res); goto err_free; } /* Save slave's original ("permanent") mac address for modes * that need it, and for restoring it upon release, and then * set it to the master's address */ bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr, slave_dev->addr_len); if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* Set slave to master's mac address. The application already * set the master's mac address to that of the first slave */ memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); ss.ss_family = slave_dev->type; res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } } /* set no_addrconf flag before open to prevent IPv6 addrconf */ slave_dev->priv_flags |= IFF_NO_ADDRCONF; /* open the slave since the application closed it */ res = dev_open(slave_dev, extack); if (res) { slave_err(bond_dev, slave_dev, "Opening slave failed\n"); goto err_restore_mac; } slave_dev->priv_flags |= IFF_BONDING; /* initialize slave stats */ dev_get_stats(new_slave->dev, &new_slave->slave_stats); if (bond_is_lb(bond)) { /* bond_alb_init_slave() must be called before all other stages since * it might fail and we do not want to have to undo everything */ res = bond_alb_init_slave(bond, new_slave); if (res) goto err_close; } res = vlan_vids_add_by_dev(slave_dev, bond_dev); if (res) { slave_err(bond_dev, slave_dev, "Couldn't add bond vlan ids\n"); goto err_close; } prev_slave = bond_last_slave(bond); new_slave->delay = 0; new_slave->link_failure_count = 0; if (bond_update_speed_duplex(new_slave) && bond_needs_speed_duplex(bond)) new_slave->link = BOND_LINK_DOWN; new_slave->last_rx = jiffies - (msecs_to_jiffies(bond->params.arp_interval) + 1); for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) new_slave->target_last_arp_rx[i] = new_slave->last_rx; new_slave->last_tx = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); if ((link_reporting == -1) && !bond->params.arp_interval) { /* miimon is set but a bonded network driver * does not support ETHTOOL/MII and * arp_interval is not set. Note: if * use_carrier is enabled, we will never go * here (because netif_carrier is always * supported); thus, we don't need to change * the messages for netif_carrier. */ slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n"); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n"); } } /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { if (bond->params.updelay) { bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_NOW); new_slave->delay = bond->params.updelay; } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } } else { bond_set_slave_link_state(new_slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); } } else if (bond->params.arp_interval) { bond_set_slave_link_state(new_slave, (netif_carrier_ok(slave_dev) ? BOND_LINK_UP : BOND_LINK_DOWN), BOND_SLAVE_NOTIFY_NOW); } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } if (new_slave->link != BOND_LINK_DOWN) new_slave->last_link_up = jiffies; slave_dbg(bond_dev, slave_dev, "Initial state of slave is BOND_LINK_%s\n", new_slave->link == BOND_LINK_DOWN ? "DOWN" : (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); if (bond_uses_primary(bond) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { rcu_assign_pointer(bond->primary_slave, new_slave); bond->force_primary = true; } } switch (BOND_MODE(bond)) { case BOND_MODE_ACTIVEBACKUP: bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ if (!prev_slave) { SLAVE_AD_INFO(new_slave)->id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond); } else { SLAVE_AD_INFO(new_slave)->id = SLAVE_AD_INFO(prev_slave)->id + 1; } bond_3ad_bind_slave(new_slave); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: slave_dbg(bond_dev, slave_dev, "This slave is always active in trunk mode\n"); /* always active in trunk mode */ bond_set_active_slave(new_slave); /* In trunking mode there is little meaning to curr_active_slave * anyway (it holds no special properties of the bond device), * so we can change it without calling change_active_interface() */ if (!rcu_access_pointer(bond->curr_active_slave) && new_slave->link == BOND_LINK_UP) rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ #ifdef CONFIG_NET_POLL_CONTROLLER if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { slave_info(bond_dev, slave_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; goto err_detach; } } #endif if (!(bond_dev->features & NETIF_F_LRO)) dev_disable_lro(slave_dev); res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling netdev_rx_handler_register\n", res); goto err_detach; } res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; } bond_lower_state_changed(new_slave); res = bond_sysfs_slave_add(new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_sysfs_slave_add\n", res); goto err_upper_unlink; } /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ if (!bond_uses_primary(bond)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { res = dev_set_promiscuity(slave_dev, 1); if (res) goto err_sysfs_del; } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { res = dev_set_allmulti(slave_dev, 1); if (res) { if (bond_dev->flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); goto err_sysfs_del; } } if (bond_dev->flags & IFF_UP) { netif_addr_lock_bh(bond_dev); dev_mc_sync_multiple(slave_dev, bond_dev); dev_uc_sync_multiple(slave_dev, bond_dev); netif_addr_unlock_bh(bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_add(slave_dev, lacpdu_mcast_addr); } } bond->slave_cnt++; bond_compute_features(bond); bond_set_carrier(bond); /* Needs to be called before bond_select_active_slave(), which will * remove the maddrs if the slave is selected as active slave. */ bond_slave_ns_maddrs_add(bond, new_slave); if (bond_uses_primary(bond)) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave does not support XDP"); res = -EOPNOTSUPP; goto err_sysfs_del; } } else if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = bond->xdp_prog, .extack = extack, }; if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); res = -EOPNOTSUPP; goto err_sysfs_del; } res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); goto err_sysfs_del; } if (bond->xdp_prog) bpf_prog_inc(bond->xdp_prog); } bond_xdp_set_features(bond_dev); slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ bond_queue_slave_event(new_slave); return 0; /* Undo stages on error */ err_sysfs_del: bond_sysfs_slave_del(new_slave); err_upper_unlink: bond_upper_dev_unlink(bond, new_slave); err_unregister: netdev_rx_handler_unregister(slave_dev); err_detach: vlan_vids_del_by_dev(slave_dev, bond_dev); if (rcu_access_pointer(bond->primary_slave) == new_slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (rcu_access_pointer(bond->curr_active_slave) == new_slave) { block_netpoll_tx(); bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); unblock_netpoll_tx(); } /* either primary_slave or curr_active_slave might've changed */ synchronize_rcu(); slave_disable_netpoll(new_slave); err_close: if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's * MAC if this slave's MAC is in use by the bond, or at * least print a warning. */ bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr, new_slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); } err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: kobject_put(&new_slave->kobj); err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ if (!bond_has_slaves(bond)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); if (bond_dev->type != ARPHRD_ETHER) { dev_close(bond_dev); bond_ether_setup(bond_dev); } } return res; } /* Try to release the slave device <slave> from the bond device <master> * It is legal to access curr_active_slave without a lock because all the function * is RTNL-locked. If "all" is true it means that the function is being called * while destroying a bond interface and all slaves are being released. * * The rules for slave state should be: * for Active/Backup: * Active stays on all backups go down * for Bonded connections: * The first up interface should be left on and all others downed. */ static int __bond_release_one(struct net_device *bond_dev, struct net_device *slave_dev, bool all, bool unregister) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr_storage ss; int old_flags = bond_dev->flags; netdev_features_t old_features = bond_dev->features; /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || !netdev_has_upper_dev(slave_dev, bond_dev)) { slave_dbg(bond_dev, slave_dev, "cannot release slave\n"); return -EINVAL; } block_netpoll_tx(); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ slave_info(bond_dev, slave_dev, "interface not enslaved\n"); unblock_netpoll_tx(); return -EINVAL; } bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); bond_sysfs_slave_del(slave); /* recompute stats just before removing the slave */ bond_get_stats(bond->dev, &bond->bond_stats); if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = NULL, .extack = NULL, }; if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ netdev_rx_handler_unregister(slave_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); bond_upper_dev_unlink(bond, slave); if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, slave); slave_info(bond_dev, slave_dev, "Releasing %s interface\n", bond_is_active_slave(slave) ? "active" : "backup"); oldcurrent = rcu_access_pointer(bond->curr_active_slave); RCU_INIT_POINTER(bond->current_arp_slave, NULL); if (!all && (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) slave_warn(bond_dev, slave_dev, "the permanent HWaddr of slave - %pM - is still in use by bond - set the HWaddr of slave to a different address to avoid conflicts\n", slave->perm_hwaddr); } if (rtnl_dereference(bond->primary_slave) == slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (oldcurrent == slave) bond_change_active_slave(bond, NULL); /* Must be called after bond_change_active_slave () as the slave * might change from an active slave to a backup slave. Then it is * necessary to clear the maddrs on the backup slave. */ bond_slave_ns_maddrs_del(bond, slave); if (bond_is_lb(bond)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave * has been cleared (if our_slave == old_current), * but before a new active slave is selected. */ bond_alb_deinit_slave(bond, slave); } if (all) { RCU_INIT_POINTER(bond->curr_active_slave, NULL); } else if (oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. */ bond_select_active_slave(bond); } bond_set_carrier(bond); if (!bond_has_slaves(bond)) eth_hw_addr_random(bond_dev); unblock_netpoll_tx(); synchronize_rcu(); bond->slave_cnt--; if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n"); vlan_vids_del_by_dev(slave_dev, bond_dev); /* If the mode uses primary, then this case was handled above by * bond_change_active_slave(..., NULL) */ if (!bond_uses_primary(bond)) { /* unset promiscuity level from slave * NOTE: The NETDEV_CHANGEADDR call above may change the value * of the IFF_PROMISC flag in the bond_dev, but we need the * value of that flag before that change, as that was the value * when this slave was attached, so we cache at the start of the * function and use it here. Same goes for ALLMULTI below */ if (old_flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); /* unset allmulti level from slave */ if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); if (old_flags & IFF_UP) bond_hw_addr_flush(bond_dev, slave_dev); } slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ bond_hw_addr_copy(ss.__data, slave->perm_hwaddr, slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); } if (unregister) __dev_set_mtu(slave_dev, slave->original_mtu); else dev_set_mtu(slave_dev, slave->original_mtu); if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; bond_xdp_set_features(bond_dev); kobject_put(&slave->kobj); return 0; } /* A wrapper used because of ndo_del_link */ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) { return __bond_release_one(bond_dev, slave_dev, false, false); } /* First release a slave and then destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. */ static int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); if (ret == 0 && !bond_has_slaves(bond) && bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); unregister_netdevice(bond_dev); } return ret; } static void bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); bond_fill_ifbond(bond, info); } static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; int i = 0, res = -ENODEV; struct slave *slave; bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; bond_fill_ifslave(slave, info); break; } } return res; } /*-------------------------------- Monitoring -------------------------------*/ /* called with rcu_read_lock() */ static int bond_miimon_inspect(struct bonding *bond) { bool ignore_updelay = false; int link_state, commit = 0; struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { ignore_updelay = !rcu_dereference(bond->curr_active_slave); } else { struct bond_up_slave *usable_slaves; usable_slaves = rcu_dereference(bond->usable_slaves); if (usable_slaves && usable_slaves->count == 0) ignore_updelay = true; } bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); link_state = bond_check_dev_link(bond, slave->dev, 0); switch (slave->link) { case BOND_LINK_UP: if (link_state) continue; bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; slave->delay = bond->params.downdelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n", (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) ? (bond_is_active_slave(slave) ? "active " : "backup ") : "", bond->params.downdelay * bond->params.miimon); } fallthrough; case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ bond_propose_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status up again after %d ms\n", (bond->params.downdelay - slave->delay) * bond->params.miimon); commit++; continue; } if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; continue; } slave->delay--; break; case BOND_LINK_DOWN: if (!link_state) continue; bond_propose_link_state(slave, BOND_LINK_BACK); commit++; slave->delay = bond->params.updelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n", ignore_updelay ? 0 : bond->params.updelay * bond->params.miimon); } fallthrough; case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status down again after %d ms\n", (bond->params.updelay - slave->delay) * bond->params.miimon); commit++; continue; } if (ignore_updelay) slave->delay = 0; if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; ignore_updelay = false; continue; } slave->delay--; break; } } return commit; } static void bond_miimon_link_change(struct bonding *bond, struct slave *slave, char link) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: bond_3ad_handle_link_change(slave, link); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_alb_handle_link_change(bond, slave, link); break; case BOND_MODE_XOR: bond_update_slave_arr(bond, NULL); break; } } static void bond_miimon_commit(struct bonding *bond) { struct slave *slave, *primary, *active; bool do_failover = false; struct list_head *iter; ASSERT_RTNL(); bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: /* For 802.3ad mode, check current slave speed and * duplex again in case its port was disabled after * invalid speed/duplex reporting but recovered before * link monitoring could make a decision on the actual * link status */ if (BOND_MODE(bond) == BOND_MODE_8023AD && slave->link == BOND_LINK_UP) bond_3ad_adapter_speed_duplex_changed(slave); continue; case BOND_LINK_UP: if (bond_update_speed_duplex(slave) && bond_needs_speed_duplex(bond)) { slave->link = BOND_LINK_DOWN; if (net_ratelimit()) slave_warn(bond->dev, slave->dev, "failed to get link speed/duplex\n"); continue; } bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); slave->last_link_up = jiffies; primary = rtnl_dereference(bond->primary_slave); if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* prevent it from being the active one */ bond_set_backup_slave(slave); } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, slave->duplex ? "full" : "half"); bond_miimon_link_change(bond, slave, BOND_LINK_UP); active = rtnl_dereference(bond->curr_active_slave); if (!active || slave == primary || slave->prio > active->prio) do_failover = true; continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_8023AD) bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); bond_miimon_link_change(bond, slave, BOND_LINK_DOWN); if (slave == rcu_access_pointer(bond->curr_active_slave)) do_failover = true; continue; default: slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", slave->link_new_state); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* bond_mii_monitor * * Really a wrapper that splits the mii monitor into two phases: an * inspection, then (if inspection indicates something needs to be done) * an acquisition of appropriate locks followed by a commit phase to * implement whatever link state changes are indicated. */ static void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; bool commit; unsigned long delay; struct slave *slave; struct list_head *iter; delay = msecs_to_jiffies(bond->params.miimon); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); commit = !!bond_miimon_inspect(bond); if (bond->send_peer_notif) { rcu_read_unlock(); if (rtnl_trylock()) { bond->send_peer_notif--; rtnl_unlock(); } } else { rcu_read_unlock(); } if (commit) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; should_notify_peers = false; goto re_arm; } bond_for_each_slave(bond, slave, iter) { bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER); } bond_miimon_commit(bond); rtnl_unlock(); /* might sleep, hold no other locks */ } re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); if (should_notify_peers) { if (!rtnl_trylock()) return; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } } static int bond_upper_dev_walk(struct net_device *upper, struct netdev_nested_priv *priv) { __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { struct netdev_nested_priv priv = { .data = (void *)&ip, }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); return ret; } #define BOND_VLAN_PROTO_NONE cpu_to_be16(0xffff) static bool bond_handle_vlan(struct slave *slave, struct bond_vlan_tag *tags, struct sk_buff *skb) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct bond_vlan_tag *outer_tag = tags; if (!tags || tags->vlan_proto == BOND_VLAN_PROTO_NONE) return true; tags++; /* Go through all the tags backwards and add them to the packet */ while (tags->vlan_proto != BOND_VLAN_PROTO_NONE) { if (!tags->vlan_id) { tags++; continue; } slave_dbg(bond_dev, slave_dev, "inner tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), tags->vlan_id); skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto, tags->vlan_id); if (!skb) { net_err_ratelimited("failed to insert inner VLAN tag\n"); return false; } tags++; } /* Set the outer tag */ if (outer_tag->vlan_id) { slave_dbg(bond_dev, slave_dev, "outer tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), outer_tag->vlan_id); __vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto, outer_tag->vlan_id); } return true; } /* We go to the (large) trouble of VLAN tagging ARP frames because * switches in VLAN mode (especially if ports are configured as * "native" to a VLAN) might not pass non-tagged frames. */ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip, __be32 src_ip, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n", arp_op, &dest_ip, &src_ip); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); if (!skb) { net_err_ratelimited("ARP packet allocation failed\n"); return; } if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); arp_xmit(skb); } return; } /* Validate the device path between the @start_dev and the @end_dev. * The path is valid if the @end_dev is reachable through device * stacking. * When the path is validated, collect any vlan information in the * path. */ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level) { struct bond_vlan_tag *tags; struct net_device *upper; struct list_head *iter; if (start_dev == end_dev) { tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC); if (!tags) return ERR_PTR(-ENOMEM); tags[level].vlan_proto = BOND_VLAN_PROTO_NONE; return tags; } netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { tags = bond_verify_device_path(upper, end_dev, level + 1); if (IS_ERR_OR_NULL(tags)) { if (IS_ERR(tags)) return tags; continue; } if (is_vlan_dev(upper)) { tags[level].vlan_proto = vlan_dev_vlan_proto(upper); tags[level].vlan_id = vlan_dev_vlan_id(upper); } return tags; } return NULL; } static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { struct rtable *rt; struct bond_vlan_tag *tags; __be32 *targets = bond->params.arp_targets, addr; int i; for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI4\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) { /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", bond->dev->name, &targets[i]); bond_arp_send(slave, ARPOP_REQUEST, targets[i], 0, tags); continue; } /* bond device itself */ if (rt->dst.dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, rt->dst.dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n", &targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL"); ip_rt_put(rt); continue; found: addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); bond_arp_send(slave, ARPOP_REQUEST, targets[i], addr, tags); kfree(tags); } } static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { int i; if (!sip || !bond_has_this_ip(bond, tip)) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 tip %pI4 not found\n", __func__, &sip, &tip); return; } i = bond_get_targets_ip(bond->params.arp_targets, sip); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 not found in targets\n", __func__, &sip); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; unsigned int alen; alen = arp_hdr_len(bond->dev); if (alen > skb_headlen(skb)) { arp = kmalloc(alen, GFP_ATOMIC); if (!arp) goto out_unlock; if (skb_copy_bits(skb, 0, arp, alen) < 0) goto out_unlock; } if (arp->ar_hln != bond->dev->addr_len || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK || arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_pln != 4) goto out_unlock; arp_ptr = (unsigned char *)(arp + 1); arp_ptr += bond->dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4 + bond->dev->addr_len; memcpy(&tip, arp_ptr, 4); slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI4 tip %pI4\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * * (a) the slave receiving the ARP is active (which includes the * current ARP slave, if any), or * * (b) the receiving slave isn't active, but there is a currently * active slave and it received valid arp reply(s) after it became * the currently active slave, or * * (c) there is an ARP slave that sent an ARP during the prior ARP * interval, and we receive an ARP reply on any slave. We accept * these because switch FDB update delays may deliver the ARP * reply to a slave other than the sender of the ARP request. * * Note: for (b), backup slaves are receiving the broadcast ARP * request, not a reply. This request passes from the sending * slave through the L2 switch(es) to the receiving slave. Since * this is checking the request, sip/tip are swapped for * validation. * * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) kfree(arp); return RX_HANDLER_ANOTHER; } #if IS_ENABLED(CONFIG_IPV6) static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr, const struct in6_addr *saddr, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct in6_addr mcaddr; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "NS on slave: dst %pI6c src %pI6c\n", daddr, saddr); skb = ndisc_ns_create(slave_dev, daddr, saddr, 0); if (!skb) { net_err_ratelimited("NS packet allocation failed\n"); return; } addrconf_addr_solict_mult(daddr, &mcaddr); if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); ndisc_send_skb(skb, &mcaddr, saddr); } } static void bond_ns_send_all(struct bonding *bond, struct slave *slave) { struct in6_addr *targets = bond->params.ns_targets; struct bond_vlan_tag *tags; struct dst_entry *dst; struct in6_addr saddr; struct flowi6 fl6; int i; for (i = 0; i < BOND_MAX_NS_TARGETS && !ipv6_addr_any(&targets[i]); i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI6c\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { dst_release(dst); /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to ns_ip6_target %pI6c and arp_validate is set\n", bond->dev->name, &targets[i]); bond_ns_send(slave, &targets[i], &in6addr_any, tags); continue; } /* bond device itself */ if (dst->dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, dst->dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to ns_ip6_target %pI6c via dst->dev %s\n", &targets[i], dst->dev ? dst->dev->name : "NULL"); dst_release(dst); continue; found: if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr)) bond_ns_send(slave, &targets[i], &saddr, tags); else bond_ns_send(slave, &targets[i], &in6addr_any, tags); dst_release(dst); kfree(tags); } } static int bond_confirm_addr6(struct net_device *dev, struct netdev_nested_priv *priv) { struct in6_addr *addr = (struct in6_addr *)priv->data; return ipv6_chk_addr(dev_net(dev), addr, dev, 0); } static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr) { struct netdev_nested_priv priv = { .data = addr, }; int ret = false; if (bond_confirm_addr6(bond->dev, &priv)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_confirm_addr6, &priv)) ret = true; rcu_read_unlock(); return ret; } static void bond_validate_na(struct bonding *bond, struct slave *slave, struct in6_addr *saddr, struct in6_addr *daddr) { int i; /* Ignore NAs that: * 1. Source address is unspecified address. * 2. Dest address is neither all-nodes multicast address nor * exist on bond interface. */ if (ipv6_addr_any(saddr) || (!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) && !bond_has_this_ip6(bond, daddr))) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n", __func__, saddr, daddr); return; } i = bond_get_targets_ip6(bond->params.ns_targets, saddr); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c not found in targets\n", __func__, saddr); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct slave *curr_active_slave, *curr_arp_slave; struct in6_addr *saddr, *daddr; struct { struct ipv6hdr ip6; struct icmp6hdr icmp6; } *combined, _combined; if (skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto out; combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; daddr = &combined->ip6.daddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), saddr, daddr); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * see bond_arp_rcv(). */ if (bond_is_active_slave(slave)) bond_validate_na(bond, slave, saddr, daddr); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); out: return RX_HANDLER_ANOTHER; } #endif int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { #if IS_ENABLED(CONFIG_IPV6) bool is_ipv6 = skb->protocol == __cpu_to_be16(ETH_P_IPV6); #endif bool is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n", __func__, skb->dev->name); /* Use arp validate logic for both ARP and NS */ if (!slave_do_arp_validate(bond, slave)) { if ((slave_do_arp_validate_only(bond) && is_arp) || #if IS_ENABLED(CONFIG_IPV6) (slave_do_arp_validate_only(bond) && is_ipv6) || #endif !slave_do_arp_validate_only(bond)) slave->last_rx = jiffies; return RX_HANDLER_ANOTHER; } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); #if IS_ENABLED(CONFIG_IPV6) } else if (is_ipv6) { return bond_na_rcv(skb, bond, slave); #endif } else { return RX_HANDLER_ANOTHER; } } static void bond_send_validate(struct bonding *bond, struct slave *slave) { bond_arp_send_all(bond, slave); #if IS_ENABLED(CONFIG_IPV6) bond_ns_send_all(bond, slave); #endif } /* function to verify if we're in the arp_interval timeslice, returns true if * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval + * arp_interval/2) . the arp_interval/2 is needed for really fast networks. */ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod) { int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); return time_in_range(jiffies, last_act - delta_in_ticks, last_act + mod * delta_in_ticks + delta_in_ticks/2); } /* This function is called regularly to monitor each slave's link * ensuring that traffic is being sent and received when arp monitoring * is used in load-balancing mode. if the adapter has been dormant, then an * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ static void bond_loadbalance_arp_mon(struct bonding *bond) { struct slave *slave, *oldcurrent; struct list_head *iter; int do_failover = 0, slave_state_changed = 0; if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); oldcurrent = rcu_dereference(bond->curr_active_slave); /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into * the picture unless it is null. also, slave->last_link_up is not * needed here because we send an arp on each slave and give a slave * as long as it needs to get the tx/rx within the delta. * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ bond_for_each_slave_rcu(bond, slave, iter) { unsigned long last_tx = slave_last_tx(slave); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_tx, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and * curr_active_slave being null after enslaving * is closed. */ if (!oldcurrent) { slave_info(bond->dev, slave->dev, "link status definitely up\n"); do_failover = 1; } else { slave_info(bond->dev, slave->dev, "interface is now up\n"); } } } else { /* slave->link == BOND_LINK_UP */ /* not all switches will respond to an arp request * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; slave_info(bond->dev, slave->dev, "interface is now down\n"); if (slave == oldcurrent) do_failover = 1; } } /* note: if switch is in round-robin mode, all links * must tx arp to ensure all links rx an arp - otherwise * links may oscillate or not come up at all; if switch is * in something like xor mode, there is nothing we can * do - all replies will be rx'ed on same link causing slaves * to be unstable during low/no traffic periods */ if (bond_slave_is_up(slave)) bond_send_validate(bond, slave); } rcu_read_unlock(); if (do_failover || slave_state_changed) { if (!rtnl_trylock()) goto re_arm; bond_for_each_slave(bond, slave, iter) { if (slave->link_new_state != BOND_LINK_NOCHANGE) slave->link = slave->link_new_state; } if (slave_state_changed) { bond_slave_state_change(bond); if (BOND_MODE(bond) == BOND_MODE_XOR) bond_update_slave_arr(bond, NULL); } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } rtnl_unlock(); } re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, msecs_to_jiffies(bond->params.arp_interval)); } /* Called to inspect slaves for active-backup mode ARP monitor link state * changes. Sets proposed link state in slaves to specify what action * should take place for the slave. Returns 0 if no changes are found, >0 * if changes to link states must be committed. * * Called with rcu_read_lock held. */ static int bond_ab_arp_inspect(struct bonding *bond) { unsigned long last_tx, last_rx; struct list_head *iter; struct slave *slave; int commit = 0; bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; } else if (slave->link == BOND_LINK_BACK) { bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; } continue; } /* Give slaves 2*delta after being enslaved or made * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ if (bond_time_in_interval(bond, slave->last_link_up, 2)) continue; /* Backup slave is down if: * - No current_arp_slave AND * - more than (missed_max+1)*delta since last receive AND * - the bond has an IP address * * Note: a non-null current_arp_slave indicates * the curr_active_slave went down and we are * searching for a new one; under this condition * we only take the curr_active_slave down - this * gives each slave a chance to tx/rx traffic * before being taken out */ if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && !bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } /* Active slave is down if: * - more than missed_max*delta since transmitting OR * - (more than missed_max*delta since receive AND * the bond has an IP address) */ last_tx = slave_last_tx(slave); if (bond_is_active_slave(slave) && (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } } return commit; } /* Called to commit link state changes noted by inspection step of * active-backup mode ARP monitor. * * Called with RTNL hold. */ static void bond_ab_arp_commit(struct bonding *bond) { bool do_failover = false; struct list_head *iter; unsigned long last_tx; struct slave *slave; bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: last_tx = slave_last_tx(slave); if (rtnl_dereference(bond->curr_active_slave) != slave || (!rtnl_dereference(bond->curr_active_slave) && bond_time_in_interval(bond, last_tx, 1))) { struct slave *current_arp_slave; current_arp_slave = rtnl_dereference(bond->current_arp_slave); bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (current_arp_slave) { bond_set_slave_inactive_flags( current_arp_slave, BOND_SLAVE_NOTIFY_NOW); RCU_INIT_POINTER(bond->current_arp_slave, NULL); } slave_info(bond->dev, slave->dev, "link status definitely up\n"); if (!rtnl_dereference(bond->curr_active_slave) || slave == rtnl_dereference(bond->primary_slave) || slave->prio > rtnl_dereference(bond->curr_active_slave)->prio) do_failover = true; } continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); if (slave == rtnl_dereference(bond->curr_active_slave)) { RCU_INIT_POINTER(bond->current_arp_slave, NULL); do_failover = true; } continue; case BOND_LINK_FAIL: bond_set_slave_link_state(slave, BOND_LINK_FAIL, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); /* A slave has just been enslaved and has become * the current active slave. */ if (rtnl_dereference(bond->curr_active_slave)) RCU_INIT_POINTER(bond->current_arp_slave, NULL); continue; default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", slave->link_new_state); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* Send ARP probes for active-backup mode ARP monitor. * * Called with rcu_read_lock held. */ static bool bond_ab_arp_probe(struct bonding *bond) { struct slave *slave, *before = NULL, *new_slave = NULL, *curr_arp_slave = rcu_dereference(bond->current_arp_slave), *curr_active_slave = rcu_dereference(bond->curr_active_slave); struct list_head *iter; bool found = false; bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; if (curr_arp_slave && curr_active_slave) netdev_info(bond->dev, "PROBE: c_arp %s && cas %s BAD\n", curr_arp_slave->dev->name, curr_active_slave->dev->name); if (curr_active_slave) { bond_send_validate(bond, curr_active_slave); return should_notify_rtnl; } /* if we don't have a curr_active_slave, search for the next available * backup slave from the current_arp_slave and make it the candidate * for becoming the curr_active_slave */ if (!curr_arp_slave) { curr_arp_slave = bond_first_slave_rcu(bond); if (!curr_arp_slave) return should_notify_rtnl; } bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; if (found && !new_slave && bond_slave_is_up(slave)) new_slave = slave; /* if the link state is up at this point, we * mark it down - this can happen if we have * simultaneous link failures and * reselect_active_interface doesn't make this * one the current slave so it is still marked * up when it is actually down */ if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_LATER); if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_LATER); slave_info(bond->dev, slave->dev, "backup interface is now down\n"); } if (slave == curr_arp_slave) found = true; } if (!new_slave && before) new_slave = before; if (!new_slave) goto check_state; bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_LATER); bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_send_validate(bond, new_slave); new_slave->last_link_up = jiffies; rcu_assign_pointer(bond->current_arp_slave, new_slave); check_state: bond_for_each_slave_rcu(bond, slave, iter) { if (slave->should_notify || slave->should_notify_link) { should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; break; } } return should_notify_rtnl; } static void bond_activebackup_arp_mon(struct bonding *bond) { bool should_notify_peers = false; bool should_notify_rtnl = false; int delta_in_ticks; delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); if (bond_ab_arp_inspect(bond)) { rcu_read_unlock(); /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { delta_in_ticks = 1; should_notify_peers = false; goto re_arm; } bond_ab_arp_commit(bond); rtnl_unlock(); rcu_read_lock(); } should_notify_rtnl = bond_ab_arp_probe(bond); rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); if (should_notify_peers || should_notify_rtnl) { if (!rtnl_trylock()) return; if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } if (should_notify_rtnl) { bond_slave_state_notify(bond); bond_slave_link_notify(bond); } rtnl_unlock(); } } static void bond_arp_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_activebackup_arp_mon(bond); else bond_loadbalance_arp_mon(bond); } /*-------------------------- netdev event handling --------------------------*/ /* Change device name */ static int bond_event_changename(struct bonding *bond) { bond_remove_proc_entry(bond); bond_create_proc_entry(bond); bond_debug_reregister(bond); return NOTIFY_DONE; } static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev) { struct bonding *event_bond = netdev_priv(bond_dev); netdev_dbg(bond_dev, "%s called\n", __func__); switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); #ifdef CONFIG_XFRM_OFFLOAD xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); #endif /* CONFIG_XFRM_OFFLOAD */ break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); break; default: break; } return NOTIFY_DONE; } static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev), *primary; struct bonding *bond; struct net_device *bond_dev; /* A netdev event can be generated while enslaving a device * before netdev_rx_handler_register is called in which case * slave will be NULL */ if (!slave) { netdev_dbg(slave_dev, "%s called on NULL slave\n", __func__); return NOTIFY_DONE; } bond_dev = slave->bond->dev; bond = slave->bond; primary = rtnl_dereference(bond->primary_slave); slave_dbg(bond_dev, slave_dev, "%s called\n", __func__); switch (event) { case NETDEV_UNREGISTER: if (bond_dev->type != ARPHRD_ETHER) bond_release_and_destroy(bond_dev, slave_dev); else __bond_release_one(bond_dev, slave_dev, false, true); break; case NETDEV_UP: case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave * in weird state. Mark it as link-fail if the link was * previously up or link-down if it hasn't yet come up, and * let link-monitoring (miimon) set it right when correct * speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) { if (slave->last_link_up) slave->link = BOND_LINK_FAIL; else slave->link = BOND_LINK_DOWN; } if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); fallthrough; case NETDEV_DOWN: /* Refresh slave-array if applicable! * If the setup does not use miimon or arpmon (mode-specific!), * then these events will not cause the slave-array to be * refreshed. This will cause xmit to use a slave that is not * usable. Avoid such situation by refeshing the array at these * events. If these (miimon/arpmon) parameters are configured * then array gets refreshed twice and that should be fine! */ if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); break; case NETDEV_CHANGEMTU: /* TODO: Should slaves be allowed to * independently alter their MTU? For * an active-backup bond, slaves need * not be the same type of device, so * MTUs may vary. For other modes, * slaves arguably should have the * same MTUs. To do this, we'd need to * take over the slave's change_mtu * function for the duration of their * servitude. */ break; case NETDEV_CHANGENAME: /* we don't care if we don't have primary set */ if (!bond_uses_primary(bond) || !bond->params.primary[0]) break; if (slave == primary) { /* slave's name changed - he's no longer primary */ RCU_INIT_POINTER(bond->primary_slave, NULL); } else if (!strcmp(slave_dev->name, bond->params.primary)) { /* we have a new primary slave */ rcu_assign_pointer(bond->primary_slave, slave); } else { /* we didn't change primary - exit */ break; } netdev_info(bond->dev, "Primary slave changed to %s, reselecting active slave\n", primary ? slave_dev->name : "none"); block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: if (!bond->notifier_ctx) { bond->notifier_ctx = true; bond_compute_features(bond); bond->notifier_ctx = false; } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, slave->bond->dev); break; case NETDEV_XDP_FEAT_CHANGE: bond_xdp_set_features(bond_dev); break; default: break; } return NOTIFY_DONE; } /* bond_netdev_event: handle netdev notifier chain events. * * This function receives events for the netdev chain. The caller (an * ioctl handler calling blocking_notifier_call_chain) holds the necessary * locks for us to safely manipulate the slave devices (RTNL lock, * dev_probe_lock). */ static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); netdev_dbg(event_dev, "%s received %s\n", __func__, netdev_cmd_to_name(event)); if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; if (event_dev->flags & IFF_MASTER) { int ret; ret = bond_master_netdev_event(event, event_dev); if (ret != NOTIFY_DONE) return ret; } if (event_dev->flags & IFF_SLAVE) return bond_slave_netdev_event(event, event_dev); return NOTIFY_DONE; } static struct notifier_block bond_netdev_notifier = { .notifier_call = bond_netdev_event, }; /*---------------------------- Hashing Policies -----------------------------*/ /* Helper to access data in a packet, with or without a backing skb. * If skb is given the data is linearized if necessary via pskb_may_pull. */ static inline const void *bond_pull_data(struct sk_buff *skb, const void *data, int hlen, int n) { if (likely(n <= hlen)) return data; else if (skb && likely(pskb_may_pull(skb, n))) return skb->data; return NULL; } /* L2 hash helper */ static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { struct ethhdr *ep; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; ep = (struct ethhdr *)(data + mhoff); return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto); } static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data, int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34) { const struct ipv6hdr *iph6; const struct iphdr *iph; if (l2_proto == htons(ETH_P_IP)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph)); if (!data) return false; iph = (const struct iphdr *)(data + *nhoff); iph_to_flow_copy_v4addrs(fk, iph); *nhoff += iph->ihl << 2; if (!ip_is_fragment(iph)) *ip_proto = iph->protocol; } else if (l2_proto == htons(ETH_P_IPV6)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6)); if (!data) return false; iph6 = (const struct ipv6hdr *)(data + *nhoff); iph_to_flow_copy_v6addrs(fk, iph6); *nhoff += sizeof(*iph6); *ip_proto = iph6->nexthdr; } else { return false; } if (l34 && *ip_proto >= 0) fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); return true; } static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { u32 srcmac_vendor = 0, srcmac_dev = 0; struct ethhdr *mac_hdr; u16 vlan = 0; int i; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; mac_hdr = (struct ethhdr *)(data + mhoff); for (i = 0; i < 3; i++) srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; for (i = 3; i < ETH_ALEN; i++) srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i]; if (skb && skb_vlan_tag_present(skb)) vlan = skb_vlan_tag_get(skb); return vlan ^ srcmac_vendor ^ srcmac_dev; } /* Extract the appropriate headers based on bond's xmit policy */ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk) { bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; int ip_proto = -1; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, fk, data, l2_proto, nhoff, hlen, 0); default: break; } fk->ports.ports = 0; memset(&fk->icmp, 0, sizeof(fk->icmp)); if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34)) return false; /* ICMP error packets contains at least 8 bytes of the header * of the packet which generated the error. Use this information * to correlate ICMP error packets within the same flow which * generated the error. */ if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) { skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen); if (ip_proto == IPPROTO_ICMP) { if (!icmp_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmphdr); } else if (ip_proto == IPPROTO_ICMPV6) { if (!icmpv6_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmp6hdr); } return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34); } return true; } static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); /* discard lowest hash bit to deal with the common even ports pattern */ if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || xmit_policy == BOND_XMIT_POLICY_ENCAP34) return hash >> 1; return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize * the data as required, but this function can be used without it if the data is * known to be linear (e.g. with xdp_buff). */ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int mhoff, int nhoff, int hlen) { struct flow_keys flow; u32 hash; if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC) return bond_vlan_srcmac_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow)) return bond_eth_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { hash = bond_eth_hash(skb, data, mhoff, hlen); } else { if (flow.icmp.id) memcpy(&hash, &flow.icmp, sizeof(hash)); else memcpy(&hash, &flow.ports.ports, sizeof(hash)); } return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** * bond_xmit_hash - generate a hash value based on the xmit policy * @bond: bonding device * @skb: buffer to use for headers * * This function will extract the necessary headers from the skb buffer and use * them to generate a hash based on the xmit_policy set in the bonding device */ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) { if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && skb->l4_hash) return skb->hash; return __bond_xmit_hash(bond, skb, skb->data, skb->protocol, 0, skb_network_offset(skb), skb_headlen(skb)); } /** * bond_xmit_hash_xdp - generate a hash value based on the xmit policy * @bond: bonding device * @xdp: buffer to use for headers * * The XDP variant of bond_xmit_hash. */ static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp) { struct ethhdr *eth; if (xdp->data + sizeof(struct ethhdr) > xdp->data_end) return 0; eth = (struct ethhdr *)xdp->data; return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0, sizeof(struct ethhdr), xdp->data_end - xdp->data); } /*-------------------------- Device entry points ----------------------------*/ void bond_work_init_all(struct bonding *bond) { INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor); INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } static void bond_work_cancel_all(struct bonding *bond) { cancel_delayed_work_sync(&bond->mii_work); cancel_delayed_work_sync(&bond->arp_work); cancel_delayed_work_sync(&bond->alb_work); cancel_delayed_work_sync(&bond->ad_work); cancel_delayed_work_sync(&bond->mcast_work); cancel_delayed_work_sync(&bond->slave_arr_work); } static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { bond->rr_tx_counter = alloc_percpu(u32); if (!bond->rr_tx_counter) return -ENOMEM; } /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { if (bond_uses_primary(bond) && slave != rcu_access_pointer(bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); } else if (BOND_MODE(bond) != BOND_MODE_8023AD) { bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_NOW); } } } if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB))) return -ENOMEM; if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB) queue_delayed_work(bond->wq, &bond->alb_work, 0); } if (bond->params.miimon) /* link check interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->mii_work, 0); if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); bond->recv_probe = bond_rcv_validate; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) dev_mc_add(slave->dev, lacpdu_mcast_addr); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); return 0; } static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; bond_work_cancel_all(bond); bond->send_peer_notif = 0; if (bond_is_lb(bond)) bond_alb_deinitialize(bond); bond->recv_probe = NULL; if (bond_uses_primary(bond)) { rcu_read_lock(); slave = rcu_dereference(bond->curr_active_slave); if (slave) bond_hw_addr_flush(bond_dev, slave->dev); rcu_read_unlock(); } else { struct list_head *iter; bond_for_each_slave(bond, slave, iter) bond_hw_addr_flush(bond_dev, slave->dev); } return 0; } /* fold stats, assuming all rtnl_link_stats64 fields are u64, but * that some drivers can provide 32bit values only. */ static void bond_fold_stats(struct rtnl_link_stats64 *_res, const struct rtnl_link_stats64 *_new, const struct rtnl_link_stats64 *_old) { const u64 *new = (const u64 *)_new; const u64 *old = (const u64 *)_old; u64 *res = (u64 *)_res; int i; for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { u64 nv = new[i]; u64 ov = old[i]; s64 delta = nv - ov; /* detects if this particular field is 32bit only */ if (((nv | ov) >> 32) == 0) delta = (s64)(s32)((u32)nv - (u32)ov); /* filter anomalies, some drivers reset their stats * at down/up events. */ if (delta > 0) res[i] += delta; } } #ifdef CONFIG_LOCKDEP static int bond_get_lowest_level_rcu(struct net_device *dev) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int cur = 0, max = 0; now = dev; iter = &dev->adj_list.lower; while (1) { next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; if (max <= cur) max = cur; break; } if (!next) { if (!cur) return max; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return max; } #endif static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; int nest_level = 0; rcu_read_lock(); #ifdef CONFIG_LOCKDEP nest_level = bond_get_lowest_level_rcu(bond_dev); #endif spin_lock_nested(&bond->stats_lock, nest_level); memcpy(stats, &bond->bond_stats, sizeof(*stats)); bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); bond_fold_stats(stats, new, &slave->slave_stats); /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); rcu_read_unlock(); } static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct mii_ioctl_data *mii = NULL; netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCGMIIPHY: mii = if_mii(ifr); if (!mii) return -EINVAL; mii->phy_id = 0; fallthrough; case SIOCGMIIREG: /* We do this again just in case we were called by SIOCGMIIREG * instead of SIOCGMIIPHY. */ mii = if_mii(ifr); if (!mii) return -EINVAL; if (mii->reg_num == 1) { mii->val_out = 0; if (netif_carrier_ok(bond->dev)) mii->val_out = BMSR_LSTATUS; } break; default: return -EOPNOTSUPP; } return 0; } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct net_device *slave_dev = NULL; struct ifbond k_binfo; struct ifbond __user *u_binfo = NULL; struct ifslave k_sinfo; struct ifslave __user *u_sinfo = NULL; struct bond_opt_value newval; struct net *net; int res = 0; netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) return -EFAULT; bond_info_query(bond_dev, &k_binfo); if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) return -EFAULT; return 0; case SIOCBONDSLAVEINFOQUERY: u_sinfo = (struct ifslave __user *)ifr->ifr_data; if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) return -EFAULT; res = bond_slave_info_query(bond_dev, &k_sinfo); if (res == 0 && copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) return -EFAULT; return res; default: break; } net = dev_net(bond_dev); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; slave_dev = __dev_get_by_name(net, ifr->ifr_slave); slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); if (!slave_dev) return -ENODEV; switch (cmd) { case SIOCBONDENSLAVE: res = bond_enslave(bond_dev, slave_dev, NULL); break; case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); break; case SIOCBONDSETHWADDR: res = bond_set_dev_addr(bond_dev, slave_dev); break; case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, &newval); break; default: res = -EOPNOTSUPP; } return res; } static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr, void __user *data, int cmd) { struct ifreq ifrdata = { .ifr_data = data }; switch (cmd) { case BOND_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY); case BOND_SLAVE_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY); case BOND_ENSLAVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE); case BOND_RELEASE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE); case BOND_SETHWADDR_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR); case BOND_CHANGE_ACTIVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE); } return -EOPNOTSUPP; } static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); if (change & IFF_PROMISC) bond_set_promiscuity(bond, bond_dev->flags & IFF_PROMISC ? 1 : -1); if (change & IFF_ALLMULTI) bond_set_allmulti(bond, bond_dev->flags & IFF_ALLMULTI ? 1 : -1); } static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; rcu_read_lock(); if (bond_uses_primary(bond)) { slave = rcu_dereference(bond->curr_active_slave); if (slave) { dev_uc_sync(slave->dev, bond_dev); dev_mc_sync(slave->dev, bond_dev); } } else { bond_for_each_slave_rcu(bond, slave, iter) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } } rcu_read_unlock(); } static int bond_neigh_init(struct neighbour *n) { struct bonding *bond = netdev_priv(n->dev); const struct net_device_ops *slave_ops; struct neigh_parms parms; struct slave *slave; int ret = 0; rcu_read_lock(); slave = bond_first_slave_rcu(bond); if (!slave) goto out; slave_ops = slave->dev->netdev_ops; if (!slave_ops->ndo_neigh_setup) goto out; /* TODO: find another way [1] to implement this. * Passing a zeroed structure is fragile, * but at least we do not pass garbage. * * [1] One way would be that ndo_neigh_setup() never touch * struct neigh_parms, but propagate the new neigh_setup() * back to ___neigh_create() / neigh_parms_alloc() */ memset(&parms, 0, sizeof(parms)); ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); if (ret) goto out; if (parms.neigh_setup) ret = parms.neigh_setup(n); out: rcu_read_unlock(); return ret; } /* The bonding ndo_neigh_setup is called at init time beofre any * slave exists. So we must declare proxy setup function which will * be used at run time to resolve the actual slave neigh param setup. * * It's also called by master devices (such as vlans) to setup their * underlying devices. In that case - do nothing, we're already set up from * our init. */ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) { /* modify only our neigh_parms */ if (parms->dev == dev) parms->neigh_setup = bond_neigh_init; return 0; } /* Change the MTU of all of a master's slaves to match the master */ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res = 0; netdev_dbg(bond_dev, "bond=%p, new_mtu=%d\n", bond, new_mtu); bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "s %p c_m %p\n", slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); if (res) { /* If we failed to set the slave's mtu to the new value * we must abort the operation even in ACTIVE_BACKUP * mode, because if we allow the backup slaves to have * different mtu values than the active slave we'll * need to change their mtu when doing a failover. That * means changing their mtu from timer context, which * is probably not a good idea. */ slave_dbg(bond_dev, slave->dev, "err %d setting mtu to %d\n", res, new_mtu); goto unwind; } } WRITE_ONCE(bond_dev->mtu, new_mtu); return 0; unwind: /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) slave_dbg(bond_dev, rollback_slave->dev, "unwind err %d\n", tmp_res); } return res; } /* Change HW address * * Note that many devices must be down to change the HW address, and * downing the master releases all slaves. We can make bonds full of * bonding devices to test this, however. */ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct sockaddr_storage *ss = addr, tmp_ss; struct list_head *iter; int res = 0; if (BOND_MODE(bond) == BOND_MODE_ALB) return bond_alb_set_mac_address(bond_dev, addr); netdev_dbg(bond_dev, "%s: bond=%p\n", __func__, bond); /* If fail_over_mac is enabled, do nothing and return success. * Returning an error causes ifenslave to fail. */ if (bond->params.fail_over_mac && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) return 0; if (!is_valid_ether_addr(ss->__data)) return -EADDRNOTAVAIL; bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "%s: slave=%p\n", __func__, slave); res = dev_set_mac_address(slave->dev, addr, NULL); if (res) { /* TODO: consider downing the slave * and retry ? * User should expect communications * breakage anyway until ARP finish * updating, so... */ slave_dbg(bond_dev, slave->dev, "%s: err %d\n", __func__, res); goto unwind; } } /* success */ dev_addr_set(bond_dev, ss->__data); return 0; unwind: memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len); tmp_ss.ss_family = bond_dev->type; /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mac_address(rollback_slave->dev, (struct sockaddr *)&tmp_ss, NULL); if (tmp_res) { slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n", __func__, tmp_res); } } return res; } /** * bond_get_slave_by_id - get xmit slave with slave_id * @bond: bonding device that is transmitting * @slave_id: slave id up to slave_cnt-1 through which to transmit * * This function tries to get slave with slave_id but in case * it fails, it tries to find the first available slave for transmission. */ static struct slave *bond_get_slave_by_id(struct bonding *bond, int slave_id) { struct list_head *iter; struct slave *slave; int i = slave_id; /* Here we start from the slave with slave_id */ bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) { if (bond_slave_can_tx(slave)) return slave; } } /* Here we start from the first slave up to slave_id */ i = slave_id; bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) break; if (bond_slave_can_tx(slave)) return slave; } /* no slave that can tx has been found */ return NULL; } /** * bond_rr_gen_slave_id - generate slave id based on packets_per_slave * @bond: bonding device to use * * Based on the value of the bonding device's packets_per_slave parameter * this function generates a slave id, which is usually used as the next * slave to transmit through. */ static u32 bond_rr_gen_slave_id(struct bonding *bond) { u32 slave_id; struct reciprocal_value reciprocal_packets_per_slave; int packets_per_slave = bond->params.packets_per_slave; switch (packets_per_slave) { case 0: slave_id = get_random_u32(); break; case 1: slave_id = this_cpu_inc_return(*bond->rr_tx_counter); break; default: reciprocal_packets_per_slave = bond->params.reciprocal_packets_per_slave; slave_id = this_cpu_inc_return(*bond->rr_tx_counter); slave_id = reciprocal_divide(slave_id, reciprocal_packets_per_slave); break; } return slave_id; } static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond, struct sk_buff *skb) { struct slave *slave; int slave_cnt; u32 slave_id; /* Start with the curr_active_slave that joined the bond as the * default for sending IGMP traffic. For failover purposes one * needs to maintain some consistency for the interface that will * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ if (skb->protocol == htons(ETH_P_IP)) { int noff = skb_network_offset(skb); struct iphdr *iph; if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) goto non_igmp; iph = ip_hdr(skb); if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct slave *slave; int slave_cnt; u32 slave_id; const struct ethhdr *eth; void *data = xdp->data; if (data + sizeof(struct ethhdr) > xdp->data_end) goto non_igmp; eth = (struct ethhdr *)data; data += sizeof(struct ethhdr); /* See comment on IGMP in bond_xmit_roundrobin_slave_get() */ if (eth->h_proto == htons(ETH_P_IP)) { const struct iphdr *iph; if (data + sizeof(struct iphdr) > xdp->data_end) goto non_igmp; iph = (struct iphdr *)data; if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_roundrobin_slave_get(bond, skb); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond) { return rcu_dereference(bond->curr_active_slave); } /* In active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. */ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_activebackup_slave_get(bond); if (slave) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } /* Use this to update slave_array when (a) it's not appropriate to update * slave_array right away (note that update_slave_array() may sleep) * and / or (b) RTNL is not held. */ void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay) { queue_delayed_work(bond->wq, &bond->slave_arr_work, delay); } /* Slave array work handler. Holds only RTNL */ static void bond_slave_arr_handler(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, slave_arr_work.work); int ret; if (!rtnl_trylock()) goto err; ret = bond_update_slave_arr(bond, NULL); rtnl_unlock(); if (ret) { pr_warn_ratelimited("Failed to update slave array from WT\n"); goto err; } return; err: bond_slave_arr_work_rearm(bond, 1); } static void bond_skip_slave(struct bond_up_slave *slaves, struct slave *skipslave) { int idx; /* Rare situation where caller has asked to skip a specific * slave but allocation failed (most likely!). BTW this is * only possible when the call is initiated from * __bond_release_one(). In this situation; overwrite the * skipslave entry in the array with the last entry from the * array to avoid a situation where the xmit path may choose * this to-be-skipped slave to send a packet out. */ for (idx = 0; slaves && idx < slaves->count; idx++) { if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; slaves->count--; break; } } } static void bond_set_slave_arr(struct bonding *bond, struct bond_up_slave *usable_slaves, struct bond_up_slave *all_slaves) { struct bond_up_slave *usable, *all; usable = rtnl_dereference(bond->usable_slaves); rcu_assign_pointer(bond->usable_slaves, usable_slaves); kfree_rcu(usable, rcu); all = rtnl_dereference(bond->all_slaves); rcu_assign_pointer(bond->all_slaves, all_slaves); kfree_rcu(all, rcu); } static void bond_reset_slave_arr(struct bonding *bond) { bond_set_slave_arr(bond, NULL, NULL); } /* Build the usable slaves array in control path for modes that use xmit-hash * to determine the slave interface - * (a) BOND_MODE_8023AD * (b) BOND_MODE_XOR * (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0 * * The caller is expected to hold RTNL only and NO other lock! */ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) { struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL; struct slave *slave; struct list_head *iter; int agg_id = 0; int ret = 0; might_sleep(); usable_slaves = kzalloc(struct_size(usable_slaves, arr, bond->slave_cnt), GFP_KERNEL); all_slaves = kzalloc(struct_size(all_slaves, arr, bond->slave_cnt), GFP_KERNEL); if (!usable_slaves || !all_slaves) { ret = -ENOMEM; goto out; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; spin_lock_bh(&bond->mode_lock); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { spin_unlock_bh(&bond->mode_lock); pr_debug("bond_3ad_get_active_agg_info failed\n"); /* No active aggragator means it's not safe to use * the previous array. */ bond_reset_slave_arr(bond); goto out; } spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg; agg = SLAVE_AD_INFO(slave)->port.aggregator; if (!agg || agg->aggregator_identifier != agg_id) continue; } if (!bond_slave_can_tx(slave)) continue; slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", usable_slaves->count); usable_slaves->arr[usable_slaves->count++] = slave; } bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; out: if (ret != 0 && skipslave) { bond_skip_slave(rtnl_dereference(bond->all_slaves), skipslave); bond_skip_slave(rtnl_dereference(bond->usable_slaves), skipslave); } kfree_rcu(all_slaves, rcu); kfree_rcu(usable_slaves, rcu); return ret; } static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, struct sk_buff *skb, struct bond_up_slave *slaves) { struct slave *slave; unsigned int count; u32 hash; hash = bond_xmit_hash(bond, skb); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; slave = slaves->arr[hash % count]; return slave; } static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct bond_up_slave *slaves; unsigned int count; u32 hash; hash = bond_xmit_hash_xdp(bond, xdp); slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; return slaves->arr[hash % count]; } /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. */ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct bond_up_slave *slaves; struct slave *slave; slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(dev, skb); } /* in broadcast mode, we send everything to all usable interfaces. */ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; bool xmit_suc = false; bool skb_used = false; bond_for_each_slave_rcu(bond, slave, iter) { struct sk_buff *skb2; if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)) continue; if (bond_is_last_slave(bond, slave)) { skb2 = skb; skb_used = true; } else { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { net_err_ratelimited("%s: Error: %s: skb_clone() failed\n", bond_dev->name, __func__); continue; } } if (bond_dev_queue_xmit(bond, skb2, slave->dev) == NETDEV_TX_OK) xmit_suc = true; } if (!skb_used) dev_kfree_skb_any(skb); if (xmit_suc) return NETDEV_TX_OK; dev_core_stats_tx_dropped_inc(bond_dev); return NET_XMIT_DROP; } /*------------------------- Device initialization ---------------------------*/ /* Lookup the slave that corresponds to a qid */ static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { struct slave *slave = NULL; struct list_head *iter; if (!skb_rx_queue_recorded(skb)) return 1; /* Find out if any slaves have the same mapping as this skb. */ bond_for_each_slave_rcu(bond, slave, iter) { if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) { if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_dev_queue_xmit(bond, skb, slave->dev); return 0; } /* If the slave isn't UP, use default transmit policy. */ break; } } return 1; } static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the bonding driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb); if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, struct sk_buff *skb, bool all_slaves) { struct bonding *bond = netdev_priv(master_dev); struct bond_up_slave *slaves; struct slave *slave = NULL; switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xmit_roundrobin_slave_get(bond, skb); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: if (all_slaves) slaves = rcu_dereference(bond->all_slaves); else slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); break; case BOND_MODE_BROADCAST: break; case BOND_MODE_ALB: slave = bond_xmit_alb_slave_get(bond, skb); break; case BOND_MODE_TLB: slave = bond_xmit_tlb_slave_get(bond, skb); break; default: /* Should never happen, mode already checked */ WARN_ONCE(true, "Unknown bonding mode"); break; } if (slave) return slave->dev; return NULL; } static void bond_sk_to_flow(struct sock *sk, struct flow_keys *flow) { switch (sk->sk_family) { #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (ipv6_only_sock(sk) || ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) { flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; flow->addrs.v6addrs.src = inet6_sk(sk)->saddr; flow->addrs.v6addrs.dst = sk->sk_v6_daddr; break; } fallthrough; #endif default: /* AF_INET */ flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; flow->addrs.v4addrs.src = inet_sk(sk)->inet_rcv_saddr; flow->addrs.v4addrs.dst = inet_sk(sk)->inet_daddr; break; } flow->ports.src = inet_sk(sk)->inet_sport; flow->ports.dst = inet_sk(sk)->inet_dport; } /** * bond_sk_hash_l34 - generate a hash value based on the socket's L3 and L4 fields * @sk: socket to use for headers * * This function will extract the necessary field from the socket and use * them to generate a hash based on the LAYER34 xmit_policy. * Assumes that sk is a TCP or UDP socket. */ static u32 bond_sk_hash_l34(struct sock *sk) { struct flow_keys flow; u32 hash; bond_sk_to_flow(sk, &flow); /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, struct sock *sk) { struct bond_up_slave *slaves; struct slave *slave; unsigned int count; u32 hash; slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; hash = bond_sk_hash_l34(sk); slave = slaves->arr[hash % count]; return slave->dev; } static struct net_device *bond_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { struct bonding *bond = netdev_priv(dev); struct net_device *lower = NULL; rcu_read_lock(); if (bond_sk_check(bond)) lower = __bond_sk_get_lower_dev(bond, sk); rcu_read_unlock(); return lower; } #if IS_ENABLED(CONFIG_TLS_DEVICE) static netdev_tx_t bond_tls_device_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *dev) { struct net_device *tls_netdev = rcu_dereference(tls_get_ctx(skb->sk)->netdev); /* tls_netdev might become NULL, even if tls_is_skb_tx_device_offloaded * was true, if tls_device_down is running in parallel, but it's OK, * because bond_get_slave_by_dev has a NULL check. */ if (likely(bond_get_slave_by_dev(bond, tls_netdev))) return bond_dev_queue_xmit(bond, skb, tls_netdev); return bond_tx_drop(dev, skb); } #endif static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); if (bond_should_override_tx_queue(bond) && !bond_slave_override(bond, skb)) return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_TLS_DEVICE) if (tls_is_skb_tx_device_offloaded(skb)) return bond_tls_device_xmit(bond, skb, dev); #endif switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return bond_xmit_roundrobin(skb, dev); case BOND_MODE_ACTIVEBACKUP: return bond_xmit_activebackup(skb, dev); case BOND_MODE_8023AD: case BOND_MODE_XOR: return bond_3ad_xor_xmit(skb, dev); case BOND_MODE_BROADCAST: return bond_xmit_broadcast(skb, dev); case BOND_MODE_ALB: return bond_alb_xmit(skb, dev); case BOND_MODE_TLB: return bond_tlb_xmit(skb, dev); default: /* Should never happen, mode already checked */ netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond)); WARN_ON_ONCE(1); return bond_tx_drop(dev, skb); } } static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); netdev_tx_t ret = NETDEV_TX_OK; /* If we risk deadlock from transmitting this in the * netpoll path, tell netpoll to queue the frame for later tx */ if (unlikely(is_netpoll_tx_blocked(dev))) return NETDEV_TX_BUSY; rcu_read_lock(); if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else ret = bond_tx_drop(dev, skb); rcu_read_unlock(); return ret; } static struct net_device * bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; /* Caller needs to hold rcu_read_lock() */ switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp); break; default: if (net_ratelimit()) netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond)); return NULL; } if (slave) return slave->dev; return NULL; } static int bond_xdp_xmit(struct net_device *bond_dev, int n, struct xdp_frame **frames, u32 flags) { int nxmit, err = -ENXIO; rcu_read_lock(); for (nxmit = 0; nxmit < n; nxmit++) { struct xdp_frame *frame = frames[nxmit]; struct xdp_frame *frames1[] = {frame}; struct net_device *slave_dev; struct xdp_buff xdp; xdp_convert_frame_to_buff(frame, &xdp); slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp); if (!slave_dev) { err = -ENXIO; break; } err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags); if (err < 1) break; } rcu_read_unlock(); /* If error happened on the first frame then we can pass the error up, otherwise * report the number of frames that were xmitted. */ if (err < 0) return (nxmit == 0 ? err : nxmit); return nxmit; } static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave, *rollback_slave; struct bpf_prog *old_prog; struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = prog, .extack = extack, }; int err; ASSERT_RTNL(); if (!bond_xdp_check(bond)) { BOND_NL_ERR(dev, extack, "No native XDP support for the current bonding mode"); return -EOPNOTSUPP; } old_prog = bond->xdp_prog; bond->xdp_prog = prog; bond_for_each_slave(bond, slave, iter) { struct net_device *slave_dev = slave->dev; if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave device does not support XDP"); err = -EOPNOTSUPP; goto err; } if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); err = -EOPNOTSUPP; goto err; } err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); goto err; } if (prog) bpf_prog_inc(prog); } if (prog) { static_branch_inc(&bpf_master_redirect_enabled_key); } else if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&bpf_master_redirect_enabled_key); } return 0; err: /* unwind the program changes */ bond->xdp_prog = old_prog; xdp.prog = old_prog; xdp.extack = NULL; /* do not overwrite original error */ bond_for_each_slave(bond, rollback_slave, iter) { struct net_device *slave_dev = rollback_slave->dev; int err_unwind; if (slave == rollback_slave) break; err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); else if (xdp.prog) bpf_prog_inc(xdp.prog); } return err; } static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return bond_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) { if (speed == 0 || speed == SPEED_UNKNOWN) speed = slave->speed; else speed = min(speed, slave->speed); return speed; } /* Set the BOND_PHC_INDEX flag to notify user space */ static int bond_set_phc_index_flag(struct kernel_hwtstamp_config *kernel_cfg) { struct ifreq *ifr = kernel_cfg->ifr; struct hwtstamp_config cfg; if (kernel_cfg->copied_to_user) { /* Lower device has a legacy implementation */ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) return -EFAULT; } else { kernel_cfg->flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; } return 0; } static int bond_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_get_lower(real_dev, cfg); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; if (!(cfg->flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX)) return -EOPNOTSUPP; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_set_lower(real_dev, cfg, extack); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; /* Since bond_slave_can_tx returns false for all inactive or down slaves, we * do not need to check mode. Though link speed might not represent * the true receive or transmit bandwidth (not all modes are symmetric) * this is an accurate maximum. */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { bond_update_speed_duplex(slave); if (slave->speed != SPEED_UNKNOWN) { if (BOND_MODE(bond) == BOND_MODE_BROADCAST) speed = bond_mode_bcast_speed(slave, speed); else speed += slave->speed; } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; } } cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", BOND_ABI_VERSION); } static int bond_ethtool_get_ts_info(struct net_device *bond_dev, struct kernel_ethtool_ts_info *info) { struct bonding *bond = netdev_priv(bond_dev); struct kernel_ethtool_ts_info ts_info; struct net_device *real_dev; bool sw_tx_support = false; struct list_head *iter; struct slave *slave; int ret = 0; rcu_read_lock(); real_dev = bond_option_active_slave_get_rcu(bond); dev_hold(real_dev); rcu_read_unlock(); if (real_dev) { ret = ethtool_get_ts_info_by_layer(real_dev, info); } else { /* Check if all slaves support software tx timestamping */ rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info); if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) { sw_tx_support = true; continue; } sw_tx_support = false; break; } rcu_read_unlock(); } if (sw_tx_support) info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE; dev_put(real_dev); return ret; } static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = bond_ethtool_get_link_ksettings, .get_ts_info = bond_ethtool_get_ts_info, }; static const struct net_device_ops bond_netdev_ops = { .ndo_init = bond_init, .ndo_uninit = bond_uninit, .ndo_open = bond_open, .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, .ndo_eth_ioctl = bond_eth_ioctl, .ndo_siocbond = bond_do_ioctl, .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, .ndo_set_rx_mode = bond_set_rx_mode, .ndo_change_mtu = bond_change_mtu, .ndo_set_mac_address = bond_set_mac_address, .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, .ndo_poll_controller = bond_poll_controller, #endif .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_features_check = passthru_features_check, .ndo_get_xmit_slave = bond_xmit_get_slave, .ndo_sk_get_lower_dev = bond_sk_get_lower_dev, .ndo_bpf = bond_xdp, .ndo_xdp_xmit = bond_xdp_xmit, .ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave, .ndo_hwtstamp_get = bond_hwtstamp_get, .ndo_hwtstamp_set = bond_hwtstamp_set, }; static const struct device_type bond_type = { .name = "bond", }; static void bond_destructor(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); if (bond->wq) destroy_workqueue(bond->wq); free_percpu(bond->rr_tx_counter); } void bond_setup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); bond->params = bonding_defaults; /* Initialize pointers */ bond->dev = bond_dev; /* Initialize the device entry points */ ether_setup(bond_dev); bond_dev->max_mtu = ETH_MAX_MTU; bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; bond_dev->needs_free_netdev = true; bond_dev->priv_destructor = bond_destructor; SET_NETDEV_DEVTYPE(bond_dev, &bond_type); /* Initialize the device options */ bond_dev->flags |= IFF_MASTER; bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE; bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); #ifdef CONFIG_XFRM_OFFLOAD /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; INIT_LIST_HEAD(&bond->ipsec_list); mutex_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ bond_dev->lltx = true; /* Don't allow bond devices to change network namespaces. */ bond_dev->netns_local = true; /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special * care is taken in the various xmit functions * when there are slaves that are not hw accel * capable */ bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; bond_dev->features |= NETIF_F_GSO_PARTIAL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; /* Only enable XFRM features if this is an active-backup config */ if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ } /* Destroy a bonding device. * Must be under rtnl_lock when this function is called. */ static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ bond_for_each_slave(bond, slave, iter) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); #ifdef CONFIG_XFRM_OFFLOAD mutex_destroy(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ bond_set_slave_arr(bond, NULL, NULL); list_del_rcu(&bond->bond_list); bond_debug_unregister(bond); } /*------------------------- Module initialization ---------------------------*/ static int __init bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; struct bond_opt_value newval; const struct bond_opt_value *valptr; int arp_all_targets_value = 0; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0 }; int arp_ip_count; int bond_mode = BOND_MODE_ROUNDROBIN; int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; int lacp_fast = 0; int tlb_dynamic_lb; /* Convert string parameters. */ if (mode) { bond_opt_initstr(&newval, mode); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval); if (!valptr) { pr_err("Error: Invalid bonding mode \"%s\"\n", mode); return -EINVAL; } bond_mode = valptr->value; } if (xmit_hash_policy) { if (bond_mode == BOND_MODE_ROUNDROBIN || bond_mode == BOND_MODE_ACTIVEBACKUP || bond_mode == BOND_MODE_BROADCAST) { pr_info("xmit_hash_policy param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, xmit_hash_policy); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), &newval); if (!valptr) { pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", xmit_hash_policy); return -EINVAL; } xmit_hashtype = valptr->value; } } if (lacp_rate) { if (bond_mode != BOND_MODE_8023AD) { pr_info("lacp_rate param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, lacp_rate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE), &newval); if (!valptr) { pr_err("Error: Invalid lacp rate \"%s\"\n", lacp_rate); return -EINVAL; } lacp_fast = valptr->value; } } if (ad_select) { bond_opt_initstr(&newval, ad_select); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), &newval); if (!valptr) { pr_err("Error: Invalid ad_select \"%s\"\n", ad_select); return -EINVAL; } params->ad_select = valptr->value; if (bond_mode != BOND_MODE_8023AD) pr_warn("ad_select param only affects 802.3ad mode\n"); } else { params->ad_select = BOND_AD_STABLE; } if (max_bonds < 0) { pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", miimon, INT_MAX); miimon = 0; } if (updelay < 0) { pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", updelay, INT_MAX); updelay = 0; } if (downdelay < 0) { pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", downdelay, INT_MAX); downdelay = 0; } if ((use_carrier != 0) && (use_carrier != 1)) { pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", use_carrier); use_carrier = 1; } if (num_peer_notif < 0 || num_peer_notif > 255) { pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", num_peer_notif); num_peer_notif = 1; } /* reset values for 802.3ad/TLB/ALB */ if (!bond_mode_uses_arp(bond_mode)) { if (!miimon) { pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); pr_warn("Forcing miimon to 100msec\n"); miimon = BOND_DEFAULT_MIIMON; } } if (tx_queues < 1 || tx_queues > 255) { pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n", tx_queues, BOND_DEFAULT_TX_QUEUES); tx_queues = BOND_DEFAULT_TX_QUEUES; } if ((all_slaves_active != 0) && (all_slaves_active != 1)) { pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n", all_slaves_active); all_slaves_active = 0; } if (resend_igmp < 0 || resend_igmp > 255) { pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n", resend_igmp, BOND_DEFAULT_RESEND_IGMP); resend_igmp = BOND_DEFAULT_RESEND_IGMP; } bond_opt_initval(&newval, packets_per_slave); if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) { pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n", packets_per_slave, USHRT_MAX); packets_per_slave = 1; } if (bond_mode == BOND_MODE_ALB) { pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n", updelay); } if (!miimon) { if (updelay || downdelay) { /* just warn the user the up/down delay will have * no effect since miimon is zero... */ pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", updelay, downdelay); } } else { /* don't allow arp monitoring */ if (arp_interval) { pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", miimon, arp_interval); arp_interval = 0; } if ((updelay % miimon) != 0) { pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", updelay, miimon, (updelay / miimon) * miimon); } updelay /= miimon; if ((downdelay % miimon) != 0) { pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", downdelay, miimon, (downdelay / miimon) * miimon); } downdelay /= miimon; } if (arp_interval < 0) { pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", arp_interval, INT_MAX); arp_interval = 0; } for (arp_ip_count = 0, i = 0; (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { __be32 ip; /* not a complete check, but good enough to catch mistakes */ if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || !bond_is_ip_target_ok(ip)) { pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", arp_ip_target[i]); arp_interval = 0; } else { if (bond_get_targets_ip(arp_target, ip) == -1) arp_target[arp_ip_count++] = ip; else pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", arp_interval); arp_interval = 0; } if (arp_validate) { if (!arp_interval) { pr_err("arp_validate requires arp_interval\n"); return -EINVAL; } bond_opt_initstr(&newval, arp_validate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE), &newval); if (!valptr) { pr_err("Error: invalid arp_validate \"%s\"\n", arp_validate); return -EINVAL; } arp_validate_value = valptr->value; } else { arp_validate_value = 0; } if (arp_all_targets) { bond_opt_initstr(&newval, arp_all_targets); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS), &newval); if (!valptr) { pr_err("Error: invalid arp_all_targets_value \"%s\"\n", arp_all_targets); arp_all_targets_value = 0; } else { arp_all_targets_value = valptr->value; } } if (miimon) { pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, arp_validate_value); pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) pr_cont(" %s", arp_ip_target[i]); pr_cont("\n"); } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n"); } if (primary && !bond_mode_uses_primary(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ pr_warn("Warning: %s primary device specified but has no effect in %s mode\n", primary, bond_mode_name(bond_mode)); primary = NULL; } if (primary && primary_reselect) { bond_opt_initstr(&newval, primary_reselect); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT), &newval); if (!valptr) { pr_err("Error: Invalid primary_reselect \"%s\"\n", primary_reselect); return -EINVAL; } primary_reselect_value = valptr->value; } else { primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; } if (fail_over_mac) { bond_opt_initstr(&newval, fail_over_mac); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC), &newval); if (!valptr) { pr_err("Error: invalid fail_over_mac \"%s\"\n", fail_over_mac); return -EINVAL; } fail_over_mac_value = valptr->value; if (bond_mode != BOND_MODE_ACTIVEBACKUP) pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); } else { fail_over_mac_value = BOND_FOM_NONE; } bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse( bond_opt_get(BOND_OPT_AD_ACTOR_SYS_PRIO), &newval); if (!valptr) { pr_err("Error: No ad_actor_sys_prio default value"); return -EINVAL; } ad_actor_sys_prio = valptr->value; valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_USER_PORT_KEY), &newval); if (!valptr) { pr_err("Error: No ad_user_port_key default value"); return -EINVAL; } ad_user_port_key = valptr->value; bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); if (!valptr) { pr_err("Error: No tlb_dynamic_lb default value"); return -EINVAL; } tlb_dynamic_lb = valptr->value; if (lp_interval == 0) { pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; } /* fill params struct with the proper values */ params->mode = bond_mode; params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->num_peer_notif = num_peer_notif; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->arp_all_targets = arp_all_targets_value; params->missed_max = 2; params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; params->use_carrier = use_carrier; params->lacp_active = 1; params->lacp_fast = lacp_fast; params->primary[0] = 0; params->primary_reselect = primary_reselect_value; params->fail_over_mac = fail_over_mac_value; params->tx_queues = tx_queues; params->all_slaves_active = all_slaves_active; params->resend_igmp = resend_igmp; params->min_links = min_links; params->lp_interval = lp_interval; params->packets_per_slave = packets_per_slave; params->tlb_dynamic_lb = tlb_dynamic_lb; params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; params->coupled_control = 1; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); } else { /* reciprocal_packets_per_slave is unused if * packets_per_slave is 0 or 1, just initialize it */ params->reciprocal_packets_per_slave = (struct reciprocal_value) { 0 }; } if (primary) strscpy_pad(params->primary, primary, sizeof(params->primary)); memcpy(params->arp_targets, arp_target, sizeof(arp_target)); #if IS_ENABLED(CONFIG_IPV6) memset(params->ns_targets, 0, sizeof(struct in6_addr) * BOND_MAX_NS_TARGETS); #endif return 0; } /* Called from registration process */ static int bond_init(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); netdev_dbg(bond_dev, "Begin bond_init\n"); bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, bond_dev->name); if (!bond->wq) return -ENOMEM; bond->notifier_ctx = false; spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); list_add_tail_rcu(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); bond_debug_register(bond); /* Ensure valid dev_addr */ if (is_zero_ether_addr(bond_dev->dev_addr) && bond_dev->addr_assign_type == NET_ADDR_PERM) eth_hw_addr_random(bond_dev); return 0; } unsigned int bond_get_num_tx_queues(void) { return tx_queues; } /* Create a new bond based on the specified name and bonding parameters. * If name is NULL, obtain a suitable "bond%d" name for us. * Caller must NOT hold rtnl_lock; we need to release it here before we * set up our sysfs entries. */ int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; struct bonding *bond; int res = -ENOMEM; rtnl_lock(); bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "bond%d", NET_NAME_UNKNOWN, bond_setup, tx_queues); if (!bond_dev) goto out; bond = netdev_priv(bond_dev); dev_net_set(bond_dev, net); bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); if (res < 0) { free_netdev(bond_dev); goto out; } netif_carrier_off(bond_dev); bond_work_init_all(bond); out: rtnl_unlock(); return res; } static int __net_init bond_net_init(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bn->net = net; INIT_LIST_HEAD(&bn->dev_list); bond_create_proc_dir(bn); bond_create_sysfs(bn); return 0; } /* According to commit 69b0216ac255 ("bonding: fix bonding_masters * race condition in bond unloading") we need to remove sysfs files * before we remove our devices (done later in bond_net_exit_batch_rtnl()) */ static void __net_exit bond_net_pre_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bond_destroy_sysfs(bn); } static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_kill_list) { struct bond_net *bn; struct net *net; /* Kill off any bonds created after unregistering bond rtnl ops */ list_for_each_entry(net, net_list, exit_list) { struct bonding *bond, *tmp_bond; bn = net_generic(net, bond_net_id); list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) unregister_netdevice_queue(bond->dev, dev_kill_list); } } /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory * only after all bonds are gone") bond_destroy_proc_dir() is called * after bond_net_exit_batch_rtnl() has completed. */ static void __net_exit bond_net_exit_batch(struct list_head *net_list) { struct bond_net *bn; struct net *net; list_for_each_entry(net, net_list, exit_list) { bn = net_generic(net, bond_net_id); bond_destroy_proc_dir(bn); } } static struct pernet_operations bond_net_ops = { .init = bond_net_init, .pre_exit = bond_net_pre_exit, .exit_batch_rtnl = bond_net_exit_batch_rtnl, .exit_batch = bond_net_exit_batch, .id = &bond_net_id, .size = sizeof(struct bond_net), }; static int __init bonding_init(void) { int i; int res; res = bond_check_params(&bonding_defaults); if (res) goto out; bond_create_debugfs(); res = register_pernet_subsys(&bond_net_ops); if (res) goto err_net_ops; res = bond_netlink_init(); if (res) goto err_link; for (i = 0; i < max_bonds; i++) { res = bond_create(&init_net, NULL); if (res) goto err; } skb_flow_dissector_init(&flow_keys_bonding, flow_keys_bonding_keys, ARRAY_SIZE(flow_keys_bonding_keys)); register_netdevice_notifier(&bond_netdev_notifier); out: return res; err: bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); err_net_ops: bond_destroy_debugfs(); goto out; } static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); bond_netlink_fini(); unregister_pernet_subsys(&bond_net_ops); bond_destroy_debugfs(); #ifdef CONFIG_NET_POLL_CONTROLLER /* Make sure we don't have an imbalance on our netpoll blocking */ WARN_ON(atomic_read(&netpoll_block_tx)); #endif } module_init(bonding_init); module_exit(bonding_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); |
| 108 108 40 116 69 56 1 48 14 51 8 85 356 141 141 85 83 81 72 77 72 67 72 72 65 73 7 83 7 62 83 107 83 109 73 97 110 109 99 110 5 44 33 16 222 16 1 318 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_HOST_H #define __KVM_HOST_H #include <linux/types.h> #include <linux/hardirq.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/preempt.h> #include <linux/msi.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rcupdate.h> #include <linux/ratelimit.h> #include <linux/err.h> #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> #include <linux/ftrace.h> #include <linux/hashtable.h> #include <linux/instrumentation.h> #include <linux/interval_tree.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <asm/kvm_host.h> #include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_IDS #define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally * used in kvm, other bits are visible for userspace which are defined in * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) /* * Bit 63 of the memslot generation number is an "update in-progress flag", * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. * * This is necessary because the actual memslots update is not atomic with * respect to the generation number update. Updating the generation number * first would allow a vCPU to cache a spte from the old memslots using the * new generation number, and updating the generation number after switching * to the new memslots would allow cache hits using the old generation number * to reference the defunct memslots. * * This mechanism is used to prevent getting hits in KVM's caches while a * memslot update is in-progress, and to prevent cache hits *after* updating * the actual generation number against accesses that were inserted into the * cache *before* the memslots were updated. */ #define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63) /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 #ifndef KVM_MAX_NR_ADDRESS_SPACES #define KVM_MAX_NR_ADDRESS_SPACES 1 #endif /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, * mask bit 63 to indicate the noslot pfn. */ #define KVM_PFN_ERR_MASK (0x7ffULL << 52) #define KVM_PFN_ERR_NOSLOT_MASK (0xfffULL << 52) #define KVM_PFN_NOSLOT (0x1ULL << 63) #define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK) #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) #define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) #define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } /* * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted * by a pending signal. Note, the signal may or may not be fatal. */ static inline bool is_sigpending_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_ERR_SIGPENDING; } /* * error_noslot pfns indicate that the gfn can not be * translated to pfn - it is not in slot or failed to * translate it to pfn. */ static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } /* * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) * provide own defines and kvm_is_error_hva */ #ifndef KVM_HVA_ERR_BAD #define KVM_HVA_ERR_BAD (PAGE_OFFSET) #define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE) static inline bool kvm_is_error_hva(unsigned long addr) { return addr >= PAGE_OFFSET; } #endif static inline bool kvm_is_error_gpa(gpa_t gpa) { return gpa == INVALID_GPA; } #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) #define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_DIRTY_RING_SOFT_FULL 3 #define KVM_REQUEST_ARCH_BASE 8 /* * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no * guarantee the vCPU received an IPI and has actually exited guest mode. */ #define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 extern struct mutex kvm_lock; extern struct list_head vm_list; struct kvm_io_range { gpa_t addr; int len; struct kvm_io_device *dev; }; #define NR_IOBUS_DEVS 1000 struct kvm_io_bus { int dev_count; int ioeventfd_count; struct kvm_io_range range[]; }; enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, KVM_IOCSR_BUS, KVM_NR_BUSES }; int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie); int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { struct work_struct work; struct list_head link; struct list_head queue; struct kvm_vcpu *vcpu; gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; bool notpresent_injected; }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { unsigned long attributes; }; enum kvm_gfn_range_filter { KVM_FILTER_SHARED = BIT(0), KVM_FILTER_PRIVATE = BIT(1), }; struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); #endif enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, EXITING_GUEST_MODE, READING_SHADOW_PAGE_TABLES, }; struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). */ struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; bool writable; }; /* * Used to check if the mapping is valid or not. Never use 'kvm_host_map' * directly to check for that. */ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) { return !!map->hva; } static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) { return single_task_running() && !need_resched() && ktime_before(cur, stop); } /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. */ struct kvm_mmio_fragment { gpa_t gpa; void *data; unsigned len; }; struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier preempt_notifier; #endif int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index into kvm->vcpu_array */ int ____srcu_idx; /* Don't use this directly. You've been warned. */ #ifdef CONFIG_PROVE_RCU int srcu_depth; #endif int mode; u64 requests; unsigned long guest_debug; struct mutex mutex; struct kvm_run *run; #ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; #endif struct pid *pid; rwlock_t pid_lock; int sigset_active; sigset_t sigset; unsigned int halt_poll_ns; bool valid_wakeup; #ifdef CONFIG_HAS_IOMEM int mmio_needed; int mmio_read_completed; int mmio_is_write; int mmio_cur_fragment; int mmio_nr_fragments; struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS]; #endif #ifdef CONFIG_KVM_ASYNC_PF struct { u32 queued; struct list_head queue; struct list_head done; spinlock_t lock; } async_pf; #endif #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT /* * Cpu relax intercept or pause loop exit optimization * in_spin_loop: set when a vcpu does a pause loop exit * or cpu relax intercepted. * dy_eligible: indicates whether vcpu is eligible for directed yield. */ struct { bool in_spin_loop; bool dy_eligible; } spin_loop; #endif bool wants_to_run; bool preempted; bool ready; bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; /* * The most recently used memslot by this vCPU and the slots generation * for which it is valid. * No wraparound protection is needed since generations won't overflow in * thousands of years, even assuming 1M memslot operations per second. */ struct kvm_memory_slot *last_used_slot; u64 last_used_slot_gen; }; /* * Start accounting time towards a guest. * Must be called before entering guest context. */ static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the * stime pending cputime to flush. */ instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); } /* * Enter guest context and enter an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_enter_irqoff(void) { /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In * addition CPU may stay in a guest mode for quite a long time (up to * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ if (!context_tracking_guest_enter()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Deprecated. Architectures should move to guest_timing_enter_irqoff() and * guest_state_enter_irqoff(). */ static __always_inline void guest_enter_irqoff(void) { guest_timing_enter_irqoff(); guest_context_enter_irqoff(); } /** * guest_state_enter_irqoff - Fixup state when entering a guest * * Entry to a guest will enable interrupts, but the kernel state is interrupts * disabled when this is invoked. Also tell RCU about it. * * 1) Trace interrupts on state * 2) Invoke context tracking if enabled to adjust RCU state * 3) Tell lockdep that interrupts are enabled * * Invoked from architecture specific code before entering a guest. * Must be called with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_enter_irqoff() before this. * * Note: this is analogous to exit_to_user_mode(). */ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); } /* * Exit guest context and exit an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_exit_irqoff(void) { /* * Guest mode is treated as a quiescent state, see * guest_context_enter_irqoff() for more details. */ if (!context_tracking_guest_exit()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Stop accounting time towards a guest. * Must be called after exiting guest context. */ static __always_inline void guest_timing_exit_irqoff(void) { instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } /* * Deprecated. Architectures should move to guest_state_exit_irqoff() and * guest_timing_exit_irqoff(). */ static __always_inline void guest_exit_irqoff(void) { guest_context_exit_irqoff(); guest_timing_exit_irqoff(); } static inline void guest_exit(void) { unsigned long flags; local_irq_save(flags); guest_exit_irqoff(); local_irq_restore(flags); } /** * guest_state_exit_irqoff - Establish state when returning from guest mode * * Entry from a guest disables interrupts, but guest mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. * * 1) Tell lockdep that interrupts are disabled * 2) Invoke context tracking if enabled to reactivate RCU * 3) Trace interrupts off state * * Invoked from architecture specific code after exiting a guest. * Must be invoked with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_exit_irqoff() after this. * * Note: this is analogous to enter_from_user_mode(). */ static __always_inline void guest_state_exit_irqoff(void) { lockdep_hardirqs_off(CALLER_ADDR0); guest_context_exit_irqoff(); instrumentation_begin(); trace_hardirqs_off_finish(); instrumentation_end(); } static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* * The memory barrier ensures a previous write to vcpu->requests cannot * be reordered with the read of vcpu->mode. It pairs with the general * memory barrier following the write of vcpu->mode in VCPU RUN. */ smp_mb__before_atomic(); return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE); } /* * Some of the bitops functions do not support too long bitmaps. * This number must be determined not to exceed such limits. */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) /* * Since at idle each memslot belongs to two memslot sets it has to contain * two embedded nodes for each data structure that it forms a part of. * * Two memslot sets (one active and one inactive) are necessary so the VM * continues to run on one memslot set while the other is being modified. * * These two memslot sets normally point to the same set of memslots. * They can, however, be desynchronized when performing a memslot management * operation by replacing the memslot to be modified by its copy. * After the operation is complete, both memslot sets once again point to * the same, common set of memslot data. * * The memslots themselves are independent of each other so they can be * individually added or deleted. */ struct kvm_memory_slot { struct hlist_node id_node[2]; struct interval_tree_node hva_node[2]; struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; u32 flags; short id; u16 as_id; #ifdef CONFIG_KVM_PRIVATE_MEM struct { /* * Writes protected by kvm->slots_lock. Acquiring a * reference via kvm_gmem_get_file() is protected by * either kvm->slots_lock or kvm->srcu. */ struct file *file; pgoff_t pgoff; } gmem; #endif }; static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) { return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); } static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; } static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long len = kvm_dirty_bitmap_bytes(memslot); return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); } #ifndef KVM_DIRTY_LOG_MANUAL_CAPS #define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE #endif struct kvm_s390_adapter_int { u64 ind_addr; u64 summary_addr; u64 ind_offset; u32 summary_offset; u32 adapter_id; }; struct kvm_hv_sint { u32 vcpu; u32 sint; }; struct kvm_xen_evtchn { u32 port; u32 vcpu_id; int vcpu_idx; u32 priority; }; struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); union { struct { unsigned irqchip; unsigned pin; } irqchip; struct { u32 address_lo; u32 address_hi; u32 data; u32 flags; u32 devid; } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; u32 nr_rt_entries; /* * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ struct hlist_head map[] __counted_by(nr_rt_entries); }; #endif bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); #ifndef KVM_INTERNAL_MEM_SLOTS #define KVM_INTERNAL_MEM_SLOTS 0 #endif #define KVM_MEM_SLOTS_NUM SHRT_MAX #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) #if KVM_MAX_NR_ADDRESS_SPACES == 1 static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) { return KVM_MAX_NR_ADDRESS_SPACES; } static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; } #endif /* * Arch code must define kvm_arch_has_private_mem if support for private memory * is enabled. */ #if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; } #endif #ifndef kvm_arch_has_readonly_mem static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) { return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); } #endif struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; struct rb_root_cached hva_tree; struct rb_root gfn_tree; /* * The mapping table from slot id to memslot. * * 7-bit bucket count matches the size of the old id to index array for * 512 slots, while giving good performance with this slot count. * Higher bucket counts bring only small performance improvements but * always result in higher memory usage (even for lower memslot counts). */ DECLARE_HASHTABLE(id_hash, 7); int node_idx; }; struct kvm { #ifdef KVM_HAVE_MMU_RWLOCK rwlock_t mmu_lock; #else spinlock_t mmu_lock; #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; /* * Protects the arch-specific fields of struct kvm_memory_slots in * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; /* The two memslot sets - active and inactive (per address space) */ struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2]; /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES]; struct xarray vcpu_array; /* * Protected by slots_lock, but can be read outside if an * incorrect answer is acceptable. */ atomic_t nr_memslots_dirty_logging; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; /* For management / invalidation of gfn_to_pfn_caches */ spinlock_t gpc_lock; struct list_head gpc_list; /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only * incremented after storing the kvm_vcpu pointer in vcpus, * and is accessed atomically. */ atomic_t online_vcpus; int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_IRQCHIP struct { spinlock_t lock; struct list_head items; /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; #endif struct list_head ioeventfds; struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; #ifdef CONFIG_KVM_MMIO struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; spinlock_t ring_lock; struct list_head coalesced_zones; #endif struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP /* * Update side is protected by irq_lock. */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head irq_ack_notifier_list; #endif #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; #endif struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool dirty_ring_with_bitmap; bool vm_bugged; bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES /* Protected by slots_locks (for writes) and RCU (for reads) */ struct xarray mem_attr_array; #endif char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_info(fmt, ...) \ pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug(fmt, ...) \ pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug_ratelimited(fmt, ...) \ pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \ ## __VA_ARGS__) #define kvm_pr_unimpl(fmt, ...) \ pr_err_ratelimited("kvm [%i]: " fmt, \ task_tgid_nr(current), ## __VA_ARGS__) /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...) \ kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \ (vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__) #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) #define vcpu_debug_ratelimited(vcpu, fmt, ...) \ kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \ ## __VA_ARGS__) #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) static inline void kvm_vm_dead(struct kvm *kvm) { kvm->vm_dead = true; kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); } static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; kvm_vm_dead(kvm); } #define KVM_BUG(cond, kvm, fmt...) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) #define KVM_BUG_ON(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) /* * Note, "data corruption" refers to corruption of host kernel data structures, * not guest data. Guest data corruption, suspected or confirmed, that is tied * and contained to a single VM should *never* BUG() and potentially panic the * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure * is corrupted and that corruption can have a cascading effect to other parts * of the hosts and/or to other VMs. */ #define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) \ BUG_ON(__ret); \ else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PROVE_RCU WARN_ONCE(vcpu->srcu_depth++, "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); #endif vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); } static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); #ifdef CONFIG_PROVE_RCU WARN_ONCE(--vcpu->srcu_depth, "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); #endif } static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); } static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) { return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); } static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); /* * Explicitly verify the target vCPU is online, as the anti-speculation * logic only limits the CPU's ability to speculate, e.g. given a "bad" * index, clamping the index to 0 would return vCPU0, not NULL. */ if (i >= num_vcpus) return NULL; i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return xa_load(&kvm->vcpu_array, i); } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ if (atomic_read(&kvm->online_vcpus)) \ xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; unsigned long i; if (id < 0) return NULL; if (id < KVM_MAX_VCPUS) vcpu = kvm_get_vcpu(kvm, id); if (vcpu && vcpu->vcpu_id == id) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) if (vcpu->vcpu_id == id) return vcpu; return NULL; } void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) { } #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else static inline int kvm_irqfd_init(void) { return 0; } static inline void kvm_irqfd_exit(void) { } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { return __kvm_memslots(kvm, 0); } static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) { int as_id = kvm_arch_vcpu_memslots_id(vcpu); return __kvm_memslots(vcpu->kvm, as_id); } static inline bool kvm_memslots_empty(struct kvm_memslots *slots) { return RB_EMPTY_ROOT(&slots->gfn_tree); } bool kvm_are_all_memslots_empty(struct kvm *kvm); #define kvm_for_each_memslot(memslot, bkt, slots) \ hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ if (WARN_ON_ONCE(!memslot->npages)) { \ } else static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { struct kvm_memory_slot *slot; int idx = slots->node_idx; hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { if (slot->id == id) return slot; } return NULL; } /* Iterator used for walking memslots that overlap a gfn range. */ struct kvm_memslot_iter { struct kvm_memslots *slots; struct rb_node *node; struct kvm_memory_slot *slot; }; static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) { iter->node = rb_next(iter->node); if (!iter->node) return; iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, struct kvm_memslots *slots, gfn_t start) { int idx = slots->node_idx; struct rb_node *tmp; struct kvm_memory_slot *slot; iter->slots = slots; /* * Find the so called "upper bound" of a key - the first node that has * its key strictly greater than the searched one (the start gfn in our case). */ iter->node = NULL; for (tmp = slots->gfn_tree.rb_node; tmp; ) { slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); if (start < slot->base_gfn) { iter->node = tmp; tmp = tmp->rb_left; } else { tmp = tmp->rb_right; } } /* * Find the slot with the lowest gfn that can possibly intersect with * the range, so we'll ideally have slot start <= range start */ if (iter->node) { /* * A NULL previous node means that the very first slot * already has a higher start gfn. * In this case slot start > range start. */ tmp = rb_prev(iter->node); if (tmp) iter->node = tmp; } else { /* a NULL node below means no slots */ iter->node = rb_last(&slots->gfn_tree); } if (iter->node) { iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); /* * It is possible in the slot start < range start case that the * found slot ends before or at range start (slot end <= range start) * and so it does not overlap the requested range. * * In such non-overlapping case the next slot (if it exists) will * already have slot start > range start, otherwise the logic above * would have found it instead of the current slot. */ if (iter->slot->base_gfn + iter->slot->npages <= start) kvm_memslot_iter_next(iter); } } static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) { if (!iter->node) return false; /* * If this slot starts beyond or at the end of the range so does * every next one */ return iter->slot->base_gfn < end; } /* Iterate over each memslot at least partially intersecting [start, end) range */ #define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ for (kvm_memslot_iter_start(iter, slots, start); \ kvm_memslot_iter_is_valid(iter, end); \ kvm_memslot_iter_next(iter)) struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot * - delete an existing memory slot * - modify an existing memory slot * -- move it in the guest physical memory space * -- just change its flags * * Since flags can be changed by some of these operations, the following * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, KVM_MR_DELETE, KVM_MR_MOVE, KVM_MR_FLAGS_ONLY, }; int kvm_set_internal_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages); struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { return __gfn_to_page(kvm, gfn, true); } unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); static inline void kvm_release_page_unused(struct page *page) { if (!page) return; put_page(page); } void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, bool unused, bool dirty) { lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); if (!page) return; /* * If the page that KVM got from the *primary MMU* is writable, and KVM * installed or reused a SPTE, mark the page/folio dirty. Note, this * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if * the GFN is write-protected. Folios can't be safely marked dirty * outside of mmu_lock as doing so could race with writeback on the * folio. As a result, KVM can't mark folios dirty in the fast page * fault handler, and so KVM must (somewhat) speculatively mark the * folio dirty if KVM could locklessly make the SPTE writable. */ if (unused) kvm_release_page_unused(page); else if (dirty) kvm_release_page_dirty(page); else kvm_release_page_clean(page); } kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, unsigned int foll, bool *writable, struct page **refcounted_page); static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool write, bool *writable, struct page **refcounted_page) { return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, write ? FOLL_WRITE : 0, writable, refcounted_page); } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); #define __kvm_get_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = get_user(v, __uaddr); \ __ret; \ }) #define kvm_get_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) #define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) #define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, bool writable); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, true); } static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, false); } unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len); int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** * kvm_gpc_init - initialize gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest * physical address. * * @gpc: struct gfn_to_pfn_cache object. * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for * invalidations to be processed. Callers are required to use kvm_gpc_check() * to ensure that the cache is valid before accessing the target page. */ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); /** * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. * * @gpc: struct gfn_to_pfn_cache object. * @hva: userspace virtual address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * The semantics of this function are the same as those of kvm_gpc_activate(). It * merely bypasses a layer of address translation. */ int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); /** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. * * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock * while calling this function, and then continue to hold the lock until the * access is complete. * * Callers in IN_GUEST_MODE may do so without locking, although they should * still hold a read lock on kvm->scru for the memslot checks. */ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_refresh - update a previously initialized cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful * return from this function does not mean the page can be immediately * accessed because it may have raced with an invalidation. Callers must * still lock and check the cache status, as this function does not return * with the lock still held to permit access. */ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * * This removes a cache from the VM's list to be processed on MMU notifier * invocation. */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && !kvm_is_error_gpa(gpc->gpa); } static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && kvm_is_error_gpa(gpc->gpa); } void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); void kvm_vcpu_halt(struct kvm_vcpu *vcpu); bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif void kvm_mmu_invalidate_begin(struct kvm *kvm); void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); void kvm_mmu_invalidate_end(struct kvm *kvm); bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot); #endif int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #endif #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #else static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING /* * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of * kvm_usage_count, i.e. at the beginning of the generic hardware enabling * sequence, and at the end of the generic hardware disabling sequence. */ void kvm_arch_enable_virtualization(void); void kvm_arch_disable_virtualization(void); /* * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to * do the actual twiddling of hardware bits. The hooks are called on all * online CPUs when KVM enables/disabled virtualization, and on a single CPU * when that CPU is onlined/offlined (including for Resume/Suspend). */ int kvm_arch_enable_virtualization_cpu(void); void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* * All architectures that want to use vzalloc currently also * need their own kvm_arch_alloc_vm implementation. */ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } #endif static inline void __kvm_arch_free_vm(struct kvm *kvm) { kvfree(kvm); } #ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { __kvm_arch_free_vm(kvm); } #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { return -ENOTSUPP; } #else int kvm_arch_flush_remote_tlbs(struct kvm *kvm); #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { return -EOPNOTSUPP; } #else int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); #endif #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA void kvm_arch_register_noncoherent_dma(struct kvm *kvm); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm); #else static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { } static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { } static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return false; } #endif #ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE void kvm_arch_start_assignment(struct kvm *kvm); void kvm_arch_end_assignment(struct kvm *kvm); bool kvm_arch_has_assigned_device(struct kvm *kvm); #else static inline void kvm_arch_start_assignment(struct kvm *kvm) { } static inline void kvm_arch_end_assignment(struct kvm *kvm) { } static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } #endif static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP return vcpu->arch.waitp; #else return &vcpu->wait; #endif } /* * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns * true if the vCPU was blocking and was awakened, false otherwise. */ static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); } static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) { return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); } #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and * ready to accept virtual IRQ. On some architectures the virtual interrupt * controller is dynamically instantiated and this is not always true. */ bool kvm_arch_intc_initialized(struct kvm *kvm); #else static inline bool kvm_arch_intc_initialized(struct kvm *kvm) { return true; } #endif #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); void kvm_unregister_perf_callbacks(void); #else static inline void kvm_register_perf_callbacks(void *ign) {} static inline void kvm_unregister_perf_callbacks(void) {} #endif /* CONFIG_GUEST_PERF_EVENTS */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; int kvm_irq_map_gsi(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *entries, int gsi); int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin); int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level, bool line_status); int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_gsi(struct kvm *kvm, int gsi); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { if (!slot) return NULL; if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else return NULL; } /* * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * * With "approx" set returns the memslot also when the address falls * in a hole. In that case one of the memslots bordering the hole is * returned. */ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; struct rb_node *node; int idx = slots->node_idx; slot = NULL; for (node = slots->gfn_tree.rb_node; node; ) { slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); if (gfn >= slot->base_gfn) { if (gfn < slot->base_gfn + slot->npages) return slot; node = node->rb_right; } else node = node->rb_left; } return approx ? slot : NULL; } static inline struct kvm_memory_slot * ____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); slot = try_get_memslot(slot, gfn); if (slot) return slot; slot = search_memslots(slots, gfn, approx); if (slot) { atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } /* * __gfn_to_memslot() and its descendants are here to allow arch code to inline * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline * because that would bloat other code too much. */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { return ____gfn_to_memslot(slots, gfn, false); } static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { /* * The index was checked originally in search_memslots. To avoid * that a malicious guest builds a Spectre gadget out of e.g. page * table walks, do not let the processor speculate loads outside * the guest's registered memslots. */ unsigned long offset = gfn - slot->base_gfn; offset = array_index_nospec(offset, slot->npages); return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) { return gfn_to_memslot(kvm, gfn)->id; } static inline gfn_t hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot) { gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT; return slot->base_gfn + gfn_offset; } static inline gpa_t gfn_to_gpa(gfn_t gfn) { return (gpa_t)gfn << PAGE_SHIFT; } static inline gfn_t gpa_to_gfn(gpa_t gpa) { return (gfn_t)(gpa >> PAGE_SHIFT); } static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); return !kvm_is_error_hva(hva); } static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) { lockdep_assert_held(&gpc->lock); if (!gpc->memslot) return; mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); } enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, }; struct kvm_stat_data { struct kvm *kvm; const struct _kvm_stats_desc *desc; enum kvm_stat_kind kind; }; struct _kvm_stats_desc { struct kvm_stats_desc desc; char name[KVM_STATS_NAME_SIZE]; }; #define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ .flags = type | unit | base | \ BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ .exponent = exp, \ .size = sz, \ .bucket_size = bsz #define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, generic.stat) \ }, \ .name = #stat, \ } #define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ }, \ .name = #stat, \ } #define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, stat) \ }, \ .name = #stat, \ } #define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, stat) \ }, \ .name = #stat, \ } /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) #define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ unit, base, exponent, 1, 0) #define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ unit, base, exponent, 1, 0) #define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ unit, base, exponent, 1, 0) #define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ unit, base, exponent, sz, bsz) #define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ unit, base, exponent, sz, 0) /* Cumulative counter, read/write */ #define STATS_DESC_COUNTER(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous counter, read only */ #define STATS_DESC_ICOUNTER(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Peak counter, read/write */ #define STATS_DESC_PCOUNTER(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous boolean value, read only */ #define STATS_DESC_IBOOLEAN(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Peak (sticky) boolean value, read/write */ #define STATS_DESC_PBOOLEAN(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9) /* Linear histogram for time in nanosecond */ #define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz, bsz) /* Logarithmic histogram for time in nanosecond */ #define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz) #define KVM_GENERIC_VM_STATS() \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) #define KVM_GENERIC_VCPU_STATS() \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); /** * kvm_stats_linear_hist_update() - Update bucket value for linear histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the linear histogram's bucket * @bucket_size: the size (width) of a bucket */ static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, u64 value, size_t bucket_size) { size_t index = div64_u64(value, bucket_size); index = min(index, size - 1); ++data[index]; } /** * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the logarithmic histogram's bucket */ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) { size_t index = fls64(value); index = min(index, size - 1); ++data[index]; } #define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) #define KVM_STATS_LOG_HIST_UPDATE(array, value) \ kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value) extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* * Ensure the read of mmu_invalidate_in_progress happens before * the read of mmu_invalidate_seq. This interacts with the * smp_wmb() in mmu_notifier_invalidate_range_end to make sure * that the caller either sees the old (non-zero) value of * mmu_invalidate_in_progress or the new (incremented) value of * mmu_invalidate_seq. * * PowerPC Book3s HV KVM calls this under a per-page lock rather * than under kvm->mmu_lock, for scalability, so can't rely on * kvm->mmu_lock to keep things ordered. */ smp_rmb(); if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { lockdep_assert_held(&kvm->mmu_lock); /* * If mmu_invalidate_in_progress is non-zero, then the range maintained * by kvm_mmu_notifier_invalidate_range_start contains all addresses * that might be being invalidated. Note that it may include some false * positives, due to shortcuts when handing concurrent invalidations. */ if (unlikely(kvm->mmu_invalidate_in_progress)) { /* * Dropping mmu_lock after bumping mmu_invalidate_in_progress * but before updating the range is a KVM bug. */ if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA || kvm->mmu_invalidate_range_end == INVALID_GPA)) return 1; if (gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return 1; } if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } /* * This lockless version of the range-based retry check *must* be paired with a * call to the locked version after acquiring mmu_lock, i.e. this is safe to * use only as a pre-check to avoid contending mmu_lock. This version *will* * get false negatives and false positives. */ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { /* * Use READ_ONCE() to ensure the in-progress flag and sequence counter * are always read from memory, e.g. so that checking for retry in a * loop won't result in an infinite retry loop. Don't force loads for * start+end, as the key to avoiding infinite retry loops is observing * the 1=>0 transition of in-progress, i.e. getting false negatives * due to stale start+end values is acceptable. */ if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return true; return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */ bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); #else static inline void kvm_free_irq_routing(struct kvm *kvm) {} static inline int kvm_init_irq_routing(struct kvm *kvm) { return 0; } #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin) { return false; } #endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's * caller. Paired with the smp_mb__after_atomic in kvm_check_request. */ smp_wmb(); set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Request that don't require vCPU action should never be logged in * vcpu->requests. The vCPU won't clear the request, so it will stay * logged indefinitely and prevent the vCPU from entering the guest. */ BUILD_BUG_ON(!__builtin_constant_p(req) || (req & KVM_REQUEST_NO_ACTION)); __kvm_make_request(req, vcpu); } static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); } static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) { clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { if (kvm_test_request(req, vcpu)) { kvm_clear_request(req, vcpu); /* * Ensure the rest of the request is visible to kvm_check_request's * caller. Paired with the smp_wmb in kvm_make_request. */ smp_mb__after_atomic(); return true; } else { return false; } } #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool kvm_rebooting; #endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; }; /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; /* * create is called holding kvm->lock and any operations not suitable * to do while holding the lock should be deferred to init (see * below). */ int (*create)(struct kvm_device *dev, u32 type); /* * init is called after create if create is successful and is called * outside of holding kvm->lock. */ void (*init)(struct kvm_device *dev); /* * Destroy is responsible for freeing dev. * * Destroy may be called before or after destructors are called * on emulated I/O regions, depending on whether a reference is * held by a vcpu or other kvm component that gets destroyed * after the emulated I/O. */ void (*destroy)(struct kvm_device *dev); /* * Release is an alternative method to free the device. It is * called when the device file descriptor is closed. Once * release is called, the destroy method will not be called * anymore as the device is removed from the device list of * the VM. kvm->lock is held. */ void (*release)(struct kvm_device *dev); int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, unsigned long arg); int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma); }; struct kvm_device *kvm_device_from_filp(struct file *filp); int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; extern struct kvm_device_ops kvm_arm_vgic_v3_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.in_spin_loop = val; } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.dy_eligible = val; } #else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) { return (memslot && memslot->id < KVM_USER_MEM_SLOTS && !(memslot->flags & KVM_MEMSLOT_INVALID)); } struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS /* If we wakeup during the poll time, was it a sucessful poll? */ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return vcpu->valid_wakeup; } #else static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return true; } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ #ifdef CONFIG_HAVE_KVM_NO_POLL /* Callback that tells if we must not poll */ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); #else static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return false; } #endif /* CONFIG_HAVE_KVM_NO_POLL */ #ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); #else static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -ENOIOCTLCMD; } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { return 0; } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { vcpu->run->exit_reason = KVM_EXIT_INTR; vcpu->stat.signal_exits++; } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ /* * If more than one page is being (un)accounted, @virt must be the address of * the first page of a block of pages what were allocated together (i.e * accounted together). * * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() * is thread-safe. */ static inline void kvm_account_pgtable_pages(void *virt, int nr) { mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); } /* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This * value can be tuned to higher if e.g. PML is enabled on the host. */ #define KVM_DIRTY_RING_RSVD_ENTRIES 64 /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES 65536 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t size, bool is_write, bool is_exec, bool is_private) { vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; vcpu->run->memory_fault.gpa = gpa; vcpu->run->memory_fault.size = size; /* RWX flags are not (yet) defined or communicated to userspace. */ vcpu->run->memory_fault.flags = 0; if (is_private) vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) { return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) && kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; } #else static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ #ifdef CONFIG_KVM_PRIVATE_MEM int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order); #else static inline int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order) { KVM_BUG_ON(1, kvm); return -EIO; } #endif /* CONFIG_KVM_PRIVATE_MEM */ #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); #endif #ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM /** * kvm_gmem_populate() - Populate/prepare a GPA range with guest data * * @kvm: KVM instance * @gfn: starting GFN to be populated * @src: userspace-provided buffer containing data to copy into GFN range * (passed to @post_populate, and incremented on each iteration * if not NULL) * @npages: number of pages to copy from userspace-buffer * @post_populate: callback to issue for each gmem page that backs the GPA * range * @opaque: opaque data to pass to @post_populate callback * * This is primarily intended for cases where a gmem-backed GPA range needs * to be initialized with userspace-provided data prior to being mapped into * the guest as a private page. This should be called with the slots->lock * held so that caller-enforced invariants regarding the expected memory * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. * * Returns the number of pages that were populated. */ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, void __user *src, int order, void *opaque); long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); #endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range); #endif #endif |
| 26 26 26 51 22 46 51 40 15 20 20 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth or update dirty limit at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; bool freerun; bool dirty_exceeded; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; if (rt_or_dl_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ if (thresh > UINT_MAX) thresh = UINT_MAX; /* This makes sure bg_thresh is within 32-bits as well */ if (bg_thresh >= thresh) bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_or_dl_task(tsk)) dirty += dirty / 4; /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ return min_t(unsigned long, dirty, UINT_MAX); } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > UINT_MAX) { dirty_background_bytes = old_bytes; return -ERANGE; } dirty_background_ratio = 0; } return ret; } static int dirty_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } static int dirty_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { vm_dirty_bytes = old_bytes; return -ERANGE; } writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other wb_domain_writeout_add calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); if (!dirty_thresh) return -EINVAL; ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); if (min_ratio < 0) return min_ratio; return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); if (max_ratio < 0) return max_ratio; return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } static inline bool dtc_is_global(struct dirty_throttle_control *dtc) { return mdtc_gdtc(dtc) == NULL; } /* * Dirty background will ignore pages being written as we're trying to * decide whether to put more under writeback. */ static void domain_dirty_avail(struct dirty_throttle_control *dtc, bool include_writeback) { if (dtc_is_global(dtc)) { dtc->avail = global_dirtyable_memory(); dtc->dirty = global_node_page_state(NR_FILE_DIRTY); if (include_writeback) dtc->dirty += global_node_page_state(NR_WRITEBACK); } else { unsigned long filepages = 0, headroom = 0, writeback = 0; mem_cgroup_wb_stats(dtc->wb, &filepages, &headroom, &dtc->dirty, &writeback); if (include_writeback) dtc->dirty += writeback; mdtc_calc_avail(dtc, filepages, headroom); } } /** * __wb_calc_thresh - @wb's share of dirty threshold * @dtc: dirty_throttle_context of interest * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc * * Note that balance_dirty_pages() will only seriously take dirty throttling * threshold as a hard limit when sleeping max_pause per page is not enough * to keep the dirty pages under control. For example, when the device is * completely stalled due to some error conditions, or when there are 1000 * dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. For dirty throttling limit, the term * "dirty" in the context of dirty balancing includes all PG_dirty and * PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); struct bdi_writeback *wb = dtc->wb; u64 wb_thresh; u64 wb_max_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this wb's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ if (thresh > dtc->dirty) { if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100); else wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8); } wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); if (wb_thresh > wb_max_thresh) wb_thresh = wb_max_thresh; return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; domain_dirty_avail(&gdtc, true); return __wb_calc_thresh(&gdtc, thresh); } unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; domain_dirty_avail(&gdtc, true); domain_dirty_avail(&mdtc, true); domain_dirty_limits(&mdtc); return __wb_calc_thresh(&mdtc, mdtc.thresh); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } static unsigned long domain_poll_intv(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh; if (strictlimit) { dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; } return dirty_poll_interval(dirty, thresh); } /* * Throttle it only when the background writeback cannot catch-up. This avoids * (excessively) small writeouts when the wb limits are ramping up in case of * !strictlimit. * * In strictlimit case make decision based on the wb counters and limits. Small * writeouts when the wb limits are ramping up are the price we consciously pay * for strictlimit-ing. */ static void domain_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh, bg_thresh; if (unlikely(strictlimit)) { wb_dirty_limits(dtc); dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; bg_thresh = dtc->wb_bg_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; bg_thresh = dtc->bg_thresh; } dtc->freerun = dirty <= dirty_freerun_ceiling(thresh, bg_thresh); } static void balance_domain_limits(struct dirty_throttle_control *dtc, bool strictlimit) { domain_dirty_avail(dtc, true); domain_dirty_limits(dtc); domain_dirty_freerun(dtc, strictlimit); } static void wb_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->freerun = false; /* was already handled in domain_dirty_freerun */ if (strictlimit) return; wb_dirty_limits(dtc); /* * LOCAL_THROTTLE tasks must not be throttled when below the per-wb * freerun ceiling. */ if (!(current->flags & PF_LOCAL_THROTTLE)) return; dtc->freerun = dtc->wb_dirty < dirty_freerun_ceiling(dtc->wb_thresh, dtc->wb_bg_thresh); } static inline void wb_dirty_exceeded(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->dirty_exceeded = (dtc->wb_dirty > dtc->wb_thresh) && ((dtc->dirty > dtc->thresh) || strictlimit); } /* * The limits fields dirty_exceeded and pos_ratio won't be updated if wb is * in freerun state. Please don't use these invalid fields in freerun case. */ static void balance_wb_limits(struct dirty_throttle_control *dtc, bool strictlimit) { wb_dirty_freerun(dtc, strictlimit); if (dtc->freerun) return; wb_dirty_exceeded(dtc, strictlimit); wb_position_ratio(dtc); } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_dirty; long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; nr_dirty = global_node_page_state(NR_FILE_DIRTY); balance_domain_limits(gdtc, strictlimit); if (mdtc) { /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ balance_domain_limits(mdtc, strictlimit); } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (gdtc->freerun && (!mdtc || mdtc->freerun)) { unsigned long intv; unsigned long m_intv; free_running: intv = domain_poll_intv(gdtc, strictlimit); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = domain_poll_intv(mdtc, strictlimit); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ balance_wb_limits(gdtc, strictlimit); if (gdtc->freerun) goto free_running; sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ balance_wb_limits(mdtc, strictlimit); if (mdtc->freerun) goto free_running; if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } wb->dirty_exceeded = gdtc->dirty_exceeded || (mdtc && mdtc->dirty_exceeded); if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /* * Similar to wb_dirty_limits, wb_bg_dirty_limits also calculates dirty * and thresh, but it's for background writeback. */ static void wb_bg_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; dtc->wb_bg_thresh = __wb_calc_thresh(dtc, dtc->bg_thresh); if (dtc->wb_bg_thresh < 2 * wb_stat_error()) dtc->wb_dirty = wb_stat_sum(wb, WB_RECLAIMABLE); else dtc->wb_dirty = wb_stat(wb, WB_RECLAIMABLE); } static bool domain_over_bg_thresh(struct dirty_throttle_control *dtc) { domain_dirty_avail(dtc, false); domain_dirty_limits(dtc); if (dtc->dirty > dtc->bg_thresh) return true; wb_bg_dirty_limits(dtc); if (dtc->wb_dirty > dtc->wb_bg_thresh) return true; return false; } /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; if (domain_over_bg_thresh(&gdtc)) return true; if (mdtc_valid(&mdtc)) return domain_over_bg_thresh(&mdtc); return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static const struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by writeback * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The caller * can then use the TOWRITE tag to identify pages eligible for writeback. * This mechanism is used to avoid livelocking of writeback by a process * steadily creating new dirty pages in the file (thus it is important for this * function to be quick so that it can tag pages faster than a dirtying process * can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); static bool folio_prepare_writeback(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio) { /* * Folio truncated or invalidated. We can freely skip it then, * even for data integrity operations: the folio has disappeared * concurrently, so there could be no real expectation of this * data integrity operation even if there is now a new, dirty * folio at the same pagecache index. */ if (unlikely(folio->mapping != mapping)) return false; /* * Did somebody else write it for us? */ if (!folio_test_dirty(folio)) return false; if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) return false; folio_wait_writeback(folio); } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) return false; return true; } static xa_mark_t wbc_to_tag(struct writeback_control *wbc) { if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) return PAGECACHE_TAG_TOWRITE; return PAGECACHE_TAG_DIRTY; } static pgoff_t wbc_end(struct writeback_control *wbc) { if (wbc->range_cyclic) return -1; return wbc->range_end >> PAGE_SHIFT; } static struct folio *writeback_get_folio(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio; retry: folio = folio_batch_next(&wbc->fbatch); if (!folio) { folio_batch_release(&wbc->fbatch); cond_resched(); filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc), wbc_to_tag(wbc), &wbc->fbatch); folio = folio_batch_next(&wbc->fbatch); if (!folio) return NULL; } folio_lock(folio); if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) { folio_unlock(folio); goto retry; } trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); return folio; } /** * writeback_iter - iterate folio of a mapping for writeback * @mapping: address space structure to write * @wbc: writeback context * @folio: previously iterated folio (%NULL to start) * @error: in-out pointer for writeback errors (see below) * * This function returns the next folio for the writeback operation described by * @wbc on @mapping and should be called in a while loop in the ->writepages * implementation. * * To start the writeback operation, %NULL is passed in the @folio argument, and * for every subsequent iteration the folio returned previously should be passed * back in. * * If there was an error in the per-folio writeback inside the writeback_iter() * loop, @error should be set to the error value. * * Once the writeback described in @wbc has finished, this function will return * %NULL and if there was an error in any iteration restore it to @error. * * Note: callers should not manually break out of the loop using break or goto * but must keep calling writeback_iter() until it returns %NULL. * * Return: the folio to write or %NULL if the loop is done. */ struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error) { if (!folio) { folio_batch_init(&wbc->fbatch); wbc->saved_err = *error = 0; /* * For range cyclic writeback we remember where we stopped so * that we can continue where we stopped. * * For non-cyclic writeback we always start at the beginning of * the passed in range. */ if (wbc->range_cyclic) wbc->index = mapping->writeback_index; else wbc->index = wbc->range_start >> PAGE_SHIFT; /* * To avoid livelocks when other processes dirty new pages, we * first tag pages which should be written back and only then * start writing them. * * For data-integrity writeback we have to be careful so that we * do not miss some pages (e.g., because some other process has * cleared the TOWRITE tag we set). The rule we follow is that * TOWRITE tag can be cleared only by the process clearing the * DIRTY tag (and submitting the page for I/O). */ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, wbc->index, wbc_end(wbc)); } else { wbc->nr_to_write -= folio_nr_pages(folio); WARN_ON_ONCE(*error > 0); /* * For integrity writeback we have to keep going until we have * written all the folios we tagged for writeback above, even if * we run past wbc->nr_to_write or encounter errors. * We stash away the first error we encounter in wbc->saved_err * so that it can be retrieved when we're done. This is because * the file system may still have state to clear for each folio. * * For background writeback we exit as soon as we run past * wbc->nr_to_write or encounter the first error. */ if (wbc->sync_mode == WB_SYNC_ALL) { if (*error && !wbc->saved_err) wbc->saved_err = *error; } else { if (*error || wbc->nr_to_write <= 0) goto done; } } folio = writeback_get_folio(mapping, wbc); if (!folio) { /* * To avoid deadlocks between range_cyclic writeback and callers * that hold pages in PageWriteback to aggregate I/O until * the writeback iteration finishes, we do not loop back to the * start of the file. Doing so causes a page lock/page * writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping * back to the start of the file violates that rule and causes * deadlocks. */ if (wbc->range_cyclic) mapping->writeback_index = 0; /* * Return the first error we encountered (if there was any) to * the caller. */ *error = wbc->saved_err; } return folio; done: if (wbc->range_cyclic) mapping->writeback_index = folio_next_index(folio); folio_batch_release(&wbc->fbatch); return NULL; } EXPORT_SYMBOL_GPL(writeback_iter); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * Return: %0 on success, negative error code otherwise * * Note: please use writeback_iter() instead. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct folio *folio = NULL; int error; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { error = writepage(folio, wbc, data); if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } } return error; } EXPORT_SYMBOL(write_cache_pages); static int writeback_use_writepage(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio = NULL; struct blk_plug plug; int err; blk_start_plug(&plug); while ((folio = writeback_iter(mapping, wbc, folio, &err))) { err = mapping->a_ops->writepage(&folio->page, wbc); if (err == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); err = 0; } mapping_set_error(mapping, err); } blk_finish_plug(&plug); return err; } int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); } else if (mapping->a_ops->writepage) { ret = writeback_use_writepage(mapping, wbc); } else { /* deal with chardevs and other special files */ ret = 0; } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * It is the caller's responsibility to prevent the folio from being truncated * while this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). * When called from mark_buffer_dirty(), the filesystem should hold a * reference to the buffer_head that is being marked dirty, which causes * try_to_free_buffers() to fail. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { if (folio_test_set_dirty(folio)) return false; __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * folio_mark_dirty() is racy if the caller has no reference against * folio->mapping->host, and if the folio is unlocked. This is because another * CPU could truncate the folio off the mapping and then free the mapping. * * Usually, the folio _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the folio should be locked before running folio_mark_dirty(). */ bool folio_mark_dirty_lock(struct folio *folio) { bool ret; folio_lock(folio); ret = folio_mark_dirty(folio); folio_unlock(folio); return ret; } EXPORT_SYMBOL(folio_mark_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 31 31 31 31 31 31 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/drivers/char/serial_core.h * * Copyright (C) 2000 Deep Blue Solutions Ltd. */ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> #include <linux/lockdep.h> #include <linux/printk.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/sysrq.h> #include <uapi/linux/serial_core.h> #ifdef CONFIG_SERIAL_CORE_CONSOLE #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else #define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; struct serial_struct; struct serial_port_device; struct device; struct gpio_desc; /** * struct uart_ops -- interface between serial_core and the driver * * This structure describes all the operations that can be done on the * physical hardware. * * @tx_empty: ``unsigned int ()(struct uart_port *port)`` * * This function tests whether the transmitter fifo and shifter for the * @port is empty. If it is empty, this function should return * %TIOCSER_TEMT, otherwise return 0. If the port does not support this * operation, then it should return %TIOCSER_TEMT. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @set_mctrl: ``void ()(struct uart_port *port, unsigned int mctrl)`` * * This function sets the modem control lines for @port to the state * described by @mctrl. The relevant bits of @mctrl are: * * - %TIOCM_RTS RTS signal. * - %TIOCM_DTR DTR signal. * - %TIOCM_OUT1 OUT1 signal. * - %TIOCM_OUT2 OUT2 signal. * - %TIOCM_LOOP Set the port into loopback mode. * * If the appropriate bit is set, the signal should be driven * active. If the bit is clear, the signal should be driven * inactive. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @get_mctrl: ``unsigned int ()(struct uart_port *port)`` * * Returns the current state of modem control inputs of @port. The state * of the outputs should not be returned, since the core keeps track of * their state. The state information should include: * * - %TIOCM_CAR state of DCD signal * - %TIOCM_CTS state of CTS signal * - %TIOCM_DSR state of DSR signal * - %TIOCM_RI state of RI signal * * The bit is set if the signal is currently driven active. If * the port does not support CTS, DCD or DSR, the driver should * indicate that the signal is permanently active. If RI is * not available, the signal should not be indicated as active. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_tx: ``void ()(struct uart_port *port)`` * * Stop transmitting characters. This might be due to the CTS line * becoming inactive or the tty layer indicating we want to stop * transmission due to an %XOFF character. * * The driver should stop transmitting characters as soon as possible. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @start_tx: ``void ()(struct uart_port *port)`` * * Start transmitting characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @throttle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that input buffers for the line discipline are * close to full, and it should somehow signal that no more characters * should be sent to the serial port. * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @unthrottle() and termios modification by the * tty layer. * * @unthrottle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that characters can now be sent to the serial * port without fear of overrunning the input buffers of the line * disciplines. * * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @throttle() and termios modification by the * tty layer. * * @send_xchar: ``void ()(struct uart_port *port, char ch)`` * * Transmit a high priority character, even if the port is stopped. This * is used to implement XON/XOFF flow control and tcflow(). If the serial * driver does not implement this function, the tty core will append the * character to the circular buffer and then call start_tx() / stop_tx() * to flush the data out. * * Do not transmit if @ch == '\0' (%__DISABLED_CHAR). * * Locking: none. * Interrupts: caller dependent. * * @start_rx: ``void ()(struct uart_port *port)`` * * Start receiving characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_rx: ``void ()(struct uart_port *port)`` * * Stop receiving characters; the @port is in the process of being closed. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @enable_ms: ``void ()(struct uart_port *port)`` * * Enable the modem status interrupts. * * This method may be called multiple times. Modem status interrupts * should be disabled when the @shutdown() method is called. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @break_ctl: ``void ()(struct uart_port *port, int ctl)`` * * Control the transmission of a break signal. If @ctl is nonzero, the * break signal should be transmitted. The signal should be terminated * when another call is made with a zero @ctl. * * Locking: caller holds tty_port->mutex * * @startup: ``int ()(struct uart_port *port)`` * * Grab any interrupt resources and initialise any low level driver state. * Enable the port for reception. It should not activate RTS nor DTR; * this will be done via a separate call to @set_mctrl(). * * This method will only be called when the port is initially opened. * * Locking: port_sem taken. * Interrupts: globally disabled. * * @shutdown: ``void ()(struct uart_port *port)`` * * Disable the @port, disable any break condition that may be in effect, * and free any interrupt resources. It should not disable RTS nor DTR; * this will have already been done via a separate call to @set_mctrl(). * * Drivers must not access @port->state once this call has completed. * * This method will only be called when there are no more users of this * @port. * * Locking: port_sem taken. * Interrupts: caller dependent. * * @flush_buffer: ``void ()(struct uart_port *port)`` * * Flush any write buffers, reset any DMA state and stop any ongoing DMA * transfers. * * This will be called whenever the @port->state->xmit circular buffer is * cleared. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @set_termios: ``void ()(struct uart_port *port, struct ktermios *new, * struct ktermios *old)`` * * Change the @port parameters, including word length, parity, stop bits. * Update @port->read_status_mask and @port->ignore_status_mask to * indicate the types of events we are interested in receiving. Relevant * ktermios::c_cflag bits are: * * - %CSIZE - word size * - %CSTOPB - 2 stop bits * - %PARENB - parity enable * - %PARODD - odd parity (when %PARENB is in force) * - %ADDRB - address bit (changed through uart_port::rs485_config()). * - %CREAD - enable reception of characters (if not set, still receive * characters from the port, but throw them away). * - %CRTSCTS - if set, enable CTS status change reporting. * - %CLOCAL - if not set, enable modem status change reporting. * * Relevant ktermios::c_iflag bits are: * * - %INPCK - enable frame and parity error events to be passed to the TTY * layer. * - %BRKINT / %PARMRK - both of these enable break events to be passed to * the TTY layer. * - %IGNPAR - ignore parity and framing errors. * - %IGNBRK - ignore break errors. If %IGNPAR is also set, ignore overrun * errors as well. * * The interaction of the ktermios::c_iflag bits is as follows (parity * error given as an example): * * ============ ======= ======= ========================================= * Parity error INPCK IGNPAR * ============ ======= ======= ========================================= * n/a 0 n/a character received, marked as %TTY_NORMAL * None 1 n/a character received, marked as %TTY_NORMAL * Yes 1 0 character received, marked as %TTY_PARITY * Yes 1 1 character discarded * ============ ======= ======= ========================================= * * Other flags may be used (eg, xon/xoff characters) if your hardware * supports hardware "soft" flow control. * * Locking: caller holds tty_port->mutex * Interrupts: caller dependent. * This call must not sleep * * @set_ldisc: ``void ()(struct uart_port *port, struct ktermios *termios)`` * * Notifier for discipline change. See * Documentation/driver-api/tty/tty_ldisc.rst. * * Locking: caller holds tty_port->mutex * * @pm: ``void ()(struct uart_port *port, unsigned int state, * unsigned int oldstate)`` * * Perform any power management related activities on the specified @port. * @state indicates the new state (defined by enum uart_pm_state), * @oldstate indicates the previous state. * * This function should not be used to grab any resources. * * This will be called when the @port is initially opened and finally * closed, except when the @port is also the system console. This will * occur even if %CONFIG_PM is not set. * * Locking: none. * Interrupts: caller dependent. * * @type: ``const char *()(struct uart_port *port)`` * * Return a pointer to a string constant describing the specified @port, * or return %NULL, in which case the string 'unknown' is substituted. * * Locking: none. * Interrupts: caller dependent. * * @release_port: ``void ()(struct uart_port *port)`` * * Release any memory and IO region resources currently in use by the * @port. * * Locking: none. * Interrupts: caller dependent. * * @request_port: ``int ()(struct uart_port *port)`` * * Request any memory and IO region resources required by the port. If any * fail, no resources should be registered when this function returns, and * it should return -%EBUSY on failure. * * Locking: none. * Interrupts: caller dependent. * * @config_port: ``void ()(struct uart_port *port, int type)`` * * Perform any autoconfiguration steps required for the @port. @type * contains a bit mask of the required configuration. %UART_CONFIG_TYPE * indicates that the port requires detection and identification. * @port->type should be set to the type found, or %PORT_UNKNOWN if no * port was detected. * * %UART_CONFIG_IRQ indicates autoconfiguration of the interrupt signal, * which should be probed using standard kernel autoprobing techniques. * This is not necessary on platforms where ports have interrupts * internally hard wired (eg, system on a chip implementations). * * Locking: none. * Interrupts: caller dependent. * * @verify_port: ``int ()(struct uart_port *port, * struct serial_struct *serinfo)`` * * Verify the new serial port information contained within @serinfo is * suitable for this port type. * * Locking: none. * Interrupts: caller dependent. * * @ioctl: ``int ()(struct uart_port *port, unsigned int cmd, * unsigned long arg)`` * * Perform any port specific IOCTLs. IOCTL commands must be defined using * the standard numbering system found in <asm/ioctl.h>. * * Locking: none. * Interrupts: caller dependent. * * @poll_init: ``int ()(struct uart_port *port)`` * * Called by kgdb to perform the minimal hardware initialization needed to * support @poll_put_char() and @poll_get_char(). Unlike @startup(), this * should not request interrupts. * * Locking: %tty_mutex and tty_port->mutex taken. * Interrupts: n/a. * * @poll_put_char: ``void ()(struct uart_port *port, unsigned char ch)`` * * Called by kgdb to write a single character @ch directly to the serial * @port. It can and should block until there is space in the TX FIFO. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @poll_get_char: ``int ()(struct uart_port *port)`` * * Called by kgdb to read a single character directly from the serial * port. If data is available, it should be returned; otherwise the * function should return %NO_POLL_CHAR immediately. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int mctrl); unsigned int (*get_mctrl)(struct uart_port *); void (*stop_tx)(struct uart_port *); void (*start_tx)(struct uart_port *); void (*throttle)(struct uart_port *); void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); const char *(*type)(struct uart_port *); void (*release_port)(struct uart_port *); int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); int (*ioctl)(struct uart_port *, unsigned int, unsigned long); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct uart_port *); void (*poll_put_char)(struct uart_port *, unsigned char); int (*poll_get_char)(struct uart_port *); #endif }; #define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) struct uart_icount { __u32 cts; __u32 dsr; __u32 rng; __u32 dcd; __u32 rx; __u32 tx; __u32 frame; __u32 overrun; __u32 parity; __u32 brk; __u32 buf_overrun; }; typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ unsigned long iobase; /* in/out[bwl] */ unsigned char __iomem *membase; /* read/write[bwl] */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); unsigned int (*get_divisor)(struct uart_port *, unsigned int baud, unsigned int *frac); void (*set_divisor)(struct uart_port *, unsigned int baud, unsigned int quot, unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); void (*unthrottle)(struct uart_port *port); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct ktermios *termios, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); unsigned int ctrl_id; /* optional serial core controller id */ unsigned int port_id; /* optional serial core port id */ unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ #define UPIO_UNKNOWN ((unsigned char)~0U) /* UCHAR_MAX */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ #define UPIO_MEM32 (SERIAL_IO_MEM32) /* 32b little endian */ #define UPIO_AU (SERIAL_IO_AU) /* Au1x00 and RT288x type IO */ #define UPIO_TSI (SERIAL_IO_TSI) /* Tsi108/109 type IO */ #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ unsigned char quirks; /* internal quirks */ /* internal quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ /* flags must be updated while holding port mutex */ upf_t flags; /* * These flags must be equivalent to the flags defined in * include/uapi/linux/tty_flags.h which are the userspace definitions * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ #ifdef CONFIG_HAS_IOPORT #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) #else #define UPF_FOURPORT 0 #endif #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) #define UPF_SPD_CUST ((__force upf_t) ASYNC_SPD_CUST /* 0x0030 */ ) #define UPF_SPD_WARP ((__force upf_t) ASYNC_SPD_WARP /* 0x1010 */ ) #define UPF_SPD_MASK ((__force upf_t) ASYNC_SPD_MASK /* 0x1030 */ ) #define UPF_SKIP_TEST ((__force upf_t) ASYNC_SKIP_TEST /* 6 */ ) #define UPF_AUTO_IRQ ((__force upf_t) ASYNC_AUTO_IRQ /* 7 */ ) #define UPF_HARDPPS_CD ((__force upf_t) ASYNC_HARDPPS_CD /* 11 */ ) #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) BIT_ULL(19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) BIT_ULL(20)) #define UPF_AUTO_RTS ((__force upf_t) BIT_ULL(21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) BIT_ULL(22)) #define UPF_CONS_FLOW ((__force upf_t) BIT_ULL(23)) #define UPF_SHARE_IRQ ((__force upf_t) BIT_ULL(24)) #define UPF_EXAR_EFR ((__force upf_t) BIT_ULL(25)) #define UPF_BUG_THRE ((__force upf_t) BIT_ULL(26)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) BIT_ULL(27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) BIT_ULL(28)) #define UPF_FIXED_PORT ((__force upf_t) BIT_ULL(29)) #define UPF_DEAD ((__force upf_t) BIT_ULL(30)) #define UPF_IOREMAP ((__force upf_t) BIT_ULL(31)) #define UPF_FULL_PROBE ((__force upf_t) BIT_ULL(32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) #define UPF_USR_MASK ((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY)) #if __UPF_CHANGE_MASK > ASYNC_FLAGS #error Change mask not equivalent to userspace-visible bit defines #endif /* * Must hold termios_rwsem, port mutex and port lock to change; * can hold any one lock to read. */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; unsigned int line; /* port index */ unsigned int minor; resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* serial port physical parent device */ struct serial_port_device *port_dev; /* serial core port device */ unsigned long sysrq; /* sysrq timeout */ u8 sysrq_ch; /* char for sysrq */ unsigned char has_sysrq; unsigned char sysrq_seq; /* index in sysrq_toggle_seq */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct gpio_desc *rs485_rx_during_tx_gpio; /* Output GPIO that sets the state of RS485 RX during TX */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; /* * Only for console->device_lock()/_unlock() callbacks and internal * port lock wrapper synchronization. */ static inline void __uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); } /* * Only for console->device_lock()/_unlock() callbacks and internal * port lock wrapper synchronization. */ static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { spin_unlock_irqrestore(&up->lock, flags); } /** * uart_port_set_cons - Safely set the @cons field for a uart * @up: The uart port to set * @con: The new console to set to * * This function must be used to set @up->cons. It uses the port lock to * synchronize with the port lock wrappers in order to ensure that the console * cannot change or disappear while another context is holding the port lock. */ static inline void uart_port_set_cons(struct uart_port *up, struct console *con) { unsigned long flags; __uart_port_lock_irqsave(up, &flags); up->cons = con; __uart_port_unlock_irqrestore(up, flags); } /* Only for internal port lock wrapper usage. */ static inline bool __uart_port_using_nbcon(struct uart_port *up) { lockdep_assert_held_once(&up->lock); if (likely(!uart_console(up))) return false; /* * @up->cons is only modified under the port lock. Therefore it is * certain that it cannot disappear here. * * @up->cons->node is added/removed from the console list under the * port lock. Therefore it is certain that the registration status * cannot change here, thus @up->cons->flags can be read directly. */ if (hlist_unhashed_lockless(&up->cons->node) || !(up->cons->flags & CON_NBCON) || !up->cons->write_atomic) { return false; } return true; } /* Only for internal port lock wrapper usage. */ static inline bool __uart_port_nbcon_try_acquire(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return true; return nbcon_device_try_acquire(up->cons); } /* Only for internal port lock wrapper usage. */ static inline void __uart_port_nbcon_acquire(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return; while (!nbcon_device_try_acquire(up->cons)) cpu_relax(); } /* Only for internal port lock wrapper usage. */ static inline void __uart_port_nbcon_release(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return; nbcon_device_release(up->cons); } /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); __uart_port_nbcon_acquire(up); } /** * uart_port_lock_irq - Lock the UART port and disable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); __uart_port_nbcon_acquire(up); } /** * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage */ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); __uart_port_nbcon_acquire(up); } /** * uart_port_trylock - Try to lock the UART port * @up: Pointer to UART port structure * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock(struct uart_port *up) { if (!spin_trylock(&up->lock)) return false; if (!__uart_port_nbcon_try_acquire(up)) { spin_unlock(&up->lock); return false; } return true; } /** * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { if (!spin_trylock_irqsave(&up->lock, *flags)) return false; if (!__uart_port_nbcon_try_acquire(up)) { spin_unlock_irqrestore(&up->lock, *flags); return false; } return true; } /** * uart_port_unlock - Unlock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_unlock(struct uart_port *up) { __uart_port_nbcon_release(up); spin_unlock(&up->lock); } /** * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_unlock_irq(struct uart_port *up) { __uart_port_nbcon_release(up); spin_unlock_irq(&up->lock); } /** * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts * @up: Pointer to UART port structure * @flags: The saved interrupt flags for restore */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { __uart_port_nbcon_release(up); spin_unlock_irqrestore(&up->lock, flags); } static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); } static inline void serial_port_out(struct uart_port *up, int offset, int value) { up->serial_out(up, offset, value); } /** * enum uart_pm_state - power states for UARTs * @UART_PM_STATE_ON: UART is powered, up and operational * @UART_PM_STATE_OFF: UART is powered off * @UART_PM_STATE_UNDEFINED: sentinel */ enum uart_pm_state { UART_PM_STATE_ON = 0, UART_PM_STATE_OFF = 3, /* number taken from ACPI */ UART_PM_STATE_UNDEFINED, }; /* * This is the state information which is persistent across opens. */ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; atomic_t refcount; wait_queue_head_t remove_wait; struct uart_port *uart_port; }; #define UART_XMIT_SIZE PAGE_SIZE /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 /** * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars * @up: uart_port structure describing the port * @chars: number of characters sent * * This function advances the tail of circular xmit buffer by the number of * @chars transmitted and handles accounting of transmitted bytes (into * @up's icount.tx). */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { struct tty_port *tport = &up->state->port; kfifo_skip_count(&tport->xmit_fifo, chars); up->icount.tx += chars; } static inline unsigned int uart_fifo_out(struct uart_port *up, unsigned char *buf, unsigned int chars) { struct tty_port *tport = &up->state->port; chars = kfifo_out(&tport->xmit_fifo, buf, chars); up->icount.tx += chars; return chars; } static inline unsigned int uart_fifo_get(struct uart_port *up, unsigned char *ch) { struct tty_port *tport = &up->state->port; unsigned int chars; chars = kfifo_get(&tport->xmit_fifo, ch); up->icount.tx += chars; return chars; } struct module; struct tty_driver; struct uart_driver { struct module *owner; const char *driver_name; const char *dev_name; int major; int minor; int nr; struct console *cons; /* * these are private; the low level driver should not * touch these; they should be initialised to NULL */ struct uart_state *state; struct tty_driver *tty_driver; }; void uart_write_wakeup(struct uart_port *port); /** * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() * * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer */ enum UART_TX_FLAGS { UART_TX_NOSTOP = BIT(0), }; #define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ if (__port->x_char) { \ (ch) = __port->x_char; \ (put_char); \ __port->x_char = 0; \ continue; \ } \ \ if (uart_tx_stopped(__port)) \ break; \ \ if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ (put_char); \ } \ \ (tx_done); \ \ pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ pending; \ }) /** * uart_port_tx_limited -- transmit helper for uart_port with count limiting * @port: uart port * @ch: variable to store a character to be written to the HW * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * This helper transmits characters from the xmit buffer to the hardware using * @put_char(). It does so until @count characters are sent and while @tx_ready * evaluates to true. * * Returns: the number of characters in the xmit buffer when done. * * The expression in macro parameters shall be designed as follows: * * **tx_ready:** should evaluate to true if the HW can accept more data to * be sent. This parameter can be %true, which means the HW is always ready. * * **put_char:** shall write @ch to the device of @port. * * **tx_done:** when the write loop is done, this can perform arbitrary * action before potential invocation of ops->stop_tx() happens. If the * driver does not need to do anything, use e.g. ({}). * * For all of them, @port->lock is held, interrupts are locally disabled and * the expressions must not sleep. */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) /** * uart_port_tx_flags -- transmit helper for uart_port with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); /* * Calculates FIFO drain time. */ static inline unsigned long uart_fifo_timeout(struct uart_port *port) { u64 fifo_timeout = (u64)READ_ONCE(port->frame_time) * port->fifosize; /* Add .02 seconds of slop */ fifo_timeout += 20 * NSEC_PER_MSEC; return max(nsecs_to_jiffies(fifo_timeout), 1UL); } /* Base timer interval for polling */ static inline unsigned long uart_poll_timeout(struct uart_port *port) { unsigned long timeout = uart_fifo_timeout(port); return timeout > 6 ? (timeout / 2 - 2) : 1; } /* * Console helpers. */ struct earlycon_device { struct console *con; struct uart_port port; char options[32]; /* e.g., 115200n8 */ unsigned int baud; }; struct earlycon_id { char name[15]; char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); }; extern const struct earlycon_id __earlycon_table[]; extern const struct earlycon_id __earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used #else #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif #define OF_EARLYCON_DECLARE(_name, compat, fn) \ static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ EARLYCON_USED_OR_UNUSED __section("__earlycon_table") \ __aligned(__alignof__(struct earlycon_id)) \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn } #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif /* Variant of uart_console_registered() when the console_list_lock is held. */ static inline bool uart_console_registered_locked(struct uart_port *port) { return uart_console(port) && console_is_registered_locked(port->cons); } static inline bool uart_console_registered(struct uart_port *port) { return uart_console(port) && console_is_registered(port->cons); } struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options); void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow); int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_read_port_properties(struct uart_port *port); int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); /* * Power Management */ int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; if ((tty && tty->flow.stopped) || port->hw_stopped) return 1; return 0; } static inline bool uart_cts_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_CTS_ENABLE); } static inline bool uart_softcts_mode(struct uart_port *uport) { upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; return ((uport->status & mask) == UPSTAT_CTS_ENABLE); } /* * The following are helper functions for the low level drivers. */ void uart_handle_dcd_change(struct uart_port *uport, bool active); void uart_handle_cts_change(struct uart_port *uport, bool active); void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag); void uart_xchar_out(struct uart_port *uport, int offset); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch); static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { handle_sysrq(ch); port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { port->sysrq_ch = ch; port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock(port); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock(port); if (sysrq_ch) handle_sysrq(sysrq_ch); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock_irqrestore(port, flags); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock_irqrestore(port, flags); if (sysrq_ch) handle_sysrq(sysrq_ch); } #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { uart_port_unlock(port); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { uart_port_unlock_irqrestore(port, flags); } #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* * We do the SysRQ and SAK checking like this... */ static inline int uart_handle_break(struct uart_port *port) { struct uart_state *state = port->state; if (port->handle_break) port->handle_break(port); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL if (port->has_sysrq && uart_console(port)) { if (!port->sysrq) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return 1; } port->sysrq = 0; } #endif if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; } /* * UART_ENABLE_MS - determine if port should enable modem status irqs */ #define UART_ENABLE_MS(port,cflag) ((port)->flags & UPF_HARDPPS_CD || \ (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ |
| 101 101 18 18 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_INTERNAL_H #define _LINUX_HIGHMEM_INTERNAL_H /* * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft. */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); static inline void kmap_assert_nomap(void) { DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx); } #else static inline void kmap_local_fork(struct task_struct *tsk) { } static inline void kmap_assert_nomap(void) { } #endif #ifdef CONFIG_HIGHMEM #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); void kunmap_high(struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } static inline void kunmap(struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } static inline struct page *kmap_to_page(void *addr) { return __kmap_to_page(addr); } static inline void kmap_flush_unused(void) { __kmap_flush_unused(); } static inline void *kmap_local_page(struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } static inline void *kmap_local_pfn(unsigned long pfn) { return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_page_prot(page, prot); } static inline void *kmap_atomic(struct page *page) { return kmap_atomic_prot(page, kmap_prot); } static inline void *kmap_atomic_pfn(unsigned long pfn) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } unsigned long __nr_free_highpages(void); unsigned long __totalhigh_pages(void); static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || (addr >= __fix_to_virt(FIX_KMAP_END) && addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(struct page *page) { } static inline void kmap_flush_unused(void) { } static inline void kunmap(struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_local_page(struct page *page) { return page_address(page); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { return page_address(&folio->page) + offset; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); } static inline void *kmap_local_pfn(unsigned long pfn) { return kmap_local_page(pfn_to_page(pfn)); } static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } static inline void *kmap_atomic(struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return page_address(page); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { return kmap_atomic(page); } static inline void *kmap_atomic_pfn(unsigned long pfn) { return kmap_atomic(pfn_to_page(pfn)); } static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } static inline unsigned long nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { return false; } #endif /* CONFIG_HIGHMEM */ /** * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! * @__addr: Virtual address to be unmapped * * Unmaps an address previously mapped by kmap_atomic() and re-enables * pagefaults. Depending on PREEMP_RT configuration, re-enables also * migration and preemption. Users should not count on these side effects. * * Mappings should be unmapped in the reverse order that they were mapped. * See kmap_local_page() for details on nesting. * * @__addr can be any address within the mapped page, so there is no need * to subtract any offset that has been added. In contrast to kunmap(), * this function takes the address returned from kmap_atomic(), not the * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_atomic(__addr); \ } while (0) /** * kunmap_local - Unmap a page mapped via kmap_local_page(). * @__addr: An address within the page mapped * * @__addr can be any address within the mapped page. Commonly it is the * address return from kmap_local_page(), but it can also include offsets. * * Unmapping should be done in the reverse order of the mapping. See * kmap_local_page() for details. */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_local(__addr); \ } while (0) #endif |
| 491 491 491 491 25 25 22 491 490 22 24 2 2 2 492 491 22 24 2 2 2 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __ro_after_init; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } static unsigned long enforced_nproc_rlimit(void) { unsigned long limit = RLIM_INFINITY; /* Is RLIMIT_NPROC currently enforced? */ if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || (current_user_ns() != &init_user_ns)) limit = rlimit(RLIMIT_NPROC); return limit; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifying that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = security_create_user_ns(new); if (ret < 0) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; refcount_set(&ns->ns.count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } #if IS_ENABLED(CONFIG_BINFMT_MISC) kfree(ns->binfmt_misc); #endif retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (refcount_dec_and_test(&parent->ns.count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /* * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /* * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /* * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /* * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /* * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /* * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /* * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /* * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup_array(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certain the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also has the appropriate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); if (set_cred_ucounts(cred) < 0) return -EINVAL; return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT); return 0; } subsys_initcall(user_namespaces_init); |
| 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ #include <linux/bitfield.h> #include <linux/bug.h> #include <linux/const.h> #include <linux/limits.h> #define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) #define FORTIFY_REASON_DIR(r) FIELD_GET(BIT(0), r) #define FORTIFY_REASON_FUNC(r) FIELD_GET(GENMASK(7, 1), r) #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) /* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif #ifndef fortify_warn_once # define fortify_warn_once(x...) WARN_ONCE(x) #endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 #define EACH_FORTIFY_FUNC(macro) \ macro(strncpy), \ macro(strnlen), \ macro(strlen), \ macro(strscpy), \ macro(strlcat), \ macro(strcat), \ macro(strncat), \ macro(memset), \ macro(memcpy), \ macro(memmove), \ macro(memscan), \ macro(memcmp), \ macro(memchr), \ macro(memchr_inv), \ macro(kmemdup), \ macro(strcpy), \ macro(UNKNOWN), #define MAKE_FORTIFY_FUNC(func) FORTIFY_FUNC_##func enum fortify_func { EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC) }; void __fortify_report(const u8 reason, const size_t avail, const size_t size); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) __cold __noreturn; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ char *__p = (char *)(p); \ size_t __ret = SIZE_MAX; \ const size_t __p_size = __member_size(p); \ if (__p_size != SIZE_MAX && \ __builtin_constant_p(*__p)) { \ size_t __p_len = __p_size - 1; \ if (__builtin_constant_p(__p[__p_len]) && \ __p[__p_len] == '\0') \ __ret = __builtin_strlen(__p); \ } \ __ret; \ }) #if defined(__SANITIZE_ADDRESS__) #if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); #elif defined(CONFIG_KASAN_GENERIC) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); #else /* CONFIG_KASAN_SW_TAGS */ extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); #endif extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #if defined(__SANITIZE_MEMORY__) /* * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the * corresponding __msan_XXX functions. */ #include <linux/kmsan_string.h> #define __underlying_memcpy __msan_memcpy #define __underlying_memmove __msan_memmove #define __underlying_memset __msan_memset #else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #endif #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif /** * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking * * @dst: Destination memory address to write to * @src: Source memory address to read from * @bytes: How many bytes to write to @dst from @src * @justification: Free-form text or comment describing why the use is needed * * This should be used for corner cases where the compiler cannot do the * right thing, or during transitions between APIs, etc. It should be used * very rarely, and includes a place for justification detailing where bounds * checking has happened, and why existing solutions cannot be employed. */ #define unsafe_memcpy(dst, src, bytes, justification) \ __underlying_memcpy(dst, src, bytes) /* * Clang's use of __builtin_*object_size() within inlines needs hinting via * __pass_*object_size(). The preference is to only ever use type 1 (member * size, rather than struct size), but there remain some stragglers using * type 0 that will be converted in the future. */ #if __has_builtin(__builtin_dynamic_object_size) #define POS __pass_dynamic_object_size(1) #define POS0 __pass_dynamic_object_size(0) #else #define POS __pass_object_size(1) #define POS0 __pass_object_size(0) #endif #define __compiletime_lessthan(bounds, length) ( \ __builtin_constant_p((bounds) < (length)) && \ (bounds) < (length) \ ) /** * strncpy - Copy a string to memory with non-guaranteed NUL padding * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * @size: bytes to write at @p * * If strlen(@q) >= @size, the copy of @q will stop after @size bytes, * and @p will NOT be NUL-terminated * * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes * will be written to @p until @size total bytes have been written. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * over-reads of @q, it cannot defend against writing unterminated * results to @p. Using strncpy() remains ambiguous and fragile. * Instead, please choose an alternative, so that the expectation * of @p's contents is unambiguous: * * +--------------------+--------------------+------------+ * | **p** needs to be: | padded to **size** | not padded | * +====================+====================+============+ * | NUL-terminated | strscpy_pad() | strscpy() | * +--------------------+--------------------+------------+ * | not NUL-terminated | strtomem_pad() | strtomem() | * +--------------------+--------------------+------------+ * * Note strscpy*()'s differing return values for detecting truncation, * and strtomem*()'s expectation that the destination is marked with * __nonstring when it is a character array. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { const size_t p_size = __member_size(p); if (__compiletime_lessthan(p_size, size)) __write_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_strncpy, FORTIFY_WRITE, p_size, size, p); return __underlying_strncpy(p, q, size); } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); /** * strnlen - Return bounded count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * @maxlen: maximum number of characters to count. * * Returns number of characters in @p (NOT including the final NUL), or * @maxlen, if no NUL has been found up to there. * */ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { const size_t p_size = __member_size(p); const size_t p_len = __compiletime_strlen(p); size_t ret; /* We can take compile-time actions when maxlen is const. */ if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) { /* If p is const, we can use its compile-time-known len. */ if (maxlen >= p_size) return p_len; } /* Do not check characters beyond the end of p. */ ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(FORTIFY_FUNC_strnlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* * Defined after fortified strnlen to reuse it. However, it must still be * possible for strlen() to be used on compile-time strings for use in * static initializers (i.e. as a constant expression). */ /** * strlen - Return count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * * Do not use this function unless the string length is known at * compile-time. When @p is unterminated, this function may crash * or return unexpected counts that could lead to memory content * exposures. Prefer strnlen(). * * Returns number of characters in @p (NOT including the final NUL). * */ #define strlen(p) \ __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ __builtin_strlen(p), __fortify_strlen(p)) __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) __kernel_size_t __fortify_strlen(const char * const POS p) { const size_t p_size = __member_size(p); __kernel_size_t ret; /* Give up if we don't know how large p is. */ if (p_size == SIZE_MAX) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(FORTIFY_FUNC_strlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* Defined after fortified strnlen() to reuse it. */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy); __FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size) { /* Use string size rather than possible enclosing struct size. */ const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t len; /* If we cannot get size of p and q default to call strscpy. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strscpy(p, q, size); /* * If size can be known at compile time and is greater than * p_size, generate a compile time write overflow error. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Short-circuit for compile-time known-safe lengths. */ if (__compiletime_lessthan(p_size, SIZE_MAX)) { len = __compiletime_strlen(q); if (len < SIZE_MAX && __compiletime_lessthan(len, size)) { __underlying_memcpy(p, q, len + 1); return len; } } /* * This call protects from read overflow, because len will default to q * length if it smaller than size. */ len = strnlen(q, size); /* * If len equals size, we will copy only size bytes which leads to * -E2BIG being returned. * Otherwise we will copy len + 1 because of the final '\O'. */ len = len == size ? size : len + 1; /* * Generate a runtime write overflow error if len is greater than * p_size. */ if (p_size < len) fortify_panic(FORTIFY_FUNC_strscpy, FORTIFY_WRITE, p_size, len, -E2BIG); /* * We can now safely call vanilla strscpy because we are protected from: * 1. Read overflow thanks to call to strnlen(). * 2. Write overflow thanks to above ifs. */ return __real_strscpy(p, q, len); } /* Defined after fortified strlen() to reuse it. */ extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat); /** * strlcat - Append a string to an existing string * * @p: pointer to %NUL-terminated string to append to * @q: pointer to %NUL-terminated string to append from * @avail: Maximum bytes available in @p * * Appends %NUL-terminated string @q after the %NUL-terminated * string at @p, but will not write beyond @avail bytes total, * potentially truncating the copy from @q. @p will stay * %NUL-terminated only if a %NUL already existed within * the @avail bytes of @p. If so, the resulting number of * bytes copied from @q will be at most "@avail - strlen(@p) - 1". * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf(), seq_buf, or similar. * * Returns total bytes that _would_ have been contained by @p * regardless of truncation, similar to snprintf(). If return * value is >= @avail, the string has been truncated. * */ __FORTIFY_INLINE size_t strlcat(char * const POS p, const char * const POS q, size_t avail) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len; size_t actual, wanted; /* Give up immediately if both buffer sizes are unknown. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strlcat(p, q, avail); p_len = strnlen(p, avail); copy_len = strlen(q); wanted = actual = p_len + copy_len; /* Cannot append any more: report truncation. */ if (avail <= p_len) return wanted; /* Give up if string is already overflowed. */ if (p_size <= p_len) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_READ, p_size, p_len + 1, wanted); if (actual >= avail) { copy_len = avail - p_len - 1; actual = p_len + copy_len; } /* Give up if copy will overflow. */ if (p_size <= actual) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_WRITE, p_size, actual + 1, wanted); __underlying_memcpy(p + p_len, q, copy_len); p[actual] = '\0'; return wanted; } /* Defined after fortified strlcat() to reuse it. */ /** * strcat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to NUL-terminated source string to append from * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the * destination buffer size is known to the compiler. Prefer * building the string with formatting, via scnprintf() or similar. * At the very least, use strncat(). * * Returns @p. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) char *strcat(char * const POS p, const char *q) { const size_t p_size = __member_size(p); const size_t wanted = strlcat(p, q, p_size); if (p_size <= wanted) fortify_panic(FORTIFY_FUNC_strcat, FORTIFY_WRITE, p_size, wanted + 1, p); return p; } /** * strncat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to source string to append from * @count: Maximum bytes to read from @q * * Appends at most @count bytes from @q (stopping at the first * NUL byte) after the NUL-terminated string at @p. @p will be * NUL-terminated. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf() or similar. * * Returns @p. * */ /* Defined after fortified strlen() and strnlen() to reuse them. */ __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len, total; if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); total = p_len + copy_len + 1; if (p_size < total) fortify_panic(FORTIFY_FUNC_strncat, FORTIFY_WRITE, p_size, total, p); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE bool fortify_memset_chk(__kernel_size_t size, const size_t p_size, const size_t p_size_field) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); /* Warn when write size is larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(FORTIFY_FUNC_memset, FORTIFY_WRITE, p_size, size, true); return false; } #define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ size_t __fortify_size = (size_t)(size); \ fortify_memset_chk(__fortify_size, p_size, p_size_field), \ __underlying_memset(p, c, __fortify_size); \ }) /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #ifndef CONFIG_KMSAN #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ __struct_size(p), __member_size(p)) #endif /* * To make sure the compiler can enforce protection against buffer overflows, * memcpy(), memmove(), and memset() must not be used beyond individual * struct members. If you need to copy across multiple members, please use * struct_group() to create a named mirror of an anonymous struct union. * (e.g. see struct sk_buff.) Read overflow checking is currently only * done when a write overflow is also present, or when building with W=1. * * Mitigation coverage matrix * Bounds checking at: * +-------+-------+-------+-------+ * | Compile time | Run time | * memcpy() argument sizes: | write | read | write | read | * dest source length +-------+-------+-------+-------+ * memcpy(known, known, constant) | y | y | n/a | n/a | * memcpy(known, unknown, constant) | y | n | n/a | V | * memcpy(known, known, dynamic) | n | n | B | B | * memcpy(known, unknown, dynamic) | n | n | B | V | * memcpy(unknown, known, constant) | n | y | V | n/a | * memcpy(unknown, unknown, constant) | n | n | V | V | * memcpy(unknown, known, dynamic) | n | n | V | B | * memcpy(unknown, unknown, dynamic) | n | n | V | V | * +-------+-------+-------+-------+ * * y = perform deterministic compile-time bounds checking * n = cannot perform deterministic compile-time bounds checking * n/a = no run-time bounds checking needed since compile-time deterministic * B = can perform run-time bounds checking (currently unimplemented) * V = vulnerable to run-time overflow (will need refactoring to solve) * */ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t p_size, const size_t q_size, const size_t p_size_field, const size_t q_size_field, const u8 func) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); if (__compiletime_lessthan(q_size_field, q_size) && __compiletime_lessthan(q_size, size)) __read_overflow2(); /* Warn when write size argument larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); /* * Warn for source field over-read when building with W=1 * or when an over-write happened, so both can be fixed at * the same time. */ if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || __compiletime_lessthan(p_size_field, size)) && __compiletime_lessthan(q_size_field, size)) __read_overflow2_field(q_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(func, FORTIFY_WRITE, p_size, size, true); else if (q_size != SIZE_MAX && q_size < size) fortify_panic(func, FORTIFY_READ, p_size, size, true); /* * Warn when writing beyond destination field size. * * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be * detected at compile-time (as can be done when the destination * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; return false; } /* * To work around what seems to be an optimizer bug, the macro arguments * need to have const copies or the values end up changed by the time they * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture * __bos() results in const temp vars") for more details. */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ const size_t __p_size = (p_size); \ const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ /* Keep a mutable version of the size for the final copy. */ \ size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ /* Hide only the run-time size from value range tracking to */ \ /* silence compile-time false positive bounds warnings. */ \ if (!__builtin_constant_p(__copy_size)) \ OPTIMIZER_HIDE_VAR(__copy_size); \ __underlying_##op(p, q, __copy_size); \ }) /* * Notes about compile-time buffer size detection: * * With these types... * * struct middle { * u16 a; * u8 middle_buf[16]; * int b; * }; * struct end { * u16 a; * u8 end_buf[16]; * }; * struct flex { * int a; * u8 flex_buf[]; * }; * * void func(TYPE *ptr) { ... } * * Cases where destination size cannot be currently detected: * - the size of ptr's object (seemingly by design, gcc & clang fail): * __builtin_object_size(ptr, 1) == SIZE_MAX * - the size of flexible arrays in ptr's obj (by design, dynamic size): * __builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX * - the size of ANY array at the end of ptr's obj (gcc and clang bug): * __builtin_object_size(ptr->end_buf, 1) == SIZE_MAX * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836 * * Cases where destination size is currently detected: * - the size of non-array members within ptr's object: * __builtin_object_size(ptr->a, 1) == 2 * - the size of non-flexible-array in the middle of ptr's obj: * __builtin_object_size(ptr->middle_buf, 1) == 16 * */ /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memcpy) #define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memscan, FORTIFY_READ, p_size, size, NULL); return __real_memscan(p, c, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { const size_t p_size = __struct_size(p); const size_t q_size = __struct_size(q); if (__builtin_constant_p(size)) { if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (__compiletime_lessthan(q_size, size)) __read_overflow2(); } if (p_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, p_size, size, INT_MIN); else if (q_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, q_size, size, INT_MIN); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr, FORTIFY_READ, p_size, size, NULL); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr_inv, FORTIFY_READ, p_size, size, NULL); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); __FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } #define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * * Do not use this function. While FORTIFY_SOURCE tries to avoid * overflows, this is only possible when the sizes of @q and @p are * known to the compiler. Prefer strscpy(), though note its different * return values for detecting truncation. * * Returns @p. * */ /* Defined after fortified strlen to reuse it. */ __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) char *strcpy(char * const POS p, const char * const POS q) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t size; /* If neither buffer size is known, immediately give up. */ if (__builtin_constant_p(p_size) && __builtin_constant_p(q_size) && p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strcpy(p, q); size = strlen(q) + 1; /* Compile-time check for const size overflow. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(FORTIFY_FUNC_strcpy, FORTIFY_WRITE, p_size, size, p); __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #undef POS #undef POS0 #endif /* _LINUX_FORTIFY_STRING_H_ */ |
| 500 502 500 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Procedures for maintaining information about logical memory blocks. * * Peter Bergner, IBM Corp. June 2001. * Copyright (C) 2001 Peter Bergner. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/poison.h> #include <linux/pfn.h> #include <linux/debugfs.h> #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 #ifndef INIT_MEMBLOCK_RESERVED_REGIONS # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif #ifndef INIT_MEMBLOCK_MEMORY_REGIONS #define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS #endif /** * DOC: memblock overview * * Memblock is a method of managing memory regions during the early * boot period when the usual kernel memory allocators are not up and * running. * * Memblock views the system memory as collections of contiguous * regions. There are several types of these collections: * * * ``memory`` - describes the physical memory available to the * kernel; this may differ from the actual physical memory installed * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated * * ``physmem`` - describes the actual physical memory available during * boot regardless of the possible restrictions and memory hot(un)plug; * the ``physmem`` type is only available on some architectures. * * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA * systems. Every memory type is described by the struct memblock_type * which contains an array of memory regions along with * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not * overlap with areas that should be reserved, for example initrd. * * The early architecture setup should tell memblock what the physical * memory layout is by using memblock_add() or memblock_add_node() * functions. The first function does not assign the region to a NUMA * node and it is appropriate for UMA systems. Yet, it is possible to * use it on NUMA systems as well and assign the region to a NUMA node * later in the setup process using memblock_set_node(). The * memblock_add_node() performs such an assignment directly. * * Once memblock is setup the memory can be allocated using one of the * API variants: * * * memblock_phys_alloc*() - these functions return the **physical** * address of the allocated memory * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. * * As the system boot progresses, the architecture specific mem_init() * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the * memblock data structures (except "physmem") will be discarded after the * system initialization completes. */ #ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP struct memblock_type physmem = { .regions = memblock_physmem_init_regions, .max = INIT_PHYSMEM_REGIONS, .name = "physmem", }; #endif /* * keep a pointer to &memblock.memory in the text section to use it in * __next_mem_range() and its helpers. * For architectures that do not keep memblock data after init, this * pointer will be reset to NULL at memblock_discard() */ static __refdata struct memblock_type *memblock_memory = &memblock.memory; #define for_each_memblock_type(i, memblock_type, rgn) \ for (i = 0, rgn = &memblock_type->regions[0]; \ i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) #define memblock_dbg(fmt, ...) \ do { \ if (memblock_debug) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock; static int memblock_reserved_in_slab __initdata_memblock; bool __init_memblock memblock_has_mirror(void) { return system_has_some_mirror; } static enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { return *size = min(*size, PHYS_ADDR_MAX - base); } /* * Address comparison utilities */ unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } bool __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { unsigned long i; memblock_cap_size(base, &size); for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) return true; return false; } /** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); cand = round_up(this_start, align); if (cand < this_end && this_end - cand >= size) return cand; } return 0; } /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_end < size) continue; cand = round_down(this_end - size, align); if (cand >= this_start) return cand; } return 0; } /** * memblock_find_in_range_node - find free area in given range and node * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, enum memblock_flags flags) { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); if (memblock_bottom_up()) return __memblock_find_range_bottom_up(start, end, size, align, nid, flags); else return __memblock_find_range_top_down(start, end, size, align, nid, flags); } /** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { phys_addr_t ret; enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; } return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; memmove(&type->regions[r], &type->regions[r + 1], (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { WARN_ON(type->total_size != 0); type->regions[0].base = 0; type->regions[0].size = 0; type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } #ifndef CONFIG_ARCH_KEEP_MEMBLOCK /** * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { phys_addr_t addr, size; if (memblock.reserved.regions != memblock_reserved_init_regions) { addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); if (memblock_reserved_in_slab) kfree(memblock.reserved.regions); else memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); if (memblock_memory_in_slab) kfree(memblock.memory.regions); else memblock_free_late(addr, size); } memblock_memory = NULL; } #endif /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled * @new_area_start: starting address of memory range to avoid overlap with * @new_area_size: size of memory range to avoid overlap with * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_start, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr, new_end; int use_slab = slab_is_available(); int *in_slab; /* We don't allow resizing until we know about the reserved regions * of memory that aren't suitable for allocation */ if (!memblock_can_resize) panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; /* * We need to allocated new one align to PAGE_SIZE, * so we can free them completely later. */ old_alloc_size = PAGE_ALIGN(old_size); new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) in_slab = &memblock_memory_in_slab; else in_slab = &memblock_reserved_in_slab; /* Try to find some space for it */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { /* only exclude range when trying to double reserved.regions */ if (type != &memblock.reserved) new_area_start = new_area_size = 0; addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", type->name, type->max, type->max * 2); return -1; } new_end = addr + new_size - 1; memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", type->name, type->max * 2, &addr, &new_end); /* * Found space, we now need to move the array over before we add the * reserved region since it may be our reserved array itself that is * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); old_array = type->regions; type->regions = new_array; type->max <<= 1; /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; return 0; } /** * memblock_merge_regions - merge neighboring compatible regions * @type: memblock type to scan * @start_rgn: start scanning from (@start_rgn - 1) * @end_rgn: end scanning at (@end_rgn - 1) * Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn) */ static void __init_memblock memblock_merge_regions(struct memblock_type *type, unsigned long start_rgn, unsigned long end_rgn) { int i = 0; if (start_rgn) i = start_rgn - 1; end_rgn = min(end_rgn, type->cnt - 1); while (i < end_rgn) { struct memblock_region *this = &type->regions[i]; struct memblock_region *next = &type->regions[i + 1]; if (this->base + this->size != next->base || memblock_get_region_node(this) != memblock_get_region_node(next) || this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; } this->size += next->size; /* move forward from next + 1, index of which is i + 2 */ memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); type->cnt--; end_rgn--; } } /** * memblock_insert_region - insert new memblock region * @type: memblock type to insert into * @idx: index for the insertion point * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region * @flags: flags of the new region * * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; BUG_ON(type->cnt >= type->max); memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); int idx, nr_new, start_rgn = -1, end_rgn; struct memblock_region *rgn; if (!size) return 0; /* special case for empty array */ if (type->regions[0].size == 0) { WARN_ON(type->cnt != 0 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; type->cnt = 1; return 0; } /* * The worst case is when new range overlaps all existing regions, * then we'll need type->cnt + 1 empty regions in @type. So if * type->cnt * 2 + 1 is less than or equal to type->max, we know * that there is enough empty regions in @type, and we can insert * regions directly. */ if (type->cnt * 2 + 1 <= type->max) insert = true; repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; /* * @rgn overlaps. If it separates the lower part of new * area, insert that portion. */ if (rbase > base) { #ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } } /* area below @rend is dealt with, forget about it */ base = min(rend, end); } /* insert the remaining portion */ if (base < end) { nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx, base, end - base, nid, flags); } } if (!nr_new) return 0; /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. */ if (!insert) { while (type->cnt + nr_new > type->max) if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; } else { memblock_merge_regions(type, start_rgn, end_rgn); return 0; } } /** * memblock_add_node - add new memblock region within a NUMA node * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, &base, &end, nid, flags, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** * memblock_add - add new memblock region * @base: base address of the new region * @size: size of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold * @threshold_bytes: maximal memory size that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. * Check if amount of such memory is below @threshold_bytes. * * Return: true on success, false on failure. */ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) { unsigned long nr_pages = 0; unsigned long start_pfn, end_pfn, mem_size_mb; int nid, i; /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } if ((nr_pages << PAGE_SHIFT) > threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); return false; } return true; } /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate * @size: size of range to isolate * @start_rgn: out parameter for the start of isolated region * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and the index of the * first region after the range is returned in *@end_rgn. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); int idx; struct memblock_region *rgn; *start_rgn = *end_rgn = 0; if (!size) return 0; /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; if (rbase < base) { /* * @rgn intersects from below. Split and continue * to process the next region - the new top half. */ rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the * current region - the new bottom half. */ rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) *start_rgn = idx; *end_rgn = idx + 1; } } return 0; } static int __init_memblock memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = end_rgn - 1; i >= start_rgn; i--) memblock_remove_region(type, i); return 0; } int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_remove_range(&memblock.memory, base, size); } /** * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); } /** * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif /** * memblock_setclr_flag - set or clear flag for a memory region * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int set, int flag) { int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) { struct memblock_region *r = &type->regions[i]; if (set) r->flags |= flag; else r->flags &= ~flag; } memblock_merge_regions(type, start_rgn, end_rgn); return 0; } /** * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { if (!mirrored_kernelcore) return 0; system_has_some_mirror = true; return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. * @base: the base phys addr of the region * @size: the size of the region * * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the * direct mapping of the physical memory. These regions will still be * covered by the memory map. The struct page representing NOMAP memory * frames in the memory map will be PageReserved() * * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from * memblock, the caller must inform kmemleak to ignore that memory * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); } /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized * for this region. * @base: the base phys addr of the region * @size: the size of the region * * struct pages will not be initialized for reserved memory regions marked with * %MEMBLOCK_RSRV_NOINIT. * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.reserved, base, size, 1, MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; } /** * __next_mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of * *@idx contains index into type_a and the upper 32bit indexes the * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) * * The upper 32bit indexes the following regions. * * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) * * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b < type_b->cnt + 1; idx_b++) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; /* * The region which ends first is * advanced for the next iteration. */ if (m_end <= r_end) idx_a++; else idx_b++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Finds the next range from type_a which is not marked as unsuitable * in type_b. * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) idx_b = type_b->cnt; else idx_b = 0; } for (; idx_a >= 0; idx_a--) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b >= 0; idx_b--) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ if (m_end > r_start) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; if (m_start >= r_start) idx_a--; else idx_b--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /* * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid) { struct memblock_type *type = &memblock.memory; struct memblock_region *r; int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { *idx = -1; return; } if (out_start_pfn) *out_start_pfn = PFN_UP(r->base); if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) *out_nid = r_nid; } /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for * @type: memblock type to set node ID for * @nid: node ID to set * * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { #ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type, start_rgn, end_rgn); #endif return 0; } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() * * @idx: pointer to u64 loop variable * @zone: zone in which all of the memory blocks reside * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL * * This function is meant to be a zone/pfn specific wrapper for the * for_each_mem_range type iterators. Specifically they are used in the * deferred memory init routines and as such we were duplicating much of * this logic throughout the code. So instead of having it in multiple * locations it seemed like it would make more sense to centralize this to * one new iterator that does everything they need. */ void __init_memblock __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn) { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); unsigned long spfn = PFN_UP(spa); /* * Verify the end is at least past the start of the zone and * that we have at least one PFN to initialize. */ if (zone->zone_start_pfn < epfn && spfn < epfn) { /* if we went too far just stop searching */ if (zone_end_pfn(zone) <= spfn) { *idx = U64_MAX; break; } if (out_spfn) *out_spfn = max(zone->zone_start_pfn, spfn); if (out_epfn) *out_epfn = min(zone_end_pfn(zone), epfn); return; } __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); } /* signal end of iteration */ if (out_spfn) *out_spfn = ULONG_MAX; if (out_epfn) *out_epfn = 0; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** * memblock_alloc_range_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * * If the specified node can not hold the requested memory and @exact_nid * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any * memory region. * * In addition, function using kmemleak_alloc_phys for allocated boot * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) { void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid); return vaddr ? virt_to_phys(vaddr) : 0; } if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); align = SMP_CACHE_BYTES; } again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) goto done; if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (found && !memblock_reserve(found, size)) goto done; } if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } return 0; done: /* * Skip kmemleak for those places like kasan_init() and * early_pgtable_alloc() due to high volume. */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * Memblock allocated blocks are never reported as * leaks. This is because many of these blocks are * only referred via the physical address which is * not looked up by kmemleak. */ kmemleak_alloc_phys(found, size, 0); /* * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, * require memory to be accepted before it can be used by the * guest. * * Accept the memory of the allocated buffer. */ accept_memory(found, size); return found; } /** * memblock_phys_alloc_range - allocate a memory block inside specified range * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (physical address) * @end: the upper bound of the memory region to allocate (physical address) * * Allocate @size bytes in the between @start and @end. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end) { memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, &start, &end, (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Allocates memory block from the specified NUMA node. If the node * has no available memory, attempts to allocated from any node in the * system. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. * * The @min_addr limit is dropped if it can not be satisfied and the allocation * will fall back to memory below @min_addr. Other constraints, such * as node and mirrored memory will be handled again in * memblock_alloc_range_nid(). * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid, bool exact_nid) { phys_addr_t alloc; if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, exact_nid); if (!alloc) return NULL; return phys_to_virt(alloc); } /** * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node * without zeroing memory * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_exact_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, true); } /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); } /** * memblock_alloc_try_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { void *ptr; memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); return ptr; } /** * __memblock_alloc_or_panic - Try to allocate memory and panic on failure * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @func: caller func name * * This function attempts to allocate memory using memblock_alloc, * and in case of failure, it calls panic with the formatted message. * This function should not be used directly, please use the macro memblock_alloc_or_panic. */ void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align, const char *func) { void *addr = memblock_alloc(size, align); if (unlikely(!addr)) panic("%s: Failed to allocate %pap bytes\n", func, &size); return addr; } /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * This is only useful when the memblock allocator has already been torn * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } /* * Remaining API functions */ phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } phys_addr_t __init_memblock memblock_reserved_size(void) { return memblock.reserved.total_size; } /** * memblock_estimated_nr_free_pages - return estimated number of free pages * from memblock point of view * * During bootup, subsystems might need a rough estimate of the number of free * pages in the whole system, before precise numbers are available from the * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers * obtained from the buddy might be very imprecise during bootup. * * Return: * An estimated number of free pages from memblock point of view. */ unsigned long __init memblock_estimated_nr_free_pages(void) { return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); } /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { return memblock.memory.regions[0].base; } phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = PHYS_ADDR_MAX; struct memblock_region *r; /* * translate the memory @limit size into the max address within one of * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; } limit -= r->size; } return max_addr; } void __init memblock_enforce_memory_limit(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, PHYS_ADDR_MAX); memblock_remove_range(&memblock.reserved, max_addr, PHYS_ADDR_MAX); } void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; if (!size) return; if (!memblock_memory->total_size) { pr_warn("%s: No memory registered yet\n", __func__); return; } ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) return; /* remove all the MAP regions */ for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); for (i = start_rgn - 1; i >= 0; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); /* truncate the reserved regions */ memblock_remove_range(&memblock.reserved, 0, base); memblock_remove_range(&memblock.reserved, base + size, PHYS_ADDR_MAX); } void __init memblock_mem_limit_remove_map(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; memblock_cap_memory_range(0, max_addr); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; do { unsigned int mid = (right + left) / 2; if (addr < type->regions[mid].base) right = mid; else if (addr >= (type->regions[mid].base + type->regions[mid].size)) left = mid + 1; else return mid; } while (left < right); return -1; } bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); if (i == -1) return false; return !memblock_is_nomap(&memblock.memory.regions[i]); } int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return memblock_get_region_node(&type->regions[mid]); } /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) is a subset of a memory block. * * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } /** * memblock_is_region_reserved - check if a region intersects reserved memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) intersects a reserved * memory block. * * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { return memblock_overlaps_region(&memblock.reserved, base, size); } void __init_memblock memblock_trim_memory(phys_addr_t align) { phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); if (start == orig_start && end == orig_end) continue; if (start < end) { r->base = start; r->size = end - start; } else { memblock_remove_region(&memblock.memory, r - memblock.memory.regions); r--; } } } void __init_memblock memblock_set_current_limit(phys_addr_t limit) { memblock.current_limit = limit; } phys_addr_t __init_memblock memblock_get_current_limit(void) { return memblock.current_limit; } static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; enum memblock_flags flags; int idx; struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(idx, type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", &memblock.memory.total_size, &memblock.reserved.total_size); memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP memblock_dump(&physmem); #endif } void __init_memblock memblock_dump_all(void) { if (memblock_debug) __memblock_dump_all(); } void __init memblock_allow_resize(void) { memblock_can_resize = 1; } static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) memblock_debug = 1; return 0; } early_param("memblock", early_memblock); static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) { struct page *start_pg, *end_pg; phys_addr_t pg, pgend; /* * Convert start_pfn/end_pfn to a struct page pointer. */ start_pg = pfn_to_page(start_pfn - 1) + 1; end_pg = pfn_to_page(end_pfn - 1) + 1; /* * Convert to physical addresses, and round start upwards and end * downwards. */ pg = PAGE_ALIGN(__pa(start_pg)); pgend = PAGE_ALIGN_DOWN(__pa(end_pg)); /* * If there are free pages between these, free the section of the * memmap array. */ if (pg < pgend) memblock_phys_free(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ static void __init free_unused_memmap(void) { unsigned long start, end, prev_end = 0; int i; if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) return; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); #endif /* * Align down here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ start = pageblock_start_pfn(start); /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ if (prev_end && prev_end < start) free_memmap(prev_end, start); /* * Align up here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ prev_end = pageblock_align(end); } #ifdef CONFIG_SPARSEMEM if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { prev_end = pageblock_align(end); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); } #endif } static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; while (start < end) { /* * Free the pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for * the case. */ if (start) order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } } static unsigned long __init __free_memory_core(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = min_t(unsigned long, PFN_DOWN(end), max_low_pfn); if (start_pfn >= end_pfn) return 0; __free_pages_memory(start_pfn, end_pfn); return end_pfn - start_pfn; } static void __init memmap_init_reserved_pages(void) { struct memblock_region *region; phys_addr_t start, end; int nid; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); memblock_set_node(start, end, &memblock.reserved, nid); } /* * initialize struct pages for reserved regions that don't have * the MEMBLOCK_RSRV_NOINIT flag set */ for_each_reserved_mem_region(region) { if (!memblock_is_reserved_noinit(region)) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); } } } static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end; u64 i; memblock_clear_hotplug(0, -1); memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); return count; } static int reset_managed_pages_done __initdata; static void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) atomic_long_set(&z->managed_pages, 0); } void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; if (reset_managed_pages_done) return; for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); reset_managed_pages_done = 1; } /** * memblock_free_all - release free pages to the buddy allocator */ void __init memblock_free_all(void) { unsigned long pages; free_unused_memmap(); reset_all_zones_managed_pages(); pages = free_low_memory_core_early(); totalram_pages_add(pages); } /* Keep a table to reserve named memory */ #define RESERVE_MEM_MAX_ENTRIES 8 #define RESERVE_MEM_NAME_SIZE 16 struct reserve_mem_table { char name[RESERVE_MEM_NAME_SIZE]; phys_addr_t start; phys_addr_t size; }; static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES]; static int reserved_mem_count; /* Add wildcard region with a lookup name */ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size, const char *name) { struct reserve_mem_table *map; map = &reserved_mem_table[reserved_mem_count++]; map->start = start; map->size = size; strscpy(map->name, name); } /** * reserve_mem_find_by_name - Find reserved memory region with a given name * @name: The name that is attached to a reserved memory region * @start: If found, holds the start address * @size: If found, holds the size of the address. * * @start and @size are only updated if @name is found. * * Returns: 1 if found or 0 if not found. */ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size) { struct reserve_mem_table *map; int i; for (i = 0; i < reserved_mem_count; i++) { map = &reserved_mem_table[i]; if (!map->size) continue; if (strcmp(name, map->name) == 0) { *start = map->start; *size = map->size; return 1; } } return 0; } EXPORT_SYMBOL_GPL(reserve_mem_find_by_name); /* * Parse reserve_mem=nn:align:name */ static int __init reserve_mem(char *p) { phys_addr_t start, size, align, tmp; char *name; char *oldp; int len; if (!p) return -EINVAL; /* Check if there's room for more reserved memory */ if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES) return -EBUSY; oldp = p; size = memparse(p, &p); if (!size || p == oldp) return -EINVAL; if (*p != ':') return -EINVAL; align = memparse(p+1, &p); if (*p != ':') return -EINVAL; /* * memblock_phys_alloc() doesn't like a zero size align, * but it is OK for this command to have it. */ if (align < SMP_CACHE_BYTES) align = SMP_CACHE_BYTES; name = p + 1; len = strlen(name); /* name needs to have length but not too big */ if (!len || len >= RESERVE_MEM_NAME_SIZE) return -EINVAL; /* Make sure that name has text */ for (p = name; *p; p++) { if (!isspace(*p)) break; } if (!*p) return -EINVAL; /* Make sure the name is not already used */ if (reserve_mem_find_by_name(name, &start, &tmp)) return -EBUSY; start = memblock_phys_alloc(size, align); if (!start) return -ENOMEM; reserved_mem_add(start, size, name); return 1; } __setup("reserve_mem=", reserve_mem); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) static const char * const flagname[] = { [ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG", [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) { struct memblock_type *type = m->private; struct memblock_region *reg; int i, j, nid; unsigned int count = ARRAY_SIZE(flagname); phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; end = reg->base + reg->size - 1; nid = memblock_get_region_node(reg); seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); if (reg->flags) { for (j = 0; j < count; j++) { if (reg->flags & (1U << j)) { seq_printf(m, "%s\n", flagname[j]); break; } } if (j == count) seq_printf(m, "%s\n", "UNKNOWN"); } else { seq_printf(m, "%s\n", "NONE"); } } return 0; } DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP debugfs_create_file("physmem", 0444, root, &physmem, &memblock_debug_fops); #endif return 0; } __initcall(memblock_init_debugfs); #endif /* CONFIG_DEBUG_FS */ |
| 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Page fragment allocator * * Page Fragment: * An arbitrary-length arbitrary-offset area of memory which resides within a * 0 or higher order page. Multiple fragments within that page are * individually refcounted, in the page's reference counter. * * The page_frag functions provide a simple allocation framework for page * fragments. This is used by the network stack and network device drivers to * provide a backing region of memory for use as either an sk_buff->head, or to * be used in the "frags" portion of skb_shared_info. */ #include <linux/build_bug.h> #include <linux/export.h> #include <linux/gfp_types.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/page_frag_cache.h> #include "internal.h" static unsigned long encoded_page_create(struct page *page, unsigned int order, bool pfmemalloc) { BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK); BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE); return (unsigned long)page_address(page) | (order & PAGE_FRAG_CACHE_ORDER_MASK) | ((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT); } static unsigned long encoded_page_decode_order(unsigned long encoded_page) { return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK; } static void *encoded_page_decode_virt(unsigned long encoded_page) { return (void *)(encoded_page & PAGE_MASK); } static struct page *encoded_page_decode_page(unsigned long encoded_page) { return virt_to_page((void *)encoded_page); } static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp_mask) { unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER; struct page *page = NULL; gfp_t gfp = gfp_mask; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER, numa_mem_id(), NULL); #endif if (unlikely(!page)) { page = __alloc_pages(gfp, 0, numa_mem_id(), NULL); order = 0; } nc->encoded_page = page ? encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0; return page; } void page_frag_cache_drain(struct page_frag_cache *nc) { if (!nc->encoded_page) return; __page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page), nc->pagecnt_bias); nc->encoded_page = 0; } EXPORT_SYMBOL(page_frag_cache_drain); void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(__page_frag_cache_drain); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask) { unsigned long encoded_page = nc->encoded_page; unsigned int size, offset; struct page *page; if (unlikely(!encoded_page)) { refill: page = __page_frag_cache_refill(nc, gfp_mask); if (!page) return NULL; encoded_page = nc->encoded_page; /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; nc->offset = 0; } size = PAGE_SIZE << encoded_page_decode_order(encoded_page); offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask); if (unlikely(offset + fragsz > size)) { if (unlikely(fragsz > PAGE_SIZE)) { /* * The caller is trying to allocate a fragment * with fragsz > PAGE_SIZE but the cache isn't big * enough to satisfy the request, this may * happen in low memory conditions. * We don't release the cache page because * it could make memory pressure worse * so we simply return NULL here. */ return NULL; } page = encoded_page_decode_page(encoded_page); if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) { free_frozen_pages(page, encoded_page_decode_order(encoded_page)); goto refill; } /* OK, page count is 0, we can safely set it */ set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = 0; } nc->pagecnt_bias--; nc->offset = offset + fragsz; return encoded_page_decode_virt(encoded_page) + offset; } EXPORT_SYMBOL(__page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. */ void page_frag_free(void *addr) { struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(page_frag_free); |
| 170 52 128 129 128 51 51 51 51 51 51 201 201 201 201 200 19 19 19 201 201 201 199 201 200 201 239 238 238 237 238 238 172 15 176 39 39 17 120 217 217 238 238 17 225 187 19 172 172 64 172 173 171 172 172 172 173 173 236 204 235 236 129 112 49 204 129 204 129 39 1 39 39 39 39 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool on_lru, bool disable_irq) { unsigned long flags; if (on_lru && !folio_test_clear_lru(folio)) return; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op, on_lru) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ on_lru, \ offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_move_tail, true); } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; do { unsigned long lrusize; /* * Hold lruvec->lru_lock is safe here, since * 1) The pinned lruvec in reclaim, or * 2) From a pre-LRU page during refault (which also holds the * rcu lock, so would be safe even if the page was on the LRU * and could move simultaneously to a new lruvec). */ spin_lock_irq(&lruvec->lru_lock); /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_refault(struct folio *folio) { lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_activate, true); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { struct lru_gen_folio *lrugen; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); if (gen < 0) return true; set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0); lrugen = &folio_lruvec(folio)->lrugen; /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add, false); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file, true); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate, true); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree, true); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (put_devmap_managed_folio_refs(folio, nr_refs)) continue; if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[PAGEVEC_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } |
| 31 31 31 31 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 | // SPDX-License-Identifier: GPL-2.0+ /* * Driver core for serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright 1999 ARM Limited * Copyright (C) 2000-2001 Deep Blue Solutions Ltd. */ #include <linux/module.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/init.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/pm_runtime.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/device.h> #include <linux/serial.h> /* for serial_state and serial_icounter_struct */ #include <linux/serial_core.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/math64.h> #include <linux/security.h> #include <linux/irq.h> #include <linux/uaccess.h> #include "serial_base.h" /* * This is used to lock changes in serial line configuration. */ static DEFINE_MUTEX(port_mutex); /* * lockdep: port->lock is initialized in two places, but we * want only one lock-class: */ static struct lock_class_key port_lock_key; #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) /* * Max time with active RTS before/after data is sent. */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); static void uart_port_shutdown(struct tty_port *port); static int uart_dcd_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_DCD_ENABLE); } static inline struct uart_port *uart_port_ref(struct uart_state *state) { if (atomic_add_unless(&state->refcount, 1, 0)) return state->uart_port; return NULL; } static inline void uart_port_deref(struct uart_port *uport) { if (atomic_dec_and_test(&uport->state->refcount)) wake_up(&uport->state->remove_wait); } #define uart_port_lock(state, flags) \ ({ \ struct uart_port *__uport = uart_port_ref(state); \ if (__uport) \ uart_port_lock_irqsave(__uport, &flags); \ __uport; \ }) #define uart_port_unlock(uport, flags) \ ({ \ struct uart_port *__uport = uport; \ if (__uport) { \ uart_port_unlock_irqrestore(__uport, flags); \ uart_port_deref(__uport); \ } \ }) static inline struct uart_port *uart_port_check(struct uart_state *state) { lockdep_assert_held(&state->port.mutex); return state->uart_port; } /** * uart_write_wakeup - schedule write processing * @port: port to be processed * * This routine is used by the interrupt handler to schedule processing in the * software interrupt portion of the driver. A driver is expected to call this * function when the number of characters in the transmit buffer have dropped * below a threshold. * * Locking: @port->lock should be held */ void uart_write_wakeup(struct uart_port *port) { struct uart_state *state = port->state; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ BUG_ON(!state); tty_port_tty_wakeup(&state->port); } EXPORT_SYMBOL(uart_write_wakeup); static void uart_stop(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); if (port) port->ops->stop_tx(port); uart_port_unlock(port, flags); } static void __uart_start(struct uart_state *state) { struct uart_port *port = state->uart_port; struct serial_port_device *port_dev; int err; if (!port || port->flags & UPF_DEAD || uart_tx_stopped(port)) return; port_dev = port->port_dev; /* Increment the runtime PM usage count for the active check below */ err = pm_runtime_get(&port_dev->dev); if (err < 0 && err != -EINPROGRESS) { pm_runtime_put_noidle(&port_dev->dev); return; } /* * Start TX if enabled, and kick runtime PM. If the device is not * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); } static void uart_start(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); __uart_start(state); uart_port_unlock(port, flags); } static void uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) { unsigned long flags; unsigned int old; uart_port_lock_irqsave(port, &flags); old = port->mctrl; port->mctrl = (old & ~clear) | set; if (old != port->mctrl && !(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); uart_port_unlock_irqrestore(port, flags); } #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) static void uart_port_dtr_rts(struct uart_port *uport, bool active) { if (active) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); else uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } /* Caller holds port mutex */ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state *state, const struct ktermios *old_termios) { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; bool old_hw_stopped; /* * If we have no tty, termios, or the port does not exist, * then we can't set the parameters for this port. */ if (!tty || uport->type == PORT_UNKNOWN) return; termios = &tty->termios; uport->ops->set_termios(uport, termios, old_termios); /* * Set modem status enables based on termios cflag */ uart_port_lock_irq(uport); if (termios->c_cflag & CRTSCTS) uport->status |= UPSTAT_CTS_ENABLE; else uport->status &= ~UPSTAT_CTS_ENABLE; if (termios->c_cflag & CLOCAL) uport->status &= ~UPSTAT_DCD_ENABLE; else uport->status |= UPSTAT_DCD_ENABLE; /* reset sw-assisted CTS flow control based on (possibly) new mode */ old_hw_stopped = uport->hw_stopped; uport->hw_stopped = uart_softcts_mode(uport) && !(uport->ops->get_mctrl(uport) & TIOCM_CTS); if (uport->hw_stopped != old_hw_stopped) { if (!old_hw_stopped) uport->ops->stop_tx(uport); else __uart_start(state); } uart_port_unlock_irq(uport); } static int uart_alloc_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; unsigned long page; /* * Initialise and allocate the transmit and temporary * buffer. */ page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; uport = uart_port_lock(state, flags); if (!state->port.xmit_buf) { state->port.xmit_buf = (unsigned char *)page; kfifo_init(&state->port.xmit_fifo, state->port.xmit_buf, PAGE_SIZE); uart_port_unlock(uport, flags); } else { uart_port_unlock(uport, flags); /* * Do not free() the page under the port lock, see * uart_free_xmit_buf(). */ free_page(page); } return 0; } static void uart_free_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; char *xmit_buf; /* * Do not free() the transmit buffer page under the port lock since * this can create various circular locking scenarios. For instance, * console driver may need to allocate/free a debug object, which * can end up in printk() recursion. */ uport = uart_port_lock(state, flags); xmit_buf = port->xmit_buf; port->xmit_buf = NULL; INIT_KFIFO(port->xmit_fifo); uart_port_unlock(uport, flags); free_page((unsigned long)xmit_buf); } /* * Startup the port. This will be called once per open. All calls * will be serialised by the per-port mutex. */ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct uart_port *uport = uart_port_check(state); int retval; if (uport->type == PORT_UNKNOWN) return 1; /* * Make sure the device is in D0 state. */ uart_change_pm(state, UART_PM_STATE_ON); retval = uart_alloc_xmit_buf(&state->port); if (retval) return retval; retval = uport->ops->startup(uport); if (retval == 0) { if (uart_console(uport) && uport->cons->cflag) { tty->termios.c_cflag = uport->cons->cflag; tty->termios.c_ispeed = uport->cons->ispeed; tty->termios.c_ospeed = uport->cons->ospeed; uport->cons->cflag = 0; uport->cons->ispeed = 0; uport->cons->ospeed = 0; } /* * Initialise the hardware port settings. */ uart_change_line_settings(tty, state, NULL); /* * Setup the RTS and DTR signals once the * port is open and ready to respond. */ if (init_hw && C_BAUD(tty)) uart_port_dtr_rts(uport, true); } /* * This is to allow setserial on this port. People may want to set * port/irq/type and then reconfigure the port properly if it failed * now. */ if (retval && capable(CAP_SYS_ADMIN)) return 1; return retval; } static int uart_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct tty_port *port = &state->port; struct uart_port *uport; int retval; if (tty_port_initialized(port)) goto out_base_port_startup; retval = uart_port_startup(tty, state, init_hw); if (retval) { set_bit(TTY_IO_ERROR, &tty->flags); return retval; } out_base_port_startup: uport = uart_port_check(state); if (!uport) return -EIO; serial_base_port_startup(uport); return 0; } /* * This routine will shutdown a serial port; interrupts are disabled, and * DTR is dropped if the hangup on close termio flag is on. Calls to * uart_shutdown are serialised by the per-port semaphore. * * uport == NULL if uart_port has already been removed */ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) { struct uart_port *uport = uart_port_check(state); struct tty_port *port = &state->port; /* * Set the TTY IO error marker */ if (tty) set_bit(TTY_IO_ERROR, &tty->flags); if (uport) serial_base_port_shutdown(uport); if (tty_port_initialized(port)) { tty_port_set_initialized(port, false); /* * Turn off DTR and RTS early. */ if (uport) { if (uart_console(uport) && tty) { uport->cons->cflag = tty->termios.c_cflag; uport->cons->ispeed = tty->termios.c_ispeed; uport->cons->ospeed = tty->termios.c_ospeed; } if (!tty || C_HUPCL(tty)) uart_port_dtr_rts(uport, false); } uart_port_shutdown(port); } /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); } /** * uart_update_timeout - update per-port frame timing information * @port: uart_port structure describing the port * @cflag: termios cflag value * @baud: speed of the port * * Set the @port frame timing information from which the FIFO timeout value is * derived. The @cflag value should reflect the actual hardware settings as * number of bits, parity, stop bits and baud rate is taken into account here. * * Locking: caller is expected to take @port->lock */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud) { u64 temp = tty_get_frame_size(cflag); temp *= NSEC_PER_SEC; port->frame_time = (unsigned int)DIV64_U64_ROUND_UP(temp, baud); } EXPORT_SYMBOL(uart_update_timeout); /** * uart_get_baud_rate - return baud rate for a particular port * @port: uart_port structure describing the port in question. * @termios: desired termios settings * @old: old termios (or %NULL) * @min: minimum acceptable baud rate * @max: maximum acceptable baud rate * * Decode the termios structure into a numeric baud rate, taking account of the * magic 38400 baud rate (with spd_* flags), and mapping the %B0 rate to 9600 * baud. * * If the new baud rate is invalid, try the @old termios setting. If it's still * invalid, we try 9600 baud. If that is also invalid 0 is returned. * * The @termios structure is updated to reflect the baud rate we're actually * going to be using. Don't do this for the case where B0 is requested ("hang * up"). * * Locking: caller dependent */ unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max) { unsigned int try; unsigned int baud; unsigned int altbaud; int hung_up = 0; upf_t flags = port->flags & UPF_SPD_MASK; switch (flags) { case UPF_SPD_HI: altbaud = 57600; break; case UPF_SPD_VHI: altbaud = 115200; break; case UPF_SPD_SHI: altbaud = 230400; break; case UPF_SPD_WARP: altbaud = 460800; break; default: altbaud = 38400; break; } for (try = 0; try < 2; try++) { baud = tty_termios_baud_rate(termios); /* * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ if (try == 0 && baud == 38400) baud = altbaud; /* * Special case: B0 rate. */ if (baud == 0) { hung_up = 1; baud = 9600; } if (baud >= min && baud <= max) return baud; /* * Oops, the quotient was zero. Try again with * the old baud rate if possible. */ termios->c_cflag &= ~CBAUD; if (old) { baud = tty_termios_baud_rate(old); if (!hung_up) tty_termios_encode_baud_rate(termios, baud, baud); old = NULL; continue; } /* * As a last resort, if the range cannot be met then clip to * the nearest chip supported rate. */ if (!hung_up) { if (baud <= min) tty_termios_encode_baud_rate(termios, min + 1, min + 1); else tty_termios_encode_baud_rate(termios, max - 1, max - 1); } } return 0; } EXPORT_SYMBOL(uart_get_baud_rate); /** * uart_get_divisor - return uart clock divisor * @port: uart_port structure describing the port * @baud: desired baud rate * * Calculate the divisor (baud_base / baud) for the specified @baud, * appropriately rounded. * * If 38400 baud and custom divisor is selected, return the custom divisor * instead. * * Locking: caller dependent */ unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud) { unsigned int quot; /* * Old custom speed handling. */ if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) quot = port->custom_divisor; else quot = DIV_ROUND_CLOSEST(port->uartclk, 16 * baud); return quot; } EXPORT_SYMBOL(uart_get_divisor); static int uart_put_char(struct tty_struct *tty, u8 c) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; port = uart_port_lock(state, flags); if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } if (port) ret = kfifo_put(&state->port.xmit_fifo, c); uart_port_unlock(port, flags); return ret; } static void uart_flush_chars(struct tty_struct *tty) { uart_start(tty); } static ssize_t uart_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return -EL3HLT; port = uart_port_lock(state, flags); if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } if (port) ret = kfifo_in(&state->port.xmit_fifo, buf, count); __uart_start(state); uart_port_unlock(port, flags); return ret; } static unsigned int uart_write_room(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_lock(state, flags); ret = kfifo_avail(&state->port.xmit_fifo); uart_port_unlock(port, flags); return ret; } static unsigned int uart_chars_in_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_lock(state, flags); ret = kfifo_len(&state->port.xmit_fifo); uart_port_unlock(port, flags); return ret; } static void uart_flush_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return; pr_debug("uart_flush_buffer(%d) called\n", tty->index); port = uart_port_lock(state, flags); if (!port) return; kfifo_reset(&state->port.xmit_fifo); if (port->ops->flush_buffer) port->ops->flush_buffer(port); uart_port_unlock(port, flags); tty_port_tty_wakeup(&state->port); } /* * This function performs low-level write of high-priority XON/XOFF * character and accounting for it. * * Requires uart_port to implement .serial_out(). */ void uart_xchar_out(struct uart_port *uport, int offset) { serial_port_out(uport, offset, uport->x_char); uport->icount.tx++; uport->x_char = 0; } EXPORT_SYMBOL_GPL(uart_xchar_out); /* * This function is used to send a high-priority XON/XOFF character to * the device */ static void uart_send_xchar(struct tty_struct *tty, u8 ch) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_ref(state); if (!port) return; if (port->ops->send_xchar) port->ops->send_xchar(port, ch); else { uart_port_lock_irqsave(port, &flags); port->x_char = ch; if (ch) port->ops->start_tx(port); uart_port_unlock_irqrestore(port, flags); } uart_port_deref(port); } static void uart_throttle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->throttle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_clear_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, STOP_CHAR(tty)); uart_port_deref(port); } static void uart_unthrottle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->unthrottle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_set_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, START_CHAR(tty)); uart_port_deref(port); } static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; /* Initialize structure in case we error out later to prevent any stack info leakage. */ *retinfo = (struct serial_struct){}; /* * Ensure the state we copy is consistent and no hardware changes * occur as we go */ guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -ENODEV; retinfo->type = uport->type; retinfo->line = uport->line; retinfo->port = uport->iobase; if (HIGH_BITS_OFFSET) retinfo->port_high = (long) uport->iobase >> HIGH_BITS_OFFSET; retinfo->irq = uport->irq; retinfo->flags = (__force int)uport->flags; retinfo->xmit_fifo_size = uport->fifosize; retinfo->baud_base = uport->uartclk / 16; retinfo->close_delay = jiffies_to_msecs(port->close_delay) / 10; retinfo->closing_wait = port->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : jiffies_to_msecs(port->closing_wait) / 10; retinfo->custom_divisor = uport->custom_divisor; retinfo->hub6 = uport->hub6; retinfo->io_type = uport->iotype; retinfo->iomem_reg_shift = uport->regshift; retinfo->iomem_base = (void *)(unsigned long)uport->mapbase; return 0; } static int uart_get_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; return uart_get_info(port, ss) < 0 ? -EIO : 0; } static int uart_change_port(struct uart_port *uport, const struct serial_struct *new_info, unsigned long new_port) { unsigned long old_iobase, old_mapbase; unsigned int old_type, old_iotype, old_hub6, old_shift; int retval; old_iobase = uport->iobase; old_mapbase = uport->mapbase; old_type = uport->type; old_hub6 = uport->hub6; old_iotype = uport->iotype; old_shift = uport->regshift; if (old_type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); uport->iobase = new_port; uport->type = new_info->type; uport->hub6 = new_info->hub6; uport->iotype = new_info->io_type; uport->regshift = new_info->iomem_reg_shift; uport->mapbase = (unsigned long)new_info->iomem_base; if (uport->type == PORT_UNKNOWN || !uport->ops->request_port) return 0; retval = uport->ops->request_port(uport); if (retval == 0) return 0; /* succeeded => done */ /* * If we fail to request resources for the new port, try to restore the * old settings. */ uport->iobase = old_iobase; uport->type = old_type; uport->hub6 = old_hub6; uport->iotype = old_iotype; uport->regshift = old_shift; uport->mapbase = old_mapbase; if (old_type == PORT_UNKNOWN) return retval; retval = uport->ops->request_port(uport); /* If we failed to restore the old settings, we fail like this. */ if (retval) uport->type = PORT_UNKNOWN; /* We failed anyway. */ return -EBUSY; } static int uart_set_info(struct tty_struct *tty, struct tty_port *port, struct uart_state *state, struct serial_struct *new_info) { struct uart_port *uport = uart_port_check(state); unsigned long new_port; unsigned int change_irq, change_port, closing_wait; unsigned int old_custom_divisor, close_delay; upf_t old_flags, new_flags; int retval; if (!uport) return -EIO; new_port = new_info->port; if (HIGH_BITS_OFFSET) new_port += (unsigned long) new_info->port_high << HIGH_BITS_OFFSET; new_info->irq = irq_canonicalize(new_info->irq); close_delay = msecs_to_jiffies(new_info->close_delay * 10); closing_wait = new_info->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : msecs_to_jiffies(new_info->closing_wait * 10); change_irq = !(uport->flags & UPF_FIXED_PORT) && new_info->irq != uport->irq; /* * Since changing the 'type' of the port changes its resource * allocations, we should treat type changes the same as * IO port changes. */ change_port = !(uport->flags & UPF_FIXED_PORT) && (new_port != uport->iobase || (unsigned long)new_info->iomem_base != uport->mapbase || new_info->hub6 != uport->hub6 || new_info->io_type != uport->iotype || new_info->iomem_reg_shift != uport->regshift || new_info->type != uport->type); old_flags = uport->flags; new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; if (!(uport->flags & UPF_FIXED_PORT)) { unsigned int uartclk = new_info->baud_base * 16; /* check needs to be done here before other settings made */ if (uartclk == 0) return -EINVAL; } if (!capable(CAP_SYS_ADMIN)) { if (change_irq || change_port || (new_info->baud_base != uport->uartclk / 16) || (close_delay != port->close_delay) || (closing_wait != port->closing_wait) || (new_info->xmit_fifo_size && new_info->xmit_fifo_size != uport->fifosize) || (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0)) return -EPERM; uport->flags = ((uport->flags & ~UPF_USR_MASK) | (new_flags & UPF_USR_MASK)); uport->custom_divisor = new_info->custom_divisor; goto check_and_exit; } if (change_irq || change_port) { retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); if (retval) return retval; } /* Ask the low level driver to verify the settings. */ if (uport->ops->verify_port) { retval = uport->ops->verify_port(uport, new_info); if (retval) return retval; } if ((new_info->irq >= irq_get_nr_irqs()) || (new_info->irq < 0) || (new_info->baud_base < 9600)) return -EINVAL; if (change_port || change_irq) { /* Make sure that we are the sole user of this port. */ if (tty_port_users(port) > 1) return -EBUSY; /* * We need to shutdown the serial port at the old * port/type/irq combination. */ uart_shutdown(tty, state); } if (change_port) { retval = uart_change_port(uport, new_info, new_port); if (retval) return retval; } if (change_irq) uport->irq = new_info->irq; if (!(uport->flags & UPF_FIXED_PORT)) uport->uartclk = new_info->baud_base * 16; uport->flags = (uport->flags & ~UPF_CHANGE_MASK) | (new_flags & UPF_CHANGE_MASK); uport->custom_divisor = new_info->custom_divisor; port->close_delay = close_delay; port->closing_wait = closing_wait; if (new_info->xmit_fifo_size) uport->fifosize = new_info->xmit_fifo_size; check_and_exit: if (uport->type == PORT_UNKNOWN) return 0; if (tty_port_initialized(port)) { if (((old_flags ^ uport->flags) & UPF_SPD_MASK) || old_custom_divisor != uport->custom_divisor) { /* * If they're setting up a custom divisor or speed, * instead of clearing it, then bitch about it. */ if (uport->flags & UPF_SPD_MASK) { dev_notice_ratelimited(uport->dev, "%s sets custom speed on %s. This is deprecated.\n", current->comm, tty_name(port->tty)); } uart_change_line_settings(tty, state, NULL); } return 0; } retval = uart_startup(tty, state, true); if (retval < 0) return retval; if (retval == 0) tty_port_set_initialized(port, true); return 0; } static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; int retval; down_write(&tty->termios_rwsem); /* * This semaphore protects port->count. It is also * very useful to prevent opens. Also, take the * port configuration semaphore to make sure that a * module insertion/removal doesn't change anything * under us. */ mutex_lock(&port->mutex); retval = uart_set_info(tty, port, state, ss); mutex_unlock(&port->mutex); up_write(&tty->termios_rwsem); return retval; } /** * uart_get_lsr_info - get line status register info * @tty: tty associated with the UART * @state: UART being queried * @value: returned modem value */ static int uart_get_lsr_info(struct tty_struct *tty, struct uart_state *state, unsigned int __user *value) { struct uart_port *uport = uart_port_check(state); unsigned int result; result = uport->ops->tx_empty(uport); /* * If we're about to load something into the transmit * register, we'll pretend the transmitter isn't empty to * avoid a race condition (depending on when the transmit * interrupt happens). */ if (uport->x_char || (!kfifo_is_empty(&state->port.xmit_fifo) && !uart_tx_stopped(uport))) result &= ~TIOCSER_TEMT; return put_user(result, value); } static int uart_tiocmget(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; int result; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; uart_port_lock_irq(uport); result = uport->mctrl; result |= uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); return result; } static int uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; uart_update_mctrl(uport, set, clear); return 0; } static int uart_break_ctl(struct tty_struct *tty, int break_state) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -EIO; if (uport->type != PORT_UNKNOWN && uport->ops->break_ctl) uport->ops->break_ctl(uport, break_state); return 0; } static int uart_do_autoconfig(struct tty_struct *tty, struct uart_state *state) { struct tty_port *port = &state->port; struct uart_port *uport; int flags, ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Take the per-port semaphore. This prevents count from * changing, and hence any extra opens of the port while * we're auto-configuring. */ scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &port->mutex) { uport = uart_port_check(state); if (!uport) return -EIO; if (tty_port_users(port) != 1) return -EBUSY; uart_shutdown(tty, state); /* * If we already have a port type configured, * we must release its resources. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); flags = UART_CONFIG_TYPE; if (uport->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; /* * This will claim the ports resources if * a port is found. */ uport->ops->config_port(uport, flags); ret = uart_startup(tty, state, true); if (ret < 0) return ret; if (ret > 0) return 0; tty_port_set_initialized(port, true); } return 0; } static void uart_enable_ms(struct uart_port *uport) { /* * Force modem status interrupts on */ if (uport->ops->enable_ms) uport->ops->enable_ms(uport); } /* * Wait for any of the 4 modem inputs (DCD,RI,DSR,CTS) to change * - mask passed in arg for lines of interest * (use |'ed TIOCM_RNG/DSR/CD/CTS for masking) * Caller should use TIOCGICOUNT to see which one it was * * FIXME: This wants extracting into a common all driver implementation * of TIOCMWAIT using tty_port. */ static int uart_wait_modem_status(struct uart_state *state, unsigned long arg) { struct uart_port *uport; struct tty_port *port = &state->port; DECLARE_WAITQUEUE(wait, current); struct uart_icount cprev, cnow; int ret; /* * note the counters on entry */ uport = uart_port_ref(state); if (!uport) return -EIO; uart_port_lock_irq(uport); memcpy(&cprev, &uport->icount, sizeof(struct uart_icount)); uart_enable_ms(uport); uart_port_unlock_irq(uport); add_wait_queue(&port->delta_msr_wait, &wait); for (;;) { uart_port_lock_irq(uport); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); uart_port_unlock_irq(uport); set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd)) || ((arg & TIOCM_CTS) && (cnow.cts != cprev.cts))) { ret = 0; break; } schedule(); /* see if a signal did it */ if (signal_pending(current)) { ret = -ERESTARTSYS; break; } cprev = cnow; } __set_current_state(TASK_RUNNING); remove_wait_queue(&port->delta_msr_wait, &wait); uart_port_deref(uport); return ret; } /* * Get counter of input serial line interrupts (DCD,RI,DSR,CTS) * Return: write counters to the user passed counter struct * NB: both 1->0 and 0->1 transitions are counted except for * RI where only 0->1 is counted. */ static int uart_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { struct uart_state *state = tty->driver_data; struct uart_icount cnow; struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return -EIO; uart_port_lock_irq(uport); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); uart_port_unlock_irq(uport); uart_port_deref(uport); icount->cts = cnow.cts; icount->dsr = cnow.dsr; icount->rng = cnow.rng; icount->dcd = cnow.dcd; icount->rx = cnow.rx; icount->tx = cnow.tx; icount->frame = cnow.frame; icount->overrun = cnow.overrun; icount->parity = cnow.parity; icount->brk = cnow.brk; icount->buf_overrun = cnow.buf_overrun; return 0; } #define SER_RS485_LEGACY_FLAGS (SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | \ SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX | \ SER_RS485_TERMINATE_BUS) static int uart_check_rs485_flags(struct uart_port *port, struct serial_rs485 *rs485) { u32 flags = rs485->flags; /* Don't return -EINVAL for unsupported legacy flags */ flags &= ~SER_RS485_LEGACY_FLAGS; /* * For any bit outside of the legacy ones that is not supported by * the driver, return -EINVAL. */ if (flags & ~port->rs485_supported.flags) return -EINVAL; /* Asking for address w/o addressing mode? */ if (!(rs485->flags & SER_RS485_ADDRB) && (rs485->flags & (SER_RS485_ADDR_RECV|SER_RS485_ADDR_DEST))) return -EINVAL; /* Address given but not enabled? */ if (!(rs485->flags & SER_RS485_ADDR_RECV) && rs485->addr_recv) return -EINVAL; if (!(rs485->flags & SER_RS485_ADDR_DEST) && rs485->addr_dest) return -EINVAL; return 0; } static void uart_sanitize_serial_rs485_delays(struct uart_port *port, struct serial_rs485 *rs485) { if (!port->rs485_supported.delay_rts_before_send) { if (rs485->delay_rts_before_send) { dev_warn_ratelimited(port->dev, "%s (%d): RTS delay before sending not supported\n", port->name, port->line); } rs485->delay_rts_before_send = 0; } else if (rs485->delay_rts_before_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_before_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay before sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_before_send); } if (!port->rs485_supported.delay_rts_after_send) { if (rs485->delay_rts_after_send) { dev_warn_ratelimited(port->dev, "%s (%d): RTS delay after sending not supported\n", port->name, port->line); } rs485->delay_rts_after_send = 0; } else if (rs485->delay_rts_after_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_after_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay after sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_after_send); } } static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs485 *rs485) { u32 supported_flags = port->rs485_supported.flags; if (!(rs485->flags & SER_RS485_ENABLED)) { memset(rs485, 0, sizeof(*rs485)); return; } /* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */ if (rs485->flags & SER_RS485_MODE_RS422) { rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS); return; } rs485->flags &= supported_flags; /* Pick sane settings if the user hasn't */ if (!(rs485->flags & SER_RS485_RTS_ON_SEND) == !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) { if (supported_flags & SER_RS485_RTS_ON_SEND) { rs485->flags |= SER_RS485_RTS_ON_SEND; rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; dev_warn_ratelimited(port->dev, "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", port->name, port->line); } else { rs485->flags |= SER_RS485_RTS_AFTER_SEND; rs485->flags &= ~SER_RS485_RTS_ON_SEND; dev_warn_ratelimited(port->dev, "%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n", port->name, port->line); } } uart_sanitize_serial_rs485_delays(port, rs485); /* Return clean padding area to userspace */ memset(rs485->padding0, 0, sizeof(rs485->padding0)); memset(rs485->padding1, 0, sizeof(rs485->padding1)); } static void uart_set_rs485_termination(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_term_gpio, !!(rs485->flags & SER_RS485_TERMINATE_BUS)); } static void uart_set_rs485_rx_during_tx(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(rs485->flags & SER_RS485_RX_DURING_TX)); } static int uart_rs485_config(struct uart_port *port) { struct serial_rs485 *rs485 = &port->rs485; unsigned long flags; int ret; if (!(rs485->flags & SER_RS485_ENABLED)) return 0; uart_sanitize_serial_rs485(port, rs485); uart_set_rs485_termination(port, rs485); uart_set_rs485_rx_during_tx(port, rs485); uart_port_lock_irqsave(port, &flags); ret = port->rs485_config(port, NULL, rs485); uart_port_unlock_irqrestore(port, flags); if (ret) { memset(rs485, 0, sizeof(*rs485)); /* unset GPIOs */ gpiod_set_value_cansleep(port->rs485_term_gpio, 0); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, 0); } return ret; } static int uart_get_rs485_config(struct uart_port *port, struct serial_rs485 __user *rs485) { unsigned long flags; struct serial_rs485 aux; uart_port_lock_irqsave(port, &flags); aux = port->rs485; uart_port_unlock_irqrestore(port, flags); if (copy_to_user(rs485, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port, struct serial_rs485 __user *rs485_user) { struct serial_rs485 rs485; int ret; unsigned long flags; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return -ENOTTY; if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) return -EFAULT; ret = uart_check_rs485_flags(port, &rs485); if (ret) return ret; uart_sanitize_serial_rs485(port, &rs485); uart_set_rs485_termination(port, &rs485); uart_set_rs485_rx_during_tx(port, &rs485); uart_port_lock_irqsave(port, &flags); ret = port->rs485_config(port, &tty->termios, &rs485); if (!ret) { port->rs485 = rs485; /* Reset RTS and other mctrl lines when disabling RS485 */ if (!(rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } uart_port_unlock_irqrestore(port, flags); if (ret) { /* restore old GPIO settings */ gpiod_set_value_cansleep(port->rs485_term_gpio, !!(port->rs485.flags & SER_RS485_TERMINATE_BUS)); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(port->rs485.flags & SER_RS485_RX_DURING_TX)); return ret; } if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485))) return -EFAULT; return 0; } static int uart_get_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816) { unsigned long flags; struct serial_iso7816 aux; if (!port->iso7816_config) return -ENOTTY; uart_port_lock_irqsave(port, &flags); aux = port->iso7816; uart_port_unlock_irqrestore(port, flags); if (copy_to_user(iso7816, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816_user) { struct serial_iso7816 iso7816; int i, ret; unsigned long flags; if (!port->iso7816_config) return -ENOTTY; if (copy_from_user(&iso7816, iso7816_user, sizeof(*iso7816_user))) return -EFAULT; /* * There are 5 words reserved for future use. Check that userspace * doesn't put stuff in there to prevent breakages in the future. */ for (i = 0; i < ARRAY_SIZE(iso7816.reserved); i++) if (iso7816.reserved[i]) return -EINVAL; uart_port_lock_irqsave(port, &flags); ret = port->iso7816_config(port, &iso7816); uart_port_unlock_irqrestore(port, flags); if (ret) return ret; if (copy_to_user(iso7816_user, &port->iso7816, sizeof(port->iso7816))) return -EFAULT; return 0; } /* * Called via sys_ioctl. We can use spin_lock_irq() here. */ static int uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; void __user *uarg = (void __user *)arg; int ret = -ENOIOCTLCMD; /* * These ioctls don't rely on the hardware to be present. */ switch (cmd) { case TIOCSERCONFIG: down_write(&tty->termios_rwsem); ret = uart_do_autoconfig(tty, state); up_write(&tty->termios_rwsem); break; } if (ret != -ENOIOCTLCMD) goto out; if (tty_io_error(tty)) { ret = -EIO; goto out; } /* * The following should only be used when hardware is present. */ switch (cmd) { case TIOCMIWAIT: ret = uart_wait_modem_status(state, arg); break; } if (ret != -ENOIOCTLCMD) goto out; /* rs485_config requires more locking than others */ if (cmd == TIOCSRS485) down_write(&tty->termios_rwsem); mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) { ret = -EIO; goto out_up; } /* * All these rely on hardware being present and need to be * protected against the tty being hung up. */ switch (cmd) { case TIOCSERGETLSR: /* Get line status register */ ret = uart_get_lsr_info(tty, state, uarg); break; case TIOCGRS485: ret = uart_get_rs485_config(uport, uarg); break; case TIOCSRS485: ret = uart_set_rs485_config(tty, uport, uarg); break; case TIOCSISO7816: ret = uart_set_iso7816_config(state->uart_port, uarg); break; case TIOCGISO7816: ret = uart_get_iso7816_config(state->uart_port, uarg); break; default: if (uport->ops->ioctl) ret = uport->ops->ioctl(uport, cmd, arg); break; } out_up: mutex_unlock(&port->mutex); if (cmd == TIOCSRS485) up_write(&tty->termios_rwsem); out: return ret; } static void uart_set_ldisc(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *uport; struct tty_port *port = &state->port; if (!tty_port_initialized(port)) return; mutex_lock(&state->port.mutex); uport = uart_port_check(state); if (uport && uport->ops->set_ldisc) uport->ops->set_ldisc(uport, &tty->termios); mutex_unlock(&state->port.mutex); } static void uart_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { struct uart_state *state = tty->driver_data; struct uart_port *uport; unsigned int cflag = tty->termios.c_cflag; unsigned int iflag_mask = IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK; bool sw_changed = false; guard(mutex)(&state->port.mutex); uport = uart_port_check(state); if (!uport) return; /* * Drivers doing software flow control also need to know * about changes to these input settings. */ if (uport->flags & UPF_SOFT_FLOW) { iflag_mask |= IXANY|IXON|IXOFF; sw_changed = tty->termios.c_cc[VSTART] != old_termios->c_cc[VSTART] || tty->termios.c_cc[VSTOP] != old_termios->c_cc[VSTOP]; } /* * These are the bits that are used to setup various * flags in the low level driver. We can ignore the Bfoo * bits in c_cflag; c_[io]speed will always be set * appropriately by set_termios() in tty_ioctl.c */ if ((cflag ^ old_termios->c_cflag) == 0 && tty->termios.c_ospeed == old_termios->c_ospeed && tty->termios.c_ispeed == old_termios->c_ispeed && ((tty->termios.c_iflag ^ old_termios->c_iflag) & iflag_mask) == 0 && !sw_changed) return; uart_change_line_settings(tty, state, old_termios); /* reload cflag from termios; port driver may have overridden flags */ cflag = tty->termios.c_cflag; /* Handle transition to B0 status */ if (((old_termios->c_cflag & CBAUD) != B0) && ((cflag & CBAUD) == B0)) uart_clear_mctrl(uport, TIOCM_RTS | TIOCM_DTR); /* Handle transition away from B0 status */ else if (((old_termios->c_cflag & CBAUD) == B0) && ((cflag & CBAUD) != B0)) { unsigned int mask = TIOCM_DTR; if (!(cflag & CRTSCTS) || !tty_throttled(tty)) mask |= TIOCM_RTS; uart_set_mctrl(uport, mask); } } /* * Calls to uart_close() are serialised via the tty_lock in * drivers/tty/tty_io.c:tty_release() * drivers/tty/tty_io.c:do_tty_hangup() */ static void uart_close(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; if (!state) { struct uart_driver *drv = tty->driver->driver_state; struct tty_port *port; state = drv->state + tty->index; port = &state->port; spin_lock_irq(&port->lock); --port->count; spin_unlock_irq(&port->lock); return; } pr_debug("uart_close(%d) called\n", tty->index); tty_port_close(tty->port, tty, filp); } static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * At this point, we stop accepting input. To do this, we * disable the receive line status interrupts. */ if (WARN(!uport, "detached port still initialized!\n")) return; uart_port_lock_irq(uport); uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); serial_base_port_shutdown(uport); uart_port_shutdown(port); /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long char_time, expire, fifo_timeout; port = uart_port_ref(state); if (!port) return; if (port->type == PORT_UNKNOWN || port->fifosize == 0) { uart_port_deref(port); return; } /* * Set the check interval to be 1/5 of the estimated time to * send a single character, and make it at least 1. The check * interval should also be less than the timeout. * * Note: we have to use pretty tight timings here to satisfy * the NIST-PCTS. */ char_time = max(nsecs_to_jiffies(port->frame_time / 5), 1UL); if (timeout && timeout < char_time) char_time = timeout; if (!uart_cts_enabled(port)) { /* * If the transmitter hasn't cleared in twice the approximate * amount of time to send the entire FIFO, it probably won't * ever clear. This assumes the UART isn't doing flow * control, which is currently the case. Hence, if it ever * takes longer than FIFO timeout, this is probably due to a * UART bug of some kind. So, we clamp the timeout parameter at * 2 * FIFO timeout. */ fifo_timeout = uart_fifo_timeout(port); if (timeout == 0 || timeout > 2 * fifo_timeout) timeout = 2 * fifo_timeout; } expire = jiffies + timeout; pr_debug("uart_wait_until_sent(%d), jiffies=%lu, expire=%lu...\n", port->line, jiffies, expire); /* * Check whether the transmitter is empty every 'char_time'. * 'timeout' / 'expire' give us the maximum amount of time * we wait. */ while (!port->ops->tx_empty(port)) { msleep_interruptible(jiffies_to_msecs(char_time)); if (signal_pending(current)) break; if (timeout && time_after(jiffies, expire)) break; } uart_port_deref(port); } /* * Calls to uart_hangup() are serialised by the tty_lock in * drivers/tty/tty_io.c:do_tty_hangup() * This runs from a workqueue and can sleep for a _short_ time only. */ static void uart_hangup(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; unsigned long flags; pr_debug("uart_hangup(%d)\n", tty->index); mutex_lock(&port->mutex); uport = uart_port_check(state); WARN(!uport, "hangup of detached port!\n"); if (tty_port_active(port)) { uart_flush_buffer(tty); uart_shutdown(tty, state); spin_lock_irqsave(&port->lock, flags); port->count = 0; spin_unlock_irqrestore(&port->lock, flags); tty_port_set_active(port, false); tty_port_tty_set(port, NULL); if (uport && !uart_console(uport)) uart_change_pm(state, UART_PM_STATE_OFF); wake_up_interruptible(&port->open_wait); wake_up_interruptible(&port->delta_msr_wait); } mutex_unlock(&port->mutex); } /* uport == NULL if uart_port has already been removed */ static void uart_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * clear delta_msr_wait queue to avoid mem leaks: we may free * the irq here so the queue might never be woken up. Note * that we won't end up waiting on delta_msr_wait again since * any outstanding file descriptors should be pointing at * hung_up_tty_fops now. */ wake_up_interruptible(&port->delta_msr_wait); if (uport) { /* Free the IRQ and disable the port. */ uport->ops->shutdown(uport); /* Ensure that the IRQ handler isn't running on another CPU. */ synchronize_irq(uport->irq); } } static bool uart_carrier_raised(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int mctrl; uport = uart_port_ref(state); /* * Should never observe uport == NULL since checks for hangup should * abort the tty_port_block_til_ready() loop before checking for carrier * raised -- but report carrier raised if it does anyway so open will * continue and not sleep */ if (WARN_ON(!uport)) return true; uart_port_lock_irq(uport); uart_enable_ms(uport); mctrl = uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); uart_port_deref(uport); return mctrl & TIOCM_CAR; } static void uart_dtr_rts(struct tty_port *port, bool active) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return; uart_port_dtr_rts(uport, active); uart_port_deref(uport); } static int uart_install(struct tty_driver *driver, struct tty_struct *tty) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + tty->index; tty->driver_data = state; return tty_standard_install(driver, tty); } /* * Calls to uart_open are serialised by the tty_lock in * drivers/tty/tty_io.c:tty_open() * Note that if this fails, then uart_close() _will_ be called. * * In time, we want to scrap the "opening nonpresent ports" * behaviour and implement an alternative way for setserial * to set base addresses/ports/types. This will allow us to * get rid of a certain amount of extra tests. */ static int uart_open(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; int retval; retval = tty_port_open(&state->port, tty, filp); if (retval > 0) retval = 0; return retval; } static int uart_port_activate(struct tty_port *port, struct tty_struct *tty) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret; uport = uart_port_check(state); if (!uport || uport->flags & UPF_DEAD) return -ENXIO; /* * Start up the serial port. */ ret = uart_startup(tty, state, false); if (ret > 0) tty_port_set_active(port, true); return ret; } static const char *uart_type(struct uart_port *port) { const char *str = NULL; if (port->ops->type) str = port->ops->type(port); if (!str) str = "unknown"; return str; } #ifdef CONFIG_PROC_FS static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; enum uart_pm_state pm_state; struct uart_port *uport; char stat_buf[32]; unsigned int status; int mmio; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return; mmio = uport->iotype >= UPIO_MEM; seq_printf(m, "%d: uart:%s %s%08llX irq:%d", uport->line, uart_type(uport), mmio ? "mmio:0x" : "port:", mmio ? (unsigned long long)uport->mapbase : (unsigned long long)uport->iobase, uport->irq); if (uport->type == PORT_UNKNOWN) { seq_putc(m, '\n'); return; } if (capable(CAP_SYS_ADMIN)) { pm_state = state->pm_state; if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, UART_PM_STATE_ON); uart_port_lock_irq(uport); status = uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, pm_state); seq_printf(m, " tx:%d rx:%d", uport->icount.tx, uport->icount.rx); if (uport->icount.frame) seq_printf(m, " fe:%d", uport->icount.frame); if (uport->icount.parity) seq_printf(m, " pe:%d", uport->icount.parity); if (uport->icount.brk) seq_printf(m, " brk:%d", uport->icount.brk); if (uport->icount.overrun) seq_printf(m, " oe:%d", uport->icount.overrun); if (uport->icount.buf_overrun) seq_printf(m, " bo:%d", uport->icount.buf_overrun); #define INFOBIT(bit, str) \ if (uport->mctrl & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) #define STATBIT(bit, str) \ if (status & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) stat_buf[0] = '\0'; stat_buf[1] = '\0'; INFOBIT(TIOCM_RTS, "|RTS"); STATBIT(TIOCM_CTS, "|CTS"); INFOBIT(TIOCM_DTR, "|DTR"); STATBIT(TIOCM_DSR, "|DSR"); STATBIT(TIOCM_CAR, "|CD"); STATBIT(TIOCM_RNG, "|RI"); if (stat_buf[0]) stat_buf[0] = ' '; seq_puts(m, stat_buf); } seq_putc(m, '\n'); #undef STATBIT #undef INFOBIT } static int uart_proc_show(struct seq_file *m, void *v) { struct tty_driver *ttydrv = m->private; struct uart_driver *drv = ttydrv->driver_state; int i; seq_printf(m, "serinfo:1.0 driver%s%s revision:%s\n", "", "", ""); for (i = 0; i < drv->nr; i++) uart_line_info(m, drv, i); return 0; } #endif static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); lockdep_set_class(&port->lock, &port_lock_key); } #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL) /** * uart_console_write - write a console message to a serial port * @port: the port to write the message * @s: array of characters * @count: number of characters in string to write * @putchar: function to write character to port */ void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)) { unsigned int i; for (i = 0; i < count; i++, s++) { if (*s == '\n') putchar(port, '\r'); putchar(port, *s); } } EXPORT_SYMBOL_GPL(uart_console_write); /** * uart_get_console - get uart port for console * @ports: ports to search in * @nr: number of @ports * @co: console to search for * Returns: uart_port for the console @co * * Check whether an invalid uart number has been specified (as @co->index), and * if so, search for the first available port that does have console support. */ struct uart_port * __init uart_get_console(struct uart_port *ports, int nr, struct console *co) { int idx = co->index; if (idx < 0 || idx >= nr || (ports[idx].iobase == 0 && ports[idx].membase == NULL)) for (idx = 0; idx < nr; idx++) if (ports[idx].iobase != 0 || ports[idx].membase != NULL) break; co->index = idx; return ports + idx; } /** * uart_parse_earlycon - Parse earlycon options * @p: ptr to 2nd field (ie., just beyond '<name>,') * @iotype: ptr for decoded iotype (out) * @addr: ptr for decoded mapbase/iobase (out) * @options: ptr for <options> field; %NULL if not present (out) * * Decodes earlycon kernel command line parameters of the form: * * earlycon=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * console=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * The optional form: * * earlycon=<name>,0x<addr>,<options> * * console=<name>,0x<addr>,<options> * * is also accepted; the returned @iotype will be %UPIO_MEM. * * Returns: 0 on success or -%EINVAL on failure */ int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options) { if (strncmp(p, "mmio,", 5) == 0) { *iotype = UPIO_MEM; p += 5; } else if (strncmp(p, "mmio16,", 7) == 0) { *iotype = UPIO_MEM16; p += 7; } else if (strncmp(p, "mmio32,", 7) == 0) { *iotype = UPIO_MEM32; p += 7; } else if (strncmp(p, "mmio32be,", 9) == 0) { *iotype = UPIO_MEM32BE; p += 9; } else if (strncmp(p, "mmio32native,", 13) == 0) { *iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ? UPIO_MEM32BE : UPIO_MEM32; p += 13; } else if (strncmp(p, "io,", 3) == 0) { *iotype = UPIO_PORT; p += 3; } else if (strncmp(p, "0x", 2) == 0) { *iotype = UPIO_MEM; } else { return -EINVAL; } /* * Before you replace it with kstrtoull(), think about options separator * (',') it will not tolerate */ *addr = simple_strtoull(p, NULL, 0); p = strchr(p, ','); if (p) p++; *options = p; return 0; } EXPORT_SYMBOL_GPL(uart_parse_earlycon); /** * uart_parse_options - Parse serial port baud/parity/bits/flow control. * @options: pointer to option string * @baud: pointer to an 'int' variable for the baud rate. * @parity: pointer to an 'int' variable for the parity. * @bits: pointer to an 'int' variable for the number of data bits. * @flow: pointer to an 'int' variable for the flow control character. * * uart_parse_options() decodes a string containing the serial console * options. The format of the string is <baud><parity><bits><flow>, * eg: 115200n8r */ void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow) { const char *s = options; *baud = simple_strtoul(s, NULL, 10); while (*s >= '0' && *s <= '9') s++; if (*s) *parity = *s++; if (*s) *bits = *s++ - '0'; if (*s) *flow = *s; } EXPORT_SYMBOL_GPL(uart_parse_options); /** * uart_set_options - setup the serial console parameters * @port: pointer to the serial ports uart_port structure * @co: console pointer * @baud: baud rate * @parity: parity character - 'n' (none), 'o' (odd), 'e' (even) * @bits: number of data bits * @flow: flow control character - 'r' (rts) * * Locking: Caller must hold console_list_lock in order to serialize * early initialization of the serial-console lock. */ int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow) { struct ktermios termios; static struct ktermios dummy; /* * Ensure that the serial-console lock is initialised early. * * Note that the console-registered check is needed because * kgdboc can call uart_set_options() for an already registered * console via tty_find_polling_driver() and uart_poll_init(). */ if (!uart_console_registered_locked(port) && !port->console_reinit) uart_port_spin_lock_init(port); memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag |= CREAD | HUPCL | CLOCAL; tty_termios_encode_baud_rate(&termios, baud, baud); if (bits == 7) termios.c_cflag |= CS7; else termios.c_cflag |= CS8; switch (parity) { case 'o': case 'O': termios.c_cflag |= PARODD; fallthrough; case 'e': case 'E': termios.c_cflag |= PARENB; break; } if (flow == 'r') termios.c_cflag |= CRTSCTS; /* * some uarts on other side don't support no flow control. * So we set * DTR in host uart to make them happy */ port->mctrl |= TIOCM_DTR; port->ops->set_termios(port, &termios, &dummy); /* * Allow the setting of the UART parameters with a NULL console * too: */ if (co) { co->cflag = termios.c_cflag; co->ispeed = termios.c_ispeed; co->ospeed = termios.c_ospeed; } return 0; } EXPORT_SYMBOL_GPL(uart_set_options); #endif /* CONFIG_SERIAL_CORE_CONSOLE */ /** * uart_change_pm - set power state of the port * * @state: port descriptor * @pm_state: new state * * Locking: port->mutex has to be held */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state) { struct uart_port *port = uart_port_check(state); if (state->pm_state != pm_state) { if (port && port->ops->pm) port->ops->pm(port, pm_state, state->pm_state); state->pm_state = pm_state; } } struct uart_match { struct uart_port *port; struct uart_driver *driver; }; static int serial_match_port(struct device *dev, const void *data) { const struct uart_match *match = data; struct tty_driver *tty_drv = match->driver->tty_driver; dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) + match->port->line; return dev->devt == devt; /* Actually, only one tty per port */ } int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (tty_dev && device_may_wakeup(tty_dev)) { enable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); /* * Nothing to do if the console is not suspending * except stop_rx to prevent any asynchronous data * over RX line. However ensure that we will be * able to Re-start_rx later. */ if (!console_suspend_enabled && uart_console(uport)) { if (uport->ops->start_rx) { uart_port_lock_irq(uport); uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); } device_set_awake_path(uport->dev); return 0; } uport->suspended = 1; if (tty_port_initialized(port)) { const struct uart_ops *ops = uport->ops; int tries; unsigned int mctrl; tty_port_set_suspended(port, true); tty_port_set_initialized(port, false); uart_port_lock_irq(uport); ops->stop_tx(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); /* save mctrl so it can be restored on resume */ mctrl = uport->mctrl; uport->mctrl = 0; ops->stop_rx(uport); uart_port_unlock_irq(uport); /* * Wait for the transmitter to empty. */ for (tries = 3; !ops->tx_empty(uport) && tries; tries--) msleep(10); if (!tries) dev_err(uport->dev, "%s: Unable to drain transmitter\n", uport->name); ops->shutdown(uport); uport->mctrl = mctrl; } /* * Disable the console device before suspending. */ if (uart_console(uport)) console_stop(uport->cons); uart_change_pm(state, UART_PM_STATE_OFF); return 0; } EXPORT_SYMBOL(uart_suspend_port); int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; struct ktermios termios; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (!uport->suspended && device_may_wakeup(tty_dev)) { if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq)))) disable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); uport->suspended = 0; /* * Re-enable the console device after suspending. */ if (uart_console(uport)) { /* * First try to use the console cflag setting. */ memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag = uport->cons->cflag; termios.c_ispeed = uport->cons->ispeed; termios.c_ospeed = uport->cons->ospeed; /* * If that's unset, use the tty termios setting. */ if (port->tty && termios.c_cflag == 0) termios = port->tty->termios; if (console_suspend_enabled) uart_change_pm(state, UART_PM_STATE_ON); uport->ops->set_termios(uport, &termios, NULL); if (!console_suspend_enabled && uport->ops->start_rx) { uart_port_lock_irq(uport); uport->ops->start_rx(uport); uart_port_unlock_irq(uport); } if (console_suspend_enabled) console_start(uport->cons); } if (tty_port_suspended(port)) { const struct uart_ops *ops = uport->ops; int ret; uart_change_pm(state, UART_PM_STATE_ON); uart_port_lock_irq(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); uart_port_unlock_irq(uport); if (console_suspend_enabled || !uart_console(uport)) { /* Protected by port mutex for now */ struct tty_struct *tty = port->tty; ret = ops->startup(uport); if (ret == 0) { if (tty) uart_change_line_settings(tty, state, NULL); uart_rs485_config(uport); uart_port_lock_irq(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); ops->start_tx(uport); uart_port_unlock_irq(uport); tty_port_set_initialized(port, true); } else { /* * Failed to resume - maybe hardware went away? * Clear the "initialized" flag so we won't try * to call the low level drivers shutdown method. */ uart_shutdown(tty, state); } } tty_port_set_suspended(port, false); } return 0; } EXPORT_SYMBOL(uart_resume_port); static inline void uart_report_port(struct uart_driver *drv, struct uart_port *port) { char address[64]; switch (port->iotype) { case UPIO_PORT: snprintf(address, sizeof(address), "I/O 0x%lx", port->iobase); break; case UPIO_HUB6: snprintf(address, sizeof(address), "I/O 0x%lx offset 0x%x", port->iobase, port->hub6); break; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: snprintf(address, sizeof(address), "MMIO 0x%llx", (unsigned long long)port->mapbase); break; default: strscpy(address, "*unknown*", sizeof(address)); break; } pr_info("%s%s%s at %s (irq = %d, base_baud = %d) is a %s\n", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, address, port->irq, port->uartclk / 16, uart_type(port)); /* The magic multiplier feature is a bit obscure, so report it too. */ if (port->flags & UPF_MAGIC_MULTIPLIER) pr_info("%s%s%s extra baud rates supported: %d, %d", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, port->uartclk / 8, port->uartclk / 4); } static void uart_configure_port(struct uart_driver *drv, struct uart_state *state, struct uart_port *port) { unsigned int flags; /* * If there isn't a port here, don't do anything further. */ if (!port->iobase && !port->mapbase && !port->membase) return; /* * Now do the auto configuration stuff. Note that config_port * is expected to claim the resources and map the port for us. */ flags = 0; if (port->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; if (port->flags & UPF_BOOT_AUTOCONF) { if (!(port->flags & UPF_FIXED_TYPE)) { port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); port->ops->config_port(port, flags); if (uart_console(port)) console_unlock(); } if (port->type != PORT_UNKNOWN) { unsigned long flags; uart_report_port(drv, port); /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); /* * Ensure that the modem control lines are de-activated. * keep the DTR setting that is set in uart_set_options() * We probably don't need a spinlock around this, but */ uart_port_lock_irqsave(port, &flags); port->mctrl &= TIOCM_DTR; if (!(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); uart_port_unlock_irqrestore(port, flags); uart_rs485_config(port); if (uart_console(port)) console_unlock(); /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. * It may be that the port was not available. */ if (port->cons && !console_is_registered(port->cons)) register_console(port->cons); /* * Power down all ports by default, except the * console if we have one. */ if (!uart_console(port)) uart_change_pm(state, UART_PM_STATE_OFF); } } #ifdef CONFIG_CONSOLE_POLL static int uart_poll_init(struct tty_driver *driver, int line, char *options) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; enum uart_pm_state pm_state; struct tty_port *tport; struct uart_port *port; int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret = 0; tport = &state->port; guard(mutex)(&tport->mutex); port = uart_port_check(state); if (!port || port->type == PORT_UNKNOWN || !(port->ops->poll_get_char && port->ops->poll_put_char)) return -1; pm_state = state->pm_state; uart_change_pm(state, UART_PM_STATE_ON); if (port->ops->poll_init) { /* * We don't set initialized as we only initialized the hw, * e.g. state->xmit is still uninitialized. */ if (!tty_port_initialized(tport)) ret = port->ops->poll_init(port); } if (!ret && options) { uart_parse_options(options, &baud, &parity, &bits, &flow); console_list_lock(); ret = uart_set_options(port, NULL, baud, parity, bits, flow); console_list_unlock(); } if (ret) uart_change_pm(state, pm_state); return ret; } static int uart_poll_get_char(struct tty_driver *driver, int line) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; int ret = -1; port = uart_port_ref(state); if (port) { ret = port->ops->poll_get_char(port); uart_port_deref(port); } return ret; } static void uart_poll_put_char(struct tty_driver *driver, int line, char ch) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (ch == '\n') port->ops->poll_put_char(port, '\r'); port->ops->poll_put_char(port, ch); uart_port_deref(port); } #endif static const struct tty_operations uart_ops = { .install = uart_install, .open = uart_open, .close = uart_close, .write = uart_write, .put_char = uart_put_char, .flush_chars = uart_flush_chars, .write_room = uart_write_room, .chars_in_buffer= uart_chars_in_buffer, .flush_buffer = uart_flush_buffer, .ioctl = uart_ioctl, .throttle = uart_throttle, .unthrottle = uart_unthrottle, .send_xchar = uart_send_xchar, .set_termios = uart_set_termios, .set_ldisc = uart_set_ldisc, .stop = uart_stop, .start = uart_start, .hangup = uart_hangup, .break_ctl = uart_break_ctl, .wait_until_sent= uart_wait_until_sent, #ifdef CONFIG_PROC_FS .proc_show = uart_proc_show, #endif .tiocmget = uart_tiocmget, .tiocmset = uart_tiocmset, .set_serial = uart_set_info_user, .get_serial = uart_get_info_user, .get_icount = uart_get_icount, #ifdef CONFIG_CONSOLE_POLL .poll_init = uart_poll_init, .poll_get_char = uart_poll_get_char, .poll_put_char = uart_poll_put_char, #endif }; static const struct tty_port_operations uart_port_ops = { .carrier_raised = uart_carrier_raised, .dtr_rts = uart_dtr_rts, .activate = uart_port_activate, .shutdown = uart_tty_port_shutdown, }; /** * uart_register_driver - register a driver with the uart core layer * @drv: low level driver structure * * Register a uart driver with the core driver. We in turn register with the * tty layer, and initialise the core driver per-port state. * * We have a proc file in /proc/tty/driver which is named after the normal * driver. * * @drv->port should be %NULL, and the per-port structures should be registered * using uart_add_one_port() after this call has succeeded. * * Locking: none, Interrupts: enabled */ int uart_register_driver(struct uart_driver *drv) { struct tty_driver *normal; int i, retval = -ENOMEM; BUG_ON(drv->state); /* * Maybe we should be using a slab cache for this, especially if * we have a large number of ports to handle. */ drv->state = kcalloc(drv->nr, sizeof(struct uart_state), GFP_KERNEL); if (!drv->state) goto out; normal = tty_alloc_driver(drv->nr, TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(normal)) { retval = PTR_ERR(normal); goto out_kfree; } drv->tty_driver = normal; normal->driver_name = drv->driver_name; normal->name = drv->dev_name; normal->major = drv->major; normal->minor_start = drv->minor; normal->type = TTY_DRIVER_TYPE_SERIAL; normal->subtype = SERIAL_TYPE_NORMAL; normal->init_termios = tty_std_termios; normal->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; normal->init_termios.c_ispeed = normal->init_termios.c_ospeed = 9600; normal->driver_state = drv; tty_set_operations(normal, &uart_ops); /* * Initialise the UART state(s). */ for (i = 0; i < drv->nr; i++) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; tty_port_init(port); port->ops = &uart_port_ops; } retval = tty_register_driver(normal); if (retval >= 0) return retval; for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); tty_driver_kref_put(normal); out_kfree: kfree(drv->state); out: return retval; } EXPORT_SYMBOL(uart_register_driver); /** * uart_unregister_driver - remove a driver from the uart core layer * @drv: low level driver structure * * Remove all references to a driver from the core driver. The low level * driver must have removed all its ports via the uart_remove_one_port() if it * registered them with uart_add_one_port(). (I.e. @drv->port is %NULL.) * * Locking: none, Interrupts: enabled */ void uart_unregister_driver(struct uart_driver *drv) { struct tty_driver *p = drv->tty_driver; unsigned int i; tty_unregister_driver(p); tty_driver_kref_put(p); for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); kfree(drv->state); drv->state = NULL; drv->tty_driver = NULL; } EXPORT_SYMBOL(uart_unregister_driver); struct tty_driver *uart_console_device(struct console *co, int *index) { struct uart_driver *p = co->data; *index = co->index; return p->tty_driver; } EXPORT_SYMBOL_GPL(uart_console_device); static ssize_t uartclk_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.baud_base * 16); } static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.type); } static ssize_t line_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.line); } static ssize_t port_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); unsigned long ioaddr; uart_get_info(port, &tmp); ioaddr = tmp.port; if (HIGH_BITS_OFFSET) ioaddr |= (unsigned long)tmp.port_high << HIGH_BITS_OFFSET; return sprintf(buf, "0x%lX\n", ioaddr); } static ssize_t irq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.irq); } static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%X\n", tmp.flags); } static ssize_t xmit_fifo_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.xmit_fifo_size); } static ssize_t close_delay_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.close_delay); } static ssize_t closing_wait_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.closing_wait); } static ssize_t custom_divisor_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.custom_divisor); } static ssize_t io_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.io_type); } static ssize_t iomem_base_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%lX\n", (unsigned long)tmp.iomem_base); } static ssize_t iomem_reg_shift_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.iomem_reg_shift); } static ssize_t console_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool console = false; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) console = uart_console_registered(uport); mutex_unlock(&port->mutex); return sprintf(buf, "%c\n", console ? 'Y' : 'N'); } static ssize_t console_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool oldconsole, newconsole; int ret; ret = kstrtobool(buf, &newconsole); if (ret) return ret; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -ENXIO; oldconsole = uart_console_registered(uport); if (oldconsole && !newconsole) { ret = unregister_console(uport->cons); if (ret < 0) return ret; } else if (!oldconsole && newconsole) { if (!uart_console(uport)) return -ENOENT; uport->console_reinit = 1; register_console(uport->cons); } return count; } static DEVICE_ATTR_RO(uartclk); static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(line); static DEVICE_ATTR_RO(port); static DEVICE_ATTR_RO(irq); static DEVICE_ATTR_RO(flags); static DEVICE_ATTR_RO(xmit_fifo_size); static DEVICE_ATTR_RO(close_delay); static DEVICE_ATTR_RO(closing_wait); static DEVICE_ATTR_RO(custom_divisor); static DEVICE_ATTR_RO(io_type); static DEVICE_ATTR_RO(iomem_base); static DEVICE_ATTR_RO(iomem_reg_shift); static DEVICE_ATTR_RW(console); static struct attribute *tty_dev_attrs[] = { &dev_attr_uartclk.attr, &dev_attr_type.attr, &dev_attr_line.attr, &dev_attr_port.attr, &dev_attr_irq.attr, &dev_attr_flags.attr, &dev_attr_xmit_fifo_size.attr, &dev_attr_close_delay.attr, &dev_attr_closing_wait.attr, &dev_attr_custom_divisor.attr, &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, &dev_attr_console.attr, NULL }; static const struct attribute_group tty_dev_attr_group = { .attrs = tty_dev_attrs, }; /** * serial_core_add_one_port - attach a driver-defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure to use for this port. * * Context: task context, might sleep * * This allows the driver @drv to register its own uart_port structure with the * core driver. The main purpose is to allow the low level uart drivers to * expand uart_port, rather than having yet more levels of structures. * Caller must hold port_mutex. */ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state; struct tty_port *port; struct device *tty_dev; int num_groups; if (uport->line >= drv->nr) return -EINVAL; state = drv->state + uport->line; port = &state->port; guard(mutex)(&port->mutex); if (state->uart_port) return -EINVAL; /* Link the port to the driver state table and vice versa */ atomic_set(&state->refcount, 1); init_waitqueue_head(&state->remove_wait); state->uart_port = uport; uport->state = state; /* * If this port is in use as a console then the spinlock is already * initialised. */ if (!uart_console_registered(uport)) uart_port_spin_lock_init(uport); state->pm_state = UART_PM_STATE_UNDEFINED; uart_port_set_cons(uport, drv->cons); uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); if (!uport->name) return -ENOMEM; if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); num_groups = 2; if (uport->attr_group) num_groups++; uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups), GFP_KERNEL); if (!uport->tty_groups) return -ENOMEM; uport->tty_groups[0] = &tty_dev_attr_group; if (uport->attr_group) uport->tty_groups[1] = uport->attr_group; /* Ensure serdev drivers can call serdev_device_open() right away */ uport->flags &= ~UPF_DEAD; /* * Register the port whether it's detected or not. This allows * setserial to be used to alter this port's parameters. */ tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver, uport->line, uport->dev, &uport->port_dev->dev, port, uport->tty_groups); if (!IS_ERR(tty_dev)) { device_set_wakeup_capable(tty_dev, 1); } else { uport->flags |= UPF_DEAD; dev_err(uport->dev, "Cannot register tty device on line %d\n", uport->line); } return 0; } /** * serial_core_remove_one_port - detach a driver defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure for this port * * Context: task context, might sleep * * This unhooks (and hangs up) the specified port structure from the core * driver. No further calls will be made to the low-level code for this port. * Caller must hold port_mutex. */ static void serial_core_remove_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct uart_port *uart_port; struct tty_struct *tty; mutex_lock(&port->mutex); uart_port = uart_port_check(state); if (uart_port != uport) dev_alert(uport->dev, "Removing wrong port: %p != %p\n", uart_port, uport); if (!uart_port) { mutex_unlock(&port->mutex); return; } mutex_unlock(&port->mutex); /* * Remove the devices from the tty layer */ tty_port_unregister_device(port, drv->tty_driver, uport->line); tty = tty_port_tty_get(port); if (tty) { tty_vhangup(port->tty); tty_kref_put(tty); } /* * If the port is used as a console, unregister it */ if (uart_console(uport)) unregister_console(uport->cons); /* * Free the port IO and memory resources, if any. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); kfree(uport->tty_groups); kfree(uport->name); /* * Indicate that there isn't a port here anymore. */ uport->type = PORT_UNKNOWN; uport->port_dev = NULL; mutex_lock(&port->mutex); WARN_ON(atomic_dec_return(&state->refcount) < 0); wait_event(state->remove_wait, !atomic_read(&state->refcount)); state->uart_port = NULL; mutex_unlock(&port->mutex); } /** * uart_match_port - are the two ports equivalent? * @port1: first port * @port2: second port * * This utility function can be used to determine whether two uart_port * structures describe the same port. */ bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2) { if (port1->iotype != port2->iotype) return false; switch (port1->iotype) { case UPIO_PORT: return port1->iobase == port2->iobase; case UPIO_HUB6: return port1->iobase == port2->iobase && port1->hub6 == port2->hub6; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: return port1->mapbase == port2->mapbase; } return false; } EXPORT_SYMBOL(uart_match_port); static struct serial_ctrl_device * serial_core_get_ctrl_dev(struct serial_port_device *port_dev) { struct device *dev = &port_dev->dev; return to_serial_base_ctrl_device(dev->parent); } /* * Find a registered serial core controller device if one exists. Returns * the first device matching the ctrl_id. Caller must hold port_mutex. */ static struct serial_ctrl_device *serial_core_ctrl_find(struct uart_driver *drv, struct device *phys_dev, int ctrl_id) { struct uart_state *state; int i; lockdep_assert_held(&port_mutex); for (i = 0; i < drv->nr; i++) { state = drv->state + i; if (!state->uart_port || !state->uart_port->port_dev) continue; if (state->uart_port->dev == phys_dev && state->uart_port->ctrl_id == ctrl_id) return serial_core_get_ctrl_dev(state->uart_port->port_dev); } return NULL; } static struct serial_ctrl_device *serial_core_ctrl_device_add(struct uart_port *port) { return serial_base_ctrl_add(port, port->dev); } static int serial_core_port_device_add(struct serial_ctrl_device *ctrl_dev, struct uart_port *port) { struct serial_port_device *port_dev; port_dev = serial_base_port_add(port, ctrl_dev); if (IS_ERR(port_dev)) return PTR_ERR(port_dev); port->port_dev = port_dev; return 0; } /* * Initialize a serial core port device, and a controller device if needed. */ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) { struct serial_ctrl_device *ctrl_dev, *new_ctrl_dev = NULL; int ret; guard(mutex)(&port_mutex); /* * Prevent serial_port_runtime_resume() from trying to use the port * until serial_core_add_one_port() has completed */ port->flags |= UPF_DEAD; /* Inititalize a serial core controller device if needed */ ctrl_dev = serial_core_ctrl_find(drv, port->dev, port->ctrl_id); if (!ctrl_dev) { new_ctrl_dev = serial_core_ctrl_device_add(port); if (IS_ERR(new_ctrl_dev)) return PTR_ERR(new_ctrl_dev); ctrl_dev = new_ctrl_dev; } /* * Initialize a serial core port device. Tag the port dead to prevent * serial_port_runtime_resume() trying to do anything until port has * been registered. It gets cleared by serial_core_add_one_port(). */ ret = serial_core_port_device_add(ctrl_dev, port); if (ret) goto err_unregister_ctrl_dev; ret = serial_base_match_and_update_preferred_console(drv, port); if (ret) goto err_unregister_port_dev; ret = serial_core_add_one_port(drv, port); if (ret) goto err_unregister_port_dev; return 0; err_unregister_port_dev: serial_base_port_device_remove(port->port_dev); err_unregister_ctrl_dev: serial_base_ctrl_device_remove(new_ctrl_dev); return ret; } /* * Removes a serial core port device, and the related serial core controller * device if the last instance. */ void serial_core_unregister_port(struct uart_driver *drv, struct uart_port *port) { struct device *phys_dev = port->dev; struct serial_port_device *port_dev = port->port_dev; struct serial_ctrl_device *ctrl_dev = serial_core_get_ctrl_dev(port_dev); int ctrl_id = port->ctrl_id; mutex_lock(&port_mutex); port->flags |= UPF_DEAD; serial_core_remove_one_port(drv, port); /* Note that struct uart_port *port is no longer valid at this point */ serial_base_port_device_remove(port_dev); /* Drop the serial core controller device if no ports are using it */ if (!serial_core_ctrl_find(drv, phys_dev, ctrl_id)) serial_base_ctrl_device_remove(ctrl_dev); mutex_unlock(&port_mutex); } /** * uart_handle_dcd_change - handle a change of carrier detect state * @uport: uart_port structure for the open port * @active: new carrier detect status * * Caller must hold uport->lock. */ void uart_handle_dcd_change(struct uart_port *uport, bool active) { struct tty_port *port = &uport->state->port; struct tty_struct *tty = port->tty; struct tty_ldisc *ld; lockdep_assert_held_once(&uport->lock); if (tty) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) ld->ops->dcd_change(tty, active); tty_ldisc_deref(ld); } } uport->icount.dcd++; if (uart_dcd_enabled(uport)) { if (active) wake_up_interruptible(&port->open_wait); else if (tty) tty_hangup(tty); } } EXPORT_SYMBOL_GPL(uart_handle_dcd_change); /** * uart_handle_cts_change - handle a change of clear-to-send state * @uport: uart_port structure for the open port * @active: new clear-to-send status * * Caller must hold uport->lock. */ void uart_handle_cts_change(struct uart_port *uport, bool active) { lockdep_assert_held_once(&uport->lock); uport->icount.cts++; if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { if (active) { uport->hw_stopped = false; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { if (!active) { uport->hw_stopped = true; uport->ops->stop_tx(uport); } } } } EXPORT_SYMBOL_GPL(uart_handle_cts_change); /** * uart_insert_char - push a char to the uart layer * * User is responsible to call tty_flip_buffer_push when they are done with * insertion. * * @port: corresponding port * @status: state of the serial port RX buffer (LSR for 8250) * @overrun: mask of overrun bits in @status * @ch: character to push * @flag: flag for the character (see TTY_NORMAL and friends) */ void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag) { struct tty_port *tport = &port->state->port; if ((status & port->ignore_status_mask & ~overrun) == 0) if (tty_insert_flip_char(tport, ch, flag) == 0) ++port->icount.buf_overrun; /* * Overrun is special. Since it's reported immediately, * it doesn't affect the current character. */ if (status & ~port->ignore_status_mask & overrun) if (tty_insert_flip_char(tport, 0, TTY_OVERRUN) == 0) ++port->icount.buf_overrun; } EXPORT_SYMBOL_GPL(uart_insert_char); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL static const u8 sysrq_toggle_seq[] = CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE; static void uart_sysrq_on(struct work_struct *w) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); sysrq_toggle_support(1); pr_info("SysRq is enabled by magic sequence '%*pE' on serial\n", sysrq_toggle_seq_len, sysrq_toggle_seq); } static DECLARE_WORK(sysrq_enable_work, uart_sysrq_on); /** * uart_try_toggle_sysrq - Enables SysRq from serial line * @port: uart_port structure where char(s) after BREAK met * @ch: new character in the sequence after received BREAK * * Enables magic SysRq when the required sequence is met on port * (see CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE). * * Returns: %false if @ch is out of enabling sequence and should be * handled some other way, %true if @ch was consumed. */ bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); if (!sysrq_toggle_seq_len) return false; BUILD_BUG_ON(ARRAY_SIZE(sysrq_toggle_seq) >= U8_MAX); if (sysrq_toggle_seq[port->sysrq_seq] != ch) { port->sysrq_seq = 0; return false; } if (++port->sysrq_seq < sysrq_toggle_seq_len) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return true; } schedule_work(&sysrq_enable_work); port->sysrq = 0; return true; } EXPORT_SYMBOL_GPL(uart_try_toggle_sysrq); #endif /** * uart_get_rs485_mode() - retrieve rs485 properties for given uart * @port: uart device's target port * * This function implements the device tree binding described in * Documentation/devicetree/bindings/serial/rs485.txt. */ int uart_get_rs485_mode(struct uart_port *port) { struct serial_rs485 *rs485conf = &port->rs485; struct device *dev = port->dev; enum gpiod_flags dflags; struct gpio_desc *desc; u32 rs485_delay[2]; int ret; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return 0; ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); if (!ret) { rs485conf->delay_rts_before_send = rs485_delay[0]; rs485conf->delay_rts_after_send = rs485_delay[1]; } else { rs485conf->delay_rts_before_send = 0; rs485conf->delay_rts_after_send = 0; } uart_sanitize_serial_rs485_delays(port, rs485conf); /* * Clear full-duplex and enabled flags, set RTS polarity to active high * to get to a defined state with the following properties: */ rs485conf->flags &= ~(SER_RS485_RX_DURING_TX | SER_RS485_ENABLED | SER_RS485_TERMINATE_BUS | SER_RS485_RTS_AFTER_SEND); rs485conf->flags |= SER_RS485_RTS_ON_SEND; if (device_property_read_bool(dev, "rs485-rx-during-tx")) rs485conf->flags |= SER_RS485_RX_DURING_TX; if (device_property_read_bool(dev, "linux,rs485-enabled-at-boot-time")) rs485conf->flags |= SER_RS485_ENABLED; if (device_property_read_bool(dev, "rs485-rts-active-low")) { rs485conf->flags &= ~SER_RS485_RTS_ON_SEND; rs485conf->flags |= SER_RS485_RTS_AFTER_SEND; } /* * Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. * Works fine for short cables and users may enable for longer cables. */ desc = devm_gpiod_get_optional(dev, "rs485-term", GPIOD_OUT_LOW); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-term-gpios\n"); port->rs485_term_gpio = desc; if (port->rs485_term_gpio) port->rs485_supported.flags |= SER_RS485_TERMINATE_BUS; dflags = (rs485conf->flags & SER_RS485_RX_DURING_TX) ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; desc = devm_gpiod_get_optional(dev, "rs485-rx-during-tx", dflags); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-rx-during-tx-gpios\n"); port->rs485_rx_during_tx_gpio = desc; if (port->rs485_rx_during_tx_gpio) port->rs485_supported.flags |= SER_RS485_RX_DURING_TX; return 0; } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); /* Compile-time assertions for serial_rs485 layout */ static_assert(offsetof(struct serial_rs485, padding) == (offsetof(struct serial_rs485, delay_rts_after_send) + sizeof(__u32))); static_assert(offsetof(struct serial_rs485, padding1) == offsetof(struct serial_rs485, padding[1])); static_assert((offsetof(struct serial_rs485, padding[4]) + sizeof(__u32)) == sizeof(struct serial_rs485)); MODULE_DESCRIPTION("Serial driver core"); MODULE_LICENSE("GPL"); |
| 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(smcd->ops->get_dev(smcd)), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(smcd_dev->ops->get_dev(smcd_dev)), smcd_name, IB_DEVICE_NAME_MAX - 1)) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; struct device *dev; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { dev = smcd->ops->get_dev(smcd); pr_warn_ratelimited("smc: smcd device %s " "applied user defined pnetid " "%.16s\n", dev_name(dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net *net; ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_roce_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_ism_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { const char *ib_name = dev_name(smcddev->ops->get_dev(smcddev)); struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 4 8 1 6 1 2 2 6 4 6 7 6 4 6 4 3 4 6 6 6 5 5 1 2 2 1 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool wake_writer = false, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started reading * and it is no longer full after reading to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) { wake_writer |= pipe_full(head, tail, pipe->max_usage); tail = pipe_update_tail(pipe, buf, tail); } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(wake_writer)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; wake_writer = false; wake_next_reader = true; mutex_lock(&pipe->mutex); } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (wake_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; f->f_pipe = 0; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[0]->f_pipe = 0; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); /* * Disable permission and pre-content events, but enable legacy * inotify events for legacy users. */ file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM); file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_pipe = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_pipe = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole file system mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static const struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 1 1 10 10 10 10 10 9 10 10 10 10 8 2 1 1 1 2 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <linux/filter.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> #include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> #include <linux/dccp.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/if_hsr.h> #include <linux/mpls.h> #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <net/pkt_cls.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h> #endif #include <linux/bpf-netns.h> static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1ULL << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) { unsigned int i; memset(flow_dissector, 0, sizeof(*flow_dissector)); for (i = 0; i < key_count; i++, key++) { /* User should make sure that every key target offset is within * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); BUG_ON(dissector_uses_key(flow_dissector, key->key_id)); dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL)); BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides * any per-net-namespace one. When attaching to root, * make sure we don't have any BPF program attached * to the non-root namespaces. */ struct net *ns; for_each_net(ns) { if (ns == &init_net) continue; if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } return 0; } #endif /* CONFIG_BPF_SYSCALL */ /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset * @data: raw buffer pointer to the packet, if NULL use skb->data * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); if (!data) { data = skb->data; hlen = skb_headlen(skb); } if (poff >= 0) { __be32 *ports, _ports; ports = __skb_header_pointer(skb, thoff + poff, sizeof(_ports), data, hlen, &_ports); if (ports) return *ports; } return 0; } EXPORT_SYMBOL(__skb_flow_get_ports); static bool icmp_has_id(u8 type) { switch (type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: return true; } return false; } /** * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); if (!ih) return; key_icmp->type = ih->type; key_icmp->code = ih->code; /* As we use 0 to signal that the Id field is not present, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } EXPORT_SYMBOL(skb_flow_get_icmp_tci); /* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet * using skb_flow_get_icmp_tci(). */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) return; key_icmp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ICMP, target_container); skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } static void __skb_flow_dissect_ah(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_ah; struct ip_auth_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_ah = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_ah->spi = hdr->spi; } static void __skb_flow_dissect_esp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_esp; struct ip_esp_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_esp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_esp->spi = hdr->spi; } static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_l2tpv3 *key_l2tpv3; struct { __be32 session_id; } *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_l2tpv3 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3, target_container); key_l2tpv3->session_id = hdr->session_id; } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_meta *meta; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_META)) return; meta = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (tc_skb_ext_tc_enabled()) { struct tc_skb_ext *ext; ext = skb_ext_find(skb, TC_SKB_EXT); if (ext) meta->l2_miss = ext->l2_miss; } #endif } EXPORT_SYMBOL(skb_flow_dissect_meta); static void skb_flow_dissect_set_enc_control(enum flow_dissector_key_id type, u32 ctrl_flags, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_control *ctrl; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) return; ctrl = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; ctrl->flags = ctrl_flags; } void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT)) return; ct = nf_ct_get(skb, &ctinfo); if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; key->ct_zone = zone; return; } if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); if (cl) memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels)); #endif /* CONFIG_NF_CONNTRACK */ } EXPORT_SYMBOL(skb_flow_dissect_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct ip_tunnel_info *info; struct ip_tunnel_key *key; u32 ctrl_flags = 0; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); if (!info) return; key = &info->key; if (test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_CSUM; if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_DONT_FRAGMENT; if (test_bit(IP_TUNNEL_OAM_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_OAM; if (test_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_CRIT_OPT; switch (ip_tunnel_info_af(info)) { case AF_INET: skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ctrl_flags, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; ipv4 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, target_container); ipv4->src = key->u.ipv4.src; ipv4->dst = key->u.ipv4.dst; } break; case AF_INET6: skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ctrl_flags, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; ipv6 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, target_container); ipv6->src = key->u.ipv6.src; ipv6->dst = key->u.ipv6.dst; } break; default: skb_flow_dissect_set_enc_control(0, ctrl_flags, flow_dissector, target_container); break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_dissector_key_keyid *keyid; keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID, target_container); keyid->keyid = tunnel_id_to_key32(key->tun_id); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *tp; tp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, target_container); tp->src = key->tp_src; tp->dst = key->tp_dst; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_dissector_key_ip *ip; ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP, target_container); ip->tos = key->tos; ip->ttl = key->ttl; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; IP_TUNNEL_DECLARE_FLAGS(flags) = { }; u32 val; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); if (!info->options_len) return; enc_opt->len = info->options_len; ip_tunnel_info_opts_get(enc_opt->data, info); ip_tunnel_set_options_present(flags); ip_tunnel_flags_and(flags, info->key.tun_flags, flags); val = find_next_bit(flags, __IP_TUNNEL_FLAG_NUM, IP_TUNNEL_GENEVE_OPT_BIT); enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0; } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_hash *key; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH)) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_HASH, target_container); key->hash = skb_get_hash_raw(skb); } EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) return FLOW_DISSECT_RET_OUT_GOOD; if (lse_index >= FLOW_DIS_MPLS_MAX) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; entry = ntohl(hdr->entry); label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_dissector_key_mpls *key_mpls; struct flow_dissector_mpls_lse *lse; key_mpls = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS, target_container); lse = &key_mpls->ls[lse_index]; lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; lse->mpls_bos = bos; lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; lse->mpls_label = label; dissector_set_mpls_lse(key_mpls, lse_index); } if (*entropy_label && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { struct flow_dissector_key_keyid *key_keyid; key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); key_keyid->keyid = cpu_to_be32(label); } *entropy_label = label == MPLS_LABEL_ENTROPY; return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN; } static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { unsigned char ar_sha[ETH_ALEN]; unsigned char ar_sip[4]; unsigned char ar_tha[ETH_ALEN]; unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; struct arphdr _arp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) return FLOW_DISSECT_RET_OUT_GOOD; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); if (!arp) return FLOW_DISSECT_RET_OUT_BAD; if (arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_hln != ETH_ALEN || arp->ar_pln != 4 || (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST))) return FLOW_DISSECT_RET_OUT_BAD; arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), sizeof(_arp_eth), data, hlen, &_arp_eth); if (!arp_eth) return FLOW_DISSECT_RET_OUT_BAD; key_arp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ARP, target_container); memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); /* Only store the lower byte of the opcode; * this covers ARPOP_REPLY and ARPOP_REQUEST. */ key_arp->op = ntohs(arp->ar_op) & 0xff; ether_addr_copy(key_arp->sha, arp_eth->ar_sha); ether_addr_copy(key_arp->tha, arp_eth->ar_tha); return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_cfm(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_cfm *key, *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CFM)) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(*key), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CFM, target_container); key->mdl_ver = hdr->mdl_ver; key->opcode = hdr->opcode; return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { struct flow_dissector_key_keyid *key_keyid; struct gre_base_hdr *hdr, _hdr; int offset = 0; u16 gre_ver; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, *p_hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) return FLOW_DISSECT_RET_OUT_GOOD; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) return FLOW_DISSECT_RET_OUT_GOOD; *p_proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) return FLOW_DISSECT_RET_OUT_GOOD; } offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) offset += sizeof_field(struct gre_full_hdr, csum) + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; keyid = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_keyid), data, *p_hlen, &_keyid); if (!keyid) return FLOW_DISSECT_RET_OUT_BAD; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); if (gre_ver == 0) key_keyid->keyid = *keyid; else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { const struct ethhdr *eth; struct ethhdr _eth; eth = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_eth), data, *p_hlen, &_eth); if (!eth) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = eth->h_proto; offset += sizeof(*eth); /* Cap headers that we access via pointers at the * end of the Ethernet header as our maximum alignment * at that point is only 2 bytes. */ if (NET_IP_ALIGN) *p_hlen = *p_nhoff + offset; } } else { /* version 1, must be PPTP */ u8 _ppp_hdr[PPP_HDRLEN]; u8 *ppp_hdr; if (hdr->flags & GRE_ACK) offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), data, *p_hlen, _ppp_hdr); if (!ppp_hdr) return FLOW_DISSECT_RET_OUT_BAD; switch (PPP_PROTOCOL(ppp_hdr)) { case PPP_IP: *p_proto = htons(ETH_P_IP); break; case PPP_IPV6: *p_proto = htons(ETH_P_IPV6); break; default: /* Could probably catch some more like MPLS */ break; } offset += PPP_HDRLEN; } *p_nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } /** * __skb_flow_dissect_batadv() - dissect batman-adv header * @skb: sk_buff to with the batman-adv header * @key_control: flow dissectors control key * @data: raw buffer pointer to the packet, if NULL use skb->data * @p_proto: pointer used to update the protocol to process next * @p_nhoff: pointer used to update inner network header offset * @hlen: packet header length * @flags: any combination of FLOW_DISSECTOR_F_* * * ETH_P_BATMAN packets are tried to be dissected. Only * &struct batadv_unicast packets are actually processed because they contain an * inner ethernet header and are usually followed by actual network header. This * allows the flow dissector to continue processing the packet. * * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found, * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation, * otherwise FLOW_DISSECT_RET_OUT_BAD */ static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, const void *data, __be16 *p_proto, int *p_nhoff, int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; struct ethhdr eth; } *hdr, _hdr; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.packet_type != BATADV_UNICAST) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = hdr->eth.h_proto; *p_nhoff += sizeof(*hdr); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) return; th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); if (!th) return; if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) return; key_tcp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TCP, target_container); key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; struct flow_dissector_key_ports *key_ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS; else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) return; key_ports = skb_flow_dissector_target(flow_dissector, dissector_ports, target_container); key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); } static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = iph->tos; key_ip->ttl = iph->ttl; } static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = ipv6_get_dsfield(iph); key_ip->ttl = iph->hop_limit; } /* Maximum number of protocol headers that can be parsed in * __skb_flow_dissect */ #define MAX_FLOW_DISSECT_HDRS 15 static bool skb_flow_dissect_allowed(int *num_hdrs) { ++*num_hdrs; return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); key_control->thoff = flow_keys->thoff; if (flow_keys->is_frag) key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (flow_keys->is_first_frag) key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flow_keys->is_encap) key_control->flags |= FLOW_DIS_ENCAPSULATION; key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); key_basic->n_proto = flow_keys->n_proto; key_basic->ip_proto = flow_keys->ip_proto; if (flow_keys->addr_proto == ETH_P_IP && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); key_addrs->v4addrs.src = flow_keys->ipv4_src; key_addrs->v4addrs.dst = flow_keys->ipv4_dst; key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else if (flow_keys->addr_proto == ETH_P_IPV6 && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_keys->flow_label); } } u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); flow_keys->n_proto = proto; flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, hlen); return result; } static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr) { return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0; } /** * __skb_flow_dissect - extract the flow_keys struct and return it * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the * rest parameters. * * Caller must take care of zeroing target container memory. */ bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; int mpls_lse = 0; int num_hdrs = 0; u8 ip_proto = 0; bool ret; if (!data) { data = skb->data; proto = skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { struct metadata_dst *md_dst = skb_metadata_dst(skb); const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ if (ops->needed_headroom && (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else dsa_tag_generic_flow_dissect(skb, &proto, &offset); hlen -= offset; nhoff += offset; } } #endif } /* It is ensured by skb_flow_dissector_init() that control key will * be always present. */ key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); /* It is ensured by skb_flow_dissector_init() that basic key will * be always present. */ key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); if (skb) { if (!net) { if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } } DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; rcu_read_lock(); run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, .data = data, .data_end = data + hlen, }; __be16 n_proto = proto; struct bpf_prog *prog; u32 result; if (skb) { ctx.skb = skb; /* we can't use 'proto' in the skb case * because it might be set to skb->vlan_proto * which has been pulled from the data */ n_proto = skb->protocol; } prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); if (result == BPF_FLOW_DISSECTOR_CONTINUE) goto dissect_continue; __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } dissect_continue: rcu_read_unlock(); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) { struct flow_dissector_key_num_of_vlans *key_num_of_vlans; key_num_of_vlans = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_num_of_vlans->num_of_vlans = 0; } proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += iph->ihl * 4; ip_proto = iph->protocol; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); memcpy(&key_addrs->v4addrs.src, &iph->saddr, sizeof(key_addrs->v4addrs.src)); memcpy(&key_addrs->v4addrs.dst, &iph->daddr, sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (iph->frag_off & htons(IP_OFFSET)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } else { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } } break; } case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &iph->saddr, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &iph->daddr, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if ((dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL) || (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && ip6_flowlabel(iph)) { __be32 flow_label = ip6_flowlabel(iph); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); break; } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; __be16 saved_vlan_tpid = proto; if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) && !(key_control->flags & FLOW_DIS_ENCAPSULATION)) { struct flow_dissector_key_num_of_vlans *key_nvs; key_nvs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_nvs->num_of_vlans++; } if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; } else { fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, dissector_vlan, target_container); if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb); } else { key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & VLAN_VID_MASK; key_vlan->vlan_priority = (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; } *hdr, _hdr; u16 ppp_proto; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* least significant bit of the most significant octet * indicates if protocol field was compressed */ ppp_proto = ntohs(hdr->proto); if (ppp_proto & 0x0100) { ppp_proto = ppp_proto >> 8; nhoff += PPPOE_SES_HLEN - 1; } else { nhoff += PPPOE_SES_HLEN; } if (ppp_proto == PPP_IP) { proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_IPV6) { proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_UC) { proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_MC) { proto = htons(ETH_P_MPLS_MC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto_is_valid(ppp_proto)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; } else { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE)) { struct flow_dissector_key_pppoe *key_pppoe; key_pppoe = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE, target_container); key_pppoe->session_id = hdr->hdr.sid; key_pppoe->ppp_proto = htons(ppp_proto); key_pppoe->type = htons(ETH_P_PPP_SES); } break; } case htons(ETH_P_TIPC): { struct tipc_basic_hdr *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC, target_container); key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): fdret = __skb_flow_dissect_mpls(skb, flow_dissector, target_container, data, nhoff, hlen, mpls_lse, &mpls_el); nhoff += sizeof(struct mpls_label); mpls_lse++; break; case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += FCOE_HEADER_LEN; fdret = FLOW_DISSECT_RET_OUT_GOOD; break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): fdret = __skb_flow_dissect_arp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case htons(ETH_P_BATMAN): fdret = __skb_flow_dissect_batadv(skb, key_control, data, &proto, &nhoff, hlen, flags); break; case htons(ETH_P_1588): { struct ptp_header *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_PRP): case htons(ETH_P_HSR): { struct hsr_tag *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->encap_proto; nhoff += HSR_HLEN; fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_CFM): fdret = __skb_flow_dissect_cfm(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* Process result of proto processing */ switch (fdret) { case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; goto out_good; case FLOW_DISSECT_RET_CONTINUE: case FLOW_DISSECT_RET_IPPROTO_AGAIN: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } ip_proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (ip_proto) { case IPPROTO_GRE: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector, target_container, data, &proto, &nhoff, &hlen, flags); break; case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { u8 _opthdr[2], *opthdr; if (proto != htons(ETH_P_IPV6)) break; opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } case NEXTHDR_FRAGMENT: { struct frag_hdr _fh, *fh; if (proto != htons(ETH_P_IPV6)) break; fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), data, hlen, &_fh); if (!fh) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case IPPROTO_IPIP: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IP); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_IPV6: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IPV6); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_TCP: __skb_flow_dissect_tcp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: __skb_flow_dissect_icmp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_L2TP: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ESP: __skb_flow_dissect_esp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_AH: __skb_flow_dissect_ah(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: break; } if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) __skb_flow_dissect_ports(skb, flow_dissector, target_container, data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; break; case FLOW_DISSECT_RET_IPPROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto ip_proto_again; break; case FLOW_DISSECT_RET_OUT_GOOD: case FLOW_DISSECT_RET_CONTINUE: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } out_good: ret = true; out: key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; return ret; out_bad: ret = false; goto out; } EXPORT_SYMBOL(__skb_flow_dissect); static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static const void *flow_keys_hash_start(const struct flow_keys *flow) { BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: diff -= sizeof(flow->addrs.v4addrs); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; case FLOW_DISSECTOR_KEY_TIPC: diff -= sizeof(flow->addrs.tipckey); break; } return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.src; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); case FLOW_DISSECTOR_KEY_TIPC: return flow->addrs.tipckey.key; default: return 0; } } EXPORT_SYMBOL(flow_get_u32_src); __be32 flow_get_u32_dst(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.dst; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.dst); default: return 0; } } EXPORT_SYMBOL(flow_get_u32_dst); /* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: if ((__force u32)keys->addrs.v4addrs.dst < (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); } if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; } } static inline u32 __flow_hash_from_keys(struct flow_keys *keys, const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); hash = siphash(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; return hash; } u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); u32 flow_hash_from_keys_seed(struct flow_keys *keys, const siphash_key_t *keyval) { return __flow_hash_from_keys(keys, keyval); } EXPORT_SYMBOL(flow_hash_from_keys_seed); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } struct _flow_keys_digest_data { __be16 n_proto; u8 ip_proto; u8 padding; __be32 ports; __be32 src; __be32 dst; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow) { struct _flow_keys_digest_data *data = (struct _flow_keys_digest_data *)digest; BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); memset(digest, 0, sizeof(*digest)); data->n_proto = flow->basic.n_proto; data->ip_proto = flow->basic.ip_proto; data->ports = flow->ports.ports; data->src = flow->addrs.v4addrs.src; data->dst = flow->addrs.v4addrs.dst; } EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(net, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric_net); /** * __skb_get_hash_net: calculate a flow hash * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash_net(const struct net *net, struct sk_buff *skb) { struct flow_keys keys; u32 hash; memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); __flow_hash_secret_init(); hash = __flow_hash_from_keys(&keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash_net); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) { struct flow_keys keys; return ___skb_get_hash(skb, &keys, perturb); } EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; /* skip L4 headers for fragments after the first */ if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) return poff; switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; u8 _doff; doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff), data, hlen, &_doff); if (!doff) return poff; poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2); break; } case IPPROTO_UDP: case IPPROTO_UDPLITE: poff += sizeof(struct udphdr); break; /* For the rest, we do not really care about header * extensions at this point for now. */ case IPPROTO_ICMP: poff += sizeof(struct icmphdr); break; case IPPROTO_ICMPV6: poff += sizeof(struct icmp6hdr); break; case IPPROTO_IGMP: poff += sizeof(struct igmphdr); break; case IPPROTO_DCCP: poff += sizeof(struct dccp_hdr); break; case IPPROTO_SCTP: poff += sizeof(struct sctphdr); break; } return poff; } /** * skb_get_poff - get the offset to the payload * @skb: sk_buff to get the payload offset from * * The function will get the offset to the payload as far as it could * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) { memset(keys, 0, sizeof(*keys)); memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, sizeof(keys->addrs.v6addrs.src)); memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, sizeof(keys->addrs.v6addrs.dst)); keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); } EXPORT_SYMBOL(__get_hash_from_flowi6); static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, }; static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, }; struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); struct flow_dissector flow_keys_basic_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } core_initcall(init_default_flow_dissectors); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ union { wait_queue_head_t poll; struct rcu_head mnt_ns_rcu; }; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ struct list_head mnt_ns_list; /* entry in the sequential list of mounts namespace */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_CHECKSUM_H #define __ASM_CHECKSUM_H #include <linux/in6.h> #define _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum sum); static inline __sum16 csum_fold(__wsum csum) { u32 sum = (__force u32)csum; sum += (sum >> 16) | (sum << 16); return ~(__force __sum16)(sum >> 16); } #define csum_fold csum_fold static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum extern unsigned int do_csum(const unsigned char *buff, int len); #define do_csum do_csum #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ |
| 2 2 2 2 2 2 2 2 2 2 2 2 112 113 112 112 113 110 93 93 94 2 2 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 Arm Limited * Author: Andrew Murray <Andrew.Murray@arm.com> */ #include <linux/kvm_host.h> #include <linux/perf_event.h> #include <linux/perf/arm_pmu.h> #include <linux/perf/arm_pmuv3.h> static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); /* * Given the perf event attributes and system type, determine * if we are going to need to switch counters at guest entry/exit. */ static bool kvm_pmu_switch_needed(struct perf_event_attr *attr) { /** * With VHE the guest kernel runs at EL1 and the host at EL2, * where user (EL0) is excluded then we have no reason to switch * counters. */ if (has_vhe() && attr->exclude_user) return false; /* Only switch if attributes are different */ return (attr->exclude_host != attr->exclude_guest); } struct kvm_pmu_events *kvm_get_pmu_events(void) { return this_cpu_ptr(&kvm_pmu_events); } /* * Add events to track that we may want to switch at guest entry/exit * time. */ void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) pmu->events_host |= set; if (!attr->exclude_guest) pmu->events_guest |= set; } /* * Stop tracking events */ void kvm_clr_pmu_events(u64 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!kvm_arm_support_pmu_v3()) return; pmu->events_host &= ~clr; pmu->events_guest &= ~clr; } /* * Read a value direct from PMEVTYPER<idx> where idx is 0-30 * or PMxCFILTR_EL0 where idx is 31-32. */ static u64 kvm_vcpu_pmu_read_evtype_direct(int idx) { if (idx == ARMV8_PMU_CYCLE_IDX) return read_pmccfiltr(); else if (idx == ARMV8_PMU_INSTR_IDX) return read_pmicfiltr(); return read_pmevtypern(idx); } /* * Write a value direct to PMEVTYPER<idx> where idx is 0-30 * or PMxCFILTR_EL0 where idx is 31-32. */ static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val) { if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(val); else if (idx == ARMV8_PMU_INSTR_IDX) write_pmicfiltr(val); else write_pmevtypern(idx, val); } /* * Modify ARMv8 PMU events to include EL0 counting */ static void kvm_vcpu_pmu_enable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer &= ~ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * Modify ARMv8 PMU events to exclude EL0 counting */ static void kvm_vcpu_pmu_disable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer |= ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * On VHE ensure that only guest events have EL0 counting enabled. * This is called from both vcpu_{load,put} and the sysreg handling. * Since the latter is preemptible, special care must be taken to * disable preemption. */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u64 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; preempt_disable(); pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); preempt_enable(); } /* * On VHE ensure that only host events have EL0 counting enabled */ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u64 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest); } /* * With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU * where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched * to the value for the guest on vcpu_load(). The value for the host EL0 * will be restored on vcpu_put(), before returning to userspace. * This isn't necessary for nVHE, as the register is context switched for * every guest enter/exit. * * Return true if KVM takes care of the register. Otherwise return false. */ bool kvm_set_pmuserenr(u64 val) { struct kvm_cpu_context *hctxt; struct kvm_vcpu *vcpu; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return false; vcpu = kvm_get_running_vcpu(); if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU)) return false; hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val; return true; } /* * If we interrupted the guest to update the host PMU context, make * sure we re-apply the guest EL0 state. */ void kvm_vcpu_pmu_resync_el0(void) { struct kvm_vcpu *vcpu; if (!has_vhe() || !in_interrupt()) return; vcpu = kvm_get_running_vcpu(); if (!vcpu) return; kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu); } |
| 1 1 57 57 68 67 67 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, 0); if (!ptdesc) return NULL; return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { return __pte_alloc_one_kernel_noprof(mm); } #define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { pagetable_free(virt_to_ptdesc(pte)); } /** * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_page(ptdesc); } #define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } #define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); pagetable_dtor_free(ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table using %GFP_PGTABLE_USER for user context * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one_noprof(mm, addr); } #define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_p4d_ctor(ptdesc); return ptdesc_address(ptdesc); } #define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_P4D_ALLOC_ONE static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __p4d_alloc_one_noprof(mm, addr); } #define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) { struct ptdesc *ptdesc = virt_to_ptdesc(p4d); BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_P4D_FREE static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!mm_p4d_folded(mm)) __p4d_free(mm, p4d); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 4 */ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; ptdesc = pagetable_alloc_noprof(gfp, order); if (!ptdesc) return NULL; pagetable_pgd_ctor(ptdesc); return ptdesc_address(ptdesc); } #define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__)) static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { __pgd_free(mm, pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vrf.c: device driver to encapsulate a VRF space * * Copyright (c) 2015 Cumulus Networks. All rights reserved. * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com> * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> * * Based on dummy, team and ipvlan drivers */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <linux/inetdevice.h> #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> #include <net/sch_generic.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack.h> #include <net/inet_dscp.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.1" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ #define HT_MAP_BITS 4 #define HASH_INITVAL ((u32)0xcafef00d) struct vrf_map { DECLARE_HASHTABLE(ht, HT_MAP_BITS); spinlock_t vmap_lock; /* shared_tables: * count how many distinct tables do not comply with the strict mode * requirement. * shared_tables value must be 0 in order to enable the strict mode. * * example of the evolution of shared_tables: * | time * add vrf0 --> table 100 shared_tables = 0 | t0 * add vrf1 --> table 101 shared_tables = 0 | t1 * add vrf2 --> table 100 shared_tables = 1 | t2 * add vrf3 --> table 100 shared_tables = 1 | t3 * add vrf4 --> table 101 shared_tables = 2 v t4 * * shared_tables is a "step function" (or "staircase function") * and it is increased by one when the second vrf is associated to a * table. * * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1. * * at t3, another dev (vrf3) is bound to the same table 100 but the * value of shared_tables is still 1. * This means that no matter how many new vrfs will register on the * table 100, the shared_tables will not increase (considering only * table 100). * * at t4, vrf4 is bound to table 101, and shared_tables = 2. * * Looking at the value of shared_tables we can immediately know if * the strict_mode can or cannot be enforced. Indeed, strict_mode * can be enforced iff shared_tables = 0. * * Conversely, shared_tables is decreased when a vrf is de-associated * from a table with exactly two associated vrfs. */ u32 shared_tables; bool strict_mode; }; struct vrf_map_elem { struct hlist_node hnode; struct list_head vrf_list; /* VRFs registered to this table */ u32 table_id; int users; int ifindex; }; static unsigned int vrf_net_id; /* per netns vrf data */ struct netns_vrf { /* protected by rtnl lock */ bool add_fib_rules; struct vrf_map vmap; struct ctl_table_header *ctl_hdr; }; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; #if IS_ENABLED(CONFIG_IPV6) struct fib6_table *fib6_table; #endif u32 tb_id; struct list_head me_list; /* entry in vrf_map_elem */ int ifindex; }; static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; kfree_skb(skb); } static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); return &nn_vrf->vmap; } static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev) { return netns_vrf_map(dev_net(dev)); } static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me) { struct list_head *me_head = &me->vrf_list; struct net_vrf *vrf; if (list_empty(me_head)) return -ENODEV; vrf = list_first_entry(me_head, struct net_vrf, me_list); return vrf->ifindex; } static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags) { struct vrf_map_elem *me; me = kmalloc(sizeof(*me), flags); if (!me) return NULL; return me; } static void vrf_map_elem_free(struct vrf_map_elem *me) { kfree(me); } static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id, int ifindex, int users) { me->table_id = table_id; me->ifindex = ifindex; me->users = users; INIT_LIST_HEAD(&me->vrf_list); } static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap, u32 table_id) { struct vrf_map_elem *me; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_for_each_possible(vmap->ht, me, hnode, key) { if (me->table_id == table_id) return me; } return NULL; } static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me) { u32 table_id = me->table_id; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_add(vmap->ht, &me->hnode, key); } static void vrf_map_del_elem(struct vrf_map_elem *me) { hash_del(&me->hnode); } static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock) { spin_lock(&vmap->vmap_lock); } static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) { spin_unlock(&vmap->vmap_lock); } /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); struct vrf_map_elem *new_me, *me; u32 table_id = vrf->tb_id; bool free_new_me = false; int users; int res; /* we pre-allocate elements used in the spin-locked section (so that we * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) return -ENOMEM; vrf_map_elem_init(new_me, table_id, dev->ifindex, 0); vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) { me = new_me; vrf_map_add_elem(vmap, me); goto link_vrf; } /* we already have an entry in the vrf_map, so it means there is (at * least) a vrf registered on the specific table. */ free_new_me = true; if (vmap->strict_mode) { /* vrfs cannot share the same table */ NL_SET_ERR_MSG(extack, "Table is used by another VRF"); res = -EBUSY; goto unlock; } link_vrf: users = ++me->users; if (users == 2) ++vmap->shared_tables; list_add(&vrf->me_list, &me->vrf_list); res = 0; unlock: vrf_map_unlock(vmap); /* clean-up, if needed */ if (free_new_me) vrf_map_elem_free(new_me); return res; } /* called with rtnl lock held */ static void vrf_map_unregister_dev(struct net_device *dev) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); u32 table_id = vrf->tb_id; struct vrf_map_elem *me; int users; vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) goto unlock; list_del(&vrf->me_list); users = --me->users; if (users == 1) { --vmap->shared_tables; } else if (users == 0) { vrf_map_del_elem(me); /* no one will refer to this element anymore */ vrf_map_elem_free(me); } unlock: vrf_map_unlock(vmap); } /* return the vrf device index associated with the table_id */ static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id) { struct vrf_map *vmap = netns_vrf_map(net); struct vrf_map_elem *me; int ifindex; vrf_map_lock(vmap); if (!vmap->strict_mode) { ifindex = -EPERM; goto unlock; } me = vrf_map_lookup_elem(vmap, table_id); if (!me) { ifindex = -ENODEV; goto unlock; } ifindex = vrf_map_elem_get_vrf_ifindex(me); unlock: vrf_map_unlock(vmap); return ifindex; } /* by default VRF devices do not have a qdisc and are expected * to be created with only a single queue. */ static bool qdisc_tx_is_default(const struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; if (dev->num_tx_queues > 1) return false; txq = netdev_get_tx_queue(dev, 0); qdisc = rcu_access_pointer(txq->qdisc); return !qdisc->enqueue; } /* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { unsigned int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) dev_dstats_rx_add(dev, len); else dev_dstats_rx_dropped(dev); return NETDEV_TX_OK; } static void vrf_nf_set_untracked(struct sk_buff *skb) { if (skb_get_nfct(skb) == 0) nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } static void vrf_nf_reset_ct(struct sk_buff *skb) { if (skb_get_nfct(skb) == IP_CT_UNTRACKED) nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) static int vrf_ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) goto err; iph = ipv6_hdr(skb); memset(&fl6, 0, sizeof(fl6)); /* needed to match OIF rule */ fl6.flowi6_l3mdev = dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = iph->nexthdr; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); skb_dst_set(skb, dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; return ret; err: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #endif /* based on ip_local_out; can't use it b/c the dst is switched pointing to us */ static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { struct iphdr *ip4h; int ret = NET_XMIT_DROP; struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); memset(&fl4, 0, sizeof(fl4)); /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)); fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); skb_dst_set(skb, &rt->dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); if (!ip4h->saddr) { ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, RT_SCOPE_LINK); } memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; out: return ret; err: vrf_tx_error(vrf_dev, skb); goto out; } static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) { switch (skb->protocol) { case htons(ETH_P_IP): return vrf_process_v4_outbound(skb, dev); case htons(ETH_P_IPV6): return vrf_process_v6_outbound(skb, dev); default: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } } static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned int len = skb->len; netdev_tx_t ret; ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) dev_dstats_tx_add(dev, len); else dev_dstats_tx_dropped(dev); return ret; } static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; if (!list_empty(&vrf_dev->ptype_all) && likely(skb_headroom(skb) >= ETH_HLEN)) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; rcu_read_lock_bh(); dev_queue_xmit_nit(skb, vrf_dev); rcu_read_unlock_bh(); skb_pull(skb, ETH_HLEN); } vrf_nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) /* modelled after ip6_finish_output2 */ static int vrf_finish_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; const struct in6_addr *nexthop; struct neighbour *neigh; int ret; vrf_nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } /* modelled after ip6_output */ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, vrf_finish_output6, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rt6_info *rt6; rcu_read_lock(); rt6 = rcu_dereference(vrf->rt6); if (likely(rt6)) { dst = &rt6->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output6_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip6_local_out(net, sk, skb); } static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IPV6); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output6_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip6_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert link scope packets */ if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); } /* holding rtnl */ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { struct rt6_info *rt6 = rtnl_dereference(vrf->rt6); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rt6, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rt6) { dst = &rt6->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rt6_create(struct net_device *dev) { int flags = DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct rt6_info *rt6; int rc = -ENOMEM; /* IPv6 can be CONFIG enabled and then disabled runtime */ if (!ipv6_mod_enabled()) return 0; vrf->fib6_table = fib6_new_table(net, vrf->tb_id); if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ rt6 = ip6_dst_alloc(net, dev, flags); if (!rt6) goto out; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; out: return rc; } #else static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { return skb; } static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { } static int vrf_rt6_create(struct net_device *dev) { return 0; } #endif /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; vrf_nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) { dev->stats.tx_errors++; return -ENOMEM; } } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int ret; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return ret; } rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rtable *rth; rcu_read_lock(); rth = rcu_dereference(vrf->rth); if (likely(rth)) { dst = &rth->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip_local_out(net, sk, skb); } static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IP); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert multicast or local broadcast */ if (ipv4_is_multicast(ip_hdr(skb)->daddr) || ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); } /* called with rcu lock held */ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_out(vrf_dev, sk, skb); case AF_INET6: return vrf_ip6_out(vrf_dev, sk, skb); } return skb; } /* holding rtnl */ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) { struct rtable *rth = rtnl_dereference(vrf->rth); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rth, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rth) { dst = &rth->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rtable_create(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; if (!fib_new_table(dev_net(dev), vrf->tb_id)) return -ENOMEM; /* create a dst for routing packets out through a VRF device */ rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1); if (!rth) return -ENOMEM; rth->dst.output = vrf_output; rcu_assign_pointer(vrf->rth, rth); return 0; } /**************************** device handling ********************/ /* cycle interface to flush neighbor cache and move routes across tables */ static void cycle_netdev(struct net_device *dev, struct netlink_ext_ack *extack) { unsigned int flags = dev->flags; int ret; if (!netif_running(dev)) return; ret = dev_change_flags(dev, flags & ~IFF_UP, extack); if (ret >= 0) ret = dev_change_flags(dev, flags, extack); if (ret < 0) { netdev_err(dev, "Failed to cycle device %s; route tables might be wrong!\n", dev->name); } } static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { int ret; /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ if (port_dev == dev_net(dev)->loopback_dev) { NL_SET_ERR_MSG(extack, "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; cycle_netdev(port_dev, extack); return 0; err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave an L3 master device to a VRF"); return -EINVAL; } if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; cycle_netdev(port_dev, NULL); return 0; } static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { return do_vrf_del_slave(dev, port_dev); } static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; dev->flags = IFF_MASTER | IFF_NOARP; /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); return 0; out_rth: vrf_rtable_release(dev, vrf); out_nomem: return -ENOMEM; } static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; static u32 vrf_fib_table(const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return vrf->tb_id; } static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; } static int vrf_prepare_mac_header(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto) { struct ethhdr *eth; int err; /* in general, we do not know if there is enough space in the head of * the packet for hosting the mac header. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev)); if (unlikely(err)) /* no space in the skb head */ return -ENOBUFS; __skb_push(skb, ETH_HLEN); eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. */ ether_addr_copy(eth->h_dest, vrf_dev->dev_addr); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth->h_proto = htons(proto); /* the destination address of the Ethernet frame corresponds to the * address set on the VRF interface; therefore, the packet is intended * to be processed locally. */ skb->protocol = eth->h_proto; skb->pkt_type = PACKET_HOST; skb_postpush_rcsum(skb, skb->data, ETH_HLEN); skb_pull_inline(skb, ETH_HLEN); return 0; } /* prepare and add the mac header to the packet if it was not set previously. * In this way, packet sniffers such as tcpdump can parse the packet correctly. * If the mac header was already set, the original mac header is left * untouched and the function returns immediately. */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto, struct net_device *orig_dev) { if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); } #if IS_ENABLED(CONFIG_IPV6) /* neighbor handling is done with actual device; do not want * to flip skb->dev for those ndisc packets. This really fails * for multiple next protocols (e.g., NEXTHDR_HOP). But it is * a start. */ static bool ipv6_ndisc_frame(const struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); bool rc = false; if (iph->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; struct icmp6hdr _icmph; icmph = skb_header_pointer(skb, sizeof(*iph), sizeof(_icmph), &_icmph); if (!icmph) goto out; switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: rc = true; break; } } out: return rc; } static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, int ifindex) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_iif = ifindex, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), }; struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst)) return; skb_dst_set(skb, &rt6->dst); } static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For non-loopback strict packets, determine the dst using the original * ifindex. */ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; else vrf_ip6_input_dst(skb, vrf_dev, orig_iif); goto out; } /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { struct net_device *orig_dev = skb->dev; dev_dstats_rx_add(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IPV6, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } if (need_strict) vrf_ip6_input_dst(skb, vrf_dev, orig_iif); skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } #else static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { return skb; } #endif static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_device *orig_dev = skb->dev; skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; /* loopback traffic; do not push through packet taps again. * Reset pkt_type for upper layers to process skb */ if (skb->pkt_type == PACKET_LOOPBACK) { skb->pkt_type = PACKET_HOST; goto out; } dev_dstats_rx_add(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } /* called with rcu lock held */ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_rcv(vrf_dev, skb); case AF_INET6: return vrf_ip6_rcv(vrf_dev, skb); } return skb; } #if IS_ENABLED(CONFIG_IPV6) /* send to link-local or multicast address via interface enslaved to * VRF device. Force lookup to VRF table without changing flow struct * Note: Caller to this function must hold rcu_read_lock() and no refcnt * is taken on the dst by this function. */ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, struct flowi6 *fl6) { struct net *net = dev_net(dev); int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF; struct dst_entry *dst = NULL; struct rt6_info *rt; /* VRF device does not have a link-local address and * sending packets to link-local or mcast addresses over * a VRF device does not make sense */ if (fl6->flowi6_oif == dev->ifindex) { dst = &net->ipv6.ip6_null_entry->dst; return dst; } if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; return dst; } #endif static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_l3_rcv = vrf_l3_rcv, .l3mdev_l3_out = vrf_l3_out, #if IS_ENABLED(CONFIG_IPV6) .l3mdev_link_scope_lookup = vrf_link_scope_lookup, #endif }; static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops vrf_ethtool_ops = { .get_drvinfo = vrf_get_drvinfo, }; static inline size_t vrf_fib_rule_nl_size(void) { size_t sz; sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) { struct fib_rule_hdr *frh; struct nlmsghdr *nlh; struct sk_buff *skb; int err; if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) && !ipv6_mod_enabled()) return 0; skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0); if (!nlh) goto nla_put_failure; /* rule only needs to appear once */ nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); frh->family = family; frh->action = FR_ACT_TO_TBL; if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) goto nla_put_failure; if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) goto nla_put_failure; nlmsg_end(skb, nlh); /* fib_nl_{new,del}rule handling looks for net from skb->sk */ skb->sk = dev_net(dev)->rtnl; if (add_it) { err = fib_nl_newrule(skb, nlh, NULL); if (err == -EEXIST) err = 0; } else { err = fib_nl_delrule(skb, nlh, NULL); if (err == -ENOENT) err = 0; } nlmsg_free(skb); return err; nla_put_failure: nlmsg_free(skb); return -EMSGSIZE; } static int vrf_add_fib_rules(const struct net_device *dev) { int err; err = vrf_fib_rule(dev, AF_INET, true); if (err < 0) goto out_err; err = vrf_fib_rule(dev, AF_INET6, true); if (err < 0) goto ipv6_err; #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true); if (err < 0) goto ipmr_err; #endif #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true); if (err < 0) goto ip6mr_err; #endif return 0; #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) ip6mr_err: vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false); #endif #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) ipmr_err: vrf_fib_rule(dev, AF_INET6, false); #endif ipv6_err: vrf_fib_rule(dev, AF_INET, false); out_err: netdev_err(dev, "Failed to add FIB rules.\n"); return err; } static void vrf_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ dev->netns_local = true; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* enable offload features */ dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->hw_features = dev->features; dev->hw_enc_features = dev->features; /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EADDRNOTAVAIL; } } return 0; } static void vrf_dellink(struct net_device *dev, struct list_head *head) { struct net_device *port_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) vrf_del_slave(dev, port_dev); vrf_map_unregister_dev(dev); unregister_netdevice_queue(dev, head); } static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) { NL_SET_ERR_MSG(extack, "VRF table id is missing"); return -EINVAL; } vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); if (vrf->tb_id == RT_TABLE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE], "Invalid VRF table id"); return -EINVAL; } dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err) goto out; /* mapping between table_id and vrf; * note: such binding could not be done in the dev init function * because dev->ifindex id is not available yet. */ vrf->ifindex = dev->ifindex; err = vrf_map_register_dev(dev, extack); if (err) { unregister_netdevice(dev); goto out; } net = dev_net(dev); nn_vrf = net_generic(net, vrf_net_id); add_fib_rules = &nn_vrf->add_fib_rules; if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { vrf_map_unregister_dev(dev); unregister_netdevice(dev); goto out; } *add_fib_rules = false; } out: return err; } static size_t vrf_nl_getsize(const struct net_device *dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ } static int vrf_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); } static size_t vrf_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */ } static int vrf_fill_slave_info(struct sk_buff *skb, const struct net_device *vrf_dev, const struct net_device *slave_dev) { struct net_vrf *vrf = netdev_priv(vrf_dev); if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id)) return -EMSGSIZE; return 0; } static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { [IFLA_VRF_TABLE] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vrf_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct net_vrf), .get_size = vrf_nl_getsize, .policy = vrf_nl_policy, .validate = vrf_validate, .fill_info = vrf_fillinfo, .get_slave_size = vrf_get_slave_size, .fill_slave_info = vrf_fill_slave_info, .newlink = vrf_newlink, .dellink = vrf_dellink, .setup = vrf_setup, .maxtype = IFLA_VRF_MAX, }; static int vrf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); vrf_del_slave(vrf_dev, dev); } out: return NOTIFY_DONE; } static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; static int vrf_map_init(struct vrf_map *vmap) { spin_lock_init(&vmap->vmap_lock); hash_init(vmap->ht); vmap->strict_mode = false; return 0; } #ifdef CONFIG_SYSCTL static bool vrf_strict_mode(struct vrf_map *vmap) { bool strict_mode; vrf_map_lock(vmap); strict_mode = vmap->strict_mode; vrf_map_unlock(vmap); return strict_mode; } static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) { bool *cur_mode; int res = 0; vrf_map_lock(vmap); cur_mode = &vmap->strict_mode; if (*cur_mode == new_mode) goto unlock; if (*cur_mode) { /* disable strict mode */ *cur_mode = false; } else { if (vmap->shared_tables) { /* we cannot allow strict_mode because there are some * vrfs that share one or more tables. */ res = -EBUSY; goto unlock; } /* no tables are shared among vrfs, so we can go back * to 1:1 association between a vrf with its table. */ *cur_mode = true; } unlock: vrf_map_unlock(vmap); return res; } static int vrf_shared_table_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->extra1; struct vrf_map *vmap = netns_vrf_map(net); int proc_strict_mode = 0; struct ctl_table tmp = { .procname = table->procname, .data = &proc_strict_mode, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; int ret; if (!write) proc_strict_mode = vrf_strict_mode(vmap); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode); return ret; } static const struct ctl_table vrf_table[] = { { .procname = "strict_mode", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = vrf_shared_table_handler, /* set by the vrf_netns_init */ .extra1 = NULL, }, }; static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { struct ctl_table *table; table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) return -ENOMEM; /* init the extra1 parameter with the reference to current netns */ table[0].extra1 = net; nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table, ARRAY_SIZE(vrf_table)); if (!nn_vrf->ctl_hdr) { kfree(table); return -ENOMEM; } return 0; } static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); const struct ctl_table *table; table = nn_vrf->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } #else static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { return 0; } static void vrf_netns_exit_sysctl(struct net *net) { } #endif /* Initialize per network namespace state */ static int __net_init vrf_netns_init(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); nn_vrf->add_fib_rules = true; vrf_map_init(&nn_vrf->vmap); return vrf_netns_init_sysctl(net, nn_vrf); } static void __net_exit vrf_netns_exit(struct net *net) { vrf_netns_exit_sysctl(net); } static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .exit = vrf_netns_exit, .id = &vrf_net_id, .size = sizeof(struct netns_vrf), }; static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); if (rc < 0) goto unreg_pernet; rc = rtnl_link_register(&vrf_link_ops); if (rc < 0) goto table_lookup_unreg; return 0; table_lookup_unreg: l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); unreg_pernet: unregister_pernet_subsys(&vrf_net_ops); error: unregister_netdevice_notifier(&vrf_notifier_block); return rc; } module_init(vrf_init_module); MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); MODULE_VERSION(DRV_VERSION); |
| 264 257 15 193 228 257 3 244 4 6 6 6 6 273 246 6 10 10 8 8 3 10 6 1 10 10 10 9 1 3 3 1 2 11 244 9 1 7 7 7 256 244 244 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate hardware time stamp based on cycles if supported */ SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; union { struct { u32 xdp_frags_size; u32 xdp_frags_truesize; }; /* * Intermediate layers must ensure that destructor_arg * remains valid until skb destructor. */ void *destructor_arg; }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @unreadable: indicates that at least 1 of the fragments in this skb is * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) { return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } /* Return true if frags in this skb are readable by the host. */ static inline bool skb_frags_readable(const struct sk_buff *skb) { return !skb->unreadable; } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); if (netmem_is_net_iov(netmem)) { skb->unreadable = true; return; } page = netmem_to_page(netmem); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } #if defined(CONFIG_FAIL_SKB_REALLOC) void skb_might_realloc(struct sk_buff *skb); #else static inline void skb_might_realloc(struct sk_buff *skb) {} #endif /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_len(struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { DEBUG_NET_WARN_ON_ONCE(1); skb->mac_len = 0; } else { skb->mac_len = skb->network_header - skb->mac_header; } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); skb->transport_header = offset; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline enum skb_drop_reason pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /* Return: true if the skb_frag contains a net_iov. */ static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { return netmem_is_net_iov(frag->netmem); } /** * skb_frag_net_iov - retrieve the net_iov referred to by fragment * @frag: the fragment * * Return: the &struct net_iov associated with @frag. Returns NULL if this * frag has no associated net_iov. */ static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { if (!skb_frag_is_net_iov(frag)) return NULL; return netmem_to_net_iov(frag->netmem); } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Return: the &struct page associated with @frag. Returns NULL if this frag * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { if (skb_frag_is_net_iov(frag)) return NULL; return netmem_to_page(frag->netmem); } /** * skb_frag_netmem - retrieve the netmem referred to by a fragment * @frag: the fragment * * Return: the &netmem_ref associated with @frag. */ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { return frag->netmem; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { if (!skb_frag_page(frag)) return NULL; return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { void *ptr = page_address(skb_frag_page(frag)); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } #define skb_frag_dma_map(dev, frag, ...) \ CONCATENATE(_skb_frag_dma_map, \ COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) #define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ const skb_frag_t *uf = (frag); \ size_t uo = (offset); \ \ __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ DMA_TO_DEVICE); \ }) #define _skb_frag_dma_map1(dev, frag, offset) \ __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ __UNIQUE_ID(offset_)) #define _skb_frag_dma_map0(dev, frag) \ _skb_frag_dma_map1(dev, frag, 0) #define _skb_frag_dma_map2(dev, frag, offset, size) \ __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) #define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ __skb_frag_dma_map(dev, frag, offset, size, dir) static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 190 7 275 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/math.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct file; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } #define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else # define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif #define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) union shortname_store { unsigned char string[DNAME_INLINE_LEN]; unsigned long words[DNAME_INLINE_WORDS]; }; #define d_lock d_lockref.lock #define d_iname d_shortname.string struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ union shortname_store d_shortname; /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ /* --- cacheline 2 boundary (128 bytes) --- */ struct lockref d_lockref; /* per-dentry lock and refcount * keep separate from RCU lookup area if * possible! */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct hlist_node d_sib; /* child of parent list */ struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ union { struct hlist_node d_alias; /* inode alias list */ struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; }; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; enum d_real_type { D_REAL_DATA, D_REAL_METADATA, }; struct dentry_operations { int (*d_revalidate)(struct inode *, const struct qstr *, struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); bool (*d_unalias_trylock)(const struct dentry *); void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ #define DCACHE_OP_HASH BIT(0) #define DCACHE_OP_COMPARE BIT(1) #define DCACHE_OP_REVALIDATE BIT(2) #define DCACHE_OP_DELETE BIT(3) #define DCACHE_OP_PRUNE BIT(4) #define DCACHE_DISCONNECTED BIT(5) /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first * endeavour to clear the bit either by discovering that it is connected, * or by performing lookup operations. Any filesystem which supports * nfsd_operations MUST have a lookup function which, if it finds a * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ #define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */ #define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ #define DCACHE_CANT_MOUNT BIT(8) #define DCACHE_GENOCIDE BIT(9) #define DCACHE_SHRINK_LIST BIT(10) #define DCACHE_OP_WEAK_REVALIDATE BIT(11) #define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ #define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) /* Parent inode is watched by some fsnotify listener */ #define DCACHE_DENTRY_KILLED BIT(15) #define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ #define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) #define DCACHE_LRU_LIST BIT(19) #define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ #define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ #define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ #define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ #define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ #define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ #define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ #define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ #define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ #define DCACHE_OP_REAL BIT(26) #define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ #define DCACHE_DENTRY_CURSOR BIT(29) #define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); extern struct dentry *d_find_alias_rcu(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } ino_t d_parent_ino(struct dentry *dentry); /* * helper function for dentry_operations.d_dname() members */ extern __printf(3, 4) char *dynamic_dname(char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(const struct dentry *, char *, int); extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** * dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a live dentry, increment the reference count and return the dentry. * Caller must hold @dentry->d_lock. Making sure that dentry is alive is * caller's resonsibility. There are many conditions sufficient to guarantee * that; e.g. anything with non-negative refcount is alive, so's anything * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; return dentry; } /** * dget - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. Conversely, a dentry with * no references can disappear for any number of reasons, starting * with memory pressure. In other words, that primitive is * used to clone an existing reference; using it on something with * zero refcount is a bug. * * NOTE: it will spin if @dentry->d_lock is held. From the deadlock * avoidance point of view it is equivalent to spin_lock()/increment * refcount/spin_unlock(), so calling it under @dentry->d_lock is * always a bug; so's calling it under ->d_lock on any of its descendents. * */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_unhash_wake(struct dentry *dentry); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) __d_lookup_unhash_wake(dentry); } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, 100); } /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, type); else return dentry; } /** * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { struct qstr name; union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); static inline struct dentry *d_first_child(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); } static inline struct dentry *d_next_sibling(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); } #endif /* __LINUX_DCACHE_H */ |
| 174 174 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock LSM - Ruleset management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #include <linux/bits.h> #include <linux/bug.h> #include <linux/cleanup.h> #include <linux/compiler_types.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/overflow.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include "access.h" #include "limits.h" #include "object.h" #include "ruleset.h" static struct landlock_ruleset *create_ruleset(const u32 num_layers) { struct landlock_ruleset *new_ruleset; new_ruleset = kzalloc(struct_size(new_ruleset, access_masks, num_layers), GFP_KERNEL_ACCOUNT); if (!new_ruleset) return ERR_PTR(-ENOMEM); refcount_set(&new_ruleset->usage, 1); mutex_init(&new_ruleset->lock); new_ruleset->root_inode = RB_ROOT; #if IS_ENABLED(CONFIG_INET) new_ruleset->root_net_port = RB_ROOT; #endif /* IS_ENABLED(CONFIG_INET) */ new_ruleset->num_layers = num_layers; /* * hierarchy = NULL * num_rules = 0 * access_masks[] = 0 */ return new_ruleset; } struct landlock_ruleset * landlock_create_ruleset(const access_mask_t fs_access_mask, const access_mask_t net_access_mask, const access_mask_t scope_mask) { struct landlock_ruleset *new_ruleset; /* Informs about useless ruleset. */ if (!fs_access_mask && !net_access_mask && !scope_mask) return ERR_PTR(-ENOMSG); new_ruleset = create_ruleset(1); if (IS_ERR(new_ruleset)) return new_ruleset; if (fs_access_mask) landlock_add_fs_access_mask(new_ruleset, fs_access_mask, 0); if (net_access_mask) landlock_add_net_access_mask(new_ruleset, net_access_mask, 0); if (scope_mask) landlock_add_scope_mask(new_ruleset, scope_mask, 0); return new_ruleset; } static void build_check_rule(void) { const struct landlock_rule rule = { .num_layers = ~0, }; BUILD_BUG_ON(rule.num_layers < LANDLOCK_MAX_NUM_LAYERS); } static bool is_object_pointer(const enum landlock_key_type key_type) { switch (key_type) { case LANDLOCK_KEY_INODE: return true; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: return false; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return false; } } static struct landlock_rule * create_rule(const struct landlock_id id, const struct landlock_layer (*const layers)[], const u32 num_layers, const struct landlock_layer *const new_layer) { struct landlock_rule *new_rule; u32 new_num_layers; build_check_rule(); if (new_layer) { /* Should already be checked by landlock_merge_ruleset(). */ if (WARN_ON_ONCE(num_layers >= LANDLOCK_MAX_NUM_LAYERS)) return ERR_PTR(-E2BIG); new_num_layers = num_layers + 1; } else { new_num_layers = num_layers; } new_rule = kzalloc(struct_size(new_rule, layers, new_num_layers), GFP_KERNEL_ACCOUNT); if (!new_rule) return ERR_PTR(-ENOMEM); RB_CLEAR_NODE(&new_rule->node); if (is_object_pointer(id.type)) { /* This should be catched by insert_rule(). */ WARN_ON_ONCE(!id.key.object); landlock_get_object(id.key.object); } new_rule->key = id.key; new_rule->num_layers = new_num_layers; /* Copies the original layer stack. */ memcpy(new_rule->layers, layers, flex_array_size(new_rule, layers, num_layers)); if (new_layer) /* Adds a copy of @new_layer on the layer stack. */ new_rule->layers[new_rule->num_layers - 1] = *new_layer; return new_rule; } static struct rb_root *get_root(struct landlock_ruleset *const ruleset, const enum landlock_key_type key_type) { switch (key_type) { case LANDLOCK_KEY_INODE: return &ruleset->root_inode; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: return &ruleset->root_net_port; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); } } static void free_rule(struct landlock_rule *const rule, const enum landlock_key_type key_type) { might_sleep(); if (!rule) return; if (is_object_pointer(key_type)) landlock_put_object(rule->key.object); kfree(rule); } static void build_check_ruleset(void) { const struct landlock_ruleset ruleset = { .num_rules = ~0, .num_layers = ~0, }; BUILD_BUG_ON(ruleset.num_rules < LANDLOCK_MAX_NUM_RULES); BUILD_BUG_ON(ruleset.num_layers < LANDLOCK_MAX_NUM_LAYERS); } /** * insert_rule - Create and insert a rule in a ruleset * * @ruleset: The ruleset to be updated. * @id: The ID to build the new rule with. The underlying kernel object, if * any, must be held by the caller. * @layers: One or multiple layers to be copied into the new rule. * @num_layers: The number of @layers entries. * * When user space requests to add a new rule to a ruleset, @layers only * contains one entry and this entry is not assigned to any level. In this * case, the new rule will extend @ruleset, similarly to a boolean OR between * access rights. * * When merging a ruleset in a domain, or copying a domain, @layers will be * added to @ruleset as new constraints, similarly to a boolean AND between * access rights. */ static int insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const struct landlock_layer (*const layers)[], const size_t num_layers) { struct rb_node **walker_node; struct rb_node *parent_node = NULL; struct landlock_rule *new_rule; struct rb_root *root; might_sleep(); lockdep_assert_held(&ruleset->lock); if (WARN_ON_ONCE(!layers)) return -ENOENT; if (is_object_pointer(id.type) && WARN_ON_ONCE(!id.key.object)) return -ENOENT; root = get_root(ruleset, id.type); if (IS_ERR(root)) return PTR_ERR(root); walker_node = &root->rb_node; while (*walker_node) { struct landlock_rule *const this = rb_entry(*walker_node, struct landlock_rule, node); if (this->key.data != id.key.data) { parent_node = *walker_node; if (this->key.data < id.key.data) walker_node = &((*walker_node)->rb_right); else walker_node = &((*walker_node)->rb_left); continue; } /* Only a single-level layer should match an existing rule. */ if (WARN_ON_ONCE(num_layers != 1)) return -EINVAL; /* If there is a matching rule, updates it. */ if ((*layers)[0].level == 0) { /* * Extends access rights when the request comes from * landlock_add_rule(2), i.e. @ruleset is not a domain. */ if (WARN_ON_ONCE(this->num_layers != 1)) return -EINVAL; if (WARN_ON_ONCE(this->layers[0].level != 0)) return -EINVAL; this->layers[0].access |= (*layers)[0].access; return 0; } if (WARN_ON_ONCE(this->layers[0].level == 0)) return -EINVAL; /* * Intersects access rights when it is a merge between a * ruleset and a domain. */ new_rule = create_rule(id, &this->layers, this->num_layers, &(*layers)[0]); if (IS_ERR(new_rule)) return PTR_ERR(new_rule); rb_replace_node(&this->node, &new_rule->node, root); free_rule(this, id.type); return 0; } /* There is no match for @id. */ build_check_ruleset(); if (ruleset->num_rules >= LANDLOCK_MAX_NUM_RULES) return -E2BIG; new_rule = create_rule(id, layers, num_layers, NULL); if (IS_ERR(new_rule)) return PTR_ERR(new_rule); rb_link_node(&new_rule->node, parent_node, walker_node); rb_insert_color(&new_rule->node, root); ruleset->num_rules++; return 0; } static void build_check_layer(void) { const struct landlock_layer layer = { .level = ~0, .access = ~0, }; BUILD_BUG_ON(layer.level < LANDLOCK_MAX_NUM_LAYERS); BUILD_BUG_ON(layer.access < LANDLOCK_MASK_ACCESS_FS); } /* @ruleset must be locked by the caller. */ int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access) { struct landlock_layer layers[] = { { .access = access, /* When @level is zero, insert_rule() extends @ruleset. */ .level = 0, } }; build_check_layer(); return insert_rule(ruleset, id, &layers, ARRAY_SIZE(layers)); } static void get_hierarchy(struct landlock_hierarchy *const hierarchy) { if (hierarchy) refcount_inc(&hierarchy->usage); } static void put_hierarchy(struct landlock_hierarchy *hierarchy) { while (hierarchy && refcount_dec_and_test(&hierarchy->usage)) { const struct landlock_hierarchy *const freeme = hierarchy; hierarchy = hierarchy->parent; kfree(freeme); } } static int merge_tree(struct landlock_ruleset *const dst, struct landlock_ruleset *const src, const enum landlock_key_type key_type) { struct landlock_rule *walker_rule, *next_rule; struct rb_root *src_root; int err = 0; might_sleep(); lockdep_assert_held(&dst->lock); lockdep_assert_held(&src->lock); src_root = get_root(src, key_type); if (IS_ERR(src_root)) return PTR_ERR(src_root); /* Merges the @src tree. */ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, src_root, node) { struct landlock_layer layers[] = { { .level = dst->num_layers, } }; const struct landlock_id id = { .key = walker_rule->key, .type = key_type, }; if (WARN_ON_ONCE(walker_rule->num_layers != 1)) return -EINVAL; if (WARN_ON_ONCE(walker_rule->layers[0].level != 0)) return -EINVAL; layers[0].access = walker_rule->layers[0].access; err = insert_rule(dst, id, &layers, ARRAY_SIZE(layers)); if (err) return err; } return err; } static int merge_ruleset(struct landlock_ruleset *const dst, struct landlock_ruleset *const src) { int err = 0; might_sleep(); /* Should already be checked by landlock_merge_ruleset() */ if (WARN_ON_ONCE(!src)) return 0; /* Only merge into a domain. */ if (WARN_ON_ONCE(!dst || !dst->hierarchy)) return -EINVAL; /* Locks @dst first because we are its only owner. */ mutex_lock(&dst->lock); mutex_lock_nested(&src->lock, SINGLE_DEPTH_NESTING); /* Stacks the new layer. */ if (WARN_ON_ONCE(src->num_layers != 1 || dst->num_layers < 1)) { err = -EINVAL; goto out_unlock; } dst->access_masks[dst->num_layers - 1] = landlock_upgrade_handled_access_masks(src->access_masks[0]); /* Merges the @src inode tree. */ err = merge_tree(dst, src, LANDLOCK_KEY_INODE); if (err) goto out_unlock; #if IS_ENABLED(CONFIG_INET) /* Merges the @src network port tree. */ err = merge_tree(dst, src, LANDLOCK_KEY_NET_PORT); if (err) goto out_unlock; #endif /* IS_ENABLED(CONFIG_INET) */ out_unlock: mutex_unlock(&src->lock); mutex_unlock(&dst->lock); return err; } static int inherit_tree(struct landlock_ruleset *const parent, struct landlock_ruleset *const child, const enum landlock_key_type key_type) { struct landlock_rule *walker_rule, *next_rule; struct rb_root *parent_root; int err = 0; might_sleep(); lockdep_assert_held(&parent->lock); lockdep_assert_held(&child->lock); parent_root = get_root(parent, key_type); if (IS_ERR(parent_root)) return PTR_ERR(parent_root); /* Copies the @parent inode or network tree. */ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, parent_root, node) { const struct landlock_id id = { .key = walker_rule->key, .type = key_type, }; err = insert_rule(child, id, &walker_rule->layers, walker_rule->num_layers); if (err) return err; } return err; } static int inherit_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const child) { int err = 0; might_sleep(); if (!parent) return 0; /* Locks @child first because we are its only owner. */ mutex_lock(&child->lock); mutex_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); /* Copies the @parent inode tree. */ err = inherit_tree(parent, child, LANDLOCK_KEY_INODE); if (err) goto out_unlock; #if IS_ENABLED(CONFIG_INET) /* Copies the @parent network port tree. */ err = inherit_tree(parent, child, LANDLOCK_KEY_NET_PORT); if (err) goto out_unlock; #endif /* IS_ENABLED(CONFIG_INET) */ if (WARN_ON_ONCE(child->num_layers <= parent->num_layers)) { err = -EINVAL; goto out_unlock; } /* Copies the parent layer stack and leaves a space for the new layer. */ memcpy(child->access_masks, parent->access_masks, flex_array_size(parent, access_masks, parent->num_layers)); if (WARN_ON_ONCE(!parent->hierarchy)) { err = -EINVAL; goto out_unlock; } get_hierarchy(parent->hierarchy); child->hierarchy->parent = parent->hierarchy; out_unlock: mutex_unlock(&parent->lock); mutex_unlock(&child->lock); return err; } static void free_ruleset(struct landlock_ruleset *const ruleset) { struct landlock_rule *freeme, *next; might_sleep(); rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root_inode, node) free_rule(freeme, LANDLOCK_KEY_INODE); #if IS_ENABLED(CONFIG_INET) rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root_net_port, node) free_rule(freeme, LANDLOCK_KEY_NET_PORT); #endif /* IS_ENABLED(CONFIG_INET) */ put_hierarchy(ruleset->hierarchy); kfree(ruleset); } void landlock_put_ruleset(struct landlock_ruleset *const ruleset) { might_sleep(); if (ruleset && refcount_dec_and_test(&ruleset->usage)) free_ruleset(ruleset); } static void free_ruleset_work(struct work_struct *const work) { struct landlock_ruleset *ruleset; ruleset = container_of(work, struct landlock_ruleset, work_free); free_ruleset(ruleset); } void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset) { if (ruleset && refcount_dec_and_test(&ruleset->usage)) { INIT_WORK(&ruleset->work_free, free_ruleset_work); schedule_work(&ruleset->work_free); } } /** * landlock_merge_ruleset - Merge a ruleset with a domain * * @parent: Parent domain. * @ruleset: New ruleset to be merged. * * Returns the intersection of @parent and @ruleset, or returns @parent if * @ruleset is empty, or returns a duplicate of @ruleset if @parent is empty. */ struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset) { struct landlock_ruleset *new_dom __free(landlock_put_ruleset) = NULL; u32 num_layers; int err; might_sleep(); if (WARN_ON_ONCE(!ruleset || parent == ruleset)) return ERR_PTR(-EINVAL); if (parent) { if (parent->num_layers >= LANDLOCK_MAX_NUM_LAYERS) return ERR_PTR(-E2BIG); num_layers = parent->num_layers + 1; } else { num_layers = 1; } /* Creates a new domain... */ new_dom = create_ruleset(num_layers); if (IS_ERR(new_dom)) return new_dom; new_dom->hierarchy = kzalloc(sizeof(*new_dom->hierarchy), GFP_KERNEL_ACCOUNT); if (!new_dom->hierarchy) return ERR_PTR(-ENOMEM); refcount_set(&new_dom->hierarchy->usage, 1); /* ...as a child of @parent... */ err = inherit_ruleset(parent, new_dom); if (err) return ERR_PTR(err); /* ...and including @ruleset. */ err = merge_ruleset(new_dom, ruleset); if (err) return ERR_PTR(err); return no_free_ptr(new_dom); } /* * The returned access has the same lifetime as @ruleset. */ const struct landlock_rule * landlock_find_rule(const struct landlock_ruleset *const ruleset, const struct landlock_id id) { const struct rb_root *root; const struct rb_node *node; root = get_root((struct landlock_ruleset *)ruleset, id.type); if (IS_ERR(root)) return NULL; node = root->rb_node; while (node) { struct landlock_rule *this = rb_entry(node, struct landlock_rule, node); if (this->key.data == id.key.data) return this; if (this->key.data < id.key.data) node = node->rb_right; else node = node->rb_left; } return NULL; } /* * @layer_masks is read and may be updated according to the access request and * the matching rule. * @masks_array_size must be equal to ARRAY_SIZE(*layer_masks). * * Returns true if the request is allowed (i.e. relevant layer masks for the * request are empty). */ bool landlock_unmask_layers(const struct landlock_rule *const rule, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const size_t masks_array_size) { size_t layer_level; if (!access_request || !layer_masks) return true; if (!rule) return false; /* * An access is granted if, for each policy layer, at least one rule * encountered on the pathwalk grants the requested access, * regardless of its position in the layer stack. We must then check * the remaining layers for each inode, from the first added layer to * the last one. When there is multiple requested accesses, for each * policy layer, the full set of requested accesses may not be granted * by only one rule, but by the union (binary OR) of multiple rules. * E.g. /a/b <execute> + /a <read> => /a/b <execute + read> */ for (layer_level = 0; layer_level < rule->num_layers; layer_level++) { const struct landlock_layer *const layer = &rule->layers[layer_level]; const layer_mask_t layer_bit = BIT_ULL(layer->level - 1); const unsigned long access_req = access_request; unsigned long access_bit; bool is_empty; /* * Records in @layer_masks which layer grants access to each * requested access. */ is_empty = true; for_each_set_bit(access_bit, &access_req, masks_array_size) { if (layer->access & BIT_ULL(access_bit)) (*layer_masks)[access_bit] &= ~layer_bit; is_empty = is_empty && !(*layer_masks)[access_bit]; } if (is_empty) return true; } return false; } typedef access_mask_t get_access_mask_t(const struct landlock_ruleset *const ruleset, const u16 layer_level); /** * landlock_init_layer_masks - Initialize layer masks from an access request * * Populates @layer_masks such that for each access right in @access_request, * the bits for all the layers are set where this access right is handled. * * @domain: The domain that defines the current restrictions. * @access_request: The requested access rights to check. * @layer_masks: It must contain %LANDLOCK_NUM_ACCESS_FS or * %LANDLOCK_NUM_ACCESS_NET elements according to @key_type. * @key_type: The key type to switch between access masks of different types. * * Returns: An access mask where each access right bit is set which is handled * in any of the active layers in @domain. */ access_mask_t landlock_init_layer_masks(const struct landlock_ruleset *const domain, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const enum landlock_key_type key_type) { access_mask_t handled_accesses = 0; size_t layer_level, num_access; get_access_mask_t *get_access_mask; switch (key_type) { case LANDLOCK_KEY_INODE: get_access_mask = landlock_get_fs_access_mask; num_access = LANDLOCK_NUM_ACCESS_FS; break; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: get_access_mask = landlock_get_net_access_mask; num_access = LANDLOCK_NUM_ACCESS_NET; break; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return 0; } memset(layer_masks, 0, array_size(sizeof((*layer_masks)[0]), num_access)); /* An empty access request can happen because of O_WRONLY | O_RDWR. */ if (!access_request) return 0; /* Saves all handled accesses per layer. */ for (layer_level = 0; layer_level < domain->num_layers; layer_level++) { const unsigned long access_req = access_request; const access_mask_t access_mask = get_access_mask(domain, layer_level); unsigned long access_bit; for_each_set_bit(access_bit, &access_req, num_access) { if (BIT_ULL(access_bit) & access_mask) { (*layer_masks)[access_bit] |= BIT_ULL(layer_level); handled_accesses |= BIT_ULL(access_bit); } } } return handled_accesses; } |
| 3 3 3 3 3 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" #define DEVLINK_PORT_FN_CAPS_VALID_MASK \ (_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1) static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, DEVLINK_PORT_FN_STATE_ACTIVE), [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), [DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] = { .type = NLA_U32 }, }; #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ WARN_ON_ONCE((devlink_port)->registered) struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, unsigned int port_index) { return xa_load(&devlink->ports, port_index); } struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_PORT_INDEX]) { u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return ERR_PTR(-ENODEV); return devlink_port; } return ERR_PTR(-EINVAL); } struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_port_get_from_attrs(devlink, info->attrs); } static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, u32 cap, bool is_enable) { caps->selector |= cap; if (is_enable) caps->value |= cap; } static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_roce_get) return 0; err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable); return 0; } static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_migratable_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_migratable_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); return 0; } static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_crypto_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable); return 0; } static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_packet_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable); return 0; } static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { struct nla_bitfield32 caps = {}; int err; err = devlink_port_fn_roce_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack); if (err) return err; if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, caps.selector); if (err) return err; *msg_updated = true; return 0; } static int devlink_port_fn_max_io_eqs_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u32 max_io_eqs; int err; if (!port->ops->port_fn_max_io_eqs_get) return 0; err = port->ops->port_fn_max_io_eqs_get(port, &max_io_eqs, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put_u32(msg, DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, max_io_eqs); if (err) return err; *msg_updated = true; return 0; } int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) { if (devlink_nl_put_handle(msg, devlink_port->devlink)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) return -EMSGSIZE; return 0; } size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { struct devlink_port_attrs *attrs = &devlink_port->attrs; if (!devlink_port->attrs_set) return 0; if (attrs->lanes) { if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) return -EMSGSIZE; } if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) return -EMSGSIZE; if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_pf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_vf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_SF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_sf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_sf.pf) || nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, attrs->pci_sf.sf)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; if (!attrs->split) return 0; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->phys.port_number)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, attrs->phys.split_subport_number)) return -EMSGSIZE; break; default: break; } return 0; } static int devlink_port_fn_hw_addr_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u8 hw_addr[MAX_ADDR_LEN]; int hw_addr_len; int err; if (!port->ops->port_fn_hw_addr_get) return 0; err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); if (err) return err; *msg_updated = true; return 0; } static bool devlink_port_fn_state_valid(enum devlink_port_fn_state state) { return state == DEVLINK_PORT_FN_STATE_INACTIVE || state == DEVLINK_PORT_FN_STATE_ACTIVE; } static bool devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) { return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; } static int devlink_port_fn_state_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { enum devlink_port_fn_opstate opstate; enum devlink_port_fn_state state; int err; if (!port->ops->port_fn_state_get) return 0; err = port->ops->port_fn_state_get(port, &state, &opstate, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } if (!devlink_port_fn_state_valid(state)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid state read from driver"); return -EINVAL; } if (!devlink_port_fn_opstate_valid(opstate)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid operational state read from driver"); return -EINVAL; } if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) return -EMSGSIZE; *msg_updated = true; return 0; } static int devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_migratable_set(devlink_port, enable, extack); } static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_roce_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack); } static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nla_bitfield32 caps; u32 caps_value; int err; caps = nla_get_bitfield32(attr); caps_value = caps.value & caps.selector; if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) { err = devlink_port_fn_roce_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_ROCE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { err = devlink_port_fn_mig_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_MIGRATABLE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_PACKET, extack); if (err) return err; } return 0; } static int devlink_port_fn_max_io_eqs_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { u32 max_io_eqs; max_io_eqs = nla_get_u32(attr); return devlink_port->ops->port_fn_max_io_eqs_set(devlink_port, max_io_eqs, extack); } static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct nlattr *function_attr; bool msg_updated = false; int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_max_io_eqs_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_rel_devlink_handle_put(msg, port->devlink, port->rel_index, DEVLINK_PORT_FN_ATTR_DEVLINK, &msg_updated); out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); return err; } static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink *devlink = devlink_port->devlink; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, ibdev->name)) goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) goto nla_put_failure; if (devlink_port->linecard && nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, devlink_linecard_index(devlink_port->linecard))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { struct devlink *devlink = devlink_port->devlink; struct devlink_obj_desc desc; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } devlink_nl_obj_desc_init(&desc, devlink); devlink_nl_obj_desc_port_set(&desc, devlink_port); devlink_nl_notify_send_desc(devlink, msg, &desc); } static void devlink_ports_notify(struct devlink *devlink, enum devlink_command cmd) { struct devlink_port *devlink_port; unsigned long port_index; xa_for_each(&devlink->ports, port_index, devlink_port) devlink_port_notify(devlink_port, cmd); } void devlink_ports_notify_register(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW); } void devlink_ports_notify_unregister(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL); } int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_port *devlink_port; unsigned long port_index; int err = 0; xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); if (err) { state->idx = port_index; break; } } return err; } int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one); } static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) { int err; if (!devlink_port->ops->port_type_set) return -EOPNOTSUPP; if (port_type == devlink_port->type) return 0; err = devlink_port->ops->port_type_set(devlink_port, port_type); if (err) return err; devlink_port->desired_type = port_type; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } static int devlink_port_function_hw_addr_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { const u8 *hw_addr; int hw_addr_len; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); if (hw_addr_len > MAX_ADDR_LEN) { NL_SET_ERR_MSG(extack, "Port function hardware address too long"); return -EINVAL; } if (port->type == DEVLINK_PORT_TYPE_ETH) { if (hw_addr_len != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Address must be 6 bytes for Ethernet device"); return -EINVAL; } if (!is_unicast_ether_addr(hw_addr)) { NL_SET_ERR_MSG(extack, "Non-unicast hardware address unsupported"); return -EINVAL; } } return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len, extack); } static int devlink_port_fn_state_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { enum devlink_port_fn_state state; state = nla_get_u8(attr); return port->ops->port_fn_state_set(port, state, extack); } static int devlink_port_function_validate(struct devlink_port *devlink_port, struct nlattr **tb, struct netlink_ext_ack *extack) { const struct devlink_port_ops *ops = devlink_port->ops; struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && !ops->port_fn_hw_addr_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], "Port doesn't support function attributes"); return -EOPNOTSUPP; } if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE], "Function does not support state setting"); return -EOPNOTSUPP; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { struct nla_bitfield32 caps; caps = nla_get_bitfield32(attr); if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE && !ops->port_fn_roce_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { if (!ops->port_fn_migratable_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support migratable function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "migratable function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { if (!ops->port_fn_ipsec_crypto_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_crypto function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_crypto function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { if (!ops->port_fn_ipsec_packet_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_packet function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_packet function attribute supported for VFs only"); return -EOPNOTSUPP; } } } if (tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] && !ops->port_fn_max_io_eqs_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS], "Function does not support max_io_eqs setting"); return -EOPNOTSUPP; } return 0; } static int devlink_port_function_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; int err; err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr, devlink_function_nl_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Fail to parse port function attributes"); return err; } err = devlink_port_function_validate(port, tb, extack); if (err) return err; attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; if (attr) { err = devlink_port_function_hw_addr_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { err = devlink_port_fn_caps_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS]; if (attr) { err = devlink_port_fn_max_io_eqs_set(port, attr, extack); if (err) return err; } /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. */ attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; if (attr) err = devlink_port_fn_state_set(port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { enum devlink_port_type port_type; port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); err = devlink_port_type_set(devlink_port, port_type); if (err) return err; } if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) { struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; struct netlink_ext_ack *extack = info->extack; err = devlink_port_function_set(devlink_port, attr, extack); if (err) return err; } return 0; } int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; u32 count; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) return -EINVAL; if (!devlink_port->ops->port_split) return -EOPNOTSUPP; count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); if (!devlink_port->attrs.splittable) { /* Split ports cannot be split. */ if (devlink_port->attrs.split) NL_SET_ERR_MSG(info->extack, "Port cannot be split further"); else NL_SET_ERR_MSG(info->extack, "Port cannot be split"); return -EINVAL; } if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { NL_SET_ERR_MSG(info->extack, "Invalid split count"); return -EINVAL; } return devlink_port->ops->port_split(devlink, devlink_port, count, info->extack); } int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_unsplit) return -EOPNOTSUPP; return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; struct devlink *devlink = info->user_ptr[0]; struct devlink_port *devlink_port; struct sk_buff *msg; int err; if (!devlink->ops->port_new) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { NL_SET_ERR_MSG(extack, "Port flavour or PCI PF are not specified"); return -EINVAL; } new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); new_attrs.pfnum = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { /* Port index of the new port being created by driver. */ new_attrs.port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); new_attrs.port_index_valid = true; } if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { new_attrs.controller = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); new_attrs.controller_valid = true; } if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); new_attrs.sfnum_valid = true; } err = devlink->ops->port_new(devlink, &new_attrs, extack, &devlink_port); if (err) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto err_out_port_del; } err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; err = genlmsg_reply(msg, info); if (err) goto err_out_port_del; return 0; err_out_msg_free: nlmsg_free(msg); err_out_port_del: devlink_port->ops->port_del(devlink, devlink_port, NULL); return err; } int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_del) return -EOPNOTSUPP; return devlink_port->ops->port_del(devlink, devlink_port, extack); } static void devlink_port_type_warn(struct work_struct *work) { struct devlink_port *port = container_of(to_delayed_work(work), struct devlink_port, type_warn_dw); dev_warn(port->devlink->dev, "Type was not set for devlink port."); } static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) { /* Ignore CPU and DSA flavours. */ return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; } #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; /* Schedule a work to WARN in case driver does not set port * type within timeout. */ schedule_delayed_work(&devlink_port->type_warn_dw, DEVLINK_PORT_TYPE_WARN_TIMEOUT); } static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; cancel_delayed_work_sync(&devlink_port->type_warn_dw); } /** * devlink_port_init() - Init devlink port * * @devlink: devlink * @devlink_port: devlink port * * Initialize essential stuff that is needed for functions * that may be called before devlink port registration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_init(struct devlink *devlink, struct devlink_port *devlink_port) { if (devlink_port->initialized) return; devlink_port->devlink = devlink; INIT_LIST_HEAD(&devlink_port->region_list); devlink_port->initialized = true; } EXPORT_SYMBOL_GPL(devlink_port_init); /** * devlink_port_fini() - Deinitialize devlink port * * @devlink_port: devlink port * * Deinitialize essential stuff that is in use for functions * that may be called after devlink port unregistration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_fini(struct devlink_port *devlink_port) { WARN_ON(!list_empty(&devlink_port->region_list)); } EXPORT_SYMBOL_GPL(devlink_port_fini); static const struct devlink_port_ops devlink_port_dummy_ops = {}; /** * devl_port_register_with_ops() - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. */ int devl_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_assert_locked(devlink); ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port_init(devlink, devlink_port); devlink_port->registered = true; devlink_port->index = port_index; devlink_port->ops = ops ? ops : &devlink_port_dummy_ops; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL); if (err) { devlink_port->registered = false; return err; } INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } EXPORT_SYMBOL_GPL(devl_port_register_with_ops); /** * devlink_port_register_with_ops - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. * * Context: Takes and release devlink->lock <mutex>. */ int devlink_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_lock(devlink); err = devl_port_register_with_ops(devlink, devlink_port, port_index, ops); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_port_register_with_ops); /** * devl_port_unregister() - Unregister devlink port * * @devlink_port: devlink port */ void devl_port_unregister(struct devlink_port *devlink_port) { lockdep_assert_held(&devlink_port->devlink->lock); WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); xa_erase(&devlink_port->devlink->ports, devlink_port->index); WARN_ON(!list_empty(&devlink_port->reporter_list)); devlink_port->registered = false; } EXPORT_SYMBOL_GPL(devl_port_unregister); /** * devlink_port_unregister - Unregister devlink port * * @devlink_port: devlink port * * Context: Takes and release devlink->lock <mutex>. */ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; devl_lock(devlink); devl_port_unregister(devlink_port); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_port_unregister); static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; /* If driver registers devlink port, it should set devlink port * attributes accordingly so the compat functions are called * and the original ops are not used. */ if (ops->ndo_get_phys_port_name) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_phys_port_name * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ char name[IFNAMSIZ]; int err; err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name)); WARN_ON(err != -EOPNOTSUPP); } if (ops->ndo_get_port_parent_id) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_port_parent_id * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ struct netdev_phys_item_id ppid; int err; err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } } static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, void *type_dev) { struct net_device *netdev = type_dev; ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); if (type == DEVLINK_PORT_TYPE_NOTSET) { devlink_port_type_warn_schedule(devlink_port); } else { devlink_port_type_warn_cancel(devlink_port); if (type == DEVLINK_PORT_TYPE_ETH && netdev) devlink_port_type_netdev_checks(devlink_port, netdev); } spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; switch (type) { case DEVLINK_PORT_TYPE_ETH: devlink_port->type_eth.netdev = netdev; if (netdev) { ASSERT_RTNL(); devlink_port->type_eth.ifindex = netdev->ifindex; BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != sizeof(netdev->name)); strcpy(devlink_port->type_eth.ifname, netdev->name); } break; case DEVLINK_PORT_TYPE_IB: devlink_port->type_ib.ibdev = type_dev; break; default: break; } spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port * * If driver is calling this, most likely it is doing something wrong. */ void devlink_port_type_eth_set(struct devlink_port *devlink_port) { dev_warn(devlink_port->devlink->dev, "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); /** * devlink_port_type_ib_set - Set port type to InfiniBand * * @devlink_port: devlink port * @ibdev: related IB device */ void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev) { __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); } EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); /** * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port * * If driver is calling this for clearing Ethernet type, most likely * it is doing something wrong. */ void devlink_port_type_clear(struct devlink_port *devlink_port) { if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) dev_warn(devlink_port->devlink->dev, "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); int devlink_port_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; if (!devlink_port) return NOTIFY_OK; devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: /* Set the type but not netdev pointer. It is going to be set * later on by NETDEV_REGISTER event. Happens once during * netdevice register */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: if (devlink_net(devlink) != dev_net(netdev)) return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this * namespace. */ __devlink_port_type_set(devlink_port, devlink_port->type, netdev); break; case NETDEV_UNREGISTER: if (devlink_net(devlink) != dev_net(netdev)) return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. */ __devlink_port_type_set(devlink_port, devlink_port->type, NULL); break; case NETDEV_PRE_UNINIT: /* Clear the type and the netdev pointer. Happens one during * netdevice unregister. */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); break; } return NOTIFY_OK; } static int __devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour) { struct devlink_port_attrs *attrs = &devlink_port->attrs; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { devlink_port->switch_port = true; if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN)) attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN; } else { devlink_port->switch_port = false; } return 0; } /** * devlink_port_attrs_set - Set port attributes * * @devlink_port: devlink port * @attrs: devlink port attrs */ void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs) { int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) return; WARN_ON(attrs->splittable && attrs->split); } EXPORT_SYMBOL_GPL(devlink_port_attrs_set); /** * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PCI function number for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; attrs->pci_pf.controller = controller; attrs->pci_pf.pf = pf; attrs->pci_pf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); /** * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PCI function number for the devlink port instance * @vf: associated PCI VF number of a PF for the devlink port instance; * VF number starts from 0 for the first PCI virtual function * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; attrs->pci_vf.controller = controller; attrs->pci_vf.pf = pf; attrs->pci_vf.vf = vf; attrs->pci_vf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); /** * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PCI function number for the devlink port instance * @sf: associated SF number of a PF for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_SF); if (ret) return; attrs->pci_sf.controller = controller; attrs->pci_sf.pf = pf; attrs->pci_sf.sf = sf; attrs->pci_sf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); static void devlink_port_rel_notify_cb(struct devlink *devlink, u32 port_index) { struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } static void devlink_port_rel_cleanup_cb(struct devlink *devlink, u32 port_index, u32 rel_index) { struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (devlink_port && devlink_port->rel_index == rel_index) devlink_port->rel_index = 0; } /** * devl_port_fn_devlink_set - Attach peer devlink * instance to port function. * @devlink_port: devlink port * @fn_devlink: devlink instance to attach */ int devl_port_fn_devlink_set(struct devlink_port *devlink_port, struct devlink *fn_devlink) { ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); if (WARN_ON(devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_SF || devlink_port->attrs.pci_sf.external)) return -EINVAL; return devlink_rel_nested_in_add(&devlink_port->rel_index, devlink_port->devlink->index, devlink_port->index, devlink_port_rel_notify_cb, devlink_port_rel_cleanup_cb, fn_devlink); } EXPORT_SYMBOL_GPL(devl_port_fn_devlink_set); /** * devlink_port_linecard_set - Link port with a linecard * * @devlink_port: devlink port * @linecard: devlink linecard */ void devlink_port_linecard_set(struct devlink_port *devlink_port, struct devlink_linecard *linecard) { ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port->linecard = linecard; } EXPORT_SYMBOL_GPL(devlink_port_linecard_set); static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; if (!devlink_port->attrs_set) return -EOPNOTSUPP; switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: if (devlink_port->linecard) n = snprintf(name, len, "l%u", devlink_linecard_index(devlink_port->linecard)); if (n < len) n += snprintf(name + n, len - n, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: case DEVLINK_PORT_FLAVOUR_UNUSED: /* As CPU and DSA ports do not have a netdevice associated * case should not ever happen. */ WARN_ON(1); return -EINVAL; case DEVLINK_PORT_FLAVOUR_PCI_PF: if (attrs->pci_pf.external) { n = snprintf(name, len, "c%u", attrs->pci_pf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); break; case DEVLINK_PORT_FLAVOUR_PCI_VF: if (attrs->pci_vf.external) { n = snprintf(name, len, "c%u", attrs->pci_vf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; case DEVLINK_PORT_FLAVOUR_PCI_SF: if (attrs->pci_sf.external) { n = snprintf(name, len, "c%u", attrs->pci_sf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; case DEVLINK_PORT_FLAVOUR_VIRTUAL: return -EOPNOTSUPP; } if (n >= len) return -EINVAL; return 0; } int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len) { struct devlink_port *devlink_port; /* RTNL mutex is held here which ensures that devlink_port * instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ ASSERT_RTNL(); devlink_port = dev->devlink_port; if (!devlink_port) return -EOPNOTSUPP; return __devlink_port_phys_port_name_get(devlink_port, name, len); } int devlink_compat_switch_id_get(struct net_device *dev, struct netdev_phys_item_id *ppid) { struct devlink_port *devlink_port; /* Caller must hold RTNL mutex or reference to dev, which ensures that * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ devlink_port = dev->devlink_port; if (!devlink_port || !devlink_port->switch_port) return -EOPNOTSUPP; memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid)); return 0; } |
| 2 2 2 57 57 61 61 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kvm_host.h> #include <linux/irqchip/arm-gic-v3.h> #include "vgic.h" /* * How KVM uses GICv4 (insert rude comments here): * * The vgic-v4 layer acts as a bridge between several entities: * - The GICv4 ITS representation offered by the ITS driver * - VFIO, which is in charge of the PCI endpoint * - The virtual ITS, which is the only thing the guest sees * * The configuration of VLPIs is triggered by a callback from VFIO, * instructing KVM that a PCI device has been configured to deliver * MSIs to a vITS. * * kvm_vgic_v4_set_forwarding() is thus called with the routing entry, * and this is used to find the corresponding vITS data structures * (ITS instance, device, event and irq) using a process that is * extremely similar to the injection of an MSI. * * At this stage, we can link the guest's view of an LPI (uniquely * identified by the routing entry) and the host irq, using the GICv4 * driver mapping operation. Should the mapping succeed, we've then * successfully upgraded the guest's LPI to a VLPI. We can then start * with updating GICv4's view of the property table and generating an * INValidation in order to kickstart the delivery of this VLPI to the * guest directly, without software intervention. Well, almost. * * When the PCI endpoint is deconfigured, this operation is reversed * with VFIO calling kvm_vgic_v4_unset_forwarding(). * * Once the VLPI has been mapped, it needs to follow any change the * guest performs on its LPI through the vITS. For that, a number of * command handlers have hooks to communicate these changes to the HW: * - Any invalidation triggers a call to its_prop_update_vlpi() * - The INT command results in a irq_set_irqchip_state(), which * generates an INT on the corresponding VLPI. * - The CLEAR command results in a irq_set_irqchip_state(), which * generates an CLEAR on the corresponding VLPI. * - DISCARD translates into an unmap, similar to a call to * kvm_vgic_v4_unset_forwarding(). * - MOVI is translated by an update of the existing mapping, changing * the target vcpu, resulting in a VMOVI being generated. * - MOVALL is translated by a string of mapping updates (similar to * the handling of MOVI). MOVALL is horrible. * * Note that a DISCARD/MAPTI sequence emitted from the guest without * reprogramming the PCI endpoint after MAPTI does not result in a * VLPI being mapped, as there is no callback from VFIO (the guest * will get the interrupt via the normal SW injection). Fixing this is * not trivial, and requires some horrible messing with the VFIO * internals. Not fun. Don't do that. * * Then there is the scheduling. Each time a vcpu is about to run on a * physical CPU, KVM must tell the corresponding redistributor about * it. And if we've migrated our vcpu from one CPU to another, we must * tell the ITS (so that the messages reach the right redistributor). * This is done in two steps: first issue a irq_set_affinity() on the * irq corresponding to the vcpu, then call its_make_vpe_resident(). * You must be in a non-preemptible context. On exit, a call to * its_make_vpe_non_resident() tells the redistributor that we're done * with the vcpu. * * Finally, the doorbell handling: Each vcpu is allocated an interrupt * which will fire each time a VLPI is made pending whilst the vcpu is * not running. Each time the vcpu gets blocked, the doorbell * interrupt gets enabled. When the vcpu is unblocked (for whatever * reason), the doorbell interrupt is disabled. */ #define DB_IRQ_FLAGS (IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY | IRQ_NO_BALANCING) static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) { struct kvm_vcpu *vcpu = info; /* We got the message, no need to fire again */ if (!kvm_vgic_global_state.has_gicv4_1 && !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) disable_irq_nosync(irq); /* * The v4.1 doorbell can fire concurrently with the vPE being * made non-resident. Ensure we only update pending_last * *after* the non-residency sequence has completed. */ raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return IRQ_HANDLED; } static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) { vpe->sgi_config[irq->intid].enabled = irq->enabled; vpe->sgi_config[irq->intid].group = irq->group; vpe->sgi_config[irq->intid].priority = irq->priority; } static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int i; /* * With GICv4.1, every virtual SGI can be directly injected. So * let's pretend that they are HW interrupts, tied to a host * IRQ. The SGI code will do its magic. */ for (i = 0; i < VGIC_NR_SGIS; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); struct irq_desc *desc; unsigned long flags; int ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) goto unlock; irq->hw = true; irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); /* Transfer the full irq state to the vPE */ vgic_v4_sync_sgi_config(vpe, irq); desc = irq_to_desc(irq->host_irq); ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), false); if (!WARN_ON(ret)) { /* Transfer pending state */ ret = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, irq->pending_latch); WARN_ON(ret); irq->pending_latch = false; } unlock: raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < VGIC_NR_SGIS; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); struct irq_desc *desc; unsigned long flags; int ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!irq->hw) goto unlock; irq->hw = false; ret = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &irq->pending_latch); WARN_ON(ret); desc = irq_to_desc(irq->host_irq); irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); unlock: raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held(&kvm->arch.config_lock); kvm_arm_halt_guest(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { if (dist->nassgireq) vgic_v4_enable_vsgis(vcpu); else vgic_v4_disable_vsgis(vcpu); } kvm_arm_resume_guest(kvm); } /* * Must be called with GICv4.1 and the vPE unmapped, which * indicates the invalidation of any VPT caches associated * with the vPE, thus we can get the VLPI state by peeking * at the VPT. */ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) { struct its_vpe *vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int mask = BIT(irq->intid % BITS_PER_BYTE); void *va; u8 *ptr; va = page_address(vpe->vpt_page); ptr = va + irq->intid / BITS_PER_BYTE; *val = !!(*ptr & mask); } int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) { return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); } /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized * * We may be called each time a vITS is created, or when the * vgic is initialized. In both cases, the number of vcpus * should now be fixed. */ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int nr_vcpus, ret; unsigned long i; lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ if (dist->its_vm.vpes) return 0; nr_vcpus = atomic_read(&kvm->online_vcpus); dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes), GFP_KERNEL_ACCOUNT); if (!dist->its_vm.vpes) return -ENOMEM; dist->its_vm.nr_vpes = nr_vcpus; kvm_for_each_vcpu(i, vcpu, kvm) dist->its_vm.vpes[i] = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; ret = its_alloc_vcpu_irqs(&dist->its_vm); if (ret < 0) { kvm_err("VPE IRQ allocation failure\n"); kfree(dist->its_vm.vpes); dist->its_vm.nr_vpes = 0; dist->its_vm.vpes = NULL; return ret; } kvm_for_each_vcpu(i, vcpu, kvm) { int irq = dist->its_vm.vpes[i]->irq; unsigned long irq_flags = DB_IRQ_FLAGS; /* * Don't automatically enable the doorbell, as we're * flipping it back and forth when the vcpu gets * blocked. Also disable the lazy disabling, as the * doorbell could kick us out of the guest too * early... * * On GICv4.1, the doorbell is managed in HW and must * be left enabled. */ if (kvm_vgic_global_state.has_gicv4_1) irq_flags &= ~IRQ_NOAUTOEN; irq_set_status_flags(irq, irq_flags); ret = vgic_v4_request_vpe_irq(vcpu, irq); if (ret) { kvm_err("failed to allocate vcpu IRQ%d\n", irq); /* * Trick: adjust the number of vpes so we know * how many to nuke on teardown... */ dist->its_vm.nr_vpes = i; break; } } if (ret) vgic_v4_teardown(kvm); return ret; } /** * vgic_v4_teardown - Free the GICv4 data structures * @kvm: Pointer to the VM being destroyed */ void vgic_v4_teardown(struct kvm *kvm) { struct its_vm *its_vm = &kvm->arch.vgic.its_vm; int i; lockdep_assert_held(&kvm->arch.config_lock); if (!its_vm->vpes) return; for (i = 0; i < its_vm->nr_vpes; i++) { struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, i); int irq = its_vm->vpes[i]->irq; irq_clear_status_flags(irq, DB_IRQ_FLAGS); free_irq(irq, vcpu); } its_free_vcpu_irqs(its_vm); kfree(its_vm->vpes); its_vm->nr_vpes = 0; its_vm->vpes = NULL; } int vgic_v4_put(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI)); } int vgic_v4_load(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int err; if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; if (vcpu_get_flag(vcpu, IN_WFI)) return 0; /* * Before making the VPE resident, make sure the redistributor * corresponding to our current CPU expects us here. See the * doc in drivers/irqchip/irq-gic-v4.c to understand how this * turns into a VMOVP command at the ITS level. */ err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); if (err) return err; err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled); if (err) return err; /* * Now that the VPE is resident, let's get rid of a potential * doorbell interrupt that would still be pending. This is a * GICv4.0 only "feature"... */ if (!kvm_vgic_global_state.has_gicv4_1) err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); return err; } void vgic_v4_commit(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; /* * No need to wait for the vPE to be ready across a shallow guest * exit, as only a vcpu_put will invalidate it. */ if (!vpe->ready) its_commit_vpe(vpe); } static struct vgic_its *vgic_get_its(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *irq_entry) { struct kvm_msi msi = (struct kvm_msi) { .address_lo = irq_entry->msi.address_lo, .address_hi = irq_entry->msi.address_hi, .data = irq_entry->msi.data, .flags = irq_entry->msi.flags, .devid = irq_entry->msi.devid, }; return vgic_msi_to_its(kvm, &msi); } int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, struct kvm_kernel_irq_routing_entry *irq_entry) { struct vgic_its *its; struct vgic_irq *irq; struct its_vlpi_map map; unsigned long flags; int ret; if (!vgic_supports_direct_msis(kvm)) return 0; /* * Get the ITS, and escape early on error (not a valid * doorbell for any of our vITSs). */ its = vgic_get_its(kvm, irq_entry); if (IS_ERR(its)) return 0; mutex_lock(&its->its_lock); /* Perform the actual DevID/EventID -> LPI translation. */ ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) goto out; /* Silently exit if the vLPI is already mapped */ if (irq->hw) goto out; /* * Emit the mapping request. If it fails, the ITS probably * isn't v4 compatible, so let's silently bail out. Holding * the ITS lock should ensure that nothing can modify the * target vcpu. */ map = (struct its_vlpi_map) { .vm = &kvm->arch.vgic.its_vm, .vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe, .vintid = irq->intid, .properties = ((irq->priority & 0xfc) | (irq->enabled ? LPI_PROP_ENABLED : 0) | LPI_PROP_GROUP1), .db_enabled = true, }; ret = its_map_vlpi(virq, &map); if (ret) goto out; irq->hw = true; irq->host_irq = virq; atomic_inc(&map.vpe->vlpi_count); /* Transfer pending state */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->pending_latch) { ret = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, irq->pending_latch); WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq); /* * Clear pending_latch and communicate this state * change via vgic_queue_irq_unlock. */ irq->pending_latch = false; vgic_queue_irq_unlock(kvm, irq, flags); } else { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } out: mutex_unlock(&its->its_lock); return ret; } int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, struct kvm_kernel_irq_routing_entry *irq_entry) { struct vgic_its *its; struct vgic_irq *irq; int ret; if (!vgic_supports_direct_msis(kvm)) return 0; /* * Get the ITS, and escape early on error (not a valid * doorbell for any of our vITSs). */ its = vgic_get_its(kvm, irq_entry); if (IS_ERR(its)) return 0; mutex_lock(&its->its_lock); ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) goto out; WARN_ON(!(irq->hw && irq->host_irq == virq)); if (irq->hw) { atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; ret = its_unmap_vlpi(virq); } out: mutex_unlock(&its->its_lock); return ret; } |
| 560 529 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 234 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015, 2016 ARM Ltd. */ #ifndef __KVM_ARM_VGIC_H #define __KVM_ARM_VGIC_H #include <linux/bits.h> #include <linux/kvm.h> #include <linux/irqreturn.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/static_key.h> #include <linux/types.h> #include <linux/xarray.h> #include <kvm/iodev.h> #include <linux/list.h> #include <linux/jump_label.h> #include <linux/irqchip/arm-gic-v4.h> #define VGIC_V3_MAX_CPUS 512 #define VGIC_V2_MAX_CPUS 8 #define VGIC_NR_IRQS_LEGACY 256 #define VGIC_NR_SGIS 16 #define VGIC_NR_PPIS 16 #define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS) #define VGIC_MAX_SPI 1019 #define VGIC_MAX_RESERVED 1023 #define VGIC_MIN_LPI 8192 #define KVM_IRQCHIP_NUM_PINS (1020 - 32) #define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS) #define irq_is_spi(irq) ((irq) >= VGIC_NR_PRIVATE_IRQS && \ (irq) <= VGIC_MAX_SPI) enum vgic_type { VGIC_V2, /* Good ol' GICv2 */ VGIC_V3, /* New fancy GICv3 */ }; /* same for all guests, as depending only on the _host's_ GIC model */ struct vgic_global { /* type of the host GIC */ enum vgic_type type; /* Physical address of vgic virtual cpu interface */ phys_addr_t vcpu_base; /* GICV mapping, kernel VA */ void __iomem *vcpu_base_va; /* GICV mapping, HYP VA */ void __iomem *vcpu_hyp_va; /* virtual control interface mapping, kernel VA */ void __iomem *vctrl_base; /* virtual control interface mapping, HYP VA */ void __iomem *vctrl_hyp; /* Number of implemented list registers */ int nr_lr; /* Maintenance IRQ number */ unsigned int maint_irq; /* maximum number of VCPUs allowed (GICv2 limits us to 8) */ int max_gic_vcpus; /* Only needed for the legacy KVM_CREATE_IRQCHIP */ bool can_emulate_gicv2; /* Hardware has GICv4? */ bool has_gicv4; bool has_gicv4_1; /* Pseudo GICv3 from outer space */ bool no_hw_deactivation; /* GIC system register CPU interface */ struct static_key_false gicv3_cpuif; u32 ich_vtr_el2; }; extern struct vgic_global kvm_vgic_global_state; #define VGIC_V2_MAX_LRS (1 << 6) #define VGIC_V3_MAX_LRS 16 #define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) enum vgic_irq_config { VGIC_CONFIG_EDGE = 0, VGIC_CONFIG_LEVEL }; /* * Per-irq ops overriding some common behavious. * * Always called in non-preemptible section and the functions can use * kvm_arm_get_running_vcpu() to get the vcpu pointer for private IRQs. */ struct irq_ops { /* Per interrupt flags for special-cased interrupts */ unsigned long flags; #define VGIC_IRQ_SW_RESAMPLE BIT(0) /* Clear the active state for resampling */ /* * Callback function pointer to in-kernel devices that can tell us the * state of the input level of mapped level-triggered IRQ faster than * peaking into the physical GIC. */ bool (*get_input_level)(int vintid); }; struct vgic_irq { raw_spinlock_t irq_lock; /* Protects the content of the struct */ struct rcu_head rcu; struct list_head ap_list; struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU * SPIs and LPIs: The VCPU whose ap_list * this is queued on. */ struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should * be sent to, as a result of the * targets reg (v2) or the * affinity reg (v3). */ u32 intid; /* Guest visible INTID */ bool line_level; /* Level only */ bool pending_latch; /* The pending latch state used to calculate * the pending state for both level * and edge triggered IRQs. */ bool active; /* not used for LPIs */ bool enabled; bool hw; /* Tied to HW IRQ */ struct kref refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ unsigned int host_irq; /* linux irq corresponding to hwintid */ union { u8 targets; /* GICv2 target VCPUs mask */ u32 mpidr; /* GICv3 target VCPU */ }; u8 source; /* GICv2 SGIs only */ u8 active_source; /* GICv2 SGIs only */ u8 priority; u8 group; /* 0 == group 0, 1 == group 1 */ enum vgic_irq_config config; /* Level or edge */ struct irq_ops *ops; void *owner; /* Opaque pointer to reserve an interrupt for in-kernel devices. */ }; static inline bool vgic_irq_needs_resampling(struct vgic_irq *irq) { return irq->ops && (irq->ops->flags & VGIC_IRQ_SW_RESAMPLE); } struct vgic_register_region; struct vgic_its; enum iodev_type { IODEV_CPUIF, IODEV_DIST, IODEV_REDIST, IODEV_ITS }; struct vgic_io_device { gpa_t base_addr; union { struct kvm_vcpu *redist_vcpu; struct vgic_its *its; }; const struct vgic_register_region *regions; enum iodev_type iodev_type; int nr_regions; struct kvm_io_device dev; }; struct vgic_its { /* The base address of the ITS control register frame */ gpa_t vgic_its_base; bool enabled; struct vgic_io_device iodev; struct kvm_device *dev; /* These registers correspond to GITS_BASER{0,1} */ u64 baser_device_table; u64 baser_coll_table; /* Protects the command queue */ struct mutex cmd_lock; u64 cbaser; u32 creadr; u32 cwriter; /* migration ABI revision in use */ u32 abi_rev; /* Protects the device and collection lists */ struct mutex its_lock; struct list_head device_list; struct list_head collection_list; /* * Caches the (device_id, event_id) -> vgic_irq translation for * LPIs that are mapped and enabled. */ struct xarray translation_cache; }; struct vgic_state_iter; struct vgic_redist_region { u32 index; gpa_t base; u32 count; /* number of redistributors or 0 if single region */ u32 free_index; /* index of the next free redistributor */ struct list_head list; }; struct vgic_dist { bool in_kernel; bool ready; bool initialized; /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */ u32 vgic_model; /* Implementation revision as reported in the GICD_IIDR */ u32 implementation_rev; #define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */ #define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */ #define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3 /* Userspace can write to GICv2 IGROUPR */ bool v2_groups_user_writable; /* Do injected MSIs require an additional device ID? */ bool msis_require_devid; int nr_spis; /* base addresses in guest physical address space: */ gpa_t vgic_dist_base; /* distributor */ union { /* either a GICv2 CPU interface */ gpa_t vgic_cpu_base; /* or a number of GICv3 redistributor regions */ struct list_head rd_regions; }; /* distributor enabled */ bool enabled; /* Wants SGIs without active state */ bool nassgireq; struct vgic_irq *spis; struct vgic_io_device dist_iodev; bool has_its; bool table_write_in_progress; /* * Contains the attributes and gpa of the LPI configuration table. * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share * one address across all redistributors. * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables" */ u64 propbaser; #define LPI_XA_MARK_DEBUG_ITER XA_MARK_0 struct xarray lpi_xa; /* used by vgic-debug */ struct vgic_state_iter *iter; /* * GICv4 ITS per-VM data, containing the IRQ domain, the VPE * array, the property table pointer as well as allocation * data. This essentially ties the Linux IRQ core and ITS * together, and avoids leaking KVM's data structures anywhere * else. */ struct its_vm its_vm; }; struct vgic_v2_cpu_if { u32 vgic_hcr; u32 vgic_vmcr; u32 vgic_apr; u32 vgic_lr[VGIC_V2_MAX_LRS]; unsigned int used_lrs; }; struct vgic_v3_cpu_if { u32 vgic_hcr; u32 vgic_vmcr; u32 vgic_sre; /* Restored only, change ignored */ u32 vgic_ap0r[4]; u32 vgic_ap1r[4]; u64 vgic_lr[VGIC_V3_MAX_LRS]; /* * GICv4 ITS per-VPE data, containing the doorbell IRQ, the * pending table pointer, the its_vm pointer and a few other * HW specific things. As for the its_vm structure, this is * linking the Linux IRQ subsystem and the ITS together. */ struct its_vpe its_vpe; unsigned int used_lrs; }; struct vgic_cpu { /* CPU vif control registers for world switch */ union { struct vgic_v2_cpu_if vgic_v2; struct vgic_v3_cpu_if vgic_v3; }; struct vgic_irq *private_irqs; raw_spinlock_t ap_list_lock; /* Protects the ap_list */ /* * List of IRQs that this VCPU should consider because they are either * Active or Pending (hence the name; AP list), or because they recently * were one of the two and need to be migrated off this list to another * VCPU. */ struct list_head ap_list_head; /* * Members below are used with GICv3 emulation only and represent * parts of the redistributor. */ struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; u32 rdreg_index; atomic_t syncr_busy; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; /* GICR_CTLR.{ENABLE_LPIS,RWP} */ atomic_t ctlr; /* Cache guest priority bits */ u32 num_pri_bits; /* Cache guest interrupt ID bits */ u32 num_id_bits; }; extern struct static_key_false vgic_v2_cpuif_trap; extern struct static_key_false vgic_v3_cpuif_trap; int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr); void kvm_vgic_early_init(struct kvm *kvm); int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu); int kvm_vgic_create(struct kvm *kvm, u32 type); void kvm_vgic_destroy(struct kvm *kvm); void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_vgic_map_resources(struct kvm *kvm); int kvm_vgic_hyp_init(void); void kvm_vgic_init_cpu_hardware(void); int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, unsigned int intid, bool level, void *owner); int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, u32 vintid, struct irq_ops *ops); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid); int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid); bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); void kvm_vgic_load(struct kvm_vcpu *vcpu); void kvm_vgic_put(struct kvm_vcpu *vcpu); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) ((k)->arch.vgic.initialized) #define vgic_ready(k) ((k)->arch.vgic.ready) #define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \ ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu); void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid); void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1); /** * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW * * The host's GIC naturally limits the maximum amount of VCPUs a guest * can use. */ static inline int kvm_vgic_get_max_vcpus(void) { return kvm_vgic_global_state.max_gic_vcpus; } /** * kvm_vgic_setup_default_irq_routing: * Setup a default flat gsi routing table mapping all SPIs */ int kvm_vgic_setup_default_irq_routing(struct kvm *kvm); int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner); struct kvm_kernel_irq_routing_entry; int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); int vgic_v4_put(struct kvm_vcpu *vcpu); /* CPU HP callbacks */ void kvm_vgic_cpu_up(void); void kvm_vgic_cpu_down(void); #endif /* __KVM_ARM_VGIC_H */ |
| 3 3 3 3 3 3 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ADDRCONF_H #define _ADDRCONF_H #define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ #define TEMP_VALID_LIFETIME (7*86400) /* 1 week */ #define TEMP_PREFERRED_LIFETIME (86400) /* 24 hours */ #define REGEN_MIN_ADVANCE (2) /* 2 seconds */ #define REGEN_MAX_RETRY (3) #define MAX_DESYNC_FACTOR (600) #define ADDR_CHECK_FREQUENCY (120*HZ) #define IPV6_MAX_ADDRESSES 16 #define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ / 50 : 1) #define ADDRCONF_TIMER_FUZZ (HZ / 4) #define ADDRCONF_TIMER_FUZZ_MAX (HZ) #define ADDRCONF_NOTIFY_PRIORITY 0 #include <linux/in.h> #include <linux/in6.h> struct prefix_info { __u8 type; __u8 length; __u8 prefix_len; union __packed { __u8 flags; struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, autoconf : 1, routeraddr : 1, preferpd : 1, reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved : 4, preferpd : 1, routeraddr : 1, autoconf : 1, onlink : 1; #else #error "Please fix <asm/byteorder.h>" #endif }; }; __be32 valid; __be32 prefered; __be32 reserved2; struct in6_addr prefix; }; /* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ static_assert(sizeof(struct prefix_info) == 32); #include <linux/ipv6.h> #include <linux/netdevice.h> #include <net/if_inet6.h> #include <net/ipv6.h> struct in6_validator_info { struct in6_addr i6vi_addr; struct inet6_dev *i6vi_dev; struct netlink_ext_ack *extack; }; struct ifa6_config { const struct in6_addr *pfx; unsigned int plen; u8 ifa_proto; const struct in6_addr *peer_pfx; u32 rt_priority; u32 ifa_flags; u32 preferred_lft; u32 valid_lft; u16 scope; }; enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, }; struct inet6_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; enum addr_type_t type; bool force_rt_scope_universe; }; int addrconf_init(void); void addrconf_cleanup(void); int addrconf_add_ifaddr(struct net *net, void __user *arg); int addrconf_del_ifaddr(struct net *net, void __user *arg); int addrconf_set_dstaddr(struct net *net, void __user *arg); int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr); #endif int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, unsigned char nsegs); bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict); int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); bool inet_rcv_saddr_any(const struct sock *sk); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags); int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, const struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft); static inline void addrconf_addr_eui48_base(u8 *eui, const char *const addr) { memcpy(eui, addr, 3); eui[3] = 0xFF; eui[4] = 0xFE; memcpy(eui + 5, addr + 3, 3); } static inline void addrconf_addr_eui48(u8 *eui, const char *const addr) { addrconf_addr_eui48_base(eui, addr); eui[0] ^= 2; } static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) return -1; /* * The zSeries OSA network cards can be shared among various * OS instances, but the OSA cards have only one MAC address. * This leads to duplicate address conflicts in conjunction * with IPv6 if more than one instance uses the same card. * * The driver for these cards can deliver a unique 16-bit * identifier for each instance sharing the same card. It is * placed instead of 0xFFFE in the interface identifier. The * "u" bit of the interface identifier is not inverted in this * case. Hence the resulting interface identifier has local * scope according to RFC2373. */ addrconf_addr_eui48_base(eui, dev->dev_addr); if (dev->dev_id) { eui[3] = (dev->dev_id >> 8) & 0xFF; eui[4] = dev->dev_id & 0xFF; } else { eui[0] ^= 2; } return 0; } #define INFINITY_LIFE_TIME 0xFFFFFFFF static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* * Avoid arithmetic overflow. * Assuming unit is constant and non-zero, this "if" statement * will go away on 64bit archs. */ if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit) return LONG_MAX / unit; return timeout; } static inline int addrconf_finite_timeout(unsigned long timeout) { return ~timeout; } /* * IPv6 Address Label subsystem (addrlabel.c) */ int ipv6_addr_label_init(void); void ipv6_addr_label_cleanup(void); int ipv6_addr_label_rtnl_register(void); u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex); /* * multicast prototypes (mcast.c) */ static inline bool ipv6_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) return false; return pskb_may_pull(skb, len); } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_mc_close(struct sock *sk); void ipv6_sock_mc_close(struct sock *sk); bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr); int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr); int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr); int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr); void ipv6_mc_up(struct inet6_dev *idev); void ipv6_mc_down(struct inet6_dev *idev); void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr); void ipv6_mc_dad_complete(struct inet6_dev *idev); /* * identify MLD packets for MLD filter exceptions */ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset) { struct icmp6hdr *hdr; if (nexthdr != IPPROTO_ICMPV6 || !pskb_network_may_pull(skb, offset + sizeof(struct icmp6hdr))) return false; hdr = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (hdr->icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: return true; default: break; } return false; } void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao); /* * anycast prototypes (anycast.c) */ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); void ipv6_ac_destroy_dev(struct inet6_dev *idev); bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); int ipv6_anycast_init(void); void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); int unregister_inet6addr_notifier(struct notifier_block *nb); int inet6addr_notifier_call_chain(unsigned long val, void *v); int register_inet6addr_validator_notifier(struct notifier_block *nb); int unregister_inet6addr_validator_notifier(struct notifier_block *nb); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v); void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf); /** * __in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) { return rcu_dereference_rtnl(dev->ip6_ptr); } static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); } /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev, const struct sk_buff *skb) { if (netif_is_l3_master(dev)) dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb)); return __in6_dev_get(dev); } /** * __in6_dev_get_safely - get inet6_dev pointer from netdevice * @dev: network device * * This is a safer version of __in6_dev_get */ static inline struct inet6_dev *__in6_dev_get_safely(const struct net_device *dev) { if (likely(dev)) return rcu_dereference_rtnl(dev->ip6_ptr); else return NULL; } /** * in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * This version can be used in any context, and takes a reference * on the inet6_dev. Callers must use in6_dev_put() later to * release this reference. */ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) { struct inet6_dev *idev; rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); if (idev) refcount_inc(&idev->refcnt); rcu_read_unlock(); return idev; } static inline struct neigh_parms *__in6_dev_nd_parms_get_rcu(const struct net_device *dev) { struct inet6_dev *idev = __in6_dev_get(dev); return idev ? idev->nd_parms : NULL; } void in6_dev_finish_destroy(struct inet6_dev *idev); static inline void in6_dev_put(struct inet6_dev *idev) { if (refcount_dec_and_test(&idev->refcnt)) in6_dev_finish_destroy(idev); } static inline void in6_dev_put_clear(struct inet6_dev **pidev) { struct inet6_dev *idev = *pidev; if (idev) { in6_dev_put(idev); *pidev = NULL; } } static inline void __in6_dev_put(struct inet6_dev *idev) { refcount_dec(&idev->refcnt); } static inline void in6_dev_hold(struct inet6_dev *idev) { refcount_inc(&idev->refcnt); } /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { const struct inet6_dev *idev = __in6_dev_get(dev); if (unlikely(!idev)) return true; return !!READ_ONCE(idev->cnf.ignore_routes_with_linkdown); } void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) { if (refcount_dec_and_test(&ifp->refcnt)) inet6_ifa_finish_destroy(ifp); } static inline void __in6_ifa_put(struct inet6_ifaddr *ifp) { refcount_dec(&ifp->refcnt); } static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) { refcount_inc(&ifp->refcnt); } static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) { return refcount_inc_not_zero(&ifp->refcnt); } /* * compute link-local solicited-node multicast address */ static inline void addrconf_addr_solict_mult(const struct in6_addr *addr, struct in6_addr *solicited) { ipv6_addr_set(solicited, htonl(0xFF020000), 0, htonl(0x1), htonl(0xFF000000) | addr->s6_addr32[3]); } static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000001))) == 0; #endif } static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000002))) == 0; #endif } static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) { return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); } static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | ((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) & cpu_to_be64(0xffffffffff000000UL))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x00000001)) | (addr->s6_addr[12] ^ 0xff)) == 0; #endif } static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(0x6a))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x0000006a))) == 0; #endif } #ifdef CONFIG_PROC_FS int if6_proc_init(void); void if6_proc_exit(void); #endif int inet6_fill_ifmcaddr(struct sk_buff *skb, const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args); int inet6_fill_ifacaddr(struct sk_buff *skb, const struct ifacaddr6 *ifaca, struct inet6_fill_args *args); #endif |
| 424 53 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/drivers/clocksource/arm_arch_timer.c * * Copyright (C) 2011 ARM Ltd. * All Rights Reserved */ #define pr_fmt(fmt) "arch_timer: " fmt #include <linux/init.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/clockchips.h> #include <linux/clocksource.h> #include <linux/clocksource_ids.h> #include <linux/interrupt.h> #include <linux/kstrtox.h> #include <linux/of_irq.h> #include <linux/of_address.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/sched_clock.h> #include <linux/acpi.h> #include <linux/arm-smccc.h> #include <linux/ptp_kvm.h> #include <asm/arch_timer.h> #include <asm/virt.h> #include <clocksource/arm_arch_timer.h> #define CNTTIDR 0x08 #define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4)) #define CNTACR(n) (0x40 + ((n) * 4)) #define CNTACR_RPCT BIT(0) #define CNTACR_RVCT BIT(1) #define CNTACR_RFRQ BIT(2) #define CNTACR_RVOFF BIT(3) #define CNTACR_RWVT BIT(4) #define CNTACR_RWPT BIT(5) #define CNTPCT_LO 0x00 #define CNTVCT_LO 0x08 #define CNTFRQ 0x10 #define CNTP_CVAL_LO 0x20 #define CNTP_CTL 0x2c #define CNTV_CVAL_LO 0x30 #define CNTV_CTL 0x3c /* * The minimum amount of time a generic counter is guaranteed to not roll over * (40 years) */ #define MIN_ROLLOVER_SECS (40ULL * 365 * 24 * 3600) static unsigned arch_timers_present __initdata; struct arch_timer { void __iomem *base; struct clock_event_device evt; }; static struct arch_timer *arch_timer_mem __ro_after_init; #define to_arch_timer(e) container_of(e, struct arch_timer, evt) static u32 arch_timer_rate __ro_after_init; static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init; static const char *arch_timer_ppi_names[ARCH_TIMER_MAX_TIMER_PPI] = { [ARCH_TIMER_PHYS_SECURE_PPI] = "sec-phys", [ARCH_TIMER_PHYS_NONSECURE_PPI] = "phys", [ARCH_TIMER_VIRT_PPI] = "virt", [ARCH_TIMER_HYP_PPI] = "hyp-phys", [ARCH_TIMER_HYP_VIRT_PPI] = "hyp-virt", }; static struct clock_event_device __percpu *arch_timer_evt; static enum arch_timer_ppi_nr arch_timer_uses_ppi __ro_after_init = ARCH_TIMER_VIRT_PPI; static bool arch_timer_c3stop __ro_after_init; static bool arch_timer_mem_use_virtual __ro_after_init; static bool arch_counter_suspend_stop __ro_after_init; #ifdef CONFIG_GENERIC_GETTIMEOFDAY static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_ARCHTIMER; #else static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_NONE; #endif /* CONFIG_GENERIC_GETTIMEOFDAY */ static cpumask_t evtstrm_available = CPU_MASK_NONE; static bool evtstrm_enable __ro_after_init = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM); static int __init early_evtstrm_cfg(char *buf) { return kstrtobool(buf, &evtstrm_enable); } early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg); /* * Makes an educated guess at a valid counter width based on the Generic Timer * specification. Of note: * 1) the system counter is at least 56 bits wide * 2) a roll-over time of not less than 40 years * * See 'ARM DDI 0487G.a D11.1.2 ("The system counter")' for more details. */ static int arch_counter_get_width(void) { u64 min_cycles = MIN_ROLLOVER_SECS * arch_timer_rate; /* guarantee the returned width is within the valid range */ return clamp_val(ilog2(min_cycles - 1) + 1, 56, 64); } /* * Architected system timer support. */ static __always_inline void arch_timer_reg_write(int access, enum arch_timer_reg reg, u64 val, struct clock_event_device *clk) { if (access == ARCH_TIMER_MEM_PHYS_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: writel_relaxed((u32)val, timer->base + CNTP_CTL); break; case ARCH_TIMER_REG_CVAL: /* * Not guaranteed to be atomic, so the timer * must be disabled at this point. */ writeq_relaxed(val, timer->base + CNTP_CVAL_LO); break; default: BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: writel_relaxed((u32)val, timer->base + CNTV_CTL); break; case ARCH_TIMER_REG_CVAL: /* Same restriction as above */ writeq_relaxed(val, timer->base + CNTV_CVAL_LO); break; default: BUILD_BUG(); } } else { arch_timer_reg_write_cp15(access, reg, val); } } static __always_inline u32 arch_timer_reg_read(int access, enum arch_timer_reg reg, struct clock_event_device *clk) { u32 val; if (access == ARCH_TIMER_MEM_PHYS_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: val = readl_relaxed(timer->base + CNTP_CTL); break; default: BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); switch (reg) { case ARCH_TIMER_REG_CTRL: val = readl_relaxed(timer->base + CNTV_CTL); break; default: BUILD_BUG(); } } else { val = arch_timer_reg_read_cp15(access, reg); } return val; } static noinstr u64 raw_counter_get_cntpct_stable(void) { return __arch_counter_get_cntpct_stable(); } static notrace u64 arch_counter_get_cntpct_stable(void) { u64 val; preempt_disable_notrace(); val = __arch_counter_get_cntpct_stable(); preempt_enable_notrace(); return val; } static noinstr u64 arch_counter_get_cntpct(void) { return __arch_counter_get_cntpct(); } static noinstr u64 raw_counter_get_cntvct_stable(void) { return __arch_counter_get_cntvct_stable(); } static notrace u64 arch_counter_get_cntvct_stable(void) { u64 val; preempt_disable_notrace(); val = __arch_counter_get_cntvct_stable(); preempt_enable_notrace(); return val; } static noinstr u64 arch_counter_get_cntvct(void) { return __arch_counter_get_cntvct(); } /* * Default to cp15 based access because arm64 uses this function for * sched_clock() before DT is probed and the cp15 method is guaranteed * to exist on arm64. arm doesn't use this before DT is probed so even * if we don't have the cp15 accessors we won't have a problem. */ u64 (*arch_timer_read_counter)(void) __ro_after_init = arch_counter_get_cntvct; EXPORT_SYMBOL_GPL(arch_timer_read_counter); static u64 arch_counter_read(struct clocksource *cs) { return arch_timer_read_counter(); } static u64 arch_counter_read_cc(const struct cyclecounter *cc) { return arch_timer_read_counter(); } static struct clocksource clocksource_counter = { .name = "arch_sys_counter", .id = CSID_ARM_ARCH_COUNTER, .rating = 400, .read = arch_counter_read, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static struct cyclecounter cyclecounter __ro_after_init = { .read = arch_counter_read_cc, }; struct ate_acpi_oem_info { char oem_id[ACPI_OEM_ID_SIZE + 1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; u32 oem_revision; }; #ifdef CONFIG_FSL_ERRATUM_A008585 /* * The number of retries is an arbitrary value well beyond the highest number * of iterations the loop has been observed to take. */ #define __fsl_a008585_read_reg(reg) ({ \ u64 _old, _new; \ int _retries = 200; \ \ do { \ _old = read_sysreg(reg); \ _new = read_sysreg(reg); \ _retries--; \ } while (unlikely(_old != _new) && _retries); \ \ WARN_ON_ONCE(!_retries); \ _new; \ }) static u64 notrace fsl_a008585_read_cntpct_el0(void) { return __fsl_a008585_read_reg(cntpct_el0); } static u64 notrace fsl_a008585_read_cntvct_el0(void) { return __fsl_a008585_read_reg(cntvct_el0); } #endif #ifdef CONFIG_HISILICON_ERRATUM_161010101 /* * Verify whether the value of the second read is larger than the first by * less than 32 is the only way to confirm the value is correct, so clear the * lower 5 bits to check whether the difference is greater than 32 or not. * Theoretically the erratum should not occur more than twice in succession * when reading the system counter, but it is possible that some interrupts * may lead to more than twice read errors, triggering the warning, so setting * the number of retries far beyond the number of iterations the loop has been * observed to take. */ #define __hisi_161010101_read_reg(reg) ({ \ u64 _old, _new; \ int _retries = 50; \ \ do { \ _old = read_sysreg(reg); \ _new = read_sysreg(reg); \ _retries--; \ } while (unlikely((_new - _old) >> 5) && _retries); \ \ WARN_ON_ONCE(!_retries); \ _new; \ }) static u64 notrace hisi_161010101_read_cntpct_el0(void) { return __hisi_161010101_read_reg(cntpct_el0); } static u64 notrace hisi_161010101_read_cntvct_el0(void) { return __hisi_161010101_read_reg(cntvct_el0); } static const struct ate_acpi_oem_info hisi_161010101_oem_info[] = { /* * Note that trailing spaces are required to properly match * the OEM table information. */ { .oem_id = "HISI ", .oem_table_id = "HIP05 ", .oem_revision = 0, }, { .oem_id = "HISI ", .oem_table_id = "HIP06 ", .oem_revision = 0, }, { .oem_id = "HISI ", .oem_table_id = "HIP07 ", .oem_revision = 0, }, { /* Sentinel indicating the end of the OEM array */ }, }; #endif #ifdef CONFIG_ARM64_ERRATUM_858921 static u64 notrace arm64_858921_read_cntpct_el0(void) { u64 old, new; old = read_sysreg(cntpct_el0); new = read_sysreg(cntpct_el0); return (((old ^ new) >> 32) & 1) ? old : new; } static u64 notrace arm64_858921_read_cntvct_el0(void) { u64 old, new; old = read_sysreg(cntvct_el0); new = read_sysreg(cntvct_el0); return (((old ^ new) >> 32) & 1) ? old : new; } #endif #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1 /* * The low bits of the counter registers are indeterminate while bit 10 or * greater is rolling over. Since the counter value can jump both backward * (7ff -> 000 -> 800) and forward (7ff -> fff -> 800), ignore register values * with all ones or all zeros in the low bits. Bound the loop by the maximum * number of CPU cycles in 3 consecutive 24 MHz counter periods. */ #define __sun50i_a64_read_reg(reg) ({ \ u64 _val; \ int _retries = 150; \ \ do { \ _val = read_sysreg(reg); \ _retries--; \ } while (((_val + 1) & GENMASK(8, 0)) <= 1 && _retries); \ \ WARN_ON_ONCE(!_retries); \ _val; \ }) static u64 notrace sun50i_a64_read_cntpct_el0(void) { return __sun50i_a64_read_reg(cntpct_el0); } static u64 notrace sun50i_a64_read_cntvct_el0(void) { return __sun50i_a64_read_reg(cntvct_el0); } #endif #ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround); EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround); static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0); /* * Force the inlining of this function so that the register accesses * can be themselves correctly inlined. */ static __always_inline void erratum_set_next_event_generic(const int access, unsigned long evt, struct clock_event_device *clk) { unsigned long ctrl; u64 cval; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_PHYS_ACCESS) { cval = evt + arch_counter_get_cntpct_stable(); write_sysreg(cval, cntp_cval_el0); } else { cval = evt + arch_counter_get_cntvct_stable(); write_sysreg(cval, cntv_cval_el0); } arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static __maybe_unused int erratum_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) { erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk); return 0; } static __maybe_unused int erratum_set_next_event_phys(unsigned long evt, struct clock_event_device *clk) { erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk); return 0; } static const struct arch_timer_erratum_workaround ool_workarounds[] = { #ifdef CONFIG_FSL_ERRATUM_A008585 { .match_type = ate_match_dt, .id = "fsl,erratum-a008585", .desc = "Freescale erratum a005858", .read_cntpct_el0 = fsl_a008585_read_cntpct_el0, .read_cntvct_el0 = fsl_a008585_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_HISILICON_ERRATUM_161010101 { .match_type = ate_match_dt, .id = "hisilicon,erratum-161010101", .desc = "HiSilicon erratum 161010101", .read_cntpct_el0 = hisi_161010101_read_cntpct_el0, .read_cntvct_el0 = hisi_161010101_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, { .match_type = ate_match_acpi_oem_info, .id = hisi_161010101_oem_info, .desc = "HiSilicon erratum 161010101", .read_cntpct_el0 = hisi_161010101_read_cntpct_el0, .read_cntvct_el0 = hisi_161010101_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 { .match_type = ate_match_local_cap_id, .id = (void *)ARM64_WORKAROUND_858921, .desc = "ARM erratum 858921", .read_cntpct_el0 = arm64_858921_read_cntpct_el0, .read_cntvct_el0 = arm64_858921_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1 { .match_type = ate_match_dt, .id = "allwinner,erratum-unknown1", .desc = "Allwinner erratum UNKNOWN1", .read_cntpct_el0 = sun50i_a64_read_cntpct_el0, .read_cntvct_el0 = sun50i_a64_read_cntvct_el0, .set_next_event_phys = erratum_set_next_event_phys, .set_next_event_virt = erratum_set_next_event_virt, }, #endif #ifdef CONFIG_ARM64_ERRATUM_1418040 { .match_type = ate_match_local_cap_id, .id = (void *)ARM64_WORKAROUND_1418040, .desc = "ARM erratum 1418040", .disable_compat_vdso = true, }, #endif }; typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *, const void *); static bool arch_timer_check_dt_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { const struct device_node *np = arg; return of_property_read_bool(np, wa->id); } static bool arch_timer_check_local_cap_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { return this_cpu_has_cap((uintptr_t)wa->id); } static bool arch_timer_check_acpi_oem_erratum(const struct arch_timer_erratum_workaround *wa, const void *arg) { static const struct ate_acpi_oem_info empty_oem_info = {}; const struct ate_acpi_oem_info *info = wa->id; const struct acpi_table_header *table = arg; /* Iterate over the ACPI OEM info array, looking for a match */ while (memcmp(info, &empty_oem_info, sizeof(*info))) { if (!memcmp(info->oem_id, table->oem_id, ACPI_OEM_ID_SIZE) && !memcmp(info->oem_table_id, table->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) && info->oem_revision == table->oem_revision) return true; info++; } return false; } static const struct arch_timer_erratum_workaround * arch_timer_iterate_errata(enum arch_timer_erratum_match_type type, ate_match_fn_t match_fn, void *arg) { int i; for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) { if (ool_workarounds[i].match_type != type) continue; if (match_fn(&ool_workarounds[i], arg)) return &ool_workarounds[i]; } return NULL; } static void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa, bool local) { int i; if (local) { __this_cpu_write(timer_unstable_counter_workaround, wa); } else { for_each_possible_cpu(i) per_cpu(timer_unstable_counter_workaround, i) = wa; } if (wa->read_cntvct_el0 || wa->read_cntpct_el0) atomic_set(&timer_unstable_counter_workaround_in_use, 1); /* * Don't use the vdso fastpath if errata require using the * out-of-line counter accessor. We may change our mind pretty * late in the game (with a per-CPU erratum, for example), so * change both the default value and the vdso itself. */ if (wa->read_cntvct_el0) { clocksource_counter.vdso_clock_mode = VDSO_CLOCKMODE_NONE; vdso_default = VDSO_CLOCKMODE_NONE; } else if (wa->disable_compat_vdso && vdso_default != VDSO_CLOCKMODE_NONE) { vdso_default = VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT; clocksource_counter.vdso_clock_mode = vdso_default; } } static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type, void *arg) { const struct arch_timer_erratum_workaround *wa, *__wa; ate_match_fn_t match_fn = NULL; bool local = false; switch (type) { case ate_match_dt: match_fn = arch_timer_check_dt_erratum; break; case ate_match_local_cap_id: match_fn = arch_timer_check_local_cap_erratum; local = true; break; case ate_match_acpi_oem_info: match_fn = arch_timer_check_acpi_oem_erratum; break; default: WARN_ON(1); return; } wa = arch_timer_iterate_errata(type, match_fn, arg); if (!wa) return; __wa = __this_cpu_read(timer_unstable_counter_workaround); if (__wa && wa != __wa) pr_warn("Can't enable workaround for %s (clashes with %s\n)", wa->desc, __wa->desc); if (__wa) return; arch_timer_enable_workaround(wa, local); pr_info("Enabling %s workaround for %s\n", local ? "local" : "global", wa->desc); } static bool arch_timer_this_cpu_has_cntvct_wa(void) { return has_erratum_handler(read_cntvct_el0); } static bool arch_timer_counter_has_wa(void) { return atomic_read(&timer_unstable_counter_workaround_in_use); } #else #define arch_timer_check_ool_workaround(t,a) do { } while(0) #define arch_timer_this_cpu_has_cntvct_wa() ({false;}) #define arch_timer_counter_has_wa() ({false;}) #endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */ static __always_inline irqreturn_t timer_handler(const int access, struct clock_event_device *evt) { unsigned long ctrl; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, evt); if (ctrl & ARCH_TIMER_CTRL_IT_STAT) { ctrl |= ARCH_TIMER_CTRL_IT_MASK; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, evt); evt->event_handler(evt); return IRQ_HANDLED; } return IRQ_NONE; } static irqreturn_t arch_timer_handler_virt(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_VIRT_ACCESS, evt); } static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt); } static irqreturn_t arch_timer_handler_phys_mem(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_MEM_PHYS_ACCESS, evt); } static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt); } static __always_inline int arch_timer_shutdown(const int access, struct clock_event_device *clk) { unsigned long ctrl; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl &= ~ARCH_TIMER_CTRL_ENABLE; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); return 0; } static int arch_timer_shutdown_virt(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_PHYS_ACCESS, clk); } static int arch_timer_shutdown_virt_mem(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_MEM_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys_mem(struct clock_event_device *clk) { return arch_timer_shutdown(ARCH_TIMER_MEM_PHYS_ACCESS, clk); } static __always_inline void set_next_event(const int access, unsigned long evt, struct clock_event_device *clk) { unsigned long ctrl; u64 cnt; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_PHYS_ACCESS) cnt = __arch_counter_get_cntpct(); else cnt = __arch_counter_get_cntvct(); arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk); arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static int arch_timer_set_next_event_virt(unsigned long evt, struct clock_event_device *clk) { set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk); return 0; } static int arch_timer_set_next_event_phys(unsigned long evt, struct clock_event_device *clk) { set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk); return 0; } static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo) { u32 cnt_lo, cnt_hi, tmp_hi; do { cnt_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4)); cnt_lo = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo)); tmp_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4)); } while (cnt_hi != tmp_hi); return ((u64) cnt_hi << 32) | cnt_lo; } static __always_inline void set_next_event_mem(const int access, unsigned long evt, struct clock_event_device *clk) { struct arch_timer *timer = to_arch_timer(clk); unsigned long ctrl; u64 cnt; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); /* Timer must be disabled before programming CVAL */ if (ctrl & ARCH_TIMER_CTRL_ENABLE) { ctrl &= ~ARCH_TIMER_CTRL_ENABLE; arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; if (access == ARCH_TIMER_MEM_VIRT_ACCESS) cnt = arch_counter_get_cnt_mem(timer, CNTVCT_LO); else cnt = arch_counter_get_cnt_mem(timer, CNTPCT_LO); arch_timer_reg_write(access, ARCH_TIMER_REG_CVAL, evt + cnt, clk); arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); } static int arch_timer_set_next_event_virt_mem(unsigned long evt, struct clock_event_device *clk) { set_next_event_mem(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk); return 0; } static int arch_timer_set_next_event_phys_mem(unsigned long evt, struct clock_event_device *clk) { set_next_event_mem(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk); return 0; } static u64 __arch_timer_check_delta(void) { #ifdef CONFIG_ARM64 const struct midr_range broken_cval_midrs[] = { /* * XGene-1 implements CVAL in terms of TVAL, meaning * that the maximum timer range is 32bit. Shame on them. * * Note that TVAL is signed, thus has only 31 of its * 32 bits to express magnitude. */ MIDR_REV_RANGE(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, APM_CPU_PART_XGENE), APM_CPU_VAR_POTENZA, 0x0, 0xf), {}, }; if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) { pr_warn_once("Broken CNTx_CVAL_EL1, using 31 bit TVAL instead.\n"); return CLOCKSOURCE_MASK(31); } #endif return CLOCKSOURCE_MASK(arch_counter_get_width()); } static void __arch_timer_setup(unsigned type, struct clock_event_device *clk) { u64 max_delta; clk->features = CLOCK_EVT_FEAT_ONESHOT; if (type == ARCH_TIMER_TYPE_CP15) { typeof(clk->set_next_event) sne; arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL); if (arch_timer_c3stop) clk->features |= CLOCK_EVT_FEAT_C3STOP; clk->name = "arch_sys_timer"; clk->rating = 450; clk->cpumask = cpumask_of(smp_processor_id()); clk->irq = arch_timer_ppi[arch_timer_uses_ppi]; switch (arch_timer_uses_ppi) { case ARCH_TIMER_VIRT_PPI: clk->set_state_shutdown = arch_timer_shutdown_virt; clk->set_state_oneshot_stopped = arch_timer_shutdown_virt; sne = erratum_handler(set_next_event_virt); break; case ARCH_TIMER_PHYS_SECURE_PPI: case ARCH_TIMER_PHYS_NONSECURE_PPI: case ARCH_TIMER_HYP_PPI: clk->set_state_shutdown = arch_timer_shutdown_phys; clk->set_state_oneshot_stopped = arch_timer_shutdown_phys; sne = erratum_handler(set_next_event_phys); break; default: BUG(); } clk->set_next_event = sne; max_delta = __arch_timer_check_delta(); } else { clk->features |= CLOCK_EVT_FEAT_DYNIRQ; clk->name = "arch_mem_timer"; clk->rating = 400; clk->cpumask = cpu_possible_mask; if (arch_timer_mem_use_virtual) { clk->set_state_shutdown = arch_timer_shutdown_virt_mem; clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem; clk->set_next_event = arch_timer_set_next_event_virt_mem; } else { clk->set_state_shutdown = arch_timer_shutdown_phys_mem; clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem; clk->set_next_event = arch_timer_set_next_event_phys_mem; } max_delta = CLOCKSOURCE_MASK(56); } clk->set_state_shutdown(clk); clockevents_config_and_register(clk, arch_timer_rate, 0xf, max_delta); } static void arch_timer_evtstrm_enable(unsigned int divider) { u32 cntkctl = arch_timer_get_cntkctl(); #ifdef CONFIG_ARM64 /* ECV is likely to require a large divider. Use the EVNTIS flag. */ if (cpus_have_final_cap(ARM64_HAS_ECV) && divider > 15) { cntkctl |= ARCH_TIMER_EVT_INTERVAL_SCALE; divider -= 8; } #endif divider = min(divider, 15U); cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK; /* Set the divider and enable virtual event stream */ cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT) | ARCH_TIMER_VIRT_EVT_EN; arch_timer_set_cntkctl(cntkctl); arch_timer_set_evtstrm_feature(); cpumask_set_cpu(smp_processor_id(), &evtstrm_available); } static void arch_timer_configure_evtstream(void) { int evt_stream_div, lsb; /* * As the event stream can at most be generated at half the frequency * of the counter, use half the frequency when computing the divider. */ evt_stream_div = arch_timer_rate / ARCH_TIMER_EVT_STREAM_FREQ / 2; /* * Find the closest power of two to the divisor. If the adjacent bit * of lsb (last set bit, starts from 0) is set, then we use (lsb + 1). */ lsb = fls(evt_stream_div) - 1; if (lsb > 0 && (evt_stream_div & BIT(lsb - 1))) lsb++; /* enable event stream */ arch_timer_evtstrm_enable(max(0, lsb)); } static int arch_timer_evtstrm_starting_cpu(unsigned int cpu) { arch_timer_configure_evtstream(); return 0; } static int arch_timer_evtstrm_dying_cpu(unsigned int cpu) { cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); return 0; } static int __init arch_timer_evtstrm_register(void) { if (!arch_timer_evt || !evtstrm_enable) return 0; return cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING, "clockevents/arm/arch_timer_evtstrm:starting", arch_timer_evtstrm_starting_cpu, arch_timer_evtstrm_dying_cpu); } core_initcall(arch_timer_evtstrm_register); static void arch_counter_set_user_access(void) { u32 cntkctl = arch_timer_get_cntkctl(); /* Disable user access to the timers and both counters */ /* Also disable virtual event stream */ cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN | ARCH_TIMER_USR_VT_ACCESS_EN | ARCH_TIMER_USR_VCT_ACCESS_EN | ARCH_TIMER_VIRT_EVT_EN | ARCH_TIMER_USR_PCT_ACCESS_EN); /* * Enable user access to the virtual counter if it doesn't * need to be workaround. The vdso may have been already * disabled though. */ if (arch_timer_this_cpu_has_cntvct_wa()) pr_info("CPU%d: Trapping CNTVCT access\n", smp_processor_id()); else cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN; arch_timer_set_cntkctl(cntkctl); } static bool arch_timer_has_nonsecure_ppi(void) { return (arch_timer_uses_ppi == ARCH_TIMER_PHYS_SECURE_PPI && arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); } static u32 check_ppi_trigger(int irq) { u32 flags = irq_get_trigger_type(irq); if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) { pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq); pr_warn("WARNING: Please fix your firmware\n"); flags = IRQF_TRIGGER_LOW; } return flags; } static int arch_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); u32 flags; __arch_timer_setup(ARCH_TIMER_TYPE_CP15, clk); flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]); enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags); if (arch_timer_has_nonsecure_ppi()) { flags = check_ppi_trigger(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); enable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI], flags); } arch_counter_set_user_access(); return 0; } static int validate_timer_rate(void) { if (!arch_timer_rate) return -EINVAL; /* Arch timer frequency < 1MHz can cause trouble */ WARN_ON(arch_timer_rate < 1000000); return 0; } /* * For historical reasons, when probing with DT we use whichever (non-zero) * rate was probed first, and don't verify that others match. If the first node * probed has a clock-frequency property, this overrides the HW register. */ static void __init arch_timer_of_configure_rate(u32 rate, struct device_node *np) { /* Who has more than one independent system counter? */ if (arch_timer_rate) return; if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) arch_timer_rate = rate; /* Check the timer frequency. */ if (validate_timer_rate()) pr_warn("frequency not available\n"); } static void __init arch_timer_banner(unsigned type) { pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n", type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "", type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? " and " : "", type & ARCH_TIMER_TYPE_MEM ? "mmio" : "", (unsigned long)arch_timer_rate / 1000000, (unsigned long)(arch_timer_rate / 10000) % 100, type & ARCH_TIMER_TYPE_CP15 ? (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ? "virt" : "phys" : "", type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? "/" : "", type & ARCH_TIMER_TYPE_MEM ? arch_timer_mem_use_virtual ? "virt" : "phys" : ""); } u32 arch_timer_get_rate(void) { return arch_timer_rate; } bool arch_timer_evtstrm_available(void) { /* * We might get called from a preemptible context. This is fine * because availability of the event stream should be always the same * for a preemptible context and context where we might resume a task. */ return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available); } static noinstr u64 arch_counter_get_cntvct_mem(void) { return arch_counter_get_cnt_mem(arch_timer_mem, CNTVCT_LO); } static struct arch_timer_kvm_info arch_timer_kvm_info; struct arch_timer_kvm_info *arch_timer_get_kvm_info(void) { return &arch_timer_kvm_info; } static void __init arch_counter_register(unsigned type) { u64 (*scr)(void); u64 start_count; int width; /* Register the CP15 based counter if we have one */ if (type & ARCH_TIMER_TYPE_CP15) { u64 (*rd)(void); if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) || arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) { if (arch_timer_counter_has_wa()) { rd = arch_counter_get_cntvct_stable; scr = raw_counter_get_cntvct_stable; } else { rd = arch_counter_get_cntvct; scr = arch_counter_get_cntvct; } } else { if (arch_timer_counter_has_wa()) { rd = arch_counter_get_cntpct_stable; scr = raw_counter_get_cntpct_stable; } else { rd = arch_counter_get_cntpct; scr = arch_counter_get_cntpct; } } arch_timer_read_counter = rd; clocksource_counter.vdso_clock_mode = vdso_default; } else { arch_timer_read_counter = arch_counter_get_cntvct_mem; scr = arch_counter_get_cntvct_mem; } width = arch_counter_get_width(); clocksource_counter.mask = CLOCKSOURCE_MASK(width); cyclecounter.mask = CLOCKSOURCE_MASK(width); if (!arch_counter_suspend_stop) clocksource_counter.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; start_count = arch_timer_read_counter(); clocksource_register_hz(&clocksource_counter, arch_timer_rate); cyclecounter.mult = clocksource_counter.mult; cyclecounter.shift = clocksource_counter.shift; timecounter_init(&arch_timer_kvm_info.timecounter, &cyclecounter, start_count); sched_clock_register(scr, width, arch_timer_rate); } static void arch_timer_stop(struct clock_event_device *clk) { pr_debug("disable IRQ%d cpu #%d\n", clk->irq, smp_processor_id()); disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]); if (arch_timer_has_nonsecure_ppi()) disable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); } static int arch_timer_dying_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); arch_timer_stop(clk); return 0; } #ifdef CONFIG_CPU_PM static DEFINE_PER_CPU(unsigned long, saved_cntkctl); static int arch_timer_cpu_pm_notify(struct notifier_block *self, unsigned long action, void *hcpu) { if (action == CPU_PM_ENTER) { __this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl()); cpumask_clear_cpu(smp_processor_id(), &evtstrm_available); } else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) { arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl)); if (arch_timer_have_evtstrm_feature()) cpumask_set_cpu(smp_processor_id(), &evtstrm_available); } return NOTIFY_OK; } static struct notifier_block arch_timer_cpu_pm_notifier = { .notifier_call = arch_timer_cpu_pm_notify, }; static int __init arch_timer_cpu_pm_init(void) { return cpu_pm_register_notifier(&arch_timer_cpu_pm_notifier); } static void __init arch_timer_cpu_pm_deinit(void) { WARN_ON(cpu_pm_unregister_notifier(&arch_timer_cpu_pm_notifier)); } #else static int __init arch_timer_cpu_pm_init(void) { return 0; } static void __init arch_timer_cpu_pm_deinit(void) { } #endif static int __init arch_timer_register(void) { int err; int ppi; arch_timer_evt = alloc_percpu(struct clock_event_device); if (!arch_timer_evt) { err = -ENOMEM; goto out; } ppi = arch_timer_ppi[arch_timer_uses_ppi]; switch (arch_timer_uses_ppi) { case ARCH_TIMER_VIRT_PPI: err = request_percpu_irq(ppi, arch_timer_handler_virt, "arch_timer", arch_timer_evt); break; case ARCH_TIMER_PHYS_SECURE_PPI: case ARCH_TIMER_PHYS_NONSECURE_PPI: err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); if (!err && arch_timer_has_nonsecure_ppi()) { ppi = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]; err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); if (err) free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_SECURE_PPI], arch_timer_evt); } break; case ARCH_TIMER_HYP_PPI: err = request_percpu_irq(ppi, arch_timer_handler_phys, "arch_timer", arch_timer_evt); break; default: BUG(); } if (err) { pr_err("can't register interrupt %d (%d)\n", ppi, err); goto out_free; } err = arch_timer_cpu_pm_init(); if (err) goto out_unreg_notify; /* Register and immediately configure the timer on the boot CPU */ err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING, "clockevents/arm/arch_timer:starting", arch_timer_starting_cpu, arch_timer_dying_cpu); if (err) goto out_unreg_cpupm; return 0; out_unreg_cpupm: arch_timer_cpu_pm_deinit(); out_unreg_notify: free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt); if (arch_timer_has_nonsecure_ppi()) free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI], arch_timer_evt); out_free: free_percpu(arch_timer_evt); arch_timer_evt = NULL; out: return err; } static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq) { int ret; irq_handler_t func; arch_timer_mem = kzalloc(sizeof(*arch_timer_mem), GFP_KERNEL); if (!arch_timer_mem) return -ENOMEM; arch_timer_mem->base = base; arch_timer_mem->evt.irq = irq; __arch_timer_setup(ARCH_TIMER_TYPE_MEM, &arch_timer_mem->evt); if (arch_timer_mem_use_virtual) func = arch_timer_handler_virt_mem; else func = arch_timer_handler_phys_mem; ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &arch_timer_mem->evt); if (ret) { pr_err("Failed to request mem timer irq\n"); kfree(arch_timer_mem); arch_timer_mem = NULL; } return ret; } static const struct of_device_id arch_timer_of_match[] __initconst = { { .compatible = "arm,armv7-timer", }, { .compatible = "arm,armv8-timer", }, {}, }; static const struct of_device_id arch_timer_mem_of_match[] __initconst = { { .compatible = "arm,armv7-timer-mem", }, {}, }; static bool __init arch_timer_needs_of_probing(void) { struct device_node *dn; bool needs_probing = false; unsigned int mask = ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM; /* We have two timers, and both device-tree nodes are probed. */ if ((arch_timers_present & mask) == mask) return false; /* * Only one type of timer is probed, * check if we have another type of timer node in device-tree. */ if (arch_timers_present & ARCH_TIMER_TYPE_CP15) dn = of_find_matching_node(NULL, arch_timer_mem_of_match); else dn = of_find_matching_node(NULL, arch_timer_of_match); if (dn && of_device_is_available(dn)) needs_probing = true; of_node_put(dn); return needs_probing; } static int __init arch_timer_common_init(void) { arch_timer_banner(arch_timers_present); arch_counter_register(arch_timers_present); return arch_timer_arch_init(); } /** * arch_timer_select_ppi() - Select suitable PPI for the current system. * * If HYP mode is available, we know that the physical timer * has been configured to be accessible from PL1. Use it, so * that a guest can use the virtual timer instead. * * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE * accesses to CNTP_*_EL1 registers are silently redirected to * their CNTHP_*_EL2 counterparts, and use a different PPI * number. * * If no interrupt provided for virtual timer, we'll have to * stick to the physical timer. It'd better be accessible... * For arm64 we never use the secure interrupt. * * Return: a suitable PPI type for the current system. */ static enum arch_timer_ppi_nr __init arch_timer_select_ppi(void) { if (is_kernel_in_hyp_mode()) return ARCH_TIMER_HYP_PPI; if (!is_hyp_mode_available() && arch_timer_ppi[ARCH_TIMER_VIRT_PPI]) return ARCH_TIMER_VIRT_PPI; if (IS_ENABLED(CONFIG_ARM64)) return ARCH_TIMER_PHYS_NONSECURE_PPI; return ARCH_TIMER_PHYS_SECURE_PPI; } static void __init arch_timer_populate_kvm_info(void) { arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI]; if (is_kernel_in_hyp_mode()) arch_timer_kvm_info.physical_irq = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]; } static int __init arch_timer_of_init(struct device_node *np) { int i, irq, ret; u32 rate; bool has_names; if (arch_timers_present & ARCH_TIMER_TYPE_CP15) { pr_warn("multiple nodes in dt, skipping\n"); return 0; } arch_timers_present |= ARCH_TIMER_TYPE_CP15; has_names = of_property_present(np, "interrupt-names"); for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++) { if (has_names) irq = of_irq_get_byname(np, arch_timer_ppi_names[i]); else irq = of_irq_get(np, i); if (irq > 0) arch_timer_ppi[i] = irq; } arch_timer_populate_kvm_info(); rate = arch_timer_get_cntfrq(); arch_timer_of_configure_rate(rate, np); arch_timer_c3stop = !of_property_read_bool(np, "always-on"); /* Check for globally applicable workarounds */ arch_timer_check_ool_workaround(ate_match_dt, np); /* * If we cannot rely on firmware initializing the timer registers then * we should use the physical timers instead. */ if (IS_ENABLED(CONFIG_ARM) && of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) arch_timer_uses_ppi = ARCH_TIMER_PHYS_SECURE_PPI; else arch_timer_uses_ppi = arch_timer_select_ppi(); if (!arch_timer_ppi[arch_timer_uses_ppi]) { pr_err("No interrupt available, giving up\n"); return -EINVAL; } /* On some systems, the counter stops ticking when in suspend. */ arch_counter_suspend_stop = of_property_read_bool(np, "arm,no-tick-in-suspend"); ret = arch_timer_register(); if (ret) return ret; if (arch_timer_needs_of_probing()) return 0; return arch_timer_common_init(); } TIMER_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init); TIMER_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init); static u32 __init arch_timer_mem_frame_get_cntfrq(struct arch_timer_mem_frame *frame) { void __iomem *base; u32 rate; base = ioremap(frame->cntbase, frame->size); if (!base) { pr_err("Unable to map frame @ %pa\n", &frame->cntbase); return 0; } rate = readl_relaxed(base + CNTFRQ); iounmap(base); return rate; } static struct arch_timer_mem_frame * __init arch_timer_mem_find_best_frame(struct arch_timer_mem *timer_mem) { struct arch_timer_mem_frame *frame, *best_frame = NULL; void __iomem *cntctlbase; u32 cnttidr; int i; cntctlbase = ioremap(timer_mem->cntctlbase, timer_mem->size); if (!cntctlbase) { pr_err("Can't map CNTCTLBase @ %pa\n", &timer_mem->cntctlbase); return NULL; } cnttidr = readl_relaxed(cntctlbase + CNTTIDR); /* * Try to find a virtual capable frame. Otherwise fall back to a * physical capable frame. */ for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) { u32 cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT | CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT; frame = &timer_mem->frame[i]; if (!frame->valid) continue; /* Try enabling everything, and see what sticks */ writel_relaxed(cntacr, cntctlbase + CNTACR(i)); cntacr = readl_relaxed(cntctlbase + CNTACR(i)); if ((cnttidr & CNTTIDR_VIRT(i)) && !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) { best_frame = frame; arch_timer_mem_use_virtual = true; break; } if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT)) continue; best_frame = frame; } iounmap(cntctlbase); return best_frame; } static int __init arch_timer_mem_frame_register(struct arch_timer_mem_frame *frame) { void __iomem *base; int ret, irq; if (arch_timer_mem_use_virtual) irq = frame->virt_irq; else irq = frame->phys_irq; if (!irq) { pr_err("Frame missing %s irq.\n", arch_timer_mem_use_virtual ? "virt" : "phys"); return -EINVAL; } if (!request_mem_region(frame->cntbase, frame->size, "arch_mem_timer")) return -EBUSY; base = ioremap(frame->cntbase, frame->size); if (!base) { pr_err("Can't map frame's registers\n"); return -ENXIO; } ret = arch_timer_mem_register(base, irq); if (ret) { iounmap(base); return ret; } arch_timers_present |= ARCH_TIMER_TYPE_MEM; return 0; } static int __init arch_timer_mem_of_init(struct device_node *np) { struct arch_timer_mem *timer_mem; struct arch_timer_mem_frame *frame; struct resource res; int ret = -EINVAL; u32 rate; timer_mem = kzalloc(sizeof(*timer_mem), GFP_KERNEL); if (!timer_mem) return -ENOMEM; if (of_address_to_resource(np, 0, &res)) goto out; timer_mem->cntctlbase = res.start; timer_mem->size = resource_size(&res); for_each_available_child_of_node_scoped(np, frame_node) { u32 n; struct arch_timer_mem_frame *frame; if (of_property_read_u32(frame_node, "frame-number", &n)) { pr_err(FW_BUG "Missing frame-number.\n"); goto out; } if (n >= ARCH_TIMER_MEM_MAX_FRAMES) { pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n", ARCH_TIMER_MEM_MAX_FRAMES - 1); goto out; } frame = &timer_mem->frame[n]; if (frame->valid) { pr_err(FW_BUG "Duplicated frame-number.\n"); goto out; } if (of_address_to_resource(frame_node, 0, &res)) goto out; frame->cntbase = res.start; frame->size = resource_size(&res); frame->virt_irq = irq_of_parse_and_map(frame_node, ARCH_TIMER_VIRT_SPI); frame->phys_irq = irq_of_parse_and_map(frame_node, ARCH_TIMER_PHYS_SPI); frame->valid = true; } frame = arch_timer_mem_find_best_frame(timer_mem); if (!frame) { pr_err("Unable to find a suitable frame in timer @ %pa\n", &timer_mem->cntctlbase); ret = -EINVAL; goto out; } rate = arch_timer_mem_frame_get_cntfrq(frame); arch_timer_of_configure_rate(rate, np); ret = arch_timer_mem_frame_register(frame); if (!ret && !arch_timer_needs_of_probing()) ret = arch_timer_common_init(); out: kfree(timer_mem); return ret; } TIMER_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem", arch_timer_mem_of_init); #ifdef CONFIG_ACPI_GTDT static int __init arch_timer_mem_verify_cntfrq(struct arch_timer_mem *timer_mem) { struct arch_timer_mem_frame *frame; u32 rate; int i; for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) { frame = &timer_mem->frame[i]; if (!frame->valid) continue; rate = arch_timer_mem_frame_get_cntfrq(frame); if (rate == arch_timer_rate) continue; pr_err(FW_BUG "CNTFRQ mismatch: frame @ %pa: (0x%08lx), CPU: (0x%08lx)\n", &frame->cntbase, (unsigned long)rate, (unsigned long)arch_timer_rate); return -EINVAL; } return 0; } static int __init arch_timer_mem_acpi_init(int platform_timer_count) { struct arch_timer_mem *timers, *timer; struct arch_timer_mem_frame *frame, *best_frame = NULL; int timer_count, i, ret = 0; timers = kcalloc(platform_timer_count, sizeof(*timers), GFP_KERNEL); if (!timers) return -ENOMEM; ret = acpi_arch_timer_mem_init(timers, &timer_count); if (ret || !timer_count) goto out; /* * While unlikely, it's theoretically possible that none of the frames * in a timer expose the combination of feature we want. */ for (i = 0; i < timer_count; i++) { timer = &timers[i]; frame = arch_timer_mem_find_best_frame(timer); if (!best_frame) best_frame = frame; ret = arch_timer_mem_verify_cntfrq(timer); if (ret) { pr_err("Disabling MMIO timers due to CNTFRQ mismatch\n"); goto out; } if (!best_frame) /* implies !frame */ /* * Only complain about missing suitable frames if we * haven't already found one in a previous iteration. */ pr_err("Unable to find a suitable frame in timer @ %pa\n", &timer->cntctlbase); } if (best_frame) ret = arch_timer_mem_frame_register(best_frame); out: kfree(timers); return ret; } /* Initialize per-processor generic timer and memory-mapped timer(if present) */ static int __init arch_timer_acpi_init(struct acpi_table_header *table) { int ret, platform_timer_count; if (arch_timers_present & ARCH_TIMER_TYPE_CP15) { pr_warn("already initialized, skipping\n"); return -EINVAL; } arch_timers_present |= ARCH_TIMER_TYPE_CP15; ret = acpi_gtdt_init(table, &platform_timer_count); if (ret) return ret; arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_PHYS_NONSECURE_PPI); arch_timer_ppi[ARCH_TIMER_VIRT_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_VIRT_PPI); arch_timer_ppi[ARCH_TIMER_HYP_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_HYP_PPI); arch_timer_populate_kvm_info(); /* * When probing via ACPI, we have no mechanism to override the sysreg * CNTFRQ value. This *must* be correct. */ arch_timer_rate = arch_timer_get_cntfrq(); ret = validate_timer_rate(); if (ret) { pr_err(FW_BUG "frequency not available.\n"); return ret; } arch_timer_uses_ppi = arch_timer_select_ppi(); if (!arch_timer_ppi[arch_timer_uses_ppi]) { pr_err("No interrupt available, giving up\n"); return -EINVAL; } /* Always-on capability */ arch_timer_c3stop = acpi_gtdt_c3stop(arch_timer_uses_ppi); /* Check for globally applicable workarounds */ arch_timer_check_ool_workaround(ate_match_acpi_oem_info, table); ret = arch_timer_register(); if (ret) return ret; if (platform_timer_count && arch_timer_mem_acpi_init(platform_timer_count)) pr_err("Failed to initialize memory-mapped timer.\n"); return arch_timer_common_init(); } TIMER_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init); #endif int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts, enum clocksource_ids *cs_id) { struct arm_smccc_res hvc_res; u32 ptp_counter; ktime_t ktime; if (!IS_ENABLED(CONFIG_HAVE_ARM_SMCCC_DISCOVERY)) return -EOPNOTSUPP; if (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ptp_counter = KVM_PTP_VIRT_COUNTER; else ptp_counter = KVM_PTP_PHYS_COUNTER; arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID, ptp_counter, &hvc_res); if ((int)(hvc_res.a0) < 0) return -EOPNOTSUPP; ktime = (u64)hvc_res.a0 << 32 | hvc_res.a1; *ts = ktime_to_timespec64(ktime); if (cycle) *cycle = (u64)hvc_res.a2 << 32 | hvc_res.a3; if (cs_id) *cs_id = CSID_ARM_ARCH_COUNTER; return 0; } EXPORT_SYMBOL_GPL(kvm_arch_ptp_get_crosststamp); |
| 594 579 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* rwsem.h: R/W semaphores, public interface * * Written by David Howells (dhowells@redhat.com). * Derived from asm-i386/semaphore.h */ #ifndef _LINUX_RWSEM_H #define _LINUX_RWSEM_H #include <linux/linkage.h> #include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> #include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ }, #else # define __RWSEM_DEP_MAP_INIT(lockname) #endif #ifndef CONFIG_PREEMPT_RT #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif /* * For an uncontended rwsem, count and owner are the only fields a task * needs to touch when acquiring the rwsem. So they are put next to each * other to increase the chance that they will share the same cacheline. * * In a contended rwsem, the owner is likely the most frequently accessed * field in the structure as the optimistic waiter that holds the osq lock * will spin on owner. For an embedded rwsem, other hot fields in the * containing structure should be moved further away from the rwsem to * reduce the chance that they will share the same cacheline causing * cacheline bouncing problem. */ struct rw_semaphore { atomic_long_t count; /* * Write owner or one of the read owners as well flags regarding * the current state of the rwsem. Can be used as a speculative * check to see if the write owner is running on the cpu. */ atomic_long_t owner; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_RWSEMS void *magic; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define RWSEM_UNLOCKED_VALUE 0UL #define RWSEM_WRITER_LOCKED (1UL << 0) #define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE; } static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE); } static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED)); } /* Common initializer macros and functions */ #ifdef CONFIG_DEBUG_RWSEMS # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else # define __RWSEM_DEBUG_INIT(lockname) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED, #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ { __RWSEM_COUNT_INIT(name), \ .owner = ATOMIC_LONG_INIT(0), \ __RWSEM_OPT_INIT(name) \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\ .wait_list = LIST_HEAD_INIT((name).wait_list), \ __RWSEM_DEBUG_INIT(name) \ __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) extern void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) /* * This is the same regardless of which rwsem implementation that is being used. * It is just a heuristic meant to be called by somebody already holding the * rwsem to see if somebody from an incompatible type is wanting access to the * lock. */ static inline int rwsem_is_contended(struct rw_semaphore *sem) { return !list_empty(&sem->wait_list); } #else /* !CONFIG_PREEMPT_RT */ #include <linux/rwbase_rt.h> struct rw_semaphore { struct rwbase_rt rwbase; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define __RWSEM_INITIALIZER(name) \ { \ .rwbase = __RWBASE_INITIALIZER(name), \ __RWSEM_DEP_MAP_INIT(name) \ } #define DECLARE_RWSEM(lockname) \ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) { return rw_base_is_locked(&sem->rwbase); } static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rwsem_is_locked(sem)); } static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) { return rw_base_is_contended(&sem->rwbase); } #endif /* CONFIG_PREEMPT_RT */ /* * The functions below are the same for all rwsem implementations including * the RT specific variant. */ static inline void rwsem_assert_held(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held(sem); else rwsem_assert_held_nolockdep(sem); } static inline void rwsem_assert_held_write(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held_write(sem); else rwsem_assert_held_write_nolockdep(sem); } /* * lock for reading */ extern void down_read(struct rw_semaphore *sem); extern int __must_check down_read_interruptible(struct rw_semaphore *sem); extern int __must_check down_read_killable(struct rw_semaphore *sem); /* * trylock for reading -- returns 1 if successful, 0 if contention */ extern int down_read_trylock(struct rw_semaphore *sem); /* * lock for writing */ extern void down_write(struct rw_semaphore *sem); extern int __must_check down_write_killable(struct rw_semaphore *sem); /* * trylock for writing -- returns 1 if successful, 0 if contention */ extern int down_write_trylock(struct rw_semaphore *sem); /* * release a read lock */ extern void up_read(struct rw_semaphore *sem); /* * release a write lock */ extern void up_write(struct rw_semaphore *sem); DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T)) DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0) DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T)) /* * downgrade write lock to read lock */ extern void downgrade_write(struct rw_semaphore *sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * nested locking. NOTE: rwsems are not allowed to recurse * (which occurs if the same task tries to acquire the same * lock instance multiple times), but multiple locks of the * same lock class might be taken, if the order of the locks * is always the same. This ordering rule can be expressed * to lockdep via the _nested() APIs, but enumerating the * subclasses that are used. (If the nesting relationship is * static then another method for expressing nested locking is * the explicit definition of lock class keys and the use of * lockdep_set_class() at lock initialization time. * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass); extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock); # define down_write_nest_lock(sem, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0) /* * Take/release a lock when not the owner will release it. * * [ This API should be avoided as much as possible - the * proper abstraction for this case is completions. ] */ extern void down_read_non_owner(struct rw_semaphore *sem); extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_read_killable_nested(sem, subclass) down_read_killable(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) # define down_write_killable_nested(sem, subclass) down_write_killable(sem) # define down_read_non_owner(sem) down_read(sem) # define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_IP6_ROUTE_H #define _NET_IP6_ROUTE_H #include <net/addrconf.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> #include <net/lwtunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> #include <net/nexthop.h> struct route_info { __u8 type; __u8 length; __u8 prefix_len; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved_h:3, route_pref:2, reserved_l:3; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved_l:3, route_pref:2, reserved_h:3; #endif __be32 lifetime; __u8 prefix[]; /* 0,8 or 16 */ }; #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 #define RT6_LOOKUP_F_HAS_SADDR 0x00000004 #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 #define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header */ #define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr)) /* * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate * between IPV6_ADDR_PREFERENCES socket option values * IPV6_PREFER_SRC_TMP = 0x1 * IPV6_PREFER_SRC_PUBLIC = 0x2 * IPV6_PREFER_SRC_COA = 0x4 * and above RT6_LOOKUP_F_SRCPREF_xxx flags. */ static inline int rt6_srcprefs2flags(unsigned int srcprefs) { return (srcprefs & IPV6_PREFER_SRC_MASK) << 3; } static inline unsigned int rt6_flags2srcprefs(int flags) { return (flags >> 3) & IPV6_PREFER_SRC_MASK; } static inline bool rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* fib entries using a nexthop object can not be coalesced into * a multipath route */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && f6i->fib6_nh->fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); static inline struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { return ip6_route_output_flags(net, sk, fl6, 0); } /* Only conditionally release dst if flags indicates * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. */ static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) { if (!(flags & RT6_LOOKUP_F_DST_NOREF) || !list_empty(&rt->dst.rt_uncached)) ip6_rt_put(rt); } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int ifindex, struct flowi6 *fl6, const struct sk_buff *skb, int flags); void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg); int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); int ip6_ins_rt(struct net *net, struct fib6_info *f6i); int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify); void rt6_flush_exceptions(struct fib6_info *f6i); void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now); static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, unsigned int prefs, int l3mdev_index, struct in6_addr *saddr) { struct net_device *l3mdev; struct net_device *dev; bool same_vrf; int err = 0; rcu_read_lock(); l3mdev = dev_get_by_index_rcu(net, l3mdev_index); if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev) dev = f6i ? fib6_info_nh_dev(f6i) : NULL; same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev; if (f6i && f6i->fib6_prefsrc.plen && same_vrf) *saddr = f6i->fib6_prefsrc.addr; else err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr); rcu_read_unlock(); return err; } struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int flags); u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *hkeys); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); void fib6_force_start_gc(struct net *net); struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); /* * support functions for ND * */ struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime); void rt6_purge_dflt_routers(struct net *net); int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; struct fib_dump_filter filter; }; int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned char nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct fib6_info *f6i); void rt6_uncached_list_add(struct rt6_info *rt); void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); if (dst) return dst_rt6_info(dst); return NULL; } /* * Store a destination cache entry in a socket */ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif } void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6); static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) { mtu = READ_ONCE(dst->dev->mtu); mtu -= lwtunnel_headroom(dst->lwtstate, mtu); } else { mtu = dst_mtu(dst); } return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc != IPV6_PMTUDISC_INTERFACE && pmtudisc != IPV6_PMTUDISC_OMIT; } static inline bool ip6_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc < IPV6_PMTUDISC_DO || pmtudisc == IPV6_PMTUDISC_OMIT; } static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; else if (unlikely(rt->rt6i_flags & RTF_CACHE)) return &rt->rt6i_dst.addr; else return daddr; } static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { struct fib6_nh *nha, *nhb; if (a->nh || b->nh) return nexthop_cmp(a->nh, b->nh); nha = a->fib6_nh; nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct inet6_dev *idev; unsigned int mtu; if (!forwarding || dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; } mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); if (idev) mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr); #endif |
| 10 11 11 11 11 1 1 1 10 10 10 10 10 10 10 10 1 1 1 1 11 11 10 11 11 1 10 10 10 10 10 2 2 2 10 10 10 1 1 1 1 1 38 36 39 13 13 4 2 18 1 15 2 5 22 3 40 7 1 4 9 4 3 16 9 7 15 15 12 11 1 15 22 22 22 15 12 1 60 60 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC MMIO handling functions */ #include <linux/bitops.h> #include <linux/bsearch.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_vgic.h> #include "vgic.h" #include "vgic-mmio.h" unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return 0; } unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return -1UL; } void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ return 0; } unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->group) value |= BIT(i); vgic_put_irq(vcpu->kvm, irq); } return value; } static void vgic_update_vsgi(struct vgic_irq *irq) { WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); } void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } else { vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } vgic_put_irq(vcpu->kvm, irq); } } /* * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value * of the enabled bit, so there is only one function for both here. */ unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->enabled) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { if (!irq->enabled) { struct irq_data *data; irq->enabled = true; data = &irq_to_desc(irq->host_irq)->irq_data; while (irqd_irq_disabled(data)) enable_irq(irq->host_irq); } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } else if (vgic_irq_is_mapped_level(irq)) { bool was_high = irq->line_level; /* * We need to update the state of the interrupt because * the guest might have changed the state of the device * while the interrupt was disabled at the VGIC level. */ irq->line_level = vgic_get_phys_line_level(irq); /* * Deactivate the physical interrupt so the GIC will let * us know when it is asserted again. */ if (!irq->active && was_high && !irq->line_level) vgic_irq_set_phys_active(irq, false); } irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) disable_irq_nosync(irq->host_irq); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } static unsigned long __read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); unsigned long flags; bool val; /* * When used from userspace with a GICv3 model: * * Pending state of interrupt is latched in pending_latch * variable. Userspace will save and restore pending state * and line_level separately. * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst * for handling of ISPENDR and ICPENDR. */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; val = false; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); } else if (!is_user && vgic_irq_is_mapped_level(irq)) { val = vgic_get_phys_line_level(irq); } else { switch (vcpu->kvm->arch.vgic.vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V3: if (is_user) { val = irq->pending_latch; break; } fallthrough; default: val = irq_is_pending(irq); break; } } value |= ((u32)val << i); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, false); } unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, true); } static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2); } static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* GICD_ISPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * GICv2 SGIs are terribly broken. We can't restore * the source of the interrupt, so just pick the vcpu * itself as the source... */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source |= BIT(vcpu->vcpu_id); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to inject it */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } irq->pending_latch = true; if (irq->hw && !is_user) vgic_irq_set_phys_active(irq, true); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, true); return 0; } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { irq->pending_latch = false; /* * We don't want the guest to effectively mask the physical * interrupt by doing a write to SPENDR followed by a write to * CPENDR for HW interrupts, so we clear the active state on * the physical side if the virtual interrupt is not active. * This may lead to taking an additional interrupt on the * host, but that should not be a problem as the worst that * can happen is an additional vgic injection. We also clear * the pending state to maintain proper semantics for edge HW * interrupts. */ vgic_irq_set_phys_pending(irq, false); if (!irq->active) vgic_irq_set_phys_active(irq, false); } static void __clear_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* GICD_ICPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * More fun with GICv2 SGIs! If we're clearing one of them * from userspace, which source vcpu to clear? Let's not * even think of it, and blow the whole set. */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source = 0; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to clear its pending bit */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, false); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } if (irq->hw && !is_user) vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, true); return 0; } /* * If we are fiddling with an IRQ's active state, we have to make sure the IRQ * is not queued on some running VCPU's LRs, because then the change to the * active state can be overwritten when the VCPU's state is synced coming back * from the guest. * * For shared interrupts as well as GICv3 private interrupts accessed from the * non-owning CPU, we have to stop all the VCPUs because interrupts can be * migrated while we don't hold the IRQ locks and we don't want to be chasing * moving targets. * * For GICv2 private interrupts we don't have to do anything because * userspace accesses to the VGIC state already require all VCPUs to be * stopped, and only the VCPU itself can modify its private interrupts * active state, which guarantees that the VCPU is not running. */ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } /* See vgic_access_active_prepare */ static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); } static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* * Even for HW interrupts, don't evaluate the HW state as * all the guest is interested in is the virtual state. */ if (irq->active) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 val; mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); val = __vgic_mmio_read_active(vcpu, addr, len); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); return val; } unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __vgic_mmio_read_active(vcpu, addr, len); } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) { if (is_uaccess) return; irq->active = active; vgic_irq_set_phys_active(irq, active); } static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active) { unsigned long flags; struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* * GICv4.1 VSGI feature doesn't track an active state, * so let's not kid ourselves, there is nothing we can * do here. */ irq->active = false; } else { u32 model = vcpu->kvm->arch.vgic.vgic_model; u8 active_source; irq->active = active; /* * The GICv2 architecture indicates that the source CPUID for * an SGI should be provided during an EOI which implies that * the active state is stored somewhere, but at the same time * this state is not architecturally exposed anywhere and we * have no way of knowing the right source. * * This may lead to a VCPU not being able to receive * additional instances of a particular SGI after migration * for a GICv2 VM on some GIC implementations. Oh well. */ active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && active && vgic_irq_is_sgi(irq->intid)) irq->active_source = active_source; } if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, false); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_cactive(vcpu, addr, len, val); return 0; } static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, true); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_sactive(vcpu, addr, len, val); return 0; } unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; u64 val = 0; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); val |= (u64)irq->priority << (i * 8); vgic_put_irq(vcpu->kvm, irq); } return val; } /* * We currently don't handle changing the priority of an interrupt that * is already pending on a VCPU. If there is a need for this, we would * need to make this VCPU exit and re-evaluate the priorities, potentially * leading to this interrupt getting presented now to the guest (if it has * been masked by the priority mask before). */ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; unsigned long flags; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); if (irq->hw && vgic_irq_is_sgi(irq->intid)) vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); u32 value = 0; int i; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->config == VGIC_CONFIG_EDGE) value |= (2U << (i * 2)); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); int i; unsigned long flags; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq; /* * The configuration cannot be changed for SGIs in general, * for PPIs this is IMPLEMENTATION DEFINED. The arch timer * code relies on PPIs being level triggered, so we also * make them read-only here. */ if (intid + i < VGIC_NR_PRIVATE_IRQS) continue; irq = vgic_get_irq(vcpu->kvm, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i * 2 + 1, &val)) irq->config = VGIC_CONFIG_EDGE; else irq->config = VGIC_CONFIG_LEVEL; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } u32 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid) { int i; u32 val = 0; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; for (i = 0; i < 32; i++) { struct vgic_irq *irq; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) val |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return val; } void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, const u32 val) { int i; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; unsigned long flags; for (i = 0; i < 32; i++) { struct vgic_irq *irq; bool new_level; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_vcpu_irq(vcpu, intid + i); /* * Line level is set irrespective of irq type * (level or edge) to avoid dependency that VM should * restore irq config before line level. */ new_level = !!(val & (1U << i)); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->line_level = new_level; if (new_level) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } static int match_region(const void *key, const void *elt) { const unsigned int offset = (unsigned long)key; const struct vgic_register_region *region = elt; if (offset < region->reg_offset) return -1; if (offset >= region->reg_offset + region->len) return 1; return 0; } const struct vgic_register_region * vgic_find_mmio_region(const struct vgic_register_region *regions, int nr_regions, unsigned int offset) { return bsearch((void *)(uintptr_t)offset, regions, nr_regions, sizeof(regions[0]), match_region); } void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_set_vmcr(vcpu, vmcr); else vgic_v3_set_vmcr(vcpu, vmcr); } void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_get_vmcr(vcpu, vmcr); else vgic_v3_get_vmcr(vcpu, vmcr); } /* * kvm_mmio_read_buf() returns a value in a format where it can be converted * to a byte array and be directly observed as the guest wanted it to appear * in memory if it had done the store itself, which is LE for the GIC, as the * guest knows the GIC is always LE. * * We convert this value to the CPUs native format to deal with it as a data * value. */ unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len) { unsigned long data = kvm_mmio_read_buf(val, len); switch (len) { case 1: return data; case 2: return le16_to_cpu(data); case 4: return le32_to_cpu(data); default: return le64_to_cpu(data); } } /* * kvm_mmio_write_buf() expects a value in a format such that if converted to * a byte array it is observed as the guest would see it if it could perform * the load directly. Since the GIC is LE, and the guest knows this, the * guest expects a value in little endian format. * * We convert the data value from the CPUs native format to LE so that the * value is returned in the proper format. */ void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, unsigned long data) { switch (len) { case 1: break; case 2: data = cpu_to_le16(data); break; case 4: data = cpu_to_le32(data); break; default: data = cpu_to_le64(data); } kvm_mmio_write_buf(buf, len, data); } static struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) { return container_of(dev, struct vgic_io_device, dev); } static bool check_region(const struct kvm *kvm, const struct vgic_register_region *region, gpa_t addr, int len) { int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; switch (len) { case sizeof(u8): flags = VGIC_ACCESS_8bit; break; case sizeof(u32): flags = VGIC_ACCESS_32bit; break; case sizeof(u64): flags = VGIC_ACCESS_64bit; break; default: return false; } if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { if (!region->bits_per_irq) return true; /* Do we access a non-allocated IRQ? */ return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; } return false; } const struct vgic_register_region * vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, int len) { const struct vgic_register_region *region; region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, addr - iodev->base_addr); if (!region || !check_region(vcpu->kvm, region, addr, len)) return NULL; return region; } static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) { *val = 0; return 0; } r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_read) *val = region->uaccess_read(r_vcpu, addr, sizeof(u32)); else *val = region->read(r_vcpu, addr, sizeof(u32)); return 0; } static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, const u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) return 0; r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_write) return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); region->write(r_vcpu, addr, sizeof(u32), *val); return 0; } /* * Userland access to VGIC registers. */ int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, bool is_write, int offset, u32 *val) { if (is_write) return vgic_uaccess_write(vcpu, dev, offset, val); else return vgic_uaccess_read(vcpu, dev, offset, val); } static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = 0; region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) { memset(val, 0, len); return 0; } switch (iodev->iodev_type) { case IODEV_CPUIF: data = region->read(vcpu, addr, len); break; case IODEV_DIST: data = region->read(vcpu, addr, len); break; case IODEV_REDIST: data = region->read(iodev->redist_vcpu, addr, len); break; case IODEV_ITS: data = region->its_read(vcpu->kvm, iodev->its, addr, len); break; } vgic_data_host_to_mmio_bus(val, len, data); return 0; } static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = vgic_data_mmio_bus_to_host(val, len); region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) return 0; switch (iodev->iodev_type) { case IODEV_CPUIF: region->write(vcpu, addr, len, data); break; case IODEV_DIST: region->write(vcpu, addr, len, data); break; case IODEV_REDIST: region->write(iodev->redist_vcpu, addr, len, data); break; case IODEV_ITS: region->its_write(vcpu->kvm, iodev->its, addr, len, data); break; } return 0; } const struct kvm_io_device_ops kvm_io_gic_ops = { .read = dispatch_mmio_read, .write = dispatch_mmio_write, }; int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type type) { struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; unsigned int len; switch (type) { case VGIC_V2: len = vgic_v2_init_dist_iodev(io_device); break; case VGIC_V3: len = vgic_v3_init_dist_iodev(io_device); break; default: BUG_ON(1); } io_device->base_addr = dist_base_address; io_device->iodev_type = IODEV_DIST; io_device->redist_vcpu = NULL; return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, len, &io_device->dev); } |
| 244 158 158 158 244 244 244 244 244 11 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 3 3 3 3 3 3 3 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * FIB front-end. * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ /* Changes: * * YOSHIFUJI Hideaki @USAGI * reworked default router selection. * - respect outgoing interface * - select from (probably) reachable routers (i.e. * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. * Ville Nuorvala * Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> #include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> #include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static int ip6_rt_type_to_error(u8 fib6_type); #define CREATE_TRACE_POINTS #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); #undef CREATE_TRACE_POINTS enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict); static size_t rt6_nlmsg_size(struct fib6_info *f6i); static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); #endif struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void rt6_uncached_list_flush_dev(struct net_device *dev) { int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt, *safe; if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; if (rt_idev && rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; } if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; netdev_ref_replace(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); handled = true; } if (handled) list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) return &ipv6_hdr(skb)->daddr; return daddr; } struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr) { struct neighbour *n; daddr = choose_neigh_daddr(gw, skb, daddr); n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; n = neigh_create(&nd_tbl, daddr, dev); return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst->dev; daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) return; if (ipv6_addr_is_multicast((const struct in6_addr *)daddr)) return; __ipv6_confirm_neigh(dev, daddr); } static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .default_advmss = ip6_default_advmss, .neigh_lookup = ip6_dst_neigh_lookup, .check = ip6_dst_check, .destroy = ip6_dst_destroy, .cow_metrics = dst_cow_metrics_generic, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; static const struct fib6_info fib6_null_entry_template = { .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), .fib6_protocol = RTPROT_KERNEL, .fib6_metric = ~(u32)0, .fib6_ref = REFCOUNT_INIT(1), .fib6_type = RTN_UNREACHABLE, .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, }; static const struct rt6_info ip6_null_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #endif static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); } /* allocate dst with ip6_dst_ops */ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); } return rt; } EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; struct fib6_info *from; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); if (blackhole_idev) { rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) return time_after(jiffies, rt->dst.expires); else return false; } static bool rt6_check_expired(const struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; } else if (from) { return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; } void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { struct fib6_info *match = res->f6i; struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; if (match->nh && have_oif_match && res->nh) return; if (skb) IP6CB(skb)->flags |= IP6SKB_MULTIPATH; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash && (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (unlikely(match->nh)) { nexthop_path_fib6_result(res, fl6->mp_hash); return; } if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; list_for_each_entry_rcu(sibling, &match->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (fl6->mp_hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; match = sibling; break; } out: res->f6i = match; res->nh = match->fib6_nh; } /* * Route lookup. rcu_read_lock() should be held. */ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh, const struct in6_addr *saddr, int oif, int flags) { const struct net_device *dev; if (nh->fib_nh_flags & RTNH_F_DEAD) return false; dev = nh->fib_nh_dev; if (oif) { if (dev->ifindex == oif) return true; } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) return true; } return false; } struct fib6_nh_dm_arg { struct net *net; const struct in6_addr *saddr; int oif; int flags; struct fib6_nh *nh; }; static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_dm_arg *arg = _arg; arg->nh = nh; return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif, arg->flags); } /* returns fib6_nh from nexthop or NULL */ static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_nh_dm_arg arg = { .net = net, .saddr = saddr, .oif = oif, .flags = flags, }; if (nexthop_is_blackhole(nh)) return NULL; if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg)) return arg.nh; return NULL; } static void rt6_device_match(struct net *net, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_info *f6i = res->f6i; struct fib6_info *spf6i; struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { bool matched = false; if (unlikely(spf6i->nh)) { nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr, oif, flags); if (nh) matched = true; } else { nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) matched = true; } if (matched) { res->f6i = spf6i; goto out; } } if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; goto out; } if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; return; out_blackhole: res->fib6_flags |= RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF struct __rt6_probe_work { struct work_struct work; struct in6_addr target; struct net_device *dev; netdevice_tracker dev_tracker; }; static void rt6_probe_deferred(struct work_struct *w) { struct in6_addr mcaddr; struct __rt6_probe_work *work = container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); netdev_put(work->dev, &work->dev_tracker); kfree(work); } static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it * is really so; aka Router Reachability Probing. * * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); if (!idev) goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } if (!work || cmpxchg(&fib6_nh->last_probe, last_probe, jiffies) != last_probe) { kfree(work); } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } out: rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) { } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) { enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { u8 nud_state = READ_ONCE(neigh->nud_state); if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock(); return ret; } static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict) { int m = 0; if (!oif || nh->fib_nh_dev->ifindex == oif) m = 2; if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2; #endif if ((strict & RT6_LOOKUP_F_REACHABLE) && !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) { int n = rt6_check_neigh(nh); if (n < 0) return n; } return m; } static bool find_match(struct fib6_nh *nh, u32 fib6_flags, int oif, int strict, int *mpri, bool *do_rr) { bool match_do_rr = false; bool rc = false; int m; if (nh->fib_nh_flags & RTNH_F_DEAD) goto out; if (ip6_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; m = rt6_score_route(nh, fib6_flags, oif, strict); if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(nh); /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; rc = true; } out: return rc; } struct fib6_nh_frl_arg { u32 flags; int oif; int strict; int *mpri; bool *do_rr; struct fib6_nh *nh; }; static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_frl_arg *arg = _arg; arg->nh = nh; return find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri, arg->do_rr); } static void __find_rr_leaf(struct fib6_info *f6i_start, struct fib6_info *nomatch, u32 metric, struct fib6_result *res, struct fib6_info **cont, int oif, int strict, bool *do_rr, int *mpri) { struct fib6_info *f6i; for (f6i = f6i_start; f6i && f6i != nomatch; f6i = rcu_dereference(f6i->fib6_next)) { bool matched = false; struct fib6_nh *nh; if (cont && f6i->fib6_metric != metric) { *cont = f6i; return; } if (fib6_check_expired(f6i)) continue; if (unlikely(f6i->nh)) { struct fib6_nh_frl_arg arg = { .flags = f6i->fib6_flags, .oif = oif, .strict = strict, .mpri = mpri, .do_rr = do_rr }; if (nexthop_is_blackhole(f6i->nh)) { res->fib6_flags = RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->f6i = f6i; res->nh = nexthop_fib6_nh(f6i->nh); return; } if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match, &arg)) { matched = true; nh = arg.nh; } } else { nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) matched = true; } if (matched) { res->f6i = f6i; res->nh = nh; res->fib6_flags = f6i->fib6_flags; res->fib6_type = f6i->fib6_type; } } } static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf, struct fib6_info *rr_head, int oif, int strict, bool *do_rr, struct fib6_result *res) { u32 metric = rr_head->fib6_metric; struct fib6_info *cont = NULL; int mpri = -1; __find_rr_leaf(rr_head, NULL, metric, res, &cont, oif, strict, do_rr, &mpri); __find_rr_leaf(leaf, rr_head, metric, res, &cont, oif, strict, do_rr, &mpri); if (res->f6i || !cont) return; __find_rr_leaf(cont, NULL, metric, res, NULL, oif, strict, do_rr, &mpri); } static void rt6_select(struct net *net, struct fib6_node *fn, int oif, struct fib6_result *res, int strict) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct fib6_info *rt0; bool do_rr = false; int key_plen; /* make sure this function or its helpers sets f6i */ res->f6i = NULL; if (!leaf || leaf == net->ipv6.fib6_null_entry) goto out; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES if (rt0->fib6_src.plen) key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) goto out; find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res); if (do_rr) { struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } } static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res) { return (res->f6i->fib6_flags & RTF_NONEXTHOP) || res->nh->fib_nh_gw_family; } #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; } /* Sanity check for prefix_len and length */ if (rinfo->length > 3) { return -EINVAL; } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { if (rinfo->length < 2) { return -EINVAL; } } else if (rinfo->prefix_len > 0) { if (rinfo->length < 1) { return -EINVAL; } } pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; else { /* this function is safe */ ipv6_addr_prefix(&prefix_buf, (struct in6_addr *)rinfo->prefix, rinfo->prefix_len); prefix = &prefix_buf; } if (rinfo->prefix_len == 0) rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { ip6_del_rt(net, rt, false); rt = NULL; } if (!rt && lifetime) rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) rt->fib6_flags = RTF_ROUTEINFO | (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); fib6_remove_gc_list(rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } return 0; } #endif /* * Misc support functions */ /* called with rcu_lock held */ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { /* for copies of local routes, dst->dev needs to be the * device if it is a master device, the master device if * device is enslaved, and the loopback as the default */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) dev = l3mdev_master_dev_rcu(dev); else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which * case we want dev returned to be dev */ } return dev; } static const int fib6_prop[RTN_MAX + 1] = { [RTN_UNSPEC] = 0, [RTN_UNICAST] = 0, [RTN_LOCAL] = 0, [RTN_BROADCAST] = 0, [RTN_ANYCAST] = 0, [RTN_MULTICAST] = 0, [RTN_BLACKHOLE] = -EINVAL, [RTN_UNREACHABLE] = -EHOSTUNREACH, [RTN_PROHIBIT] = -EACCES, [RTN_THROW] = -EAGAIN, [RTN_NAT] = -EINVAL, [RTN_XRESOLVE] = -EINVAL, }; static int ip6_rt_type_to_error(u8 fib6_type) { return fib6_prop[fib6_type]; } static unsigned short fib6_info_dst_flags(struct fib6_info *rt) { unsigned short flags = 0; if (rt->dst_nocount) flags |= DST_NOCOUNT; if (rt->dst_nopolicy) flags |= DST_NOPOLICY; return flags; } static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type) { rt->dst.error = ip6_rt_type_to_error(fib6_type); switch (fib6_type) { case RTN_BLACKHOLE: rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.output = ip6_pkt_prohibit_out; rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: case RTN_UNREACHABLE: default: rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; } } static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; if (res->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, res->fib6_type); return; } rt->dst.error = 0; rt->dst.output = ip6_output; if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; } else { rt->dst.input = ip6_forward; } if (res->nh->fib_nh_lws) { rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws); lwtunnel_set_redirect(&rt->dst); } rt->dst.lastuse = jiffies; } /* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to f6i in result */ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; const struct net_device *dev = nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; ip6_rt_init_dst(rt, res); rt->rt6i_dst = f6i->fib6_dst; rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; rt->rt6i_flags = res->fib6_flags; if (nh->fib_nh_gw_family) { rt->rt6i_gateway = nh->fib_nh_gw6; rt->rt6i_flags |= RTF_GATEWAY; } rt6_set_from(rt, f6i); #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = f6i->fib6_src; #endif } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) return fn; } } static bool ip6_hold_safe(struct net *net, struct rt6_info **prt) { struct rt6_info *rt = *prt; if (dst_hold_safe(&rt->dst)) return true; if (net) { rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); } else { rt = NULL; } *prt = rt; return false; } /* called with rcu_lock held */ static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; unsigned short flags; struct rt6_info *nrt; if (!fib6_info_hold_safe(f6i)) goto fallback; flags = fib6_info_dst_flags(f6i); nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (!nrt) { fib6_info_release(f6i); goto fallback; } ip6_rt_copy_init(nrt, res); return nrt; fallback: nrt = dev_net(dev)->ipv6.ip6_null_entry; dst_hold(&nrt->dst); return nrt; } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct fib6_node *fn; struct rt6_info *rt; rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: res.f6i = rcu_dereference(fn->leaf); if (!res.f6i) res.f6i = net->ipv6.fib6_null_entry; else rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif, flags); if (res.f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; } else if (res.fib6_flags & RTF_REJECT) { goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, fl6->flowi6_oif != 0, skb, flags); /* Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { do_create: rt = ip6_create_rt_rcu(&res); } out: trace_fib6_table_lookup(net, &res, table, fl6); rcu_read_unlock(); return rt; } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return dst_rt6_info(dst); dst_release(dst); return NULL; } EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. * It takes new route entry, the addition fails by any reason the * route is released. * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } int ip6_ins_rt(struct net *net, struct fib6_info *rt) { struct nl_info info = { .nl_net = net, }; return __ip6_ins_rt(rt, &info, NULL); } static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_info *f6i = res->f6i; struct net_device *dev; struct rt6_info *rt; /* * Clone the route. */ if (!fib6_info_hold_safe(f6i)) return NULL; dev = ip6_rt_get_dev_rcu(res); rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(rt, res); rt->rt6i_flags |= RTF_CACHE; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(res)) { if (f6i->fib6_dst.plen != 128 && ipv6_addr_equal(&f6i->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif } return rt; } static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; unsigned short flags = fib6_info_dst_flags(f6i); struct net_device *dev; struct rt6_info *pcpu_rt; if (!fib6_info_hold_safe(f6i)) return NULL; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(res); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT); rcu_read_unlock(); if (!pcpu_rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; if (f6i->nh) pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); return pcpu_rt; } static bool rt6_is_valid(const struct rt6_info *rt6) { return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); } /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { struct rt6_info *pcpu_rt; pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); dst_release(&prev->dst); } pcpu_rt = NULL; } return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct net *net, const struct fib6_result *res) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(res); if (!pcpu_rt) return NULL; p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); if (res->f6i->fib6_destroying) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } return pcpu_rt; } /* exception hash table implementation */ static DEFINE_SPINLOCK(rt6_exception_lock); /* Remove rt6_ex from hash table and free the memory * Caller must hold rt6_exception_lock */ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); net->ipv6.rt6_stats->fib_rt_cache--; /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; } /* Remove oldest rt6_ex in bucket and free the memory * Caller must hold rt6_exception_lock */ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) { struct rt6_exception *rt6_ex, *oldest = NULL; if (!bucket) return; hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) oldest = rt6_ex; } rt6_remove_exception(bucket, oldest); } static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; } __aligned(SIPHASH_ALIGNMENT) combined = { .dst = *dst, }; u64 val; net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) combined.src = *src; #endif val = siphash(&combined, sizeof(combined), &rt6_exception_key); return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rt6_exception_lock */ static struct rt6_exception * __rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rcu_read_lock() */ static struct rt6_exception * __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; WARN_ON_ONCE(!rcu_read_lock_held()); if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } static unsigned int fib6_mtu(const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; unsigned int mtu; if (res->f6i->fib6_pmtu) { mtu = res->f6i->fib6_pmtu; } else { struct net_device *dev = nh->fib_nh_dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } #define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL /* used when the flushed bit is not relevant, only access to the bucket * (ie., all bucket users except rt6_insert_exception); * * called under rcu lock; sometimes called with rt6_exception_lock held */ static struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; if (lock) bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); else bucket = rcu_dereference(nh->rt6i_exception_bucket); /* remove bucket flushed bit if set */ if (bucket) { unsigned long p = (unsigned long)bucket; p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; } return bucket; } static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) { unsigned long p = (unsigned long)bucket; return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); } /* called with rt6_exception_lock held */ static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; unsigned long p; bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); p = (unsigned long)bucket; p |= FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), GFP_ATOMIC); if (!bucket) { err = -ENOMEM; goto out; } rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } else if (fib6_nh_excptn_bucket_flushed(bucket)) { err = -EINVAL; goto out; } #ifdef CONFIG_IPV6_SUBTREES /* fib6_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * Otherwise, the exception table is indexed by * a hash of only fib6_dst. */ if (f6i->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* rt6_mtu_change() might lower mtu on f6i. * Only insert this exception route if its mtu * is less than f6i's mtu value. */ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) { err = -EINVAL; goto out; } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_remove_exception(bucket, rt6_ex); rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); if (!rt6_ex) { err = -ENOMEM; goto out; } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; /* Randomize max depth to avoid some side channels attacks. */ max_depth = FIB6_MAX_DEPTH + get_random_u32_below(FIB6_MAX_DEPTH); while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: spin_unlock_bh(&rt6_exception_lock); /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; /* Prevent rt6_insert_exception() to recreate the bucket list */ if (!from) fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { if (!from || rcu_access_pointer(rt6_ex->rt6i->from) == from) rt6_remove_exception(bucket, rt6_ex); } WARN_ON_ONCE(!from && bucket->depth); bucket++; } out: spin_unlock_bh(&rt6_exception_lock); } static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_info *f6i = arg; fib6_nh_flush_exceptions(nh, f6i); return 0; } void rt6_flush_exceptions(struct fib6_info *f6i) { if (f6i->nh) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i); else fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); } /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct rt6_info *ret = NULL; #ifdef CONFIG_IPV6_SUBTREES /* fib6i_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * However, the src addr used to create the hash * might not be exactly the passed in saddr which * is a /128 addr from the flow. * So we need to use f6i->fib6_src to redo lookup * if the passed in saddr does not find anything. * (See the logic in ip6_rt_cache_alloc() on how * rt->rt6i_src is updated.) */ if (res->f6i->fib6_src.plen) src_key = saddr; find_ex: #endif bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) ret = rt6_ex->rt6i; #ifdef CONFIG_IPV6_SUBTREES /* Use fib6_src as src_key and redo lookup */ if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) { src_key = &res->f6i->fib6_src.addr; goto find_ex; } #endif return ret; } /* Remove the passed in cached rt from the hash table that contains it */ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int err; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) { rt6_remove_exception(bucket, rt6_ex); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&rt6_exception_lock); return err; } struct fib6_nh_excptn_arg { struct rt6_info *rt; int plen; }; static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_excptn_arg *arg = _arg; int err; err = fib6_nh_remove_exception(nh, arg->plen, arg->rt); if (err == 0) return 1; return 0; } static int rt6_remove_exception_rt(struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (from->nh) { struct fib6_nh_excptn_arg arg = { .rt = rt, .plen = from->fib6_src.plen }; int rc; /* rc = 1 means an entry was found */ rc = nexthop_for_each_fib6_nh(from->nh, rt6_nh_remove_exception_rt, &arg); return rc ? 0 : -ENOENT; } return fib6_nh_remove_exception(from->fib6_nh, from->fib6_src.plen, rt); } /* Find rt6_ex which contains the passed in rt cache and * refresh its stamp */ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; } struct fib6_nh_match_arg { const struct net_device *dev; const struct in6_addr *gw; struct fib6_nh *match; }; /* determine if fib6_nh has given device and gateway */ static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_match_arg *arg = _arg; if (arg->dev != nh->fib_nh_dev || (arg->gw && !nh->fib_nh_gw_family) || (!arg->gw && nh->fib_nh_gw_family) || (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6))) return 0; arg->match = nh; /* found a match, break the loop */ return 1; } static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct fib6_info *from; struct fib6_nh *fib6_nh; rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) goto unlock; if (from->nh) { struct fib6_nh_match_arg arg = { .dev = rt->dst.dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; } fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { /* If the new MTU is lower than the route PMTU, this new MTU will be the * lowest MTU in the path: always allow updating the route PMTU to * reflect PMTU decreases. * * If the new MTU is higher, and the route PMTU is equal to the local * MTU, this means the old MTU is the lowest in the path, so allow * updating it: if other nodes now have lower MTUs, PMTU discovery will * handle this. */ if (dst_mtu(&rt->dst) >= mtu) return true; if (dst_mtu(&rt->dst) == idev->cnf.mtu6) return true; return false; } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected * route), the metrics of its rt->from have already * been updated. */ if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } } #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY && ipv6_addr_equal(gateway, &entry->rt6i_gateway)) { rt6_remove_exception(bucket, rt6_ex); } } bucket++; } } spin_unlock_bh(&rt6_exception_lock); } static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_info *rt = rt6_ex->rt6i; /* we are pruning and obsoleting aged-out and non gateway exceptions * even if others have still references to them, so that on next * dst_check() such references can be dropped. * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, rt->dst.expires)) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { pr_debug("purging route %p via non-router but gateway\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } gc_args->more++; } static void fib6_nh_age_exceptions(const struct fib6_nh *nh, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { rt6_age_examine_exception(bucket, rt6_ex, gc_args, now); } bucket++; } } spin_unlock(&rt6_exception_lock); rcu_read_unlock_bh(); } struct fib6_nh_age_excptn_arg { struct fib6_gc_args *gc_args; unsigned long now; }; static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg) { struct fib6_nh_age_excptn_arg *arg = _arg; fib6_nh_age_exceptions(nh, arg->gc_args, arg->now); return 0; } void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now) { if (f6i->nh) { struct fib6_nh_age_excptn_arg arg = { .gc_args = gc_args, .now = now }; nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions, &arg); } else { fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); } } /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) { struct fib6_node *fn, *saved_fn; fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; redo_rt6_select: rt6_select(net, fn, oif, res, strict); if (res->f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; else if (strict & RT6_LOOKUP_F_REACHABLE) { /* also consider unreachable route */ strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; } } trace_fib6_table_lookup(net, res, table, fl6); return 0; } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct rt6_info *rt = NULL; int strict = 0; WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) && !rcu_read_lock_held()); strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); fib6_table_lookup(net, table, oif, fl6, &res, strict); if (res.f6i == net->ipv6.fib6_null_entry) goto out; fib6_select_path(net, &res, fl6, oif, false, skb, strict); /*Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL); if (rt) { /* 1 refcnt is taken during ip6_rt_cache_alloc(). * As rt6_uncached_list_add() does not consume refcnt, * this refcnt is always returned to the caller even * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); rcu_read_unlock(); return rt; } } else { /* Get a percpu copy */ local_bh_disable(); rt = rt6_get_pcpu_route(&res); if (!rt) rt = rt6_make_pcpu_route(net, &res); local_bh_enable(); } out: if (!rt) rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) ip6_hold_safe(net, &rt); rcu_read_unlock(); return rt; } EXPORT_SYMBOL_GPL(ip6_pol_route); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *keys, struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; icmph = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmpv6_is_err(icmph->icmp6_type)) goto out; inner_iph = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(*icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; _flkeys = NULL; out: if (_flkeys) { keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; keys->tags.flow_label = _flkeys->tags.flow_label; keys->basic.ip_proto = _flkeys->basic.ip_proto; } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } static u32 rt6_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 rt6_multipath_custom_hash_fl6(const struct net *net, const struct flowi6 *fl6) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = fl6->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = fl6->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl6->flowi6_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl6->fl6_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.ports.src = fl6->fl6_sport; hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { struct flow_keys keys; if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, 0); flkeys = &keys; } /* Inner can be v4 or v6 */ if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; } else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.tags.flow_label = flkeys->tags.flow_label; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = rt6_multipath_custom_hash_skb(net, skb); else mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } return mhash >> 1; } /* Called with rcu held */ void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) flkeys = &_flkeys; if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } static struct dst_entry *ip6_route_output_flags_noref(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { bool any_src; if (ipv6_addr_type(&fl6->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; /* This function does not take refcnt on the dst */ dst = l3mdev_link_scope_lookup(net, fl6); if (dst) return dst; } fl6->flowi6_iif = LOOPBACK_IFINDEX; flags |= RT6_LOOKUP_F_DST_NOREF; any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(READ_ONCE(inet6_sk(sk)->srcprefs)); return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { struct dst_entry *dst; struct rt6_info *rt6; rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } rcu_read_unlock(); return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif } dst_release(dst_orig); return new ? new : ERR_PTR(-ENOMEM); } /* * Destination cache support functions */ static bool fib6_check(struct fib6_info *f6i, u32 cookie) { u32 rt_cookie = 0; if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) return false; if (fib6_check_expired(f6i)) return false; return true; } static struct dst_entry *rt6_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { u32 rt_cookie = 0; if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) return NULL; return &rt->dst; } static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { if (!__rt6_check_expired(rt) && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; else return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; struct rt6_info *rt; rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); rcu_read_unlock(); return dst_ret; } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { /* rt/dst can not be destroyed yet, * because of rcu_read_lock() */ sk_dst_reset(sk); rt6_remove_exception_rt(rt); } rcu_read_unlock(); return; } sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; from = rcu_dereference(rt->from); if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); } } static void rt6_update_expires(struct rt6_info *rt0, int timeout) { if (!(rt0->rt6i_flags & RTF_EXPIRES)) { struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) rt0->dst.expires = from->expires; rcu_read_unlock(); } dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. * [see also comment in rt6_mtu_change_route()] */ if (iph) { daddr = &iph->daddr; saddr = &iph->saddr; } else if (sk) { daddr = &sk->sk_v6_daddr; saddr = &inet6_sk(sk)->saddr; } else { daddr = NULL; saddr = NULL; } if (confirm_neigh) dst_confirm_neigh(dst, daddr); if (mtu < IPV6_MIN_MTU) return; if (mtu >= dst_mtu(dst)) return; if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); /* update rt6_ex->stamp for cache */ if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct fib6_result res = {}; struct rt6_info *nrt6; rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); if (!res.f6i) goto out_unlock; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt6->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ if (!arg.match) goto out_unlock; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } out_unlock: rcu_read_unlock(); } } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = oif, .flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { int oif = sk->sk_bound_dev_if; struct dst_entry *dst; if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; bh_lock_sock(sk); if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ip6_datagram_dst_update(sk, false); bh_unlock_sock(sk); } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif ip6_dst_store(sk, dst, ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ? &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6->saddr, &np->saddr) ? &np->saddr : #endif NULL); } static bool ip6_redirect_nh_match(const struct fib6_result *res, struct flowi6 *fl6, const struct in6_addr *gw, struct rt6_info **ret) { const struct fib6_nh *nh = res->nh; if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family || fl6->flowi6_oif != nh->fib_nh_dev->ifindex) return false; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) { struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) { *ret = rt_cache; return true; } return false; } return true; } struct fib6_nh_rd_arg { struct fib6_result *res; struct flowi6 *fl6; const struct in6_addr *gw; struct rt6_info **ret; }; static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_rd_arg *arg = _arg; arg->res->nh = nh; return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret); } /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; struct in6_addr gateway; }; INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *ret = NULL; struct fib6_result res = {}; struct fib6_nh_rd_arg arg = { .res = &res, .fl6 = fl6, .gw = &rdfl->gateway, .ret = &ret }; struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. * Due to the way the routes are chosen, this notion * is a bit fuzzy and one might need to check all possible * routes. */ rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; if (fib6_check_expired(rt)) continue; if (rt->fib6_flags & RTF_REJECT) break; if (unlikely(rt->nh)) { if (nexthop_is_blackhole(rt->nh)) continue; /* on match, res->nh is filled in and potentially ret */ if (nexthop_for_each_fib6_nh(rt->nh, fib6_nh_redirect_match, &arg)) goto out; } else { res.nh = rt->fib6_nh; if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret)) goto out; } } if (!rt) rt = net->ipv6.fib6_null_entry; else if (rt->fib6_flags & RTF_REJECT) { ret = net->ipv6.ip6_null_entry; goto out; } if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } res.f6i = rt; res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); } else { res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; ret = ip6_create_rt_rcu(&res); } rcu_read_unlock(); trace_fib6_table_lookup(net, &res, table, fl6); return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; rdfl.fl6 = *fl6; rdfl.gateway = *gateway; return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .flowi6_mark = mark, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .daddr = msg->dest, .saddr = iph->daddr, .flowi6_uid = sock_net_uid(net, NULL), }; dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; unsigned int mtu = dst_mtu(dst); struct net *net = dev_net(dev); mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) mtu = net->ipv6.sysctl.ip6_rt_min_advmss; /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) mtu = IPV6_MAXPLEN; return mtu; } INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device * * based on ip6_dst_mtu_forward and exception logic of * rt6_find_cached_rt; called with rcu_read_lock */ u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct fib6_nh *nh = res->nh; struct fib6_info *f6i = res->f6i; struct inet6_dev *idev; struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { mtu = f6i->fib6_pmtu; if (mtu) goto out; } rt = rt6_find_cached_rt(res, daddr, saddr); if (unlikely(rt)) { mtu = dst_metric_raw(&rt->dst, RTAX_MTU); } else { struct net_device *dev = nh->fib_nh_dev; mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); if (idev) mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); out: return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); if (unlikely(!idev)) return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(net, dev, 0); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); goto out; } rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: return dst; } static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; unsigned int val; int entries; if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, u32 tbid, int flags, struct fib6_result *res) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, .saddr = cfg->fc_prefsrc, }; struct fib6_table *table; int err; table = fib6_get_table(net, tbid); if (!table) return -EINVAL; if (!ipv6_addr_any(&cfg->fc_prefsrc)) flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) fib6_select_path(net, res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); return err; } static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; struct fib6_result res = {}; int err; err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res); if (!err && !(res.fib6_flags & RTF_REJECT) && /* ignore match if it is the default route */ !ipv6_addr_any(&res.f6i->fib6_dst.addr) && (res.fib6_type != RTN_UNICAST || dev != res.nh->fib_nh_dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } return err; } static int ip6_route_check_nh(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev) { const struct in6_addr *gw_addr = &cfg->fc_gateway; struct net_device *dev = _dev ? *_dev : NULL; int flags = RT6_LOOKUP_F_IFACE; struct fib6_result res = {}; int err = -EHOSTUNREACH; if (cfg->fc_table) { err = ip6_nh_lookup_table(net, cfg, gw_addr, cfg->fc_table, flags, &res); /* gw_addr can not require a gateway or resolve to a reject * route. If a device is given, it must match the result. */ if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family || (dev && dev != res.nh->fib_nh_dev)) err = -EHOSTUNREACH; } if (err < 0) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, }; err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags); if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family) err = -EHOSTUNREACH; if (err) return err; fib6_select_path(net, &res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); } err = 0; if (dev) { if (dev != res.nh->fib_nh_dev) err = -EHOSTUNREACH; } else { *_dev = dev = res.nh->fib_nh_dev; netdev_hold(dev, dev_tracker, GFP_ATOMIC); *idev = in6_dev_get(dev); } return err; } static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev, struct netlink_ext_ack *extack) { const struct in6_addr *gw_addr = &cfg->fc_gateway; int gwa_type = ipv6_addr_type(gw_addr); bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; const struct net_device *dev = *_dev; bool need_addr_check = !dev; int err = -EINVAL; /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() * will return already-added prefix route via interface that * prefix route was assigned to, which might be non-loopback. */ if (dev && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { /* IPv6 strictly inhibits using not link-local * addresses as nexthop address. * Otherwise, router will not able to send redirects. * It is very good, but in some (rare!) circumstances * (SIT, PtP, NBMA NOARP links) it is handy to allow * some exceptions. --ANK * We allow IPv4-mapped nexthops to support RFC4798-type * addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; } rcu_read_lock(); if (cfg->fc_flags & RTNH_F_ONLINK) err = ip6_route_check_nh_onlink(net, cfg, dev, extack); else err = ip6_route_check_nh(net, cfg, _dev, dev_tracker, idev); rcu_read_unlock(); if (err) goto out; } /* reload in case device was changed */ dev = *_dev; err = -EINVAL; if (!dev) { NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; } else if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Egress device can not be loopback device for this route"); goto out; } /* if we did not check gw_addr above, do so now that the * egress device has been resolved. */ if (need_addr_check && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } err = 0; out: return err; } static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) { if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif if (cfg->fc_is_fdb) { fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; return 0; } err = -ENODEV; if (cfg->fc_ifindex) { dev = netdev_get_by_index(net, cfg->fc_ifindex, dev_tracker, gfp_flags); if (!dev) goto out; idev = in6_dev_get(dev); if (!idev) goto out; } if (cfg->fc_flags & RTNH_F_ONLINK) { if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); goto out; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } fib6_nh->fib_nh_flags |= RTNH_F_ONLINK; } fib6_nh->fib_nh_weight = 1; /* We cannot add true routes via loopback here, * they would result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { netdev_put(dev, dev_tracker); in6_dev_put(idev); } dev = net->loopback_dev; netdev_hold(dev, dev_tracker, gfp_flags); idev = in6_dev_get(dev); if (!idev) { err = -ENODEV; goto out; } } goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { err = ip6_validate_gw(net, cfg, &dev, dev_tracker, &idev, extack); if (err) goto out; fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; } err = -ENODEV; if (!dev) goto out; if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; } if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; pcpu_alloc: fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); if (!fib6_nh->rt6i_pcpu) { err = -ENOMEM; goto out; } fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; out: if (idev) in6_dev_put(idev); if (err) { lwtstate_put(fib6_nh->fib_nh_lws); fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } return err; } void fib6_nh_release(struct fib6_nh *fib6_nh) { struct rt6_exception_bucket *bucket; rcu_read_lock(); fib6_nh_flush_exceptions(fib6_nh, NULL); bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); if (bucket) { rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); kfree(bucket); } rcu_read_unlock(); fib6_nh_release_dsts(fib6_nh); free_percpu(fib6_nh->rt6i_pcpu); fib_nh_common_release(&fib6_nh->nh_common); } void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { int cpu; if (!fib6_nh->rt6i_pcpu) return; for_each_possible_cpu(cpu) { struct rt6_info *pcpu_rt, **ppcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = xchg(ppcpu_rt, NULL); if (pcpu_rt) { dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); } } } static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_info *rt = NULL; struct nexthop *nh = NULL; struct fib6_table *table; struct fib6_nh *fib6_nh; int err = -EINVAL; int addr_type; /* RTF_PCPU is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_PCPU) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto out; } /* RTF_CACHE is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_CACHE) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); goto out; } if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); goto out; } if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; } if (cfg->fc_src_len > 128) { NL_SET_ERR_MSG(extack, "Invalid source address length"); goto out; } #ifndef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Specifying source address requires IPV6_SUBTREES to be enabled"); goto out; } #endif if (cfg->fc_nh_id) { nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto out; } err = fib6_check_nexthop(nh, cfg, extack); if (err) goto out; } err = -ENOBUFS; if (cfg->fc_nlinfo.nlh && !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { table = fib6_new_table(net, cfg->fc_table); } if (!table) goto out; err = -ENOMEM; rt = fib6_info_alloc(gfp_flags, !nh); if (!rt) goto out; rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; rt->fib6_protocol = cfg->fc_protocol; rt->fib6_table = table; rt->fib6_metric = cfg->fc_metric; rt->fib6_type = cfg->fc_type ? : RTN_UNICAST; rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY; ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->fib6_dst.plen = cfg->fc_dst_len; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); if (err) goto out; fib6_nh = rt->fib6_nh; /* We cannot add true routes via loopback here, they would * result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, addr_type)) rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out; } rt->fib6_prefsrc.addr = cfg->fc_prefsrc; rt->fib6_prefsrc.plen = 128; } else rt->fib6_prefsrc.plen = 0; return rt; out: fib6_info_release(rt); return ERR_PTR(err); out_free: ip_fib_metrics_put(rt->fib6_metrics); kfree(rt); return ERR_PTR(err); } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_info *rt; int err; rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); fib6_info_release(rt); return err; } static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_table *table; int err; if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: fib6_info_release(rt); return err; } int ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { struct nl_info info = { .nl_net = net, .skip_notify = skip_notify }; return __ip6_del_rt(rt, &info); } static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) goto out_put; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); skb = NULL; } else info->skip_notify = 1; } /* 'rt' points to the first sibling route. If it is not the * leaf, then we do not need to send a notification. Otherwise, * we need to check if the last sibling has a next route or not * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; last_sibling = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); replace_rt = rcu_dereference_protected( last_sibling->fib6_next, lockdep_is_held(&table->tb6_lock)); if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); else call_fib6_multipath_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, rt->fib6_nsiblings, NULL); } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; } } err = fib6_del(rt, info); out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; } static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) goto out; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; rc = rt6_remove_exception_rt(rt); out: return rc; } static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, struct fib6_nh *nh) { struct fib6_result res = { .f6i = rt, .nh = nh, }; struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); if (rt_cache) return __ip6_del_cached_rt(rt_cache, cfg); return 0; } struct fib6_nh_del_cached_rt_arg { struct fib6_config *cfg; struct fib6_info *f6i; }; static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_del_cached_rt_arg *arg = _arg; int rc; rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh); return rc != -ESRCH ? rc : 0; } static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i) { struct fib6_nh_del_cached_rt_arg arg = { .cfg = cfg, .f6i = f6i }; return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg); } static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); if (!table) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; } rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, !(cfg->fc_flags & RTF_CACHE)); if (fn) { for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; if (rt->nh && cfg->fc_nh_id && rt->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_flags & RTF_CACHE) { int rc = 0; if (rt->nh) { rc = ip6_del_cached_rt_nh(cfg, rt); } else if (cfg->fc_nh_id) { continue; } else { nh = rt->fib6_nh; rc = ip6_del_cached_rt(cfg, rt, nh); } if (rc != -ESRCH) { rcu_read_unlock(); return rc; } continue; } if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; if (rt->nh) { if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); return __ip6_del_rt(rt, &cfg->fc_nlinfo); } if (cfg->fc_nh_id) continue; nh = rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6)) continue; if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) return __ip6_del_rt(rt, &cfg->fc_nlinfo); return __ip6_del_rt_siblings(rt, cfg); } } rcu_read_unlock(); return err; } static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; struct fib6_result res = {}; struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } msg = (struct rd_msg *)icmp6_hdr(skb); if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; } in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; if (READ_ONCE(in6_dev->cnf.forwarding) || !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current * first-hop router for the specified ICMP Destination Address. */ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } lladdr = NULL; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); return; } } rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; } /* Redirect received -> path was valid. * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ dst_confirm_neigh(&rt->dst, &ipv6_hdr(skb)->saddr); neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; /* * We have finally decided to accept it. */ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); rcu_read_lock(); res.f6i = rcu_dereference(rt->from); if (!res.f6i) goto out; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev. Should be impossible */ if (!arg.match) goto out; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, &res)) { dst_release_immediate(&nrt->dst); goto out; } netevent.old = &rt->dst; netevent.new = &nrt->dst; netevent.daddr = &msg->dest; netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: rcu_read_unlock(); neigh_release(neigh); } #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* these routes do not use nexthops */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || !rt->fib6_nh->fib_nh_gw_family) continue; if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { struct fib6_config cfg = { .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; struct fib6_info *rt; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) continue; nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) break; } if (rt && !fib6_info_hold_safe(rt)) rt = NULL; rcu_read_unlock(); return rt; } struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); if (table) table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } return rt6_get_dflt_router(net, gwaddr, dev); } static void __rt6_purge_dflt_routers(struct net *net, struct fib6_table *table) { struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct net_device *dev = fib6_info_nh_dev(rt); struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!idev || idev->cnf.accept_ra != 2) && fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt, false); goto restart; } } rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } void rt6_purge_dflt_routers(struct net *net) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) __rt6_purge_dflt_routers(net, table); } } rcu_read_unlock(); } static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) { *cfg = (struct fib6_config){ .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, .fc_flags = rtmsg->rtmsg_flags, .fc_type = rtmsg->rtmsg_type, .fc_nlinfo.nl_net = net, .fc_dst = rtmsg->rtmsg_dst, .fc_src = rtmsg->rtmsg_src, .fc_gateway = rtmsg->rtmsg_gateway, }; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) { struct fib6_config cfg; int err; if (cmd != SIOCADDRT && cmd != SIOCDELRT) return -EINVAL; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtmsg_to_fib6_config(net, rtmsg, &cfg); rtnl_lock(); switch (cmd) { case SIOCADDRT: /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); break; } rtnl_unlock(); return err; } /* * Drop the packet on the floor */ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { SKB_DR_SET(reason, IP_INADDRERRORS); IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } SKB_DR_SET(reason, IP_INNOROUTES); fallthrough; case IPSTATS_MIB_OUTNOROUTES: SKB_DR_OR(reason, IP_OUTNOROUTES); IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } /* Start over by dropping the dst for l3mdev case */ if (netif_is_l3_master(skb->dev)) skb_dst_drop(skb); icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb_reason(skb, reason); return 0; } static int ip6_pkt_discard(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* * Allocate a dst for local (unicast / anycast) address. */ struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, .fc_ifindex = idev->dev->ifindex, .fc_flags = RTF_UP | RTF_NONEXTHOP, .fc_dst = *addr, .fc_dst_len = 128, .fc_protocol = RTPROT_KERNEL, .fc_nlinfo.nl_net = net, .fc_ignore_dev_down = true, }; struct fib6_info *f6i; if (anycast) { cfg.fc_type = RTN_ANYCAST; cfg.fc_flags |= RTF_ANYCAST; } else { cfg.fc_type = RTN_LOCAL; cfg.fc_flags |= RTF_LOCAL; } f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (!IS_ERR(f6i)) { f6i->dst_nocount = true; if (!anycast && (READ_ONCE(net->ipv6.devconf_all->disable_policy) || READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; } return f6i; } /* remove deleted ip from prefsrc entries */ struct arg_dev_net_ip { struct net *net; struct in6_addr *addr; }; static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; if (!rt->nh && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) && !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; spin_unlock_bh(&rt6_exception_lock); } return 0; } void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); struct arg_dev_net_ip adni = { .net = net, .addr = &ifp->addr, }; fib6_clean_all(net, fib6_remove_prefsrc, &adni); } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) return 0; nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) { fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_netdev_event { const struct net_device *dev; union { unsigned char nh_flags; unsigned long event; }; }; static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } /* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; } static int rt6_multipath_total_weight(const struct fib6_info *rt) { struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) total += iter->fib6_nh->fib_nh_weight; } return total; } static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } void rt6_multipath_rebalance(struct fib6_info *rt) { struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to * make sure upper bounds are assigned from the first sibling * onwards. */ first = rt6_multipath_first_sibling(rt); if (WARN_ON_ONCE(!first)) return; total = rt6_multipath_total_weight(first); rt6_multipath_upper_bound_set(first, total); } static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); if (rt != net->ipv6.fib6_null_entry && !rt->nh && rt->fib6_nh->fib_nh_dev == arg->dev) { rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } return 0; } void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) { struct arg_netdev_event arg = { .dev = dev, { .nh_flags = nh_flags, }, }; if (nh_flags & RTNH_F_DEAD && netif_carrier_ok(dev)) arg.nh_flags |= RTNH_F_LINKDOWN; fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } /* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; } static void rt6_multipath_flush(struct fib6_info *rt) { struct fib6_info *iter; rt->should_flush = 1; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { struct fib6_info *iter; unsigned int dead = 0; if (rt->fib6_nh->fib_nh_dev == down_dev || rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == down_dev || iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; } static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned char nh_flags) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } return 0; } void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, { .event = event, }, }; struct net *net = dev_net(dev); if (net->ipv6.sysctl.skip_notify_on_dev_down) fib6_clean_all_skip_notify(net, fib6_ifdown, &arg); else fib6_clean_all(net, fib6_ifdown, &arg); } void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; struct fib6_info *f6i; }; static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; struct fib6_info *f6i = arg->f6i; /* For administrative MTU increase, there is no way to discover * IPv6 PMTU increase, so PMTU increase should be updated here. * Since RFC 1981 doesn't include administrative MTU increase * update PMTU increase is a MUST. (i.e. jumbo frame) */ if (nh->fib_nh_dev == arg->dev) { struct inet6_dev *idev = __in6_dev_get(arg->dev); u32 mtu = f6i->fib6_pmtu; if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6)) fib6_metric_set(f6i, RTAX_MTU, arg->mtu); spin_lock_bh(&rt6_exception_lock); rt6_exceptions_update_pmtu(idev, nh, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; } static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. We still use this lock to block changes caused by addrconf/ndisc. */ idev = __in6_dev_get(arg->dev); if (!idev) return 0; if (fib6_metric_locked(f6i, RTAX_MTU)) return 0; arg->f6i = f6i; if (f6i->nh) { /* fib6_nh_mtu_change only returns 0, so this is safe */ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change, arg); } return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, .mtu = mtu, }; fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, [RTA_FLOWLABEL] = { .type = NLA_BE32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; unsigned int pref; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_tos) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): option not available for IPv6"); goto errout; } if (tb[RTA_FLOWLABEL]) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Flow label cannot be specified for this operation"); goto errout; } *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, .fc_src_len = rtm->rtm_src_len, .fc_flags = RTF_UP, .fc_protocol = rtm->rtm_protocol, .fc_type = rtm->rtm_type, .fc_nlinfo.portid = NETLINK_CB(skb).portid, .fc_nlinfo.nlh = nlh, .fc_nlinfo.nl_net = sock_net(skb->sk), }; if (rtm->rtm_type == RTN_UNREACHABLE || rtm->rtm_type == RTN_BLACKHOLE || rtm->rtm_type == RTN_PROHIBIT || rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; if (rtm->rtm_flags & RTM_F_CLONED) cfg->fc_flags |= RTF_CACHE; cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK); if (tb[RTA_NH_ID]) { if (tb[RTA_GATEWAY] || tb[RTA_OIF] || tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); goto errout; } cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]); } if (tb[RTA_GATEWAY]) { cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } if (tb[RTA_VIA]) { NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); goto errout; } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; if (nla_len(tb[RTA_DST]) < plen) goto errout; nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } if (tb[RTA_SRC]) { int plen = (rtm->rtm_src_len + 7) >> 3; if (nla_len(tb[RTA_SRC]) < plen) goto errout; nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } if (tb[RTA_PREFSRC]) cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_PRIORITY]) cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); if (tb[RTA_METRICS]) { cfg->fc_mx = nla_data(tb[RTA_METRICS]); cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack); if (err < 0) goto errout; } if (tb[RTA_PREF]) { pref = nla_get_u8(tb[RTA_PREF]); if (pref != ICMPV6_ROUTER_PREF_LOW && pref != ICMPV6_ROUTER_PREF_HIGH) pref = ICMPV6_ROUTER_PREF_MEDIUM; cfg->fc_flags |= RTF_PREF(pref); } if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); if (addrconf_finite_timeout(timeout)) { cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); cfg->fc_flags |= RTF_EXPIRES; } } err = 0; errout: return err; } struct rt6_nh { struct fib6_info *fib6_info; struct fib6_config r_cfg; struct list_head next; }; static int ip6_route_info_append(struct net *net, struct list_head *rt6_nh_list, struct fib6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if fib6_info already exists */ if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return err; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; nh->fib6_info = rt; memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->next, rt6_nh_list); return 0; } static void ip6_route_mpath_notify(struct fib6_info *rt, struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { /* if this is an APPEND route, then rt points to the first route * inserted and rt_last points to last route inserted. Userspace * wants a consistent dump of the route which starts at the first * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ rcu_read_lock(); if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) { bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool should_notify = false; struct fib6_info *leaf; struct fib6_node *fn; rcu_read_lock(); fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; leaf = rcu_dereference(fn->leaf); if (!leaf) goto out; if (rt == leaf || (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf))) should_notify = true; out: rcu_read_unlock(); return should_notify; } static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla, struct netlink_ext_ack *extack) { if (nla_len(nla) < sizeof(*gw)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); return -EINVAL; } *gw = nla_get_in6_addr(nla); return 0; } static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct fib6_config r_cfg; struct rtnexthop *rtnh; struct fib6_info *rt; struct rt6_nh *err_nh; struct rt6_nh *nh, *nh_safe; __u16 nlflags; int remaining; int attrlen; int err = 1; int nhn = 0; int replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); LIST_HEAD(rt6_nh_list); nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE; if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) goto cleanup; r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); /* RTA_ENCAP_TYPE length checked in * lwtunnel_valid_encap_type_attr */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } if (!rt6_qualify_for_ecmp(rt)) { err = -EINVAL; NL_SET_ERR_MSG(extack, "Device only routes can not be added for IPv6 using the multipath API."); fib6_info_release(rt); goto cleanup; } rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(info->nl_net, &rt6_nh_list, rt, &r_cfg); if (err) { fib6_info_release(rt); goto cleanup; } rtnh = rtnh_next(rtnh, &remaining); } if (list_empty(&rt6_nh_list)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops"); return -EINVAL; } /* for add and replace send one notification with all nexthops. * Skip the notification in fib6_add_rt2node and send one with * the full route when done */ info->skip_notify = 1; /* For add and replace, send one notification with all nexthops. For * append, send one notification with all appended nexthops. */ info->skip_notify_kernel = 1; err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } /* save reference to last route successfully inserted */ rt_last = nh->fib6_info; /* save reference to first route for notification */ if (!rt_notif) rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: * fib6_add_rt2node() has rejected it; when replacing, old * nexthops have been replaced by first new, the rest should * be added to it. */ if (cfg->fc_nlinfo.nlh) { cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; } nhn++; } /* An in-kernel notification should only be sent in case the new * multipath route is added as the first route in the node, or if * it was appended to it. We pass 'rt_notif' since it is the first * sibling and might allow us to skip some checks in the replace case. */ if (ip6_route_mpath_should_notify(rt_notif)) { enum fib_event_type fib_event; if (rt_notif->fib6_nsiblings != nhn - 1) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_multipath_entry_notifiers(info->nl_net, fib_event, rt_notif, nhn - 1, extack); if (err) { /* Delete all the siblings that were just added */ err_nh = NULL; goto add_errout; } } /* success ... tell user about new route */ ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); goto cleanup; add_errout: /* send notification for routes that were added so that * the delete notifications sent by ip6_route_del are * coherent */ if (rt_notif) ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); /* Delete routes that were already added */ list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } return err; } static int ip6_route_multipath_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; int last_err = 0; int remaining; int attrlen; int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) { last_err = err; goto next_rtnh; } r_cfg.fc_flags |= RTF_GATEWAY; } } err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; next_rtnh: rtnh = rtnh_next(rtnh, &remaining); } return last_err; } static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_nh_id && !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); return -EINVAL; } if (cfg.fc_mp) return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; return ip6_route_del(&cfg, extack); } } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else return ip6_route_add(&cfg, GFP_KERNEL, extack); } /* add the overhead of this fib6_nh to nexthop_len */ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) { int *nexthop_len = arg; *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16); /* RTA_GATEWAY */ if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); /* RTA_ENCAP */ *nexthop_len += nla_total_size(2); } return 0; } static size_t rt6_nlmsg_size(struct fib6_info *f6i) { int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { struct fib6_nh *nh = f6i->fib6_nh; struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); rcu_read_lock(); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ + nla_total_size(16) /* RTA_GATEWAY */ + nla_total_size(16) /* RTA_PREFSRC */ + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_IIF */ + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ + nexthop_len; } static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, unsigned char *flags) { if (nexthop_is_multipath(nh)) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (nexthop_mpath_fill_node(skb, nh, AF_INET6)) goto nla_put_failure; nla_nest_end(skb, mp); } else { struct fib6_nh *fib6_nh; fib6_nh = nexthop_fib6_nh(nh); if (fib_nexthop_info(skb, &fib6_nh->nh_common, AF_INET6, flags, false) < 0) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; if (rt6) { rt6_dst = &rt6->rt6i_dst; rt6_src = &rt6->rt6i_src; rt6_flags = rt6->rt6i_flags; } else { rt6_dst = &rt->fib6_dst; rt6_src = &rt->fib6_src; rt6_flags = rt->fib6_flags; } rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt6_dst->plen; rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) return 0; if (err < 0) goto nla_put_failure; } else #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) goto nla_put_failure; if (dst->lwtstate && lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, rt->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; rcu_read_lock(); list_for_each_entry_rcu(sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) { rcu_read_unlock(); goto nla_put_failure; } } rcu_read_unlock(); nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } else { if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, AF_INET6, &nh_flags, false) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } if (!dst) { if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg) { const struct net_device *dev = arg; if (nh->fib_nh_dev == dev) return 1; return 0; } static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { if (f6i->nh) { struct net_device *_dev = (struct net_device *)dev; return !!nexthop_for_each_fib6_nh(f6i->nh, fib6_info_nh_uses_dev, _dev); } if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (f6i->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; list_for_each_entry_safe(sibling, next_sibling, &f6i->fib6_siblings, fib6_siblings) { if (sibling->fib6_nh->fib_nh_dev == dev) return true; } } return false; } struct fib6_nh_exception_dump_walker { struct rt6_rtnl_dump_arg *dump; struct fib6_info *rt; unsigned int flags; unsigned int skip; unsigned int count; }; static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_nh_exception_dump_walker *w = arg; struct rt6_rtnl_dump_arg *dump = w->dump; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i, err; bucket = fib6_nh_get_excptn_bucket(nh, NULL); if (!bucket) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; } /* Expiration of entries doesn't bump sernum, insertion * does. Removal is triggered by insertion, so we can * rely on the fact that if entries change between two * partial dumps, this node is scanned again completely, * see rt6_insert_exception() and fib6_dump_table(). * * Count expired entries we go through as handled * entries that we'll skip next time, in case of partial * node dump. Otherwise, if entries expire meanwhile, * we'll skip the wrong amount. */ if (rt6_check_expired(rt6_ex->rt6i)) { w->count++; continue; } err = rt6_fill_node(dump->net, dump->skb, w->rt, &rt6_ex->rt6i->dst, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(dump->cb->skb).portid, dump->cb->nlh->nlmsg_seq, w->flags); if (err) return err; w->count++; } bucket++; } return 0; } /* Return -1 if done with node, number of handled routes on partial dump */ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct fib_dump_filter *filter = &arg->filter; unsigned int flags = NLM_F_MULTI; struct net *net = arg->net; int count = 0; if (rt == net->ipv6.fib6_null_entry) return -1; if ((filter->flags & RTM_F_PREFIX) && !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return -1; } if (filter->filter_set && ((filter->rt_type && rt->fib6_type != filter->rt_type) || (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) || (filter->protocol && rt->fib6_protocol != filter->protocol))) { return -1; } if (filter->filter_set || !filter->dump_routes || !filter->dump_exceptions) { flags |= NLM_F_DUMP_FILTERED; } if (filter->dump_routes) { if (skip) { skip--; } else { if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, flags)) { return 0; } count++; } } if (filter->dump_exceptions) { struct fib6_nh_exception_dump_walker w = { .dump = arg, .rt = rt, .flags = flags, .skip = skip, .count = 0 }; int err; rcu_read_lock(); if (rt->nh) { err = nexthop_for_each_fib6_nh(rt->nh, rt6_nh_dump_exceptions, &w); } else { err = rt6_nh_dump_exceptions(rt->fib6_nh, &w); } rcu_read_unlock(); if (err) return count + w.count; } return -1; } static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } if (tb[RTA_FLOWLABEL] && (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Invalid flow label"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_IIF: case RTA_OIF: case RTA_MARK: case RTA_UID: case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: case RTA_FLOWLABEL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; __be32 flowlabel; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); if (tb[RTA_UID]) fl6.flowi6_uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); if (tb[RTA_SPORT]) fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &fl6.flowi6_proto, AF_INET6, extack); if (err) goto errout; } flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel); if (iif) { struct net_device *dev; int flags = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) { rcu_read_unlock(); err = -ENODEV; goto errout; } fl6.flowi6_iif = iif; if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; dst = ip6_route_output(net, NULL, &fl6); } rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } if (rt == net->ipv6.ip6_null_entry) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); err = -ENOBUFS; goto errout; } skb_dst_set(skb, &rt->dst); rcu_read_lock(); from = rcu_dereference(rt->from); if (from) { if (fibmatch) err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } else { err = -ENETUNREACH; } rcu_read_unlock(); if (err < 0) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; u32 seq; int err; err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed) { struct sk_buff *skb; int err; if (READ_ONCE(f6i->offload) == offload && READ_ONCE(f6i->trap) == trap && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload, offload); WRITE_ONCE(f6i->trap, trap); /* 2 means send notifications only if offload_failed was changed. */ if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send * notification. */ return; if (!net->ipv6.sysctl.fib_notify_on_flag_change) return; skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } EXPORT_SYMBOL(fib6_info_hw_flags_set); static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (!(dev->flags & IFF_LOOPBACK)) return NOTIFY_OK; if (event == NETDEV_REGISTER) { net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } else if (event == NETDEV_UNREGISTER && dev->reg_state != NETREG_UNREGISTERED) { /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } return NOTIFY_OK; } /* * /proc */ #ifdef CONFIG_PROC_FS static int rt6_stats_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int delay; int ret; if (!write) return -EINVAL; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } static struct ctl_table ipv6_route_table_template[] = { { .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv6_sysctl_rtcache_flush }, { .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_route_table_template, sizeof(ipv6_route_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.ip6_rt_max_size; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.flush_delay; table[2].extra1 = net; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; } return table; } size_t ipv6_route_sysctl_table_size(struct net *net) { /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) return 1; return ARRAY_SIZE(ipv6_route_table_template); } #endif static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif #endif net->ipv6.sysctl.flush_delay = 0; net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: return ret; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_ip6_prohibit_entry: kfree(net->ipv6.ip6_prohibit_entry); out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_fib6_null_entry: kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } static void __net_exit ip6_route_net_exit(struct net *net) { kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, sizeof(struct ipv6_route_iter))) return -ENOMEM; if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, rt6_stats_seq_show, NULL)) { remove_proc_entry("ipv6_route", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ipv6_route", net->proc_net); remove_proc_entry("rt6_stats", net->proc_net); #endif } static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; static int __net_init ipv6_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv6.peers = bp; return 0; } static void __net_exit ipv6_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv6.peers; net->ipv6.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, }; static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) { /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif } #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) BTF_ID_LIST(btf_fib6_info_id) BTF_ID(struct, fib6_info) static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), }; static struct bpf_iter_reg ipv6_route_reg_info = { .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } static void bpf_iter_unregister(void) { bpf_iter_unreg_target(&ipv6_route_reg_info); } #endif #endif static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE, .doit = inet6_rtm_newroute}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE, .doit = inet6_rtm_delroute}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip6_route_init(void) { int ret; int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; ret = register_pernet_subsys(&ip6_route_net_ops); if (ret) goto out_register_inetpeer; ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; ret = fib6_init(); if (ret) goto out_register_subsys; ret = xfrm6_init(); if (ret) goto out_fib6_init; ret = fib6_rules_init(); if (ret) goto xfrm6_init; ret = register_pernet_subsys(&ip6_route_net_late_ops); if (ret) goto fib6_rules_init; ret = rtnl_register_many(ip6_route_rtnl_msg_handlers); if (ret < 0) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) goto out_register_late_subsys; #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) goto out_register_late_subsys; #endif #endif for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } out: return ret; out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_register_inetpeer: unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; } void ip6_route_cleanup(void) { #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_unregister(); #endif #endif unregister_netdevice_notifier(&ip6_route_dev_notifier); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } |
| 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <net/pkt_sched.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (flags & IFF_UP) continue; dev_change_flags(cpriv->dev, flags | IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (!(flags & IFF_UP)) continue; dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } /* Check child interfaces */ down_read_nested(&priv->vlan_rwsem, nesting); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } up_read(&priv->vlan_rwsem); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_update_features(dev); dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); down_write(&ppriv->vlan_rwsem); list_add_tail(&priv->list, &ppriv->child_intfs); up_write(&ppriv->vlan_rwsem); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ASSERT_RTNL(); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); list_del(&priv->list); up_write(&ppriv->vlan_rwsem); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); up_read(&priv->vlan_rwsem); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 109 109 107 18 1 113 154 94 113 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ARM_ARM64_KVM_H #include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm /* * Tracepoints for entry/exit to guest */ TRACE_EVENT(kvm_entry, TP_PROTO(unsigned long vcpu_pc), TP_ARGS(vcpu_pc), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; ), TP_printk("PC: 0x%016lx", __entry->vcpu_pc) ); TRACE_EVENT(kvm_exit, TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc), TP_ARGS(ret, esr_ec, vcpu_pc), TP_STRUCT__entry( __field( int, ret ) __field( unsigned int, esr_ec ) __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->ret = ARM_EXCEPTION_CODE(ret); __entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0; __entry->vcpu_pc = vcpu_pc; ), TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx", __print_symbolic(__entry->ret, kvm_arm_exception_type), __entry->esr_ec, __print_symbolic(__entry->esr_ec, kvm_arm_exception_class), __entry->vcpu_pc) ); TRACE_EVENT(kvm_guest_fault, TP_PROTO(unsigned long vcpu_pc, unsigned long hsr, unsigned long hxfar, unsigned long long ipa), TP_ARGS(vcpu_pc, hsr, hxfar, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, hsr ) __field( unsigned long, hxfar ) __field( unsigned long long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->hsr = hsr; __entry->hxfar = hxfar; __entry->ipa = ipa; ), TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx", __entry->ipa, __entry->hsr, __entry->hxfar, __entry->vcpu_pc) ); TRACE_EVENT(kvm_access_fault, TP_PROTO(unsigned long ipa), TP_ARGS(ipa), TP_STRUCT__entry( __field( unsigned long, ipa ) ), TP_fast_assign( __entry->ipa = ipa; ), TP_printk("IPA: %lx", __entry->ipa) ); TRACE_EVENT(kvm_irq_line, TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), TP_ARGS(type, vcpu_idx, irq_num, level), TP_STRUCT__entry( __field( unsigned int, type ) __field( int, vcpu_idx ) __field( int, irq_num ) __field( int, level ) ), TP_fast_assign( __entry->type = type; __entry->vcpu_idx = vcpu_idx; __entry->irq_num = irq_num; __entry->level = level; ), TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d", (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" : (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" : (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN", __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level) ); TRACE_EVENT(kvm_mmio_emulate, TP_PROTO(unsigned long vcpu_pc, unsigned long instr, unsigned long cpsr), TP_ARGS(vcpu_pc, instr, cpsr), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, instr ) __field( unsigned long, cpsr ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->instr = instr; __entry->cpsr = cpsr; ), TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)", __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); TRACE_EVENT(kvm_mmio_nisv, TP_PROTO(unsigned long vcpu_pc, unsigned long esr, unsigned long far, unsigned long ipa), TP_ARGS(vcpu_pc, esr, far, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, esr ) __field( unsigned long, far ) __field( unsigned long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->esr = esr; __entry->far = far; __entry->ipa = ipa; ), TP_printk("ipa %#016lx, esr %#016lx, far %#016lx, pc %#016lx", __entry->ipa, __entry->esr, __entry->far, __entry->vcpu_pc) ); TRACE_EVENT(kvm_set_way_flush, TP_PROTO(unsigned long vcpu_pc, bool cache), TP_ARGS(vcpu_pc, cache), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, cache ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->cache = cache; ), TP_printk("S/W flush at 0x%016lx (cache %s)", __entry->vcpu_pc, __entry->cache ? "on" : "off") ); TRACE_EVENT(kvm_toggle_cache, TP_PROTO(unsigned long vcpu_pc, bool was, bool now), TP_ARGS(vcpu_pc, was, now), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, was ) __field( bool, now ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->was = was; __entry->now = now; ), TP_printk("VM op at 0x%016lx (cache was %s, now %s)", __entry->vcpu_pc, __entry->was ? "on" : "off", __entry->now ? "on" : "off") ); /* * Tracepoints for arch_timer */ TRACE_EVENT(kvm_timer_update_irq, TP_PROTO(unsigned long vcpu_id, __u32 irq, int level), TP_ARGS(vcpu_id, irq, level), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( __u32, irq ) __field( int, level ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->irq = irq; __entry->level = level; ), TP_printk("VCPU: %ld, IRQ %d, level %d", __entry->vcpu_id, __entry->irq, __entry->level) ); TRACE_EVENT(kvm_get_timer_map, TP_PROTO(unsigned long vcpu_id, struct timer_map *map), TP_ARGS(vcpu_id, map), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( int, direct_vtimer ) __field( int, direct_ptimer ) __field( int, emul_vtimer ) __field( int, emul_ptimer ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); __entry->direct_ptimer = (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; __entry->emul_vtimer = (map->emul_vtimer) ? arch_timer_ctx_index(map->emul_vtimer) : -1; __entry->emul_ptimer = (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; ), TP_printk("VCPU: %ld, dv: %d, dp: %d, ev: %d, ep: %d", __entry->vcpu_id, __entry->direct_vtimer, __entry->direct_ptimer, __entry->emul_vtimer, __entry->emul_ptimer) ); TRACE_EVENT(kvm_timer_save_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk(" CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_restore_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_hrtimer_expire, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( int, timer_idx ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("arch_timer_ctx_index: %d", __entry->timer_idx) ); TRACE_EVENT(kvm_timer_emulate, TP_PROTO(struct arch_timer_context *ctx, bool should_fire), TP_ARGS(ctx, should_fire), TP_STRUCT__entry( __field( int, timer_idx ) __field( bool, should_fire ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); __entry->should_fire = should_fire; ), TP_printk("arch_timer_ctx_index: %d (should_fire: %d)", __entry->timer_idx, __entry->should_fire) ); TRACE_EVENT(kvm_nested_eret, TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2, unsigned long spsr_el2), TP_ARGS(vcpu, elr_el2, spsr_el2), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, elr_el2) __field(unsigned long, spsr_el2) __field(unsigned long, target_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->elr_el2 = elr_el2; __entry->spsr_el2 = spsr_el2; __entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __entry->elr_el2, __entry->spsr_el2, __print_symbolic(__entry->target_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_inject_nested_exception, TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type), TP_ARGS(vcpu, esr_el2, type), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, esr_el2) __field(int, type) __field(unsigned long, spsr_el2) __field(unsigned long, pc) __field(unsigned long, source_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->esr_el2 = esr_el2; __entry->type = type; __entry->spsr_el2 = *vcpu_cpsr(vcpu); __entry->pc = *vcpu_pc(vcpu); __entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __print_symbolic(__entry->type, kvm_exception_type_names), __entry->esr_el2, __entry->pc, __entry->spsr_el2, __print_symbolic(__entry->source_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_forward_sysreg_trap, TP_PROTO(struct kvm_vcpu *vcpu, u32 sysreg, bool is_read), TP_ARGS(vcpu, sysreg, is_read), TP_STRUCT__entry( __field(u64, pc) __field(u32, sysreg) __field(bool, is_read) ), TP_fast_assign( __entry->pc = *vcpu_pc(vcpu); __entry->sysreg = sysreg; __entry->is_read = is_read; ), TP_printk("%llx %c (%d,%d,%d,%d,%d)", __entry->pc, __entry->is_read ? 'R' : 'W', sys_reg_Op0(__entry->sysreg), sys_reg_Op1(__entry->sysreg), sys_reg_CRn(__entry->sysreg), sys_reg_CRm(__entry->sysreg), sys_reg_Op2(__entry->sysreg)) ); #endif /* _TRACE_ARM_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_arm /* This part must be outside protection */ #include <trace/define_trace.h> |
| 368 369 369 112 112 368 368 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / __tlb_remove_page() * - tlb_remove_page_size() / __tlb_remove_page_size() * - __tlb_remove_folio_pages() * * __tlb_remove_page_size() is the basic primitive that queues a page for * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a * boolean indicating if the queue is (now) full and a call to * tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page(), however, * instead of removing a single page, remove the given number of consecutive * pages that are all part of the same (large) folio: just like calling * __tlb_remove_page() on each page individually. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef __HAVE_ARCH_TLB_REMOVE_TABLE static inline void __tlb_remove_table(void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc); } #endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct page *page = (struct page *)table; pagetable_dtor(page_ptdesc(page)); tlb_remove_page(tlb, page); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, bool delay_rmap, int page_size); bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP /* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */ #define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); #endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */ #ifndef tlb_delay_rmap #define tlb_delay_rmap(tlb) (false) static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) #error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); tlb->vma_pfn = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds)) return; tlb_flush(tlb); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, false, page_size)) tlb_flush_mmu(tlb); } static __always_inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page, bool delay_rmap) { return __tlb_remove_page_size(tlb, page, delay_rmap, PAGE_SIZE); } /* tlb_remove_page * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when * required. */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) { tlb_remove_table(tlb, pt); } /* Like tlb_remove_ptdesc, but for page-like page directories. */ static inline void tlb_remove_page_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) { tlb_remove_page(tlb, ptdesc_page(pt)); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); #ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); #endif } static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; /* * VM_PFNMAP is more fragile because the core mm will not track the * page mapcount -- there might not be page-frames for these PFNs after * all. Force flush TLBs for such ranges to avoid munmap() vs * unmap_mapping_range() races. */ if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) { /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs. */ tlb_flush_mmu_tlbonly(tlb); } } /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { } #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for * later tlb invalidation. * * Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple * consecutive ptes instead of only a single one. */ static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb, pte_t *ptep, unsigned int nr, unsigned long address) { tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr); for (;;) { __tlb_remove_tlb_entry(tlb, ptep, address); if (--nr == 0) break; ptep++; address += PAGE_SIZE; } } #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef pte_needs_flush static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) { return true; } #endif #ifndef huge_pmd_needs_flush static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { return true; } #endif #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 1 1 1 1 1 1 | 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 | /* * llc_core.c - Minimum needed routines for sap handling and module init/exit * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/llc.h> LIST_HEAD(llc_sap_list); static DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. * * Allocates and initializes sap. */ static struct llc_sap *llc_sap_alloc(void) { struct llc_sap *sap = kzalloc(sizeof(*sap), GFP_ATOMIC); int i; if (sap) { /* sap->laddr.mac - leave as a null, it's filled by bind */ sap->state = LLC_SAP_STATE_ACTIVE; spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); refcount_set(&sap->refcnt, 1); } return sap; } static struct llc_sap *__llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value) goto out; sap = NULL; out: return sap; } /** * llc_sap_find - searches a SAP in station * @sap_value: sap to be found * * Searches for a sap in the sap list of the LLC's station upon the sap ID. * If the sap is found it will be refcounted and the user will have to do * a llc_sap_put after use. * Returns the sap or %NULL if not found. */ struct llc_sap *llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (!sap || !llc_sap_hold_safe(sap)) sap = NULL; rcu_read_unlock_bh(); return sap; } /** * llc_sap_open - open interface to the upper layers. * @lsap: SAP number. * @func: rcv func for datalink protos * * Interface function to upper layer. Each one who wants to get a SAP * (for example NetBEUI) should call this function. Returns the opened * SAP for success, NULL for failure. */ struct llc_sap *llc_sap_open(unsigned char lsap, int (*func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)) { struct llc_sap *sap = NULL; spin_lock_bh(&llc_sap_list_lock); if (__llc_sap_find(lsap)) /* SAP already exists */ goto out; sap = llc_sap_alloc(); if (!sap) goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; list_add_tail_rcu(&sap->node, &llc_sap_list); out: spin_unlock_bh(&llc_sap_list_lock); return sap; } /** * llc_sap_close - close interface for upper layers. * @sap: SAP to be closed. * * Close interface function to upper layer. Each one who wants to * close an open SAP (for example NetBEUI) should call this function. * Removes this sap from the list of saps in the station and then * frees the memory for this sap. */ void llc_sap_close(struct llc_sap *sap) { WARN_ON(sap->sk_count); spin_lock_bh(&llc_sap_list_lock); list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_2), .func = llc_rcv, }; static int __init llc_init(void) { dev_add_pack(&llc_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); } module_init(llc_init); module_exit(llc_exit); EXPORT_SYMBOL(llc_sap_list); EXPORT_SYMBOL(llc_sap_find); EXPORT_SYMBOL(llc_sap_open); EXPORT_SYMBOL(llc_sap_close); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("LLC IEEE 802.2 core support"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; struct iomap_iter; struct iomap; enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, }; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, enum dax_access_mode, void **, pfn_t *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); /* * recovery_write: recover a poisoned range by DAX device driver * capable of clearing poison. */ size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *iter); }; struct dax_holder_operations { /* * notify_failure - notify memory failure into inner holder device * @dax_dev: the dax device which contains the holder * @offset: offset on this dax device where memory failure occurs * @len: length of this memory failure event * @flags: action flags for memory failure handler */ int (*notify_failure)(struct dax_device *dax_dev, u64 offset, u64 len, int mf_flags); }; #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_nocache(struct dax_device *dax_dev); void set_dax_nomc(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline void *dax_holder(struct dax_device *dax_dev) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { return ERR_PTR(-EOPNOTSUPP); } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_nocache(struct dax_device *dax_dev) { } static inline void set_dax_nomc(struct dax_device *dax_dev) { } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { return 0; } #endif struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops); void fs_put_dax(struct dax_device *dax_dev, void *holder); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { return 0; } static inline void dax_remove_host(struct gendisk *disk) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops) { return NULL; } static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { } #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ #if IS_ENABLED(CONFIG_FS_DAX) int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_folio(struct folio *folio); void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie); #else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_folio(struct folio *folio) { if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page) { return 0; } static inline void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie) { } #endif int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops); int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } /* * Due to dax's memory and block duo personalities, hwpoison reporting * takes into consideration which personality is presently visible. * When dax acts like a block device, such as in block IO, an encounter of * dax hwpoison is reported as -EIO. * When dax acts like memory, such as in page fault, a detection of hwpoison * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON. */ static inline int dax_mem2blk_err(int err) { return (err == -EHWPOISON) ? -EIO : err; } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_resource(int target_nid, struct resource *r); #else static inline void hmem_register_resource(int target_nid, struct resource *r) { } #endif typedef int (*walk_hmem_fn)(struct device *dev, int target_nid, const struct resource *res); int walk_hmem_resources(struct device *dev, walk_hmem_fn fn); #endif |
| 83 153 83 85 83 82 152 122 152 14 69 152 153 152 153 85 85 82 12 152 152 153 139 153 153 151 152 153 152 231 231 231 85 71 92 92 83 83 1 82 83 82 82 82 83 83 9 11 85 69 83 83 82 82 83 83 83 83 69 70 83 83 83 83 70 83 83 83 83 34 33 11 11 11 11 11 11 11 9 34 34 72 71 2 2 2 71 2 2 2 1 1 1 231 231 16 16 1 1 16 16 16 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 | // SPDX-License-Identifier: GPL-2.0-only /* * Stand-alone page-table allocator for hyp stage-1 and guest stage-2. * No bombay mix was harmed in the writing of this file. * * Copyright (C) 2020 Google LLC * Author: Will Deacon <will@kernel.org> */ #include <linux/bitfield.h> #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> #define KVM_PTE_TYPE BIT(1) #define KVM_PTE_TYPE_BLOCK 0 #define KVM_PTE_TYPE_PAGE 1 #define KVM_PTE_TYPE_TABLE 1 struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; const u64 start; u64 addr; const u64 end; }; static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI); } static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); } static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { u64 granule = kvm_granule_size(ctx->level); if (!kvm_level_supports_block_mapping(ctx->level)) return false; if (granule > (ctx->end - ctx->addr)) return false; if (!IS_ALIGNED(phys, granule)) return false; return IS_ALIGNED(ctx->addr, granule); } static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level) { u64 shift = kvm_granule_shift(level); u64 mask = BIT(PAGE_SHIFT - 3) - 1; return (data->addr >> shift) & mask; } static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) { u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */ u64 mask = BIT(pgt->ia_bits) - 1; return (addr & mask) >> shift; } static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level) { struct kvm_pgtable pgt = { .ia_bits = ia_bits, .start_level = start_level, }; return kvm_pgd_page_idx(&pgt, -1ULL) + 1; } static bool kvm_pte_table(kvm_pte_t pte, s8 level) { if (level == KVM_PGTABLE_LAST_LEVEL) return false; if (!kvm_pte_valid(pte)) return false; return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; } static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops) { return mm_ops->phys_to_virt(kvm_pte_to_phys(pte)); } static void kvm_clear_pte(kvm_pte_t *ptep) { WRITE_ONCE(*ptep, 0); } static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops) { kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level) { kvm_pte_t pte = kvm_phys_to_pte(pa); u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE : KVM_PTE_TYPE_BLOCK; pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI); pte |= FIELD_PREP(KVM_PTE_TYPE, type); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id) { return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id); } static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_walker *walker = data->walker; /* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */ WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held()); return walker->cb(ctx, visit); } static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, int r) { /* * Visitor callbacks return EAGAIN when the conditions that led to a * fault are no longer reflected in the page tables due to a race to * update a PTE. In the context of a fault handler this is interpreted * as a signal to retry guest execution. * * Ignore the return code altogether for walkers outside a fault handler * (e.g. write protecting a range of memory) and chug along with the * page table walk. */ if (r == -EAGAIN) return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); return !r; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level); static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pteref, s8 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, .start = data->start, .addr = data->addr, .end = data->end, .level = level, .flags = flags, }; int ret = 0; bool reload = false; kvm_pteref_t childp; bool table = kvm_pte_table(ctx.old, level); if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); reload = true; } if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); reload = true; } /* * Reload the page table after invoking the walker callback for leaf * entries or after pre-order traversal, to allow the walker to descend * into a newly installed or replaced table. */ if (reload) { ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); } if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (!table) { data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level)); data->addr += kvm_granule_size(level); goto out; } childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: if (kvm_pgtable_walk_continue(data->walker, ret)) return 0; return ret; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level) { u32 idx; int ret = 0; if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL || level > KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) { kvm_pteref_t pteref = &pgtable[idx]; if (data->addr >= data->end) break; ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); if (ret) break; } return ret; } static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data) { u32 idx; int ret = 0; u64 limit = BIT(pgt->ia_bits); if (data->addr > limit || data->end > limit) return -ERANGE; if (!pgt->pgd) return -EINVAL; for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); if (ret) break; } return ret; } int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, }; int r; r = kvm_pgtable_walk_begin(walker); if (r) return r; r = _kvm_pgtable_walk(pgt, &walk_data); kvm_pgtable_walk_end(walker); return r; } struct leaf_walk_data { kvm_pte_t pte; s8 level; }; static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct leaf_walk_data *data = ctx->arg; data->pte = ctx->old; data->level = ctx->level; return 0; } int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, kvm_pte_t *ptep, s8 *level) { struct leaf_walk_data data; struct kvm_pgtable_walker walker = { .cb = leaf_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &data, }; int ret; ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), PAGE_SIZE, &walker); if (!ret) { if (ptep) *ptep = data.pte; if (level) *level = data.level; } return ret; } struct hyp_map_data { const u64 phys; kvm_pte_t attr; }; static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { bool device = prot & KVM_PGTABLE_PROT_DEVICE; u32 mtype = device ? MT_DEVICE_nGnRE : MT_NORMAL; kvm_pte_t attr = FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX, mtype); u32 sh = KVM_PTE_LEAF_ATTR_LO_S1_SH_IS; u32 ap = (prot & KVM_PGTABLE_PROT_W) ? KVM_PTE_LEAF_ATTR_LO_S1_AP_RW : KVM_PTE_LEAF_ATTR_LO_S1_AP_RO; if (!(prot & KVM_PGTABLE_PROT_R)) return -EINVAL; if (prot & KVM_PGTABLE_PROT_X) { if (prot & KVM_PGTABLE_PROT_W) return -EINVAL; if (device) return -EINVAL; if (system_supports_bti_kernel()) attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; } else { attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; } attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap); if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; u32 ap; if (!kvm_pte_valid(pte)) return prot; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN)) prot |= KVM_PGTABLE_PROT_X; ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte); if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO) prot |= KVM_PGTABLE_PROT_R; else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW) prot |= KVM_PGTABLE_PROT_RW; return prot; } static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; if (!kvm_block_mapping_supported(ctx, phys)) return false; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; if (!kvm_pte_valid(ctx->old)) ctx->mm_ops->get_page(ctx->ptep); else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; smp_store_release(ctx->ptep, new); return true; } static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp, new; struct hyp_map_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (hyp_map_walker_try_leaf(ctx, data)) return 0; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL); if (!childp) return -ENOMEM; new = kvm_init_table_pte(childp, mm_ops); mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); return 0; } int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot) { int ret; struct hyp_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), }; struct kvm_pgtable_walker walker = { .cb = hyp_map_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; ret = hyp_set_prot_attr(prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); isb(); return ret; } static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp = NULL; u64 granule = kvm_granule_size(ctx->level); u64 *unmapped = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EINVAL; if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN); } else { if (ctx->end - ctx->addr < granule) return -EINVAL; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); *unmapped += granule; } dsb(ish); isb(); mm_ops->put_page(ctx->ptep); if (childp) mm_ops->put_page(childp); return 0; } u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { u64 unmapped = 0; struct kvm_pgtable_walker walker = { .cb = hyp_unmap_walker, .arg = &unmapped, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; if (!pgt->mm_ops->page_count) return 0; kvm_pgtable_walk(pgt, addr, size, &walker); return unmapped; } int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops) { s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 - ARM64_HW_PGTABLE_LEVELS(va_bits); if (start_level < KVM_PGTABLE_FIRST_LEVEL || start_level > KVM_PGTABLE_LAST_LEVEL) return -EINVAL; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = va_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = NULL; pgt->force_pte_cb = NULL; return 0; } static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) { struct kvm_pgtable_walker walker = { .cb = hyp_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } struct stage2_map_data { const u64 phys; kvm_pte_t attr; u8 owner_id; kvm_pte_t *anchor; kvm_pte_t *childp; struct kvm_s2_mmu *mmu; void *memcache; /* Force mappings to page granularity */ bool force_pte; /* Walk should update owner_id only */ bool annotation; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) { u64 vtcr = VTCR_EL2_FLAGS; s8 lvls; vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT; vtcr |= VTCR_EL2_T0SZ(phys_shift); /* * Use a minimum 2 level page table to prevent splitting * host PMD huge pages at stage2. */ lvls = stage2_pgtable_levels(phys_shift); if (lvls < 2) lvls = 2; /* * When LPA2 is enabled, the HW supports an extra level of translation * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2 * to as an addition to SL0 to enable encoding this extra start level. * However, since we always use concatenated pages for the first level * lookup, we will never need this extra level and therefore do not need * to touch SL2. */ vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally * on all CPUs. In systems that have asymmetric support for the feature * this allows KVM to leverage hardware support on the subset of cores * that implement the feature. * * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by * hardware) on implementations that do not advertise support for the * feature. As such, setting HA unconditionally is safe, unless you * happen to be running on a design that has unadvertised support for * HAFDBS. Here be dragons. */ if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) vtcr |= VTCR_EL2_HA; #endif /* CONFIG_ARM64_HW_AFDBM */ if (kvm_lpa2_is_enabled()) vtcr |= VTCR_EL2_DS; /* Set the vmid bits */ vtcr |= (get_vmid_bits(mmfr1) == 16) ? VTCR_EL2_VS_16BIT : VTCR_EL2_VS_8BIT; return vtcr; } static bool stage2_has_fwb(struct kvm_pgtable *pgt) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return false; return !(pgt->flags & KVM_PGTABLE_S2_NOFWB); } void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, size_t size) { unsigned long pages, inval_pages; if (!system_supports_tlb_range()) { kvm_call_hyp(__kvm_tlb_flush_vmid, mmu); return; } pages = size >> PAGE_SHIFT; while (pages > 0) { inval_pages = min(pages, MAX_TLBI_RANGE_PAGES); kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages); addr += inval_pages << PAGE_SHIFT; pages -= inval_pages; } } #define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt)) static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { kvm_pte_t attr; u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS; switch (prot & (KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC)) { case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC: return -EINVAL; case KVM_PGTABLE_PROT_DEVICE: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE); break; case KVM_PGTABLE_PROT_NORMAL_NC: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, NORMAL_NC); break; default: attr = KVM_S2_MEMATTR(pgt, NORMAL); } if (!(prot & KVM_PGTABLE_PROT_X)) attr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; if (prot & KVM_PGTABLE_PROT_R) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; if (!kvm_pte_valid(pte)) return prot; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R) prot |= KVM_PGTABLE_PROT_R; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W) prot |= KVM_PGTABLE_PROT_W; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN)) prot |= KVM_PGTABLE_PROT_X; return prot; } static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new) { if (!kvm_pte_valid(old) || !kvm_pte_valid(new)) return true; return ((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS)); } static bool stage2_pte_is_counted(kvm_pte_t pte) { /* * The refcount tracks valid entries as well as invalid entries if they * encode ownership of a page to another entity than the page-table * owner, whose id is 0. */ return !!pte; } static bool stage2_pte_is_locked(kvm_pte_t pte) { return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED); } static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { if (!kvm_pgtable_walk_shared(ctx)) { WRITE_ONCE(*ctx->ptep, new); return true; } return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old; } /** * stage2_try_break_pte() - Invalidates a pte according to the * 'break-before-make' requirements of the * architecture. * * @ctx: context of the visited pte. * @mmu: stage-2 mmu * * Returns: true if the pte was successfully broken. * * If the removed pte was valid, performs the necessary serialization and TLB * invalidation for the old value. For counted ptes, drops the reference count * on the containing table page. */ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (stage2_pte_is_locked(ctx->old)) { /* * Should never occur if this walker has exclusive access to the * page tables. */ WARN_ON(!kvm_pgtable_walk_shared(ctx)); return false; } if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED)) return false; if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) { /* * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ if (kvm_pte_table(ctx->old, ctx->level)) { u64 size = kvm_granule_size(ctx->level); u64 addr = ALIGN_DOWN(ctx->addr, size); kvm_tlb_flush_vmid_range(mmu, addr, size); } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } if (stage2_pte_is_counted(ctx->old)) mm_ops->put_page(ctx->ptep); return true; } static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; WARN_ON(!stage2_pte_is_locked(*ctx->ptep)); if (stage2_pte_is_counted(new)) mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); } static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt) { /* * If FEAT_TLBIRANGE is implemented, defer the individual * TLB invalidations until the entire walk is finished, and * then use the range-based TLBI instructions to do the * invalidations. Condition deferred TLB invalidation on the * system supporting FWB as the optimization is entirely * pointless when the unmap walker needs to perform CMOs. */ return system_supports_tlb_range() && stage2_has_fwb(pgt); } static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { struct kvm_pgtable *pgt = ctx->arg; /* * Clear the existing PTE, and perform break-before-make if it was * valid. Depending on the system support, defer the TLB maintenance * for the same until the entire unmap walk is completed. */ if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, TLBI_TTL_UNKNOWN); } else if (!stage2_unmap_defer_tlb_flush(pgt)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } mm_ops->put_page(ctx->ptep); } static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) { u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR; return kvm_pte_valid(pte) && memattr == KVM_S2_MEMATTR(pgt, NORMAL); } static bool stage2_pte_executable(kvm_pte_t pte) { return kvm_pte_valid(pte) && !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, const struct stage2_map_data *data) { u64 phys = data->phys; /* Work out the correct PA based on how far the walk has gotten */ return phys + (ctx->addr - ctx->start); } static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { u64 phys = stage2_map_walker_phys_addr(ctx, data); if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) return false; if (data->annotation) return true; return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; u64 phys = stage2_map_walker_phys_addr(ctx, data); u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; if (!data->annotation) new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); /* * Skip updating the PTE if we are trying to recreate the exact * same mapping or only change the access permissions. Instead, * the vCPU will exit one more time from guest if still needed * and then go through the path of relaxing permissions. */ if (!stage2_pte_needs_update(ctx->old, new)) return -EAGAIN; /* If we're only changing software bits, then store them and go! */ if (!kvm_pgtable_walk_shared(ctx) && !((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) { bool old_is_counted = stage2_pte_is_counted(ctx->old); if (old_is_counted != stage2_pte_is_counted(new)) { if (old_is_counted) mm_ops->put_page(ctx->ptep); else mm_ops->get_page(ctx->ptep); } WARN_ON_ONCE(!stage2_try_set_pte(ctx, new)); return 0; } if (!stage2_try_break_pte(ctx, data->mmu)) return -EAGAIN; /* Perform CMOs before installation of the guest stage-2 PTE */ if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new)) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops), granule); if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou && stage2_pte_executable(new)) mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); stage2_make_pte(ctx, new); return 0; } static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); int ret; if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; ret = stage2_map_walker_try_leaf(ctx, data); if (ret) return ret; mm_ops->free_unlinked_table(childp, ctx->level); return 0; } static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp, new; int ret; ret = stage2_map_walker_try_leaf(ctx, data); if (ret != -E2BIG) return ret; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; if (!data->memcache) return -ENOMEM; childp = mm_ops->zalloc_page(data->memcache); if (!childp) return -ENOMEM; if (!stage2_try_break_pte(ctx, data->mmu)) { mm_ops->put_page(childp); return -EAGAIN; } /* * If we've run into an existing block mapping then replace it with * a table. Accesses beyond 'end' that fall within the new table * will be mapped lazily. */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } /* * The TABLE_PRE callback runs for table entries on the way down, looking * for table entries which we could conceivably replace with a block entry * for this mapping. If it finds one it replaces the entry and calls * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table. * * Otherwise, the LEAF callback performs the mapping at the existing leaves * instead. */ static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct stage2_map_data *data = ctx->arg; switch (visit) { case KVM_PGTABLE_WALK_TABLE_PRE: return stage2_map_walk_table_pre(ctx, data); case KVM_PGTABLE_WALK_LEAF: return stage2_map_walk_leaf(ctx, data); default: return -EINVAL; } } int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags) { int ret; struct stage2_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), .mmu = pgt->mmu, .memcache = mc, .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = flags | KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (WARN_ON((pgt->flags & KVM_PGTABLE_S2_IDMAP) && (addr != phys))) return -EINVAL; ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc, u8 owner_id) { int ret; struct stage2_map_data map_data = { .mmu = pgt->mmu, .memcache = mc, .owner_id = owner_id, .force_pte = true, .annotation = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (owner_id > KVM_MAX_OWNER_ID) return -EINVAL; ret = kvm_pgtable_walk(pgt, addr, size, &walker); return ret; } static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_s2_mmu *mmu = pgt->mmu; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = NULL; bool need_flush = false; if (!kvm_pte_valid(ctx->old)) { if (stage2_pte_is_counted(ctx->old)) { kvm_clear_pte(ctx->ptep); mm_ops->put_page(ctx->ptep); } return 0; } if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; } else if (stage2_pte_cacheable(pgt, ctx->old)) { need_flush = !stage2_has_fwb(pgt); } /* * This is similar to the map() path in that we unmap the entire * block entry and rely on the remaining portions being faulted * back lazily. */ stage2_unmap_put_pte(ctx, mmu, mm_ops); if (need_flush && mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); if (childp) mm_ops->put_page(childp); return 0; } int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { int ret; struct kvm_pgtable_walker walker = { .cb = stage2_unmap_walker, .arg = pgt, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (stage2_unmap_defer_tlb_flush(pgt)) /* Perform the deferred TLB invalidations */ kvm_tlb_flush_vmid_range(pgt->mmu, addr, size); return ret; } struct stage2_attr_data { kvm_pte_t attr_set; kvm_pte_t attr_clr; kvm_pte_t pte; s8 level; }; static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t pte = ctx->old; struct stage2_attr_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EAGAIN; data->level = ctx->level; data->pte = pte; pte &= ~data->attr_clr; pte |= data->attr_set; /* * We may race with the CPU trying to set the access flag here, * but worst-case the access flag update gets lost and will be * set on the next access instead. */ if (data->pte != pte) { /* * Invalidate instruction cache before updating the guest * stage-2 PTE if we are going to add executable permission. */ if (mm_ops->icache_inval_pou && stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), kvm_granule_size(ctx->level)); if (!stage2_try_set_pte(ctx, pte)) return -EAGAIN; } return 0; } static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, u64 size, kvm_pte_t attr_set, kvm_pte_t attr_clr, kvm_pte_t *orig_pte, s8 *level, enum kvm_pgtable_walk_flags flags) { int ret; kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI; struct stage2_attr_data data = { .attr_set = attr_set & attr_mask, .attr_clr = attr_clr & attr_mask, }; struct kvm_pgtable_walker walker = { .cb = stage2_attr_walker, .arg = &data, .flags = flags | KVM_PGTABLE_WALK_LEAF, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (ret) return ret; if (orig_pte) *orig_pte = data.pte; if (level) *level = data.level; return 0; } int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) { return stage2_update_leaf_attrs(pgt, addr, size, 0, KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, NULL, NULL, 0); } void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags) { int ret; ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, NULL, NULL, flags); if (!ret) dsb(ishst); } struct stage2_age_data { bool mkold; bool young; }; static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF; struct stage2_age_data *data = ctx->arg; if (!kvm_pte_valid(ctx->old) || new == ctx->old) return 0; data->young = true; /* * stage2_age_walker() is always called while holding the MMU lock for * write, so this will always succeed. Nonetheless, this deliberately * follows the race detection pattern of the other stage-2 walkers in * case the locking mechanics of the MMU notifiers is ever changed. */ if (data->mkold && !stage2_try_set_pte(ctx, new)) return -EAGAIN; /* * "But where's the TLBI?!", you scream. * "Over in the core code", I sigh. * * See the '->clear_flush_young()' callback on the KVM mmu notifier. */ return 0; } bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold) { struct stage2_age_data data = { .mkold = mkold, }; struct kvm_pgtable_walker walker = { .cb = stage2_age_walker, .arg = &data, .flags = KVM_PGTABLE_WALK_LEAF, }; WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); return data.young; } int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags) { int ret; s8 level; kvm_pte_t set = 0, clr = 0; if (prot & KVM_PTE_LEAF_ATTR_HI_SW) return -EINVAL; if (prot & KVM_PGTABLE_PROT_R) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (prot & KVM_PGTABLE_PROT_X) clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags); if (!ret || ret == -EAGAIN) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; } static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; if (!stage2_pte_cacheable(pgt, ctx->old)) return 0; if (mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); return 0; } int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm_pgtable_walker walker = { .cb = stage2_flush_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = pgt, }; if (stage2_has_fwb(pgt)) return 0; return kvm_pgtable_walk(pgt, addr, size, &walker); } kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte) { struct stage2_map_data map_data = { .phys = phys, .mmu = pgt->mmu, .memcache = mc, .force_pte = force_pte, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_SKIP_BBM_TLBI | KVM_PGTABLE_WALK_SKIP_CMO, .arg = &map_data, }; /* * The input address (.addr) is irrelevant for walking an * unlinked table. Construct an ambiguous IA range to map * kvm_granule_size(level) worth of memory. */ struct kvm_pgtable_walk_data data = { .walker = &walker, .addr = 0, .end = kvm_granule_size(level), }; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t *pgtable; int ret; if (!IS_ALIGNED(phys, kvm_granule_size(level))) return ERR_PTR(-EINVAL); ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ERR_PTR(ret); pgtable = mm_ops->zalloc_page(mc); if (!pgtable) return ERR_PTR(-ENOMEM); ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable, level + 1); if (ret) { kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level); return ERR_PTR(ret); } return pgtable; } /* * Get the number of page-tables needed to replace a block with a * fully populated tree up to the PTE entries. Note that @level is * interpreted as in "level @level entry". */ static int stage2_block_get_nr_page_tables(s8 level) { switch (level) { case 1: return PTRS_PER_PTE + 1; case 2: return 1; case 3: return 0; default: WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL || level > KVM_PGTABLE_LAST_LEVEL); return -EINVAL; }; } static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; struct kvm_mmu_memory_cache *mc = ctx->arg; struct kvm_s2_mmu *mmu; kvm_pte_t pte = ctx->old, new, *childp; enum kvm_pgtable_prot prot; s8 level = ctx->level; bool force_pte; int nr_pages; u64 phys; /* No huge-pages exist at the last level */ if (level == KVM_PGTABLE_LAST_LEVEL) return 0; /* We only split valid block mappings */ if (!kvm_pte_valid(pte)) return 0; nr_pages = stage2_block_get_nr_page_tables(level); if (nr_pages < 0) return nr_pages; if (mc->nobjs >= nr_pages) { /* Build a tree mapped down to the PTE granularity. */ force_pte = true; } else { /* * Don't force PTEs, so create_unlinked() below does * not populate the tree up to the PTE level. The * consequence is that the call will require a single * page of level 2 entries at level 1, or a single * page of PTEs at level 2. If we are at level 1, the * PTEs will be created recursively. */ force_pte = false; nr_pages = 1; } if (mc->nobjs < nr_pages) return -ENOMEM; mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache); phys = kvm_pte_to_phys(pte); prot = kvm_pgtable_stage2_pte_prot(pte); childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys, level, prot, mc, force_pte); if (IS_ERR(childp)) return PTR_ERR(childp); if (!stage2_try_break_pte(ctx, mmu)) { kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); return -EAGAIN; } /* * Note, the contents of the page table are guaranteed to be made * visible before the new PTE is assigned because stage2_make_pte() * writes the PTE using smp_store_release(). */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc) { struct kvm_pgtable_walker walker = { .cb = stage2_split_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = mc, }; int ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb) { size_t pgd_sz; u64 vtcr = mmu->vtcr; u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = ia_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = mmu; pgt->flags = flags; pgt->force_pte_cb = force_pte_cb; /* Ensure zeroed PGD pages are visible to the hardware walker */ dsb(ishst); return 0; } size_t kvm_pgtable_stage2_pgd_size(u64 vtcr) { u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; } static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_pte_is_counted(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { size_t pgd_sz; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; struct kvm_pgtable_walk_data data = { .walker = &walker, /* * At this point the IPA really doesn't matter, as the page * table being traversed has already been removed from the stage * 2. Set an appropriate range to cover the entire page table. */ .addr = 0, .end = kvm_granule_size(level), }; WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); WARN_ON(mm_ops->page_count(pgtable) != 1); mm_ops->put_page(pgtable); } |
| 172 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * If we have pre-content watches we need to disable readahead to make * sure that we don't find 0 filled pages in cache that we never emitted * events for. Filesystems supporting HSM must make sure to not call * this function with ractl->file unset for files handled by HSM. */ if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) return; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* See the comment in page_cache_sync_ra. */ if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { CLASS(fd, f)(fd); if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || (!S_ISREG(file_inode(fd_file(f))->i_mode) && !S_ISBLK(file_inode(fd_file(f))->i_mode))) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 501 498 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/init.c * * Copyright (C) 1995-2005 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/errno.h> #include <linux/swap.h> #include <linux/init.h> #include <linux/cache.h> #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/gfp.h> #include <linux/math.h> #include <linux/memblock.h> #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/efi.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/hugetlb.h> #include <linux/acpi_iort.h> #include <linux/kmemleak.h> #include <linux/execmem.h> #include <asm/boot.h> #include <asm/fixmap.h> #include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_host.h> #include <asm/memory.h> #include <asm/numa.h> #include <asm/rsi.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> #include <asm/xen/swiotlb-xen.h> /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() * executes, which assigns it its actual value. So use a default value * that cannot be mistaken for a real physical address. */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* * If the corresponding config options are enabled, we create both ZONE_DMA * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, * otherwise it is empty. */ phys_addr_t __ro_after_init arm64_dma_phys_limit; /* * To make optimal use of block mappings when laying out the linear * mapping, round down the base of physical memory to a size that can * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE * (64k granule), or a multiple that can be mapped using contiguous bits * in the page tables: 32 * PMD_SIZE (16k granule) */ #if defined(CONFIG_ARM64_4K_PAGES) #define ARM64_MEMSTART_SHIFT PUD_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT #else #define ARM64_MEMSTART_SHIFT PMD_SHIFT #endif /* * sparsemem vmemmap imposes an additional requirement on the alignment of * memstart_addr, due to the fact that the base of the vmemmap region * has a direct correspondence, and needs to appear sufficiently aligned * in the virtual address space. */ #if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS #define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) #else #define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) #endif static void __init arch_reserve_crashkernel(void) { unsigned long long low_size = 0; unsigned long long crash_base, crash_size; char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) return; reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high); } static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit) { return min(zone_limit, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; phys_addr_t __maybe_unused acpi_zone_dma_limit; phys_addr_t __maybe_unused dt_zone_dma_limit; phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(DMA_BIT_MASK(32)); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address(); dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL); zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit); /* * Information we get from firmware (e.g. DT dma-ranges) describe DMA * bus constraints. Devices using DMA might have their own limitations. * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM * DMA zone on platforms that have RAM there. */ if (memblock_start_of_DRAM() < U32_MAX) zone_dma_limit = min(zone_dma_limit, U32_MAX); arm64_dma_phys_limit = max_zone_phys(zone_dma_limit); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); if (!arm64_dma_phys_limit) arm64_dma_phys_limit = dma32_phys_limit; #endif if (!arm64_dma_phys_limit) arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init(max_zone_pfns); } int pfn_is_map_memory(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn); /* avoid false positives for bogus PFNs, see comment in pfn_valid() */ if (PHYS_PFN(addr) != pfn) return 0; return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_is_map_memory); static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX; /* * Limit the memory size that was specified via FDT. */ static int __init early_mem(char *p) { if (!p) return 1; memory_limit = memparse(p, &p) & PAGE_MASK; pr_notice("Memory limited to %lldMB\n", memory_limit >> 20); return 0; } early_param("mem", early_mem); void __init arm64_memblock_init(void) { s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual); /* * Corner case: 52-bit VA capable systems running KVM in nVHE mode may * be limited in their ability to support a linear map that exceeds 51 * bits of VA space, depending on the placement of the ID map. Given * that the placement of the ID map may be randomized, let's simply * limit the kernel's linear map to 51 bits as well if we detect this * configuration. */ if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 && is_hyp_mode_available() && !is_kernel_in_hyp_mode()) { pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n"); linear_region_size = min_t(u64, linear_region_size, BIT(51)); } /* Remove memory above our supported physical address size */ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX); /* * Select a suitable value for the base of physical memory. */ memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size) pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n"); /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be * high in memory. */ memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa_symbol(_end)), ULLONG_MAX); if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) { /* ensure that memstart_addr remains sufficiently aligned */ memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size, ARM64_MEMSTART_ALIGN); memblock_remove(0, memstart_addr); } /* * If we are running with a 52-bit kernel VA config on a system that * does not support it, we have to place the available physical * memory in the 48-bit addressable part of the linear region, i.e., * we have to move it upward. Since memstart_addr represents the * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible * via the linear mapping. */ if (memory_limit != PHYS_ADDR_MAX) { memblock_mem_limit_remove_map(memory_limit); memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* * Add back the memory we just removed if it results in the * initrd to become inaccessible via the linear mapping. * Otherwise, this is a no-op */ u64 base = phys_initrd_start & PAGE_MASK; u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base; /* * We can only add back the initrd memory if we don't end up * with more memory than we can address via the linear mapping. * It is up to the bootloader to position the kernel and the * initrd reasonably close to each other (i.e., within 32 GB of * each other) so that all granule/#levels combinations can * always access both. */ if (WARN(base < memblock_start_of_DRAM() || base + size > memblock_start_of_DRAM() + linear_region_size, "initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) { phys_initrd_size = 0; } else { memblock_add(base, size); memblock_clear_nomap(base, size); memblock_reserve(base, size); } } if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; /* * Use the sanitised version of id_aa64mmfr0_el1 so that linear * map randomization can be enabled by shrinking the IPA space. */ u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - BIT(id_aa64mmfr0_parange_to_phys_shift(parange)); /* * If the size of the linear region exceeds, by a sufficient * margin, the size of the region that the physical memory can * span, randomize the linear region as well. */ if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) { range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); } } /* * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. */ memblock_reserve(__pa_symbol(_stext), _end - _stext); if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ initrd_start = __phys_to_virt(phys_initrd_start); initrd_end = initrd_start + phys_initrd_size; } early_init_fdt_scan_reserved_mem(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; } void __init bootmem_init(void) { unsigned long min, max; min = PFN_UP(memblock_start_of_DRAM()); max = PFN_DOWN(memblock_end_of_DRAM()); early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); max_pfn = max_low_pfn = max; min_low_pfn = min; arch_numa_init(); /* * must be done after arch_numa_init() which calls numa_init() to * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) arm64_hugetlb_cma_reserve(); #endif kvm_hyp_reserve(); /* * sparse_init() tries to allocate memory from memblock, so must be * done after the fixed reservations */ sparse_init(); zone_sizes_init(); /* * Reserve the CMA area after arm64_dma_phys_limit was initialised. */ dma_contiguous_reserve(arm64_dma_phys_limit); /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ arch_reserve_crashkernel(); memblock_dump_all(); } /* * mem_init() marks the free areas in the mem_map and tells us how much memory * is free. This is done after various parts of the system have claimed their * memory after the kernel image. */ void __init mem_init(void) { unsigned int flags = SWIOTLB_VERBOSE; bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); if (is_realm_world()) { swiotlb = true; flags |= SWIOTLB_FORCE; } if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) { /* * If no bouncing needed for ZONE_DMA, reduce the swiotlb * buffer for kmalloc() bouncing to 1MB per 1GB of RAM. */ unsigned long size = DIV_ROUND_UP(memblock_phys_mem_size(), 1024); swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); swiotlb = true; } swiotlb_init(swiotlb, flags); swiotlb_update_mem_attributes(); /* this will put all unused low memory onto the freelists */ memblock_free_all(); /* * Check boundaries twice: Some fundamental inconsistencies can be * detected at build time already. */ #ifdef CONFIG_COMPAT BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64); #endif /* * Selected page table levels should match when derived from * scratch using the virtual address range and page size. */ BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) != CONFIG_PGTABLE_LEVELS); if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; /* * On a machine this small we won't get anywhere without * overcommit, so turn it on by default. */ sysctl_overcommit_memory = OVERCOMMIT_ALWAYS; } } void free_initmem(void) { void *lm_init_begin = lm_alias(__init_begin); void *lm_init_end = lm_alias(__init_end); WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE)); WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE)); /* Delete __init region from memblock.reserved. */ memblock_free(lm_init_begin, lm_init_end - lm_init_begin); free_reserved_area(lm_init_begin, lm_init_end, POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which * is not supported by kallsyms. */ vunmap_range((u64)__init_begin, (u64)__init_end); } void dump_mem_limit(void) { if (memory_limit != PHYS_ADDR_MAX) { pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); } else { pr_emerg("Memory Limit: none\n"); } } #ifdef CONFIG_EXECMEM static u64 module_direct_base __ro_after_init = 0; static u64 module_plt_base __ro_after_init = 0; /* * Choose a random page-aligned base address for a window of 'size' bytes which * entirely contains the interval [start, end - 1]. */ static u64 __init random_bounding_box(u64 size, u64 start, u64 end) { u64 max_pgoff, pgoff; if ((end - start) >= size) return 0; max_pgoff = (size - (end - start)) / PAGE_SIZE; pgoff = get_random_u32_inclusive(0, max_pgoff); return start - pgoff * PAGE_SIZE; } /* * Modules may directly reference data and text anywhere within the kernel * image and other modules. References using PREL32 relocations have a +/-2G * range, and so we need to ensure that the entire kernel image and all modules * fall within a 2G window such that these are always within range. * * Modules may directly branch to functions and code within the kernel text, * and to functions and code within other modules. These branches will use * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure * that the entire kernel text and all module text falls within a 128M window * such that these are always within range. With PLTs, we can expand this to a * 2G window. * * We chose the 128M region to surround the entire kernel image (rather than * just the text) as using the same bounds for the 128M and 2G regions ensures * by construction that we never select a 128M region that is not a subset of * the 2G region. For very large and unusual kernel configurations this means * we may fall back to PLTs where they could have been avoided, but this keeps * the logic significantly simpler. */ static int __init module_init_limits(void) { u64 kernel_end = (u64)_end; u64 kernel_start = (u64)_text; u64 kernel_size = kernel_end - kernel_start; /* * The default modules region is placed immediately below the kernel * image, and is large enough to use the full 2G relocation range. */ BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END); BUILD_BUG_ON(MODULES_VSIZE < SZ_2G); if (!kaslr_enabled()) { if (kernel_size < SZ_128M) module_direct_base = kernel_end - SZ_128M; if (kernel_size < SZ_2G) module_plt_base = kernel_end - SZ_2G; } else { u64 min = kernel_start; u64 max = kernel_end; if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n"); } else { module_direct_base = random_bounding_box(SZ_128M, min, max); if (module_direct_base) { min = module_direct_base; max = module_direct_base + SZ_128M; } } module_plt_base = random_bounding_box(SZ_2G, min, max); } pr_info("%llu pages in range for non-PLT usage", module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0); pr_info("%llu pages in range for PLT usage", module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0); return 0; } static struct execmem_info execmem_info __ro_after_init; struct execmem_info __init *execmem_arch_setup(void) { unsigned long fallback_start = 0, fallback_end = 0; unsigned long start = 0, end = 0; module_init_limits(); /* * Where possible, prefer to allocate within direct branch range of the * kernel such that no PLTs are necessary. */ if (module_direct_base) { start = module_direct_base; end = module_direct_base + SZ_128M; if (module_plt_base) { fallback_start = module_plt_base; fallback_end = module_plt_base + SZ_2G; } } else if (module_plt_base) { start = module_plt_base; end = module_plt_base + SZ_2G; } execmem_info = (struct execmem_info){ .ranges = { [EXECMEM_DEFAULT] = { .start = start, .end = end, .pgprot = PAGE_KERNEL, .alignment = 1, .fallback_start = fallback_start, .fallback_end = fallback_end, }, [EXECMEM_KPROBES] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL_ROX, .alignment = 1, }, [EXECMEM_BPF] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL, .alignment = 1, }, }, }; return &execmem_info; } #endif /* CONFIG_EXECMEM */ |
| 3 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct work_struct work; struct net_device *dev; u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; bool may_sleep; if (!utn->need_sync) return; /* Drivers which sleep in the callback need to update from * the workqueue, if we come from the tunnel driver's notification. */ may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (!may_sleep) __udp_tunnel_nic_device_sync(dev, utn); if (may_sleep || utn->need_replay) { queue_work(udp_tunnel_nic_workqueue, &utn->work); utn->work_pending = 1; } } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; ASSERT_RTNL(); utn = dev->udp_tunnel_nic; if (!utn) return; utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release rtnl across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) udp_tunnel_get_rx_info(dev); return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) return; list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. */ if (utn->work_pending) return; udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_flush(dev, utn); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL"); |
| 16 15 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Hyp portion of the (not much of an) Emulation layer for 32bit guests. * * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * based on arch/arm/kvm/emulate.c * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> /* * stolen from arch/arm/kernel/opcodes.c * * condition code lookup table * index into the table is test code: EQ, NE, ... LT, GT, AL, NV * * bit position in short is condition code: NZCV */ static const unsigned short cc_map[16] = { 0xF0F0, /* EQ == Z set */ 0x0F0F, /* NE */ 0xCCCC, /* CS == C set */ 0x3333, /* CC */ 0xFF00, /* MI == N set */ 0x00FF, /* PL */ 0xAAAA, /* VS == V set */ 0x5555, /* VC */ 0x0C0C, /* HI == C set && Z clear */ 0xF3F3, /* LS == C clear || Z set */ 0xAA55, /* GE == (N==V) */ 0x55AA, /* LT == (N!=V) */ 0x0A05, /* GT == (!Z && (N==V)) */ 0xF5FA, /* LE == (Z || (N!=V)) */ 0xFFFF, /* AL always */ 0 /* NV */ }; /* * Check if a trapped instruction should have been executed or not. */ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) { unsigned long cpsr; u32 cpsr_cond; int cond; /* * These are the exception classes that could fire with a * conditional instruction. */ switch (kvm_vcpu_trap_get_class(vcpu)) { case ESR_ELx_EC_CP15_32: case ESR_ELx_EC_CP15_64: case ESR_ELx_EC_CP14_MR: case ESR_ELx_EC_CP14_LS: case ESR_ELx_EC_FP_ASIMD: case ESR_ELx_EC_CP10_ID: case ESR_ELx_EC_CP14_64: case ESR_ELx_EC_SVC32: break; default: return true; } /* Is condition field valid? */ cond = kvm_vcpu_get_condition(vcpu); if (cond == 0xE) return true; cpsr = *vcpu_cpsr(vcpu); if (cond < 0) { /* This can happen in Thumb mode: examine IT state. */ unsigned long it; it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); /* it == 0 => unconditional. */ if (it == 0) return true; /* The cond for this insn works out as the top 4 bits. */ cond = (it >> 4); } cpsr_cond = cpsr >> 28; if (!((cc_map[cond] >> cpsr_cond) & 1)) return false; return true; } /** * kvm_adjust_itstate - adjust ITSTATE when emulating instructions in IT-block * @vcpu: The VCPU pointer * * When exceptions occur while instructions are executed in Thumb IF-THEN * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have * to do this little bit of work manually. The fields map like this: * * IT[7:0] -> CPSR[26:25],CPSR[15:10] */ static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) { unsigned long itbits, cond; unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_arm = !(cpsr & PSR_AA32_T_BIT); if (is_arm || !(cpsr & PSR_AA32_IT_MASK)) return; cond = (cpsr & 0xe000) >> 13; itbits = (cpsr & 0x1c00) >> (10 - 2); itbits |= (cpsr & (0x3 << 25)) >> 25; /* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */ if ((itbits & 0x7) == 0) itbits = cond = 0; else itbits = (itbits << 1) & 0x1f; cpsr &= ~PSR_AA32_IT_MASK; cpsr |= cond << 13; cpsr |= (itbits & 0x1c) << (10 - 2); cpsr |= (itbits & 0x3) << 25; *vcpu_cpsr(vcpu) = cpsr; } /** * kvm_skip_instr32 - skip a trapped instruction and proceed to the next * @vcpu: The vcpu pointer */ void kvm_skip_instr32(struct kvm_vcpu *vcpu) { u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !kvm_vcpu_trap_il_is32bit(vcpu)) pc += 2; else pc += 4; *vcpu_pc(vcpu) = pc; kvm_adjust_itstate(vcpu); } |
| 306 307 306 306 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/dax.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover the anon, shmem and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. * Shmem pmd-sized hugepages are also determined by its pmd-size control, * except when the global shmem_huge is set to SHMEM_HUGE_DENY. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static inline int check_pmd_state(pmd_t *pmd) { pmd_t pmde = pmdp_get_lockless(pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; return check_pmd_state(*pmd); } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { /* * Here the ptl is only used to check pte_same() in * do_swap_page(), so readonly version is enough. */ pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) goto abort; /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) { spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) { flush_tlb_mm(mm); goto unlock; } } } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); pte_unmap_unlock(start_pte, ptl); if (ptl != pml) spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } unlock: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool success = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); /* * The lock of new_folio is still held, we will be blocked in * the page fault path, which prevents the pte entries from * being set again. So even though the old empty PTE page may be * concurrently freed and a new PTE page is filled into the pmd * entry, it is still empty and can be removed. * * So here we only need to recheck if the state of pmd entry * still meets our requirements, rather than checking pmd_same() * like elsewhere. */ if (check_pmd_state(pmd) != SCAN_SUCCEED) goto drop_pml; ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); success = true; } if (ptl != pml) spin_unlock(ptl); drop_pml: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (success) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; mapping_set_update(&xas, mapping); __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure i_writecount is up to date and the update to nr_thps * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This is <linux/capability.h> * * Andrew G. Morgan <morgan@kernel.org> * Alexander Kjeldaas <astor@guardian.no> * with help from Aleph1, Roland Buresund and Andrew Main. * * See here for the libcap library ("POSIX draft" compliance): * * ftp://www.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/ */ #ifndef _LINUX_CAPABILITY_H #define _LINUX_CAPABILITY_H #include <uapi/linux/capability.h> #include <linux/uidgid.h> #include <linux/bits.h> #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 extern int file_caps_enabled; typedef struct { u64 val; } kernel_cap_t; /* same as vfs_ns_cap_data but in cpu endian and always filled completely */ struct cpu_vfs_cap_data { __u32 magic_etc; kuid_t rootid; kernel_cap_t permitted; kernel_cap_t inheritable; }; #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) struct file; struct inode; struct dentry; struct task_struct; struct user_namespace; struct mnt_idmap; /* * CAP_FS_MASK and CAP_NFSD_MASKS: * * The fs mask is all the privileges that fsuid==0 historically meant. * At one time in the past, that included CAP_MKNOD and CAP_LINUX_IMMUTABLE. * * It has never meant setting security.* and trusted.* xattrs. * * We could also define fsmask as follows: * 1. CAP_FS_MASK is the privilege to bypass all fs-related DAC permissions * 2. The security.* and trusted.* xattrs are fs-related MAC permissions */ # define CAP_FS_MASK (BIT_ULL(CAP_CHOWN) \ | BIT_ULL(CAP_MKNOD) \ | BIT_ULL(CAP_DAC_OVERRIDE) \ | BIT_ULL(CAP_DAC_READ_SEARCH) \ | BIT_ULL(CAP_FOWNER) \ | BIT_ULL(CAP_FSETID) \ | BIT_ULL(CAP_MAC_OVERRIDE)) #define CAP_VALID_MASK (BIT_ULL(CAP_LAST_CAP+1)-1) # define CAP_EMPTY_SET ((kernel_cap_t) { 0 }) # define CAP_FULL_SET ((kernel_cap_t) { CAP_VALID_MASK }) # define CAP_FS_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_LINUX_IMMUTABLE) }) # define CAP_NFSD_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_SYS_RESOURCE) }) # define cap_clear(c) do { (c).val = 0; } while (0) #define cap_raise(c, flag) ((c).val |= BIT_ULL(flag)) #define cap_lower(c, flag) ((c).val &= ~BIT_ULL(flag)) #define cap_raised(c, flag) (((c).val & BIT_ULL(flag)) != 0) static inline kernel_cap_t cap_combine(const kernel_cap_t a, const kernel_cap_t b) { return (kernel_cap_t) { a.val | b.val }; } static inline kernel_cap_t cap_intersect(const kernel_cap_t a, const kernel_cap_t b) { return (kernel_cap_t) { a.val & b.val }; } static inline kernel_cap_t cap_drop(const kernel_cap_t a, const kernel_cap_t drop) { return (kernel_cap_t) { a.val &~ drop.val }; } static inline bool cap_isclear(const kernel_cap_t a) { return !a.val; } static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b) { return a.val == b.val; } /* * Check if "a" is a subset of "set". * return true if ALL of the capabilities in "a" are also in "set" * cap_issubset(0101, 1111) will return true * return false if ANY of the capabilities in "a" are not in "set" * cap_issubset(1111, 0101) will return false */ static inline bool cap_issubset(const kernel_cap_t a, const kernel_cap_t set) { return !(a.val & ~set.val); } /* Used to decide between falling back on the old suser() or fsuser(). */ static inline kernel_cap_t cap_drop_fs_set(const kernel_cap_t a) { return cap_drop(a, CAP_FS_SET); } static inline kernel_cap_t cap_raise_fs_set(const kernel_cap_t a, const kernel_cap_t permitted) { return cap_combine(a, cap_intersect(permitted, CAP_FS_SET)); } static inline kernel_cap_t cap_drop_nfsd_set(const kernel_cap_t a) { return cap_drop(a, CAP_NFSD_SET); } static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a, const kernel_cap_t permitted) { return cap_combine(a, cap_intersect(permitted, CAP_NFSD_SET)); } #ifdef CONFIG_MULTIUSER extern bool has_capability(struct task_struct *t, int cap); extern bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap); extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); extern bool ns_capable_setid(struct user_namespace *ns, int cap); #else static inline bool has_capability(struct task_struct *t, int cap) { return true; } static inline bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { return true; } static inline bool has_capability_noaudit(struct task_struct *t, int cap) { return true; } static inline bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { return true; } static inline bool capable(int cap) { return true; } static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; } static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return true; } static inline bool ns_capable_setid(struct user_namespace *ns, int cap) { return true; } #endif /* CONFIG_MULTIUSER */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode); bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); static inline bool perfmon_capable(void) { return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); } static inline bool bpf_capable(void) { return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); } static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) { return ns_capable(ns, CAP_CHECKPOINT_RESTORE) || ns_capable(ns, CAP_SYS_ADMIN); } /* audit system wants to get cap info from files as well */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ |
| 160 159 161 161 159 159 160 160 161 9 9 2 92 92 111 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/irqflags.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/tlbflush.h> struct tlb_inv_context { struct kvm_s2_mmu *mmu; unsigned long flags; u64 tcr; u64 sctlr; }; static void enter_vmid_context(struct kvm_s2_mmu *mmu, struct tlb_inv_context *cxt) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); u64 val; local_irq_save(cxt->flags); if (vcpu && mmu != vcpu->arch.hw_mmu) cxt->mmu = vcpu->arch.hw_mmu; else cxt->mmu = NULL; if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* * For CPUs that are affected by ARM errata 1165522 or 1530923, * we cannot trust stage-1 to be in a correct state at that * point. Since we do not want to force a full load of the * vcpu state, we prevent the EL1 page-table walker to * allocate new TLBs. This is done by setting the EPD bits * in the TCR_EL1 register. We also need to prevent it to * allocate IPA->PA walks, so we enable the S1 MMU... */ val = cxt->tcr = read_sysreg_el1(SYS_TCR); val |= TCR_EPD1_MASK | TCR_EPD0_MASK; write_sysreg_el1(val, SYS_TCR); val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); val |= SCTLR_ELx_M; write_sysreg_el1(val, SYS_SCTLR); } /* * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and * most TLB operations target EL2/EL0. In order to affect the * guest TLBs (EL1/EL0), we need to change one of these two * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so * let's flip TGE before executing the TLB operation. * * ARM erratum 1165522 requires some special handling (again), * as we need to make sure both stages of translation are in * place before clearing TGE. __load_stage2() already * has an ISB in order to deal with this. */ __load_stage2(mmu, mmu->arch); val = read_sysreg(hcr_el2); val &= ~HCR_TGE; write_sysreg(val, hcr_el2); isb(); } static void exit_vmid_context(struct tlb_inv_context *cxt) { /* * We're done with the TLB operation, let's restore the host's * view of HCR_EL2. */ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); isb(); /* ... and the stage-2 MMU context that we switched away from */ if (cxt->mmu) __load_stage2(cxt->mmu, cxt->mmu->arch); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* Restore the registers to what they were */ write_sysreg_el1(cxt->tcr, SYS_TCR); write_sysreg_el1(cxt->sctlr, SYS_SCTLR); } local_irq_restore(cxt->flags); } void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa, int level) { struct tlb_inv_context cxt; dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); /* * We could do so much better if we had the VA as well. * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ ipa >>= 12; __tlbi_level(ipas2e1is, ipa, level); /* * We have to ensure completion of the invalidation at Stage-2, * since a table walk on another CPU could refill a TLB with a * complete (S1 + S2) walk based on the old Stage-2 mapping if * the Stage-1 invalidation happened first. */ dsb(ish); __tlbi(vmalle1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu, phys_addr_t ipa, int level) { struct tlb_inv_context cxt; dsb(nshst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); /* * We could do so much better if we had the VA as well. * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ ipa >>= 12; __tlbi_level(ipas2e1, ipa, level); /* * We have to ensure completion of the invalidation at Stage-2, * since a table walk on another CPU could refill a TLB with a * complete (S1 + S2) walk based on the old Stage-2 mapping if * the Stage-1 invalidation happened first. */ dsb(nsh); __tlbi(vmalle1); dsb(nsh); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t start, unsigned long pages) { struct tlb_inv_context cxt; unsigned long stride; /* * Since the range of addresses may not be mapped at * the same level, assume the worst case as PAGE_SIZE */ stride = PAGE_SIZE; start = round_down(start, stride); dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) { struct tlb_inv_context cxt; dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) { struct tlb_inv_context cxt; /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __tlbi(vmalle1); asm volatile("ic iallu"); dsb(nsh); isb(); exit_vmid_context(&cxt); } void __kvm_flush_vm_context(void) { dsb(ishst); __tlbi(alle1is); dsb(ish); } /* * TLB invalidation emulation for NV. For any given instruction, we * perform the following transformtions: * * - a TLBI targeting EL2 S1 is remapped to EL1 S1 * - a non-shareable TLBI is upgraded to being inner-shareable * - an outer-shareable TLBI is also mapped to inner-shareable * - an nXS TLBI is upgraded to XS */ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding) { struct tlb_inv_context cxt; int ret = 0; /* * The guest will have provided its own DSB ISHST before trapping. * If it hasn't, that's its own problem, and we won't paper over it * (plus, there is plenty of extra synchronisation before we even * get here...). */ if (mmu) enter_vmid_context(mmu, &cxt); switch (sys_encoding) { case OP_TLBI_ALLE2: case OP_TLBI_ALLE2IS: case OP_TLBI_ALLE2OS: case OP_TLBI_VMALLE1: case OP_TLBI_VMALLE1IS: case OP_TLBI_VMALLE1OS: case OP_TLBI_ALLE2NXS: case OP_TLBI_ALLE2ISNXS: case OP_TLBI_ALLE2OSNXS: case OP_TLBI_VMALLE1NXS: case OP_TLBI_VMALLE1ISNXS: case OP_TLBI_VMALLE1OSNXS: __tlbi(vmalle1is); break; case OP_TLBI_VAE2: case OP_TLBI_VAE2IS: case OP_TLBI_VAE2OS: case OP_TLBI_VAE1: case OP_TLBI_VAE1IS: case OP_TLBI_VAE1OS: case OP_TLBI_VAE2NXS: case OP_TLBI_VAE2ISNXS: case OP_TLBI_VAE2OSNXS: case OP_TLBI_VAE1NXS: case OP_TLBI_VAE1ISNXS: case OP_TLBI_VAE1OSNXS: __tlbi(vae1is, va); break; case OP_TLBI_VALE2: case OP_TLBI_VALE2IS: case OP_TLBI_VALE2OS: case OP_TLBI_VALE1: case OP_TLBI_VALE1IS: case OP_TLBI_VALE1OS: case OP_TLBI_VALE2NXS: case OP_TLBI_VALE2ISNXS: case OP_TLBI_VALE2OSNXS: case OP_TLBI_VALE1NXS: case OP_TLBI_VALE1ISNXS: case OP_TLBI_VALE1OSNXS: __tlbi(vale1is, va); break; case OP_TLBI_ASIDE1: case OP_TLBI_ASIDE1IS: case OP_TLBI_ASIDE1OS: case OP_TLBI_ASIDE1NXS: case OP_TLBI_ASIDE1ISNXS: case OP_TLBI_ASIDE1OSNXS: __tlbi(aside1is, va); break; case OP_TLBI_VAAE1: case OP_TLBI_VAAE1IS: case OP_TLBI_VAAE1OS: case OP_TLBI_VAAE1NXS: case OP_TLBI_VAAE1ISNXS: case OP_TLBI_VAAE1OSNXS: __tlbi(vaae1is, va); break; case OP_TLBI_VAALE1: case OP_TLBI_VAALE1IS: case OP_TLBI_VAALE1OS: case OP_TLBI_VAALE1NXS: case OP_TLBI_VAALE1ISNXS: case OP_TLBI_VAALE1OSNXS: __tlbi(vaale1is, va); break; case OP_TLBI_RVAE2: case OP_TLBI_RVAE2IS: case OP_TLBI_RVAE2OS: case OP_TLBI_RVAE1: case OP_TLBI_RVAE1IS: case OP_TLBI_RVAE1OS: case OP_TLBI_RVAE2NXS: case OP_TLBI_RVAE2ISNXS: case OP_TLBI_RVAE2OSNXS: case OP_TLBI_RVAE1NXS: case OP_TLBI_RVAE1ISNXS: case OP_TLBI_RVAE1OSNXS: __tlbi(rvae1is, va); break; case OP_TLBI_RVALE2: case OP_TLBI_RVALE2IS: case OP_TLBI_RVALE2OS: case OP_TLBI_RVALE1: case OP_TLBI_RVALE1IS: case OP_TLBI_RVALE1OS: case OP_TLBI_RVALE2NXS: case OP_TLBI_RVALE2ISNXS: case OP_TLBI_RVALE2OSNXS: case OP_TLBI_RVALE1NXS: case OP_TLBI_RVALE1ISNXS: case OP_TLBI_RVALE1OSNXS: __tlbi(rvale1is, va); break; case OP_TLBI_RVAAE1: case OP_TLBI_RVAAE1IS: case OP_TLBI_RVAAE1OS: case OP_TLBI_RVAAE1NXS: case OP_TLBI_RVAAE1ISNXS: case OP_TLBI_RVAAE1OSNXS: __tlbi(rvaae1is, va); break; case OP_TLBI_RVAALE1: case OP_TLBI_RVAALE1IS: case OP_TLBI_RVAALE1OS: case OP_TLBI_RVAALE1NXS: case OP_TLBI_RVAALE1ISNXS: case OP_TLBI_RVAALE1OSNXS: __tlbi(rvaale1is, va); break; default: ret = -EINVAL; } dsb(ish); isb(); if (mmu) exit_vmid_context(&cxt); return ret; } |
| 235 54 54 128 235 46 202 235 234 234 233 202 129 201 202 129 128 200 164 112 200 202 46 202 201 202 128 129 129 129 129 129 202 201 46 46 46 129 129 30 30 309 19 369 368 395 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment on MAX_NR_TIERS */ return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); if (!(flags & BIT(PG_referenced))) return 0; /* * Return the total number of accesses including PG_referenced. Also see * the comment on LRU_REFS_FLAGS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ * | Accessed through page tables and | Accessed through file descriptors | * | promoted by folio_update_gen() | and protected by folio_inc_gen() | * +-----------------------------------+-----------------------------------+ * | PG_active (set while isolated) | | * +-----------------+-----------------+-----------------+-----------------+ * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | * +-----------------------------------+-----------------------------------+ * |<---------- MIN_NR_GENS ---------->| | * |<---------------------------- MAX_NR_GENS ---------------------------->| */ if (folio_test_active(folio)) gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming) gen = MAX_NR_GENS; else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) gen = MIN_NR_GENS; else gen = MAX_NR_GENS - folio_test_workingset(folio); return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * Returns true if an uffd-wp pte was installed, false otherwise. */ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } #endif return false; } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 18 19 19 19 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 | // SPDX-License-Identifier: GPL-2.0-or-later /* auditfilter.c -- filtering of audit events * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. * Copyright 2005 IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <net/net_namespace.h> #include <net/sock.h> #include "audit.h" /* * Locking model: * * audit_filter_mutex: * Synchronizes writes and blocking reads of audit's filterlist * data. Rcu is used to traverse the filterlist and access * contents of structs audit_entry, audit_watch and opaque * LSM rules during filtering. If modified, these structures * must be copied and replace their counterparts in the filterlist. * An audit_parent struct is not accessed during filtering, so may * be written directly provided audit_filter_mutex is held. */ /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), LIST_HEAD_INIT(audit_filter_list[1]), LIST_HEAD_INIT(audit_filter_list[2]), LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), LIST_HEAD_INIT(audit_filter_list[7]), #if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[0]), LIST_HEAD_INIT(audit_rules_list[1]), LIST_HEAD_INIT(audit_rules_list[2]), LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); static void audit_free_lsm_field(struct audit_field *f) { switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: kfree(f->lsm_str); security_audit_rule_free(f->lsm_rule); } } static inline void audit_free_rule(struct audit_entry *e) { int i; struct audit_krule *erule = &e->rule; /* some rules don't have associated watches */ if (erule->watch) audit_put_watch(erule->watch); if (erule->fields) for (i = 0; i < erule->field_count; i++) audit_free_lsm_field(&erule->fields[i]); kfree(erule->fields); kfree(erule->filterkey); kfree(e); } void audit_free_rule_rcu(struct rcu_head *head) { struct audit_entry *e = container_of(head, struct audit_entry, rcu); audit_free_rule(e); } /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { struct audit_entry *entry; struct audit_field *fields; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (unlikely(!entry)) return NULL; fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); if (unlikely(!fields)) { kfree(entry); return NULL; } entry->rule.fields = fields; return entry; } /* Unpack a filter field's string representation from user-space * buffer. */ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) { char *str; if (!*bufp || (len == 0) || (len > *remain)) return ERR_PTR(-EINVAL); /* Of the currently implemented string fields, PATH_MAX * defines the longest valid length. */ if (len > PATH_MAX) return ERR_PTR(-ENAMETOOLONG); str = kmalloc(len + 1, GFP_KERNEL); if (unlikely(!str)) return ERR_PTR(-ENOMEM); memcpy(str, *bufp, len); str[len] = 0; *bufp += len; *remain -= len; return str; } /* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if ((krule->listnr != AUDIT_FILTER_EXIT && krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; return 0; } static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { unsigned n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; } p[AUDIT_WORD(n)] |= AUDIT_BIT(n); } if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { kfree(p); return -EINVAL; } classes[class] = p; return 0; } int audit_match_class(int class, unsigned syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) return 0; return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); } #ifdef CONFIG_AUDITSYSCALL static inline int audit_match_class_bits(int class, u32 *mask) { int i; if (classes[class]) { for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (mask[i] & classes[class][i]) return 0; } return 1; } static int audit_match_signal(struct audit_entry *entry) { struct audit_field *arch = entry->rule.arch_f; if (!arch) { /* When arch is unspecified, we must check both masks on biarch * as syscall number alone is ambiguous. */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask) && audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); } switch (audit_classify_arch(arch->val)) { case 0: /* native */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask)); case 1: /* 32bit on biarch */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); default: return 1; } } #endif /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; int i, err; err = -EINVAL; listnr = rule->flags & ~AUDIT_FILTER_PREPEND; switch (listnr) { default: goto exit_err; #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) goto exit_err; if (rule->field_count > AUDIT_MAX_FIELDS) goto exit_err; err = -ENOMEM; entry = audit_init_entry(rule->field_count); if (!entry) goto exit_err; entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; entry->rule.listnr = listnr; entry->rule.action = rule->action; entry->rule.field_count = rule->field_count; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; __u32 *class; if (!(*p & AUDIT_BIT(bit))) continue; *p &= ~AUDIT_BIT(bit); class = classes[i]; if (class) { int j; for (j = 0; j < AUDIT_BITMASK_SIZE; j++) entry->rule.mask[j] |= class[j]; } } return entry; exit_err: return ERR_PTR(err); } static u32 audit_ops[] = { [Audit_equal] = AUDIT_EQUAL, [Audit_not_equal] = AUDIT_NOT_EQUAL, [Audit_bitmask] = AUDIT_BIT_MASK, [Audit_bittest] = AUDIT_BIT_TEST, [Audit_lt] = AUDIT_LESS_THAN, [Audit_gt] = AUDIT_GREATER_THAN, [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, }; static u32 audit_to_op(u32 op) { u32 n; for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) ; return n; } /* check if an audit field is valid */ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch (f->type) { case AUDIT_MSGTYPE: if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; case AUDIT_FSTYPE: if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; case AUDIT_PERM: if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) return -EINVAL; break; } switch (entry->rule.listnr) { case AUDIT_FILTER_FS: switch (f->type) { case AUDIT_FSTYPE: case AUDIT_FILTERKEY: break; default: return -EINVAL; } } /* Check for valid field type and op */ switch (f->type) { case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: case AUDIT_PERS: /* <uapi/linux/personality.h> */ case AUDIT_DEVMINOR: /* all ops are valid */ break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: case AUDIT_PID: case AUDIT_MSGTYPE: case AUDIT_PPID: case AUDIT_DEVMAJOR: case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: case AUDIT_SESSIONID: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: case AUDIT_SADDR_FAM: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_WATCH: case AUDIT_DIR: case AUDIT_FILTERKEY: case AUDIT_LOGINUID_SET: case AUDIT_ARCH: case AUDIT_FSTYPE: case AUDIT_PERM: case AUDIT_FILETYPE: case AUDIT_FIELD_COMPARE: case AUDIT_EXE: /* only equal and not equal valid ops */ if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; default: /* field not recognized */ return -EINVAL; } /* Check for select valid field values */ switch (f->type) { case AUDIT_LOGINUID_SET: if ((f->val != 0) && (f->val != 1)) return -EINVAL; break; case AUDIT_PERM: if (f->val & ~15) return -EINVAL; break; case AUDIT_FILETYPE: if (f->val & ~S_IFMT) return -EINVAL; break; case AUDIT_FIELD_COMPARE: if (f->val > AUDIT_MAX_FIELD_COMPARE) return -EINVAL; break; case AUDIT_SADDR_FAM: if (f->val >= AF_MAX) return -EINVAL; break; default: break; } return 0; } /* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { int err = 0; struct audit_entry *entry; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; char *str; struct audit_fsnotify_mark *audit_mark; entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; u32 f_val; err = -EINVAL; f->op = audit_to_op(data->fieldflags[i]); if (f->op == Audit_bad) goto exit_free; f->type = data->fields[i]; f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); if (err) goto exit_free; err = -EINVAL; switch (f->type) { case AUDIT_LOGINUID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; } else if (err) goto exit_free; break; case AUDIT_WATCH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } entry->rule.buflen += f_val; break; case AUDIT_DIR: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; entry->rule.buflen += f_val; break; case AUDIT_INODE: f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; default: f->val = f_val; break; } } if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) entry->rule.inode_f = NULL; exit_nofree: return entry; exit_free: if (entry->rule.tree) audit_put_tree(entry->rule.tree); /* that's the temporary one */ if (entry->rule.exe) audit_remove_mark(entry->rule.exe); /* that's the template one */ audit_free_rule(entry); return ERR_PTR(err); } /* Pack a filter field's string representation into data block. */ static inline size_t audit_pack_string(void **bufp, const char *str) { size_t len = strlen(str); memcpy(*bufp, str, len); *bufp += len; return len; } /* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; void *bufp; int i; data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL); if (unlikely(!data)) return NULL; memset(data, 0, sizeof(*data)); data->flags = krule->flags | krule->listnr; data->action = krule->action; data->field_count = krule->field_count; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; data->fieldflags[i] = audit_ops[f->op]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->lsm_str); break; case AUDIT_WATCH: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_tree_path(krule->tree)); break; case AUDIT_FILTERKEY: data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; case AUDIT_EXE: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; data->values[i] = AUDIT_UID_UNSET; break; } fallthrough; /* if set */ default: data->values[i] = f->val; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; return data; } /* Compare two rules in kernel format. Considered success if rules * don't match. */ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) { int i; if (a->flags != b->flags || a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) return 1; for (i = 0; i < a->field_count; i++) { if (a->fields[i].type != b->fields[i].type || a->fields[i].op != b->fields[i].op) return 1; switch (a->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) return 1; break; case AUDIT_WATCH: if (strcmp(audit_watch_path(a->watch), audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: if (strcmp(audit_tree_path(a->tree), audit_tree_path(b->tree))) return 1; break; case AUDIT_FILTERKEY: /* both filterkeys exist based on above type compare */ if (strcmp(a->filterkey, b->filterkey)) return 1; break; case AUDIT_EXE: /* both paths exist based on above type compare */ if (strcmp(audit_mark_path(a->exe), audit_mark_path(b->exe))) return 1; break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) return 1; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; default: if (a->fields[i].val != b->fields[i].val) return 1; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (a->mask[i] != b->mask[i]) return 1; return 0; } /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { int ret; char *lsm_str; /* our own copy of lsm_str */ lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); if (unlikely(!lsm_str)) return -ENOMEM; df->lsm_str = lsm_str; /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", df->lsm_str); ret = 0; } return ret; } /* Duplicate an audit rule. This will be a deep copy with the exception * of the watch - that pointer is carried over. The LSM specific fields * will be updated in the copy. The point is to be able to replace the old * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ struct audit_entry *audit_dupe_rule(struct audit_krule *old) { u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; char *fk; int i, err = 0; entry = audit_init_entry(fcount); if (unlikely(!entry)) return ERR_PTR(-ENOMEM); new = &entry->rule; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->field_count = old->field_count; /* * note that we are OK with not refcounting here; audit_match_tree() * never dereferences tree and we can't get false positives there * since we'd have to have rule gone from the list *and* removed * before the chunks found by lookup had been allocated, i.e. before * the beginning of list scan. */ new->tree = old->tree; memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); /* deep copy this information, updating the lsm_rule fields, because * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_lsm_field(&new->fields[i], &old->fields[i]); break; case AUDIT_FILTERKEY: fk = kstrdup(old->filterkey, GFP_KERNEL); if (unlikely(!fk)) err = -ENOMEM; else new->filterkey = fk; break; case AUDIT_EXE: err = audit_dupe_exe(new, old); break; } if (err) { if (new->exe) audit_remove_mark(new->exe); audit_free_rule(entry); return ERR_PTR(err); } } if (old->watch) { audit_get_watch(old->watch); new->watch = old->watch; } return entry; } /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, struct list_head **p) { struct audit_entry *e, *found = NULL; struct list_head *list; int h; if (entry->rule.inode_f) { h = audit_hash_ino(entry->rule.inode_f->val); *p = list = &audit_inode_hash[h]; } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } } goto out; } else { *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } out: return found; } static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; /* Add rule to given filterlist if not a duplicate. */ static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int err = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (e) { mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) audit_put_tree(tree); return err; } if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); /* * normally audit_add_tree_rule() will free it * on failure */ if (tree) audit_put_tree(tree); return err; } } if (tree) { err = audit_add_tree_rule(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); return err; } } entry->rule.prio = ~0ULL; if (entry->rule.listnr == AUDIT_FILTER_EXIT || entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else entry->rule.prio = --prio_low; } if (entry->rule.flags & AUDIT_FILTER_PREPEND) { list_add(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { list_add_tail(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules++; if (!audit_match_signal(entry)) audit_signals++; #endif mutex_unlock(&audit_filter_mutex); return err; } /* Remove an existing rule from filterlist. */ int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (!e) { ret = -ENOENT; goto out; } if (e->rule.watch) audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); if (e->rule.exe) audit_remove_mark_rule(&e->rule); #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules--; if (!audit_match_signal(entry)) audit_signals--; #endif list_del_rcu(&e->list); list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: mutex_unlock(&audit_filter_mutex); if (tree) audit_put_tree(tree); /* that's the temporary one */ return ret; } /* List rules using struct audit_rule_data. */ static void audit_list_rules(int seq, struct sk_buff_head *q) { struct sk_buff *skb; struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1, data, struct_size(data, buf, data->buflen)); if (skb) skb_queue_tail(q, skb); kfree(data); } } skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); if (skb) skb_queue_tail(q, skb); } /* Log rule additions and removals */ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } /** * audit_rule_change - apply all rules to the specified message type * @type: audit message type * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data */ int audit_rule_change(int type, int seq, void *data, size_t datasz) { int err = 0; struct audit_entry *entry; switch (type) { case AUDIT_ADD_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: WARN_ON(1); return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); } return err; } /** * audit_list_rules_send - list the audit rules * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { struct task_struct *tsk; struct audit_netlink_list *dest; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for * auditctl to read from it... which isn't ever going to * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); put_net(dest->net); kfree(dest); return PTR_ERR(tsk); } return 0; } int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { case Audit_equal: return (left == right); case Audit_not_equal: return (left != right); case Audit_lt: return (left < right); case Audit_le: return (left <= right); case Audit_gt: return (left > right); case Audit_ge: return (left >= right); case Audit_bitmask: return (left & right); case Audit_bittest: return ((left & right) == right); default: return 0; } } int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { case Audit_equal: return uid_eq(left, right); case Audit_not_equal: return !uid_eq(left, right); case Audit_lt: return uid_lt(left, right); case Audit_le: return uid_lte(left, right); case Audit_gt: return uid_gt(left, right); case Audit_ge: return uid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) { switch (op) { case Audit_equal: return gid_eq(left, right); case Audit_not_equal: return !gid_eq(left, right); case Audit_lt: return gid_lt(left, right); case Audit_le: return gid_lte(left, right); case Audit_gt: return gid_gt(left, right); case Audit_ge: return gid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } /** * parent_len - find the length of the parent portion of a pathname * @path: pathname of which to determine length */ int parent_len(const char *path) { int plen; const char *p; plen = strlen(path); if (plen == 0) return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; /* walk backward until we find the next slash or hit beginning */ while ((*p != '/') && (p > path)) p--; /* did we find a slash? Then increment to include it in path */ if (*p == '/') p++; return p - path; } /** * audit_compare_dname_path - compare given dentry name with last component in * given path. Return of 0 indicates a match. * @dname: dentry name that we're comparing * @path: full pathname that we're comparing * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; if (parentlen == AUDIT_NAME_FULL) parentlen = parent_len(path); p = path + parentlen; /* handle trailing slashes */ pathlen -= parentlen; while (p[pathlen - 1] == '/') pathlen--; if (pathlen != dlen) return 1; return memcmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) { struct audit_entry *e; int ret = 1; /* Audit by default */ rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; struct lsm_prop prop = { }; pid_t pid; switch (f->type) { case AUDIT_PID: pid = task_tgid_nr(current); result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: result = audit_uid_comparator(audit_get_loginuid(current), f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { security_current_getlsmprop_subj(&prop); result = security_audit_rule_match( &prop, f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: result = audit_exe_compare(current, e->rule.exe); if (f->op == Audit_not_equal) result = !result; break; default: goto unlock_and_return; } if (result < 0) /* error */ goto unlock_and_return; if (!result) break; } if (result > 0) { if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } } unlock_and_return: rcu_read_unlock(); return ret; } static int update_lsm_rule(struct audit_krule *r) { struct audit_entry *entry = container_of(r, struct audit_entry, rule); struct audit_entry *nentry; int err = 0; if (!security_audit_rule_known(r)) return 0; nentry = audit_dupe_rule(r); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { /* save the first error encountered for the * return value */ err = PTR_ERR(nentry); audit_panic("error updating LSM filters"); if (r->watch) list_del(&r->rlist); list_del_rcu(&entry->list); list_del(&r->list); } else { if (r->watch || r->tree) list_replace_init(&r->rlist, &nentry->rule.rlist); list_replace_rcu(&entry->list, &nentry->list); list_replace(&r->list, &nentry->rule.list); } call_rcu(&entry->rcu, audit_free_rule_rcu); return err; } /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the * LSM field is re-initialized, and the old rule is replaced with the * updated rule. */ int audit_update_lsm_rules(void) { struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { int res = update_lsm_rule(r); if (!err) err = res; } } mutex_unlock(&audit_filter_mutex); return err; } |
| 693 31 73 166 127 693 167 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL #define mask_user_address(src) (src) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. * * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (should_fail_usercopy()) goto fail; if (can_do_masked_user_access()) from = mask_user_address(from); else { if (!access_ok(from, n)) goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); if (likely(!res)) return 0; fail: memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } /** * copy_struct_to_user: copy a struct to userspace * @dst: Destination address, in userspace. This buffer must be @ksize * bytes long. * @usize: (Alleged) size of @dst struct. * @src: Source address, in kernel space. * @ksize: Size of @src struct. * @ignored_trailing: Set to %true if there was a non-zero byte in @src that * userspace cannot see because they are using an smaller struct. * * Copies a struct from kernel space to userspace, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * Some syscalls may wish to make sure that userspace knows about everything in * the struct, and if there is a non-zero value that userspce doesn't know * about, they want to return an error (such as -EMSGSIZE) or have some other * fallback (such as adding a "you're missing some information" flag). If * @ignored_trailing is non-%NULL, it will be set to %true if there was a * non-zero byte that could not be copied to userspace (ie. was past @usize). * * While unconditionally returning an error in this case is the simplest * solution, for maximum backward compatibility you should try to only return * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. * Note that structure sizes can change due to header changes and simple * recompilations without code changes(!), so if you care about * @ignored_trailing you probably want to make sure that any new field data is * associated with a flag. Otherwise you might assume that a program knows * about data it does not. * * @ksize is just sizeof(*src), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) * { * int err; * bool ignored_trailing; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * // ... modify karg somehow ... * * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), * &ignored_trailing); * if (err) * return err; * if (ignored_trailing) * return -EMSGSIZE: * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the kernel is trying to pass userspace a newer * struct than it supports. Thus we only copy the interoperable portions * (@usize) and ignore the rest (but @ignored_trailing is set to %true if * any of the trailing (@ksize - @usize) bytes are non-zero). * * If @usize > @ksize, then the kernel is trying to pass userspace an older * struct than userspace supports. In order to make sure the * unknown-to-the-kernel fields don't contain garbage values, we zero the * trailing (@usize - @ksize) bytes. * * Returns (in all cases, some data may have been copied): * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_to_user(void __user *dst, size_t usize, const void *src, size_t ksize, bool *ignored_trailing) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize > ksize) { if (clear_user(dst + size, rest)) return -EFAULT; } if (ignored_trailing) *ignored_trailing = ksize < usize && memchr_inv(src + size, 0, rest) != NULL; /* Copy the interoperable parts of the struct. */ if (copy_to_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 252 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ }; #define SWAP_CLUSTER_MAX 32UL #define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The flags field determines if a cluster is free. This is * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * other than list, and swap_info_struct->swap_map * elements corresponding to the swap cluster. */ u16 count; u8 flags; u8 order; struct list_head list; }; /* All on-list cluster must have a non-zero flag. */ enum swap_cluster_flags { CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ CLUSTER_FLAG_FREE, CLUSTER_FLAG_NONFULL, CLUSTER_FLAG_FRAG, /* Clusters with flags above are allocatable */ CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, CLUSTER_FLAG_FULL, CLUSTER_FLAG_DISCARD, CLUSTER_FLAG_MAX, }; /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate an entry is not valid. */ #define SWAP_ENTRY_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { local_lock_t lock; /* Protect the percpu_cluster above */ unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ struct list_head full_clusters; /* full clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ atomic_long_t inuse_pages; /* number of those currently in use */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */ spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) #define MIN_SWAPPINESS 0 #define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_page_and_swap_cache(struct page *); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } static inline void free_swap_cache(struct folio *folio) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline int swapcache_prepare(swp_entry_t swp, int nr) { return 0; } static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); } static inline void swap_free(swp_entry_t entry) { swap_free_nr(entry, 1); } #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SHMEM_FS_H #define __SHMEM_FS_H #include <linux/file.h> #include <linux/swap.h> #include <linux/mempolicy.h> #include <linux/pagemap.h> #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> #include <linux/userfaultfd_k.h> /* inode in-kernel data */ #ifdef CONFIG_TMPFS_QUOTA #define SHMEM_MAXQUOTAS 2 #endif struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ union { struct offset_ctx dir_offsets; /* stable directory offsets */ struct { struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ }; }; struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ pgoff_t fallocend; /* highest fallocate endindex */ unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; #define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) #define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */ qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */ qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */ }; struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_ispace; /* How much ispace left for allocation */ raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ struct shmem_quota_limits qlimits; /* Default quota limits */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); } /* * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM bool shmem_mapping(struct address_space *mapping); #else static inline bool shmem_mapping(struct address_space *mapping) { return false; } #endif /* CONFIG_SHMEM */ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force) { return 0; } static inline bool shmem_hpage_pmd_enabled(void) { return false; } #endif #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) { return 0; } #endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); /* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); static inline struct folio *shmem_read_folio(struct address_space *mapping, pgoff_t index) { return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { return shmem_read_mapping_page_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline bool shmem_file(struct file *file) { if (!IS_ENABLED(CONFIG_SHMEM)) return false; if (!file || !file->f_mapping) return false; return shmem_mapping(file->f_mapping); } /* * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages * beyond i_size's notion of EOF, which fallocate has committed to reserving: * which split_huge_page() must therefore not delete. This use of a single * "fallocend" per inode errs on the side of not deleting a reservation when * in doubt: there are plenty of cases when it preserves unreserved pages. */ static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof) { return max(eof, SHMEM_I(inode)->fallocend); } extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL #ifdef CONFIG_TMPFS_QUOTA extern const struct dquot_operations shmem_quota_operations; extern struct quota_format_type shmem_quota_format; #endif /* CONFIG_TMPFS_QUOTA */ #endif |
| 878 883 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/irq.c * * Copyright (C) 1992 Linus Torvalds * Modifications for ARM processor Copyright (C) 1995-2000 Russell King. * Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation. * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>. * Copyright (C) 2012 ARM Ltd. */ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqchip.h> #include <linux/kprobes.h> #include <linux/memory.h> #include <linux/scs.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> #include <asm/numa.h> #include <asm/softirq_stack.h> #include <asm/stacktrace.h> #include <asm/vmap_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #ifdef CONFIG_SHADOW_CALL_STACK DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #endif static void init_irq_scs(void) { int cpu; if (!scs_is_enabled()) return; for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } #else /* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); static void init_irq_stacks(void) { int cpu; for_each_possible_cpu(cpu) per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); } #endif #ifndef CONFIG_PREEMPT_RT static void ____do_softirq(struct pt_regs *regs) { __do_softirq(); } void do_softirq_own_stack(void) { call_on_irq_stack(NULL, ____do_softirq); } #endif static void default_handle_irq(struct pt_regs *regs) { panic("IRQ taken without a root IRQ handler\n"); } static void default_handle_fiq(struct pt_regs *regs) { panic("FIQ taken without a root FIQ handler\n"); } void (*handle_arch_irq)(struct pt_regs *) __ro_after_init = default_handle_irq; void (*handle_arch_fiq)(struct pt_regs *) __ro_after_init = default_handle_fiq; int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) { if (handle_arch_irq != default_handle_irq) return -EBUSY; handle_arch_irq = handle_irq; pr_info("Root IRQ handler: %ps\n", handle_irq); return 0; } int __init set_handle_fiq(void (*handle_fiq)(struct pt_regs *)) { if (handle_arch_fiq != default_handle_fiq) return -EBUSY; handle_arch_fiq = handle_fiq; pr_info("Root FIQ handler: %ps\n", handle_fiq); return 0; } void __init init_IRQ(void) { init_irq_stacks(); init_irq_scs(); irqchip_init(); if (system_uses_irq_prio_masking()) { /* * Now that we have a stack for our IRQ handler, set * the PMR/PSR pair to a consistent state. */ WARN_ON(read_sysreg(daif) & PSR_A_BIT); local_daif_restore(DAIF_PROCCTX_NOIRQ); } } |
| 114 547 391 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 46 46 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/condition.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /* List of "struct tomoyo_condition". */ LIST_HEAD(tomoyo_condition_list); /** * tomoyo_argv - Check argv[] in "struct linux_binbrm". * * @index: Index number of @arg_ptr. * @arg_ptr: Contents of argv[@index]. * @argc: Length of @argv. * @argv: Pointer to "struct tomoyo_argv". * @checked: Set to true if @argv[@index] was found. * * Returns true on success, false otherwise. */ static bool tomoyo_argv(const unsigned int index, const char *arg_ptr, const int argc, const struct tomoyo_argv *argv, u8 *checked) { int i; struct tomoyo_path_info arg; arg.name = arg_ptr; for (i = 0; i < argc; argv++, checked++, i++) { bool result; if (index != argv->index) continue; *checked = 1; tomoyo_fill_path_info(&arg); result = tomoyo_path_matches_pattern(&arg, argv->value); if (argv->is_not) result = !result; if (!result) return false; } return true; } /** * tomoyo_envp - Check envp[] in "struct linux_binbrm". * * @env_name: The name of environment variable. * @env_value: The value of environment variable. * @envc: Length of @envp. * @envp: Pointer to "struct tomoyo_envp". * @checked: Set to true if @envp[@env_name] was found. * * Returns true on success, false otherwise. */ static bool tomoyo_envp(const char *env_name, const char *env_value, const int envc, const struct tomoyo_envp *envp, u8 *checked) { int i; struct tomoyo_path_info name; struct tomoyo_path_info value; name.name = env_name; tomoyo_fill_path_info(&name); value.name = env_value; tomoyo_fill_path_info(&value); for (i = 0; i < envc; envp++, checked++, i++) { bool result; if (!tomoyo_path_matches_pattern(&name, envp->name)) continue; *checked = 1; if (envp->value) { result = tomoyo_path_matches_pattern(&value, envp->value); if (envp->is_not) result = !result; } else { result = true; if (!envp->is_not) result = !result; } if (!result) return false; } return true; } /** * tomoyo_scan_bprm - Scan "struct linux_binprm". * * @ee: Pointer to "struct tomoyo_execve". * @argc: Length of @argc. * @argv: Pointer to "struct tomoyo_argv". * @envc: Length of @envp. * @envp: Pointer to "struct tomoyo_envp". * * Returns true on success, false otherwise. */ static bool tomoyo_scan_bprm(struct tomoyo_execve *ee, const u16 argc, const struct tomoyo_argv *argv, const u16 envc, const struct tomoyo_envp *envp) { struct linux_binprm *bprm = ee->bprm; struct tomoyo_page_dump *dump = &ee->dump; char *arg_ptr = ee->tmp; int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; bool result = true; u8 local_checked[32]; u8 *checked; if (argc + envc <= sizeof(local_checked)) { checked = local_checked; memset(local_checked, 0, sizeof(local_checked)); } else { checked = kzalloc(argc + envc, GFP_NOFS); if (!checked) return false; } while (argv_count || envp_count) { if (!tomoyo_dump_page(bprm, pos, dump)) { result = false; goto out; } pos += PAGE_SIZE - offset; while (offset < PAGE_SIZE) { /* Read. */ const char *kaddr = dump->data; const unsigned char c = kaddr[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; /* Check. */ if (argv_count) { if (!tomoyo_argv(bprm->argc - argv_count, arg_ptr, argc, argv, checked)) { result = false; break; } argv_count--; } else if (envp_count) { char *cp = strchr(arg_ptr, '='); if (cp) { *cp = '\0'; if (!tomoyo_envp(arg_ptr, cp + 1, envc, envp, checked + argc)) { result = false; break; } } envp_count--; } else { break; } arg_len = 0; } offset = 0; if (!result) break; } out: if (result) { int i; /* Check not-yet-checked entries. */ for (i = 0; i < argc; i++) { if (checked[i]) continue; /* * Return true only if all unchecked indexes in * bprm->argv[] are not matched. */ if (argv[i].is_not) continue; result = false; break; } for (i = 0; i < envc; envp++, i++) { if (checked[argc + i]) continue; /* * Return true only if all unchecked environ variables * in bprm->envp[] are either undefined or not matched. */ if ((!envp->value && !envp->is_not) || (envp->value && envp->is_not)) continue; result = false; break; } } if (checked != local_checked) kfree(checked); return result; } /** * tomoyo_scan_exec_realpath - Check "exec.realpath" parameter of "struct tomoyo_condition". * * @file: Pointer to "struct file". * @ptr: Pointer to "struct tomoyo_name_union". * @match: True if "exec.realpath=", false if "exec.realpath!=". * * Returns true on success, false otherwise. */ static bool tomoyo_scan_exec_realpath(struct file *file, const struct tomoyo_name_union *ptr, const bool match) { bool result; struct tomoyo_path_info exe; if (!file) return false; exe.name = tomoyo_realpath_from_path(&file->f_path); if (!exe.name) return false; tomoyo_fill_path_info(&exe); result = tomoyo_compare_name_union(&exe, ptr); kfree(exe.name); return result == match; } /** * tomoyo_get_dqword - tomoyo_get_name() for a quoted string. * * @start: String to save. * * Returns pointer to "struct tomoyo_path_info" on success, NULL otherwise. */ static const struct tomoyo_path_info *tomoyo_get_dqword(char *start) { char *cp = start + strlen(start) - 1; if (cp == start || *start++ != '"' || *cp != '"') return NULL; *cp = '\0'; if (*start && !tomoyo_correct_word(start)) return NULL; return tomoyo_get_name(start); } /** * tomoyo_parse_name_union_quoted - Parse a quoted word. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns true on success, false otherwise. */ static bool tomoyo_parse_name_union_quoted(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr) { char *filename = param->data; if (*filename == '@') return tomoyo_parse_name_union(param, ptr); ptr->filename = tomoyo_get_dqword(filename); return ptr->filename != NULL; } /** * tomoyo_parse_argv - Parse an argv[] condition part. * * @left: Lefthand value. * @right: Righthand value. * @argv: Pointer to "struct tomoyo_argv". * * Returns true on success, false otherwise. */ static bool tomoyo_parse_argv(char *left, char *right, struct tomoyo_argv *argv) { if (tomoyo_parse_ulong(&argv->index, &left) != TOMOYO_VALUE_TYPE_DECIMAL || *left++ != ']' || *left) return false; argv->value = tomoyo_get_dqword(right); return argv->value != NULL; } /** * tomoyo_parse_envp - Parse an envp[] condition part. * * @left: Lefthand value. * @right: Righthand value. * @envp: Pointer to "struct tomoyo_envp". * * Returns true on success, false otherwise. */ static bool tomoyo_parse_envp(char *left, char *right, struct tomoyo_envp *envp) { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; char *cp = left + strlen(left) - 1; if (*cp-- != ']' || *cp != '"') goto out; *cp = '\0'; if (!tomoyo_correct_word(left)) goto out; name = tomoyo_get_name(left); if (!name) goto out; if (!strcmp(right, "NULL")) { value = NULL; } else { value = tomoyo_get_dqword(right); if (!value) { tomoyo_put_name(name); goto out; } } envp->name = name; envp->value = value; return true; out: return false; } /** * tomoyo_same_condition - Check for duplicated "struct tomoyo_condition" entry. * * @a: Pointer to "struct tomoyo_condition". * @b: Pointer to "struct tomoyo_condition". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_condition(const struct tomoyo_condition *a, const struct tomoyo_condition *b) { return a->size == b->size && a->condc == b->condc && a->numbers_count == b->numbers_count && a->names_count == b->names_count && a->argc == b->argc && a->envc == b->envc && a->grant_log == b->grant_log && a->transit == b->transit && !memcmp(a + 1, b + 1, a->size - sizeof(*a)); } /** * tomoyo_condition_type - Get condition type. * * @word: Keyword string. * * Returns one of values in "enum tomoyo_conditions_index" on success, * TOMOYO_MAX_CONDITION_KEYWORD otherwise. */ static u8 tomoyo_condition_type(const char *word) { u8 i; for (i = 0; i < TOMOYO_MAX_CONDITION_KEYWORD; i++) { if (!strcmp(word, tomoyo_condition_keyword[i])) break; } return i; } /* Define this to enable debug mode. */ /* #define DEBUG_CONDITION */ #ifdef DEBUG_CONDITION #define dprintk printk #else #define dprintk(...) do { } while (0) #endif /** * tomoyo_commit_condition - Commit "struct tomoyo_condition". * * @entry: Pointer to "struct tomoyo_condition". * * Returns pointer to "struct tomoyo_condition" on success, NULL otherwise. * * This function merges duplicated entries. This function returns NULL if * @entry is not duplicated but memory quota for policy has exceeded. */ static struct tomoyo_condition *tomoyo_commit_condition (struct tomoyo_condition *entry) { struct tomoyo_condition *ptr; bool found = false; if (mutex_lock_interruptible(&tomoyo_policy_lock)) { dprintk(KERN_WARNING "%u: %s failed\n", __LINE__, __func__); ptr = NULL; found = true; goto out; } list_for_each_entry(ptr, &tomoyo_condition_list, head.list) { if (!tomoyo_same_condition(ptr, entry) || atomic_read(&ptr->head.users) == TOMOYO_GC_IN_PROGRESS) continue; /* Same entry found. Share this entry. */ atomic_inc(&ptr->head.users); found = true; break; } if (!found) { if (tomoyo_memory_ok(entry)) { atomic_set(&entry->head.users, 1); list_add(&entry->head.list, &tomoyo_condition_list); } else { found = true; ptr = NULL; } } mutex_unlock(&tomoyo_policy_lock); out: if (found) { tomoyo_del_condition(&entry->head.list); kfree(entry); entry = ptr; } return entry; } /** * tomoyo_get_transit_preference - Parse domain transition preference for execve(). * * @param: Pointer to "struct tomoyo_acl_param". * @e: Pointer to "struct tomoyo_condition". * * Returns the condition string part. */ static char *tomoyo_get_transit_preference(struct tomoyo_acl_param *param, struct tomoyo_condition *e) { char * const pos = param->data; bool flag; if (*pos == '<') { e->transit = tomoyo_get_domainname(param); goto done; } { char *cp = strchr(pos, ' '); if (cp) *cp = '\0'; flag = tomoyo_correct_path(pos) || !strcmp(pos, "keep") || !strcmp(pos, "initialize") || !strcmp(pos, "reset") || !strcmp(pos, "child") || !strcmp(pos, "parent"); if (cp) *cp = ' '; } if (!flag) return pos; e->transit = tomoyo_get_name(tomoyo_read_token(param)); done: if (e->transit) return param->data; /* * Return a bad read-only condition string that will let * tomoyo_get_condition() return NULL. */ return "/"; } /** * tomoyo_get_condition - Parse condition part. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns pointer to "struct tomoyo_condition" on success, NULL otherwise. */ struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param) { struct tomoyo_condition *entry = NULL; struct tomoyo_condition_element *condp = NULL; struct tomoyo_number_union *numbers_p = NULL; struct tomoyo_name_union *names_p = NULL; struct tomoyo_argv *argv = NULL; struct tomoyo_envp *envp = NULL; struct tomoyo_condition e = { }; char * const start_of_string = tomoyo_get_transit_preference(param, &e); char * const end_of_string = start_of_string + strlen(start_of_string); char *pos; rerun: pos = start_of_string; while (1) { u8 left = -1; u8 right = -1; char *left_word = pos; char *cp; char *right_word; bool is_not; if (!*left_word) break; /* * Since left-hand condition does not allow use of "path_group" * or "number_group" and environment variable's names do not * accept '=', it is guaranteed that the original line consists * of one or more repetition of $left$operator$right blocks * where "$left is free from '=' and ' '" and "$operator is * either '=' or '!='" and "$right is free from ' '". * Therefore, we can reconstruct the original line at the end * of dry run even if we overwrite $operator with '\0'. */ cp = strchr(pos, ' '); if (cp) { *cp = '\0'; /* Will restore later. */ pos = cp + 1; } else { pos = ""; } right_word = strchr(left_word, '='); if (!right_word || right_word == left_word) goto out; is_not = *(right_word - 1) == '!'; if (is_not) *(right_word++ - 1) = '\0'; /* Will restore later. */ else if (*(right_word + 1) != '=') *right_word++ = '\0'; /* Will restore later. */ else goto out; dprintk(KERN_WARNING "%u: <%s>%s=<%s>\n", __LINE__, left_word, is_not ? "!" : "", right_word); if (!strcmp(left_word, "grant_log")) { if (entry) { if (is_not || entry->grant_log != TOMOYO_GRANTLOG_AUTO) goto out; else if (!strcmp(right_word, "yes")) entry->grant_log = TOMOYO_GRANTLOG_YES; else if (!strcmp(right_word, "no")) entry->grant_log = TOMOYO_GRANTLOG_NO; else goto out; } continue; } if (!strncmp(left_word, "exec.argv[", 10)) { if (!argv) { e.argc++; e.condc++; } else { e.argc--; e.condc--; left = TOMOYO_ARGV_ENTRY; argv->is_not = is_not; if (!tomoyo_parse_argv(left_word + 10, right_word, argv++)) goto out; } goto store_value; } if (!strncmp(left_word, "exec.envp[\"", 11)) { if (!envp) { e.envc++; e.condc++; } else { e.envc--; e.condc--; left = TOMOYO_ENVP_ENTRY; envp->is_not = is_not; if (!tomoyo_parse_envp(left_word + 11, right_word, envp++)) goto out; } goto store_value; } left = tomoyo_condition_type(left_word); dprintk(KERN_WARNING "%u: <%s> left=%u\n", __LINE__, left_word, left); if (left == TOMOYO_MAX_CONDITION_KEYWORD) { if (!numbers_p) { e.numbers_count++; } else { e.numbers_count--; left = TOMOYO_NUMBER_UNION; param->data = left_word; if (*left_word == '@' || !tomoyo_parse_number_union(param, numbers_p++)) goto out; } } if (!condp) e.condc++; else e.condc--; if (left == TOMOYO_EXEC_REALPATH || left == TOMOYO_SYMLINK_TARGET) { if (!names_p) { e.names_count++; } else { e.names_count--; right = TOMOYO_NAME_UNION; param->data = right_word; if (!tomoyo_parse_name_union_quoted(param, names_p++)) goto out; } goto store_value; } right = tomoyo_condition_type(right_word); if (right == TOMOYO_MAX_CONDITION_KEYWORD) { if (!numbers_p) { e.numbers_count++; } else { e.numbers_count--; right = TOMOYO_NUMBER_UNION; param->data = right_word; if (!tomoyo_parse_number_union(param, numbers_p++)) goto out; } } store_value: if (!condp) { dprintk(KERN_WARNING "%u: dry_run left=%u right=%u match=%u\n", __LINE__, left, right, !is_not); continue; } condp->left = left; condp->right = right; condp->equals = !is_not; dprintk(KERN_WARNING "%u: left=%u right=%u match=%u\n", __LINE__, condp->left, condp->right, condp->equals); condp++; } dprintk(KERN_INFO "%u: cond=%u numbers=%u names=%u ac=%u ec=%u\n", __LINE__, e.condc, e.numbers_count, e.names_count, e.argc, e.envc); if (entry) { BUG_ON(e.names_count | e.numbers_count | e.argc | e.envc | e.condc); return tomoyo_commit_condition(entry); } e.size = sizeof(*entry) + e.condc * sizeof(struct tomoyo_condition_element) + e.numbers_count * sizeof(struct tomoyo_number_union) + e.names_count * sizeof(struct tomoyo_name_union) + e.argc * sizeof(struct tomoyo_argv) + e.envc * sizeof(struct tomoyo_envp); entry = kzalloc(e.size, GFP_NOFS); if (!entry) goto out2; *entry = e; e.transit = NULL; condp = (struct tomoyo_condition_element *) (entry + 1); numbers_p = (struct tomoyo_number_union *) (condp + e.condc); names_p = (struct tomoyo_name_union *) (numbers_p + e.numbers_count); argv = (struct tomoyo_argv *) (names_p + e.names_count); envp = (struct tomoyo_envp *) (argv + e.argc); { bool flag = false; for (pos = start_of_string; pos < end_of_string; pos++) { if (*pos) continue; if (flag) /* Restore " ". */ *pos = ' '; else if (*(pos + 1) == '=') /* Restore "!=". */ *pos = '!'; else /* Restore "=". */ *pos = '='; flag = !flag; } } goto rerun; out: dprintk(KERN_WARNING "%u: %s failed\n", __LINE__, __func__); if (entry) { tomoyo_del_condition(&entry->head.list); kfree(entry); } out2: tomoyo_put_name(e.transit); return NULL; } /** * tomoyo_get_attributes - Revalidate "struct inode". * * @obj: Pointer to "struct tomoyo_obj_info". * * Returns nothing. */ void tomoyo_get_attributes(struct tomoyo_obj_info *obj) { u8 i; struct dentry *dentry = NULL; for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) { struct inode *inode; switch (i) { case TOMOYO_PATH1: dentry = obj->path1.dentry; if (!dentry) continue; break; case TOMOYO_PATH2: dentry = obj->path2.dentry; if (!dentry) continue; break; default: if (!dentry) continue; dentry = dget_parent(dentry); break; } inode = d_backing_inode(dentry); if (inode) { struct tomoyo_mini_stat *stat = &obj->stat[i]; stat->uid = inode->i_uid; stat->gid = inode->i_gid; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->dev = inode->i_sb->s_dev; stat->rdev = inode->i_rdev; obj->stat_valid[i] = true; } if (i & 1) /* TOMOYO_PATH1_PARENT or TOMOYO_PATH2_PARENT */ dput(dentry); } } /** * tomoyo_condition - Check condition part. * * @r: Pointer to "struct tomoyo_request_info". * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond) { u32 i; unsigned long min_v[2] = { 0, 0 }; unsigned long max_v[2] = { 0, 0 }; const struct tomoyo_condition_element *condp; const struct tomoyo_number_union *numbers_p; const struct tomoyo_name_union *names_p; const struct tomoyo_argv *argv; const struct tomoyo_envp *envp; struct tomoyo_obj_info *obj; u16 condc; u16 argc; u16 envc; struct linux_binprm *bprm = NULL; if (!cond) return true; condc = cond->condc; argc = cond->argc; envc = cond->envc; obj = r->obj; if (r->ee) bprm = r->ee->bprm; if (!bprm && (argc || envc)) return false; condp = (struct tomoyo_condition_element *) (cond + 1); numbers_p = (const struct tomoyo_number_union *) (condp + condc); names_p = (const struct tomoyo_name_union *) (numbers_p + cond->numbers_count); argv = (const struct tomoyo_argv *) (names_p + cond->names_count); envp = (const struct tomoyo_envp *) (argv + argc); for (i = 0; i < condc; i++) { const bool match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; bool is_bitop[2] = { false, false }; u8 j; condp++; /* Check argv[] and envp[] later. */ if (left == TOMOYO_ARGV_ENTRY || left == TOMOYO_ENVP_ENTRY) continue; /* Check string expressions. */ if (right == TOMOYO_NAME_UNION) { const struct tomoyo_name_union *ptr = names_p++; struct tomoyo_path_info *symlink; struct tomoyo_execve *ee; struct file *file; switch (left) { case TOMOYO_SYMLINK_TARGET: symlink = obj ? obj->symlink_target : NULL; if (!symlink || !tomoyo_compare_name_union(symlink, ptr) == match) goto out; break; case TOMOYO_EXEC_REALPATH: ee = r->ee; file = ee ? ee->bprm->file : NULL; if (!tomoyo_scan_exec_realpath(file, ptr, match)) goto out; break; } continue; } /* Check numeric or bit-op expressions. */ for (j = 0; j < 2; j++) { const u8 index = j ? right : left; unsigned long value = 0; switch (index) { case TOMOYO_TASK_UID: value = from_kuid(&init_user_ns, current_uid()); break; case TOMOYO_TASK_EUID: value = from_kuid(&init_user_ns, current_euid()); break; case TOMOYO_TASK_SUID: value = from_kuid(&init_user_ns, current_suid()); break; case TOMOYO_TASK_FSUID: value = from_kuid(&init_user_ns, current_fsuid()); break; case TOMOYO_TASK_GID: value = from_kgid(&init_user_ns, current_gid()); break; case TOMOYO_TASK_EGID: value = from_kgid(&init_user_ns, current_egid()); break; case TOMOYO_TASK_SGID: value = from_kgid(&init_user_ns, current_sgid()); break; case TOMOYO_TASK_FSGID: value = from_kgid(&init_user_ns, current_fsgid()); break; case TOMOYO_TASK_PID: value = tomoyo_sys_getpid(); break; case TOMOYO_TASK_PPID: value = tomoyo_sys_getppid(); break; case TOMOYO_TYPE_IS_SOCKET: value = S_IFSOCK; break; case TOMOYO_TYPE_IS_SYMLINK: value = S_IFLNK; break; case TOMOYO_TYPE_IS_FILE: value = S_IFREG; break; case TOMOYO_TYPE_IS_BLOCK_DEV: value = S_IFBLK; break; case TOMOYO_TYPE_IS_DIRECTORY: value = S_IFDIR; break; case TOMOYO_TYPE_IS_CHAR_DEV: value = S_IFCHR; break; case TOMOYO_TYPE_IS_FIFO: value = S_IFIFO; break; case TOMOYO_MODE_SETUID: value = S_ISUID; break; case TOMOYO_MODE_SETGID: value = S_ISGID; break; case TOMOYO_MODE_STICKY: value = S_ISVTX; break; case TOMOYO_MODE_OWNER_READ: value = 0400; break; case TOMOYO_MODE_OWNER_WRITE: value = 0200; break; case TOMOYO_MODE_OWNER_EXECUTE: value = 0100; break; case TOMOYO_MODE_GROUP_READ: value = 0040; break; case TOMOYO_MODE_GROUP_WRITE: value = 0020; break; case TOMOYO_MODE_GROUP_EXECUTE: value = 0010; break; case TOMOYO_MODE_OTHERS_READ: value = 0004; break; case TOMOYO_MODE_OTHERS_WRITE: value = 0002; break; case TOMOYO_MODE_OTHERS_EXECUTE: value = 0001; break; case TOMOYO_EXEC_ARGC: if (!bprm) goto out; value = bprm->argc; break; case TOMOYO_EXEC_ENVC: if (!bprm) goto out; value = bprm->envc; break; case TOMOYO_NUMBER_UNION: /* Fetch values later. */ break; default: if (!obj) goto out; if (!obj->validate_done) { tomoyo_get_attributes(obj); obj->validate_done = true; } { u8 stat_index; struct tomoyo_mini_stat *stat; switch (index) { case TOMOYO_PATH1_UID: case TOMOYO_PATH1_GID: case TOMOYO_PATH1_INO: case TOMOYO_PATH1_MAJOR: case TOMOYO_PATH1_MINOR: case TOMOYO_PATH1_TYPE: case TOMOYO_PATH1_DEV_MAJOR: case TOMOYO_PATH1_DEV_MINOR: case TOMOYO_PATH1_PERM: stat_index = TOMOYO_PATH1; break; case TOMOYO_PATH2_UID: case TOMOYO_PATH2_GID: case TOMOYO_PATH2_INO: case TOMOYO_PATH2_MAJOR: case TOMOYO_PATH2_MINOR: case TOMOYO_PATH2_TYPE: case TOMOYO_PATH2_DEV_MAJOR: case TOMOYO_PATH2_DEV_MINOR: case TOMOYO_PATH2_PERM: stat_index = TOMOYO_PATH2; break; case TOMOYO_PATH1_PARENT_UID: case TOMOYO_PATH1_PARENT_GID: case TOMOYO_PATH1_PARENT_INO: case TOMOYO_PATH1_PARENT_PERM: stat_index = TOMOYO_PATH1_PARENT; break; case TOMOYO_PATH2_PARENT_UID: case TOMOYO_PATH2_PARENT_GID: case TOMOYO_PATH2_PARENT_INO: case TOMOYO_PATH2_PARENT_PERM: stat_index = TOMOYO_PATH2_PARENT; break; default: goto out; } if (!obj->stat_valid[stat_index]) goto out; stat = &obj->stat[stat_index]; switch (index) { case TOMOYO_PATH1_UID: case TOMOYO_PATH2_UID: case TOMOYO_PATH1_PARENT_UID: case TOMOYO_PATH2_PARENT_UID: value = from_kuid(&init_user_ns, stat->uid); break; case TOMOYO_PATH1_GID: case TOMOYO_PATH2_GID: case TOMOYO_PATH1_PARENT_GID: case TOMOYO_PATH2_PARENT_GID: value = from_kgid(&init_user_ns, stat->gid); break; case TOMOYO_PATH1_INO: case TOMOYO_PATH2_INO: case TOMOYO_PATH1_PARENT_INO: case TOMOYO_PATH2_PARENT_INO: value = stat->ino; break; case TOMOYO_PATH1_MAJOR: case TOMOYO_PATH2_MAJOR: value = MAJOR(stat->dev); break; case TOMOYO_PATH1_MINOR: case TOMOYO_PATH2_MINOR: value = MINOR(stat->dev); break; case TOMOYO_PATH1_TYPE: case TOMOYO_PATH2_TYPE: value = stat->mode & S_IFMT; break; case TOMOYO_PATH1_DEV_MAJOR: case TOMOYO_PATH2_DEV_MAJOR: value = MAJOR(stat->rdev); break; case TOMOYO_PATH1_DEV_MINOR: case TOMOYO_PATH2_DEV_MINOR: value = MINOR(stat->rdev); break; case TOMOYO_PATH1_PERM: case TOMOYO_PATH2_PERM: case TOMOYO_PATH1_PARENT_PERM: case TOMOYO_PATH2_PARENT_PERM: value = stat->mode & S_IALLUGO; break; } } break; } max_v[j] = value; min_v[j] = value; switch (index) { case TOMOYO_MODE_SETUID: case TOMOYO_MODE_SETGID: case TOMOYO_MODE_STICKY: case TOMOYO_MODE_OWNER_READ: case TOMOYO_MODE_OWNER_WRITE: case TOMOYO_MODE_OWNER_EXECUTE: case TOMOYO_MODE_GROUP_READ: case TOMOYO_MODE_GROUP_WRITE: case TOMOYO_MODE_GROUP_EXECUTE: case TOMOYO_MODE_OTHERS_READ: case TOMOYO_MODE_OTHERS_WRITE: case TOMOYO_MODE_OTHERS_EXECUTE: is_bitop[j] = true; } } if (left == TOMOYO_NUMBER_UNION) { /* Fetch values now. */ const struct tomoyo_number_union *ptr = numbers_p++; min_v[0] = ptr->values[0]; max_v[0] = ptr->values[1]; } if (right == TOMOYO_NUMBER_UNION) { /* Fetch values now. */ const struct tomoyo_number_union *ptr = numbers_p++; if (ptr->group) { if (tomoyo_number_matches_group(min_v[0], max_v[0], ptr->group) == match) continue; } else { if ((min_v[0] <= ptr->values[1] && max_v[0] >= ptr->values[0]) == match) continue; } goto out; } /* * Bit operation is valid only when counterpart value * represents permission. */ if (is_bitop[0] && is_bitop[1]) { goto out; } else if (is_bitop[0]) { switch (right) { case TOMOYO_PATH1_PERM: case TOMOYO_PATH1_PARENT_PERM: case TOMOYO_PATH2_PERM: case TOMOYO_PATH2_PARENT_PERM: if (!(max_v[0] & max_v[1]) == !match) continue; } goto out; } else if (is_bitop[1]) { switch (left) { case TOMOYO_PATH1_PERM: case TOMOYO_PATH1_PARENT_PERM: case TOMOYO_PATH2_PERM: case TOMOYO_PATH2_PARENT_PERM: if (!(max_v[0] & max_v[1]) == !match) continue; } goto out; } /* Normal value range comparison. */ if ((min_v[0] <= max_v[1] && max_v[0] >= min_v[1]) == match) continue; out: return false; } /* Check argv[] and envp[] now. */ if (r->ee && (argc || envc)) return tomoyo_scan_bprm(r->ee, argc, argv, envc, envp); return true; } |
| 112 108 5 2 113 113 112 113 113 113 3 3 3 2 106 94 91 1 2 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Authors: Alex Bennée <alex.bennee@linaro.org> * Oliver Upton <oliver.upton@linux.dev> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { preempt_disable(); /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug registers if the guest doesn't have ownership of them. */ if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; /* Write MDCR_EL2 directly if we're already at EL2 */ if (has_vhe()) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); preempt_enable(); } void kvm_init_host_debug_data(void) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); if (has_vhe()) return; if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) host_data_set_flag(HAS_SPE); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) { /* Force disable trace in protected mode in case of no TRBE */ if (is_protected_kvm_enabled()) host_data_set_flag(EL1_TRACING_CONFIGURED); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) host_data_set_flag(HAS_TRBE); } } /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. * * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. * * - Userspace is using the breakpoint/watchpoint registers to debug the * guest, and MDSCR_EL1.MDE is forced to 1. * * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, * masking all debug exceptions affected by the OS Lock. */ static void setup_external_mdscr(struct kvm_vcpu *vcpu) { /* * Use the guest's MDSCR_EL1 as a starting point, since there are * several other features controlled by MDSCR_EL1 that are not relevant * to the host. * * Clear the bits that KVM may use which also satisfies emulation of * the OS Lock as MDSCR_EL1.MDE is cleared. */ u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | MDSCR_EL1_MDE | MDSCR_EL1_KDE); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) mdscr |= MDSCR_EL1_SS; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; vcpu->arch.external_mdscr_el1 = mdscr; } void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) { u64 mdscr; /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); /* * Determine which of the possible debug states we're in: * * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do * software step or emulate the effects of the OS Lock being enabled. * * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and * the breakpoint/watchpoint registers need to be loaded eagerly. * * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint * context needs to be loaded on the CPU. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; setup_external_mdscr(vcpu); /* * Steal the guest's single-step state machine if userspace wants * single-step the guest. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); else vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; else vcpu->arch.debug_owner = VCPU_DEBUG_FREE; } kvm_arm_setup_mdcr_el2(vcpu); } void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; /* * Save the host's software step state and restore the guest's before * potentially returning to userspace. */ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); else vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; else *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; } /* * Updates ownership of the debug registers after a trapped guest access to a * breakpoint/watchpoint register. Host ownership of the debug registers is of * strictly higher priority, and it is the responsibility of the VMM to emulate * guest debug exceptions in this configuration. */ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) { if (kvm_host_owns_debug_regs(vcpu)) return; vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; kvm_arm_setup_mdcr_el2(vcpu); } void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) { if (val & OSLAR_EL1_OSLK) __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK; else __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK; preempt_disable(); kvm_arch_vcpu_put(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } void kvm_enable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_set_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_enable_trbe); void kvm_disable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_clear_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_disable_trbe); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) { if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; if (has_vhe()) { write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12); return; } *host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest; if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest) host_data_set_flag(EL1_TRACING_CONFIGURED); else host_data_clear_flag(EL1_TRACING_CONFIGURED); } EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration); |
| 9 10 10 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FUTEX_H #define _FUTEX_H #include <linux/futex.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #include <linux/compat.h> #include <linux/uaccess.h> #ifdef CONFIG_PREEMPT_RT #include <linux/rcuwait.h> #endif #include <asm/futex.h> /* * Futex flags used to encode options to functions and preserve them across * restarts. */ #define FLAGS_SIZE_8 0x0000 #define FLAGS_SIZE_16 0x0001 #define FLAGS_SIZE_32 0x0002 #define FLAGS_SIZE_64 0x0003 #define FLAGS_SIZE_MASK 0x0003 #ifdef CONFIG_MMU # define FLAGS_SHARED 0x0010 #else /* * NOMMU does not have per process address space. Let the compiler optimize * code away. */ # define FLAGS_SHARED 0x0000 #endif #define FLAGS_CLOCKRT 0x0020 #define FLAGS_HAS_TIMEOUT 0x0040 #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) { unsigned int flags = FLAGS_SIZE_32; if (!(op & FUTEX_PRIVATE_FLAG)) flags |= FLAGS_SHARED; if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; return flags; } #define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) { unsigned int flags = flags2 & FUTEX2_SIZE_MASK; if (!(flags2 & FUTEX2_PRIVATE)) flags |= FLAGS_SHARED; if (flags2 & FUTEX2_NUMA) flags |= FLAGS_NUMA; return flags; } static inline unsigned int futex_size(unsigned int flags) { return 1 << (flags & FLAGS_SIZE_MASK); } static inline bool futex_flags_valid(unsigned int flags) { /* Only 64bit futexes for 64bit code */ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64) return false; } /* Only 32bit futexes are implemented -- for now */ if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) return false; return true; } static inline bool futex_validate_input(unsigned int flags, u64 val) { int bits = 8 * futex_size(flags); if (bits < 64 && (val >> bits)) return false; return true; } #ifdef CONFIG_FAIL_FUTEX extern bool should_fail_futex(bool fshared); #else static inline bool should_fail_futex(bool fshared) { return false; } #endif /* * Hash buckets are shared by all the futex_keys that hash to the same * location. Each key may have multiple futex_q structures, one for each task * waiting on a futex. */ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; } ____cacheline_aligned_in_smp; /* * Priority Inheritance state: */ struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex_base pi_mutex; struct task_struct *owner; refcount_t refcount; union futex_key key; } __randomize_layout; struct futex_q; typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); /** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock * @wake: the wake handler for this queue * @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakeup is always to make the first condition true, then * the second. * * PI futexes are typically woken before they are removed from the hash list via * the rt_mutex code. See futex_unqueue_pi(). */ struct futex_q { struct plist_node list; struct task_struct *task; spinlock_t *lock_ptr; futex_wake_fn *wake; void *wake_data; union futex_key key; struct futex_pi_state *pi_state; struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif } __randomize_layout; extern const struct futex_q futex_q_init; enum futex_access { FUTEX_READ, FUTEX_WRITE }; extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw); extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); /** * futex_match - Check whether two futex keys are equal * @key1: Pointer to key1 * @key2: Pointer to key2 * * Return 1 if two futex_keys are equal, 0 otherwise. */ static inline int futex_match(union futex_key *key1, union futex_key *key2) { return (key1 && key2 && key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb); extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout); extern bool __futex_wake_mark(struct futex_q *q); extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q); extern int fault_in_user_writeable(u32 __user *uaddr); extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } /* * This does a plain atomic user space read, and the user pointer has * already been verified earlier by get_futex_key() to be both aligned * and actually in user space, just like futex_atomic_cmpxchg_inatomic(). * * We still want to avoid any speculation, and while __get_user() is * the traditional model for this, it's actually slower than doing * this manually these days. * * We could just have a per-architecture special function for it, * the same way we do futex_atomic_cmpxchg_inatomic(), but rather * than force everybody to do that, write it out long-hand using * the low-level user-access infrastructure. * * This looks a bit overkill, but generally just results in a couple * of instructions. */ static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from) { u32 val; if (can_do_masked_user_access()) from = masked_user_access_begin(from); else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(val, from, Efault); user_read_access_end(); *dest = val; return 0; Efault: user_read_access_end(); return -EFAULT; } static inline int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = futex_read_inatomic(dest, from); pagefault_enable(); return ret; } extern void __futex_unqueue(struct futex_q *q); extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The * exceptions involve the PI related operations, which may use futex_unqueue_pi() * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). * * Note that @task may be NULL, for async usage of futexes. */ static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) __releases(&hb->lock) { __futex_queue(q, hb, task); spin_unlock(&hb->lock); } extern void futex_unqueue_pi(struct futex_q *q); extern void wait_for_owner_exiting(int ret, struct task_struct *exiting); /* * Reflects a new waiter being added to the waitqueue. */ static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_inc(&hb->waiters); /* * Full barrier (A), see the ordering comment above. */ smp_mb__after_atomic(); #endif } /* * Reflects a waiter being removed from the waitqueue by wakeup * paths. */ static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_dec(&hb->waiters); #endif } static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP /* * Full barrier (B), see the ordering comment above. */ smp_mb(); return atomic_read(&hb->waiters); #else return 1; #endif } extern struct futex_hash_bucket *futex_q_lock(struct futex_q *q); extern void futex_q_unlock(struct futex_hash_bucket *hb); extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps, struct task_struct *task, struct task_struct **exiting, int set_waiters); extern int refill_pi_state_cache(void); extern void get_pi_state(struct futex_pi_state *pi_state); extern void put_pi_state(struct futex_pi_state *pi_state); extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked); /* * Express the locking dependencies for lockdep: */ static inline void double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { if (hb1 > hb2) swap(hb1, hb2); spin_lock(&hb1->lock); if (hb1 != hb2) spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); } static inline void double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { spin_unlock(&hb1->lock); if (hb1 != hb2) spin_unlock(&hb2->lock); } /* syscalls */ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2); extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1, u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi); extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset); extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); /** * struct futex_vector - Auxiliary struct for futex_waitv() * @w: Userspace provided data * @q: Kernel side data * * Struct used to build an array with all data need for futex_waitv() */ struct futex_vector { struct futex_waitv w; struct futex_q q; }; extern int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data); extern int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken); extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); #endif /* _FUTEX_H */ |
| 11 5 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); err_unlock: rcu_read_unlock(); return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv * @wake: Wake to call when futex is woken * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { unsigned int flags; if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; flags = futex2_to_flags(aux.flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, aux.val)) return -EINVAL; futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; futexv[i].q.wake = wake; futexv[i].q.wake_data = wake_data; } return 0; } static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, clockid_t clockid, struct hrtimer_sleeper *to) { int flag_clkid = 0, flag_init = 0; struct timespec64 ts; ktime_t time; int ret; if (!timeout) return 0; if (clockid == CLOCK_REALTIME) { flag_clkid = FLAGS_CLOCKRT; flag_init = FUTEX_CLOCK_REALTIME; } if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) return -EINVAL; if (get_timespec64(&ts, timeout)) return -EFAULT; /* * Since there's no opcode for futex_waitv, use * FUTEX_WAIT_BITSET that uses absolute timeout as well */ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); if (ret) return ret; futex_setup_timer(&time, to, flag_clkid, 0); return 0; } static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on * @nr_futexes: Length of futexv * @flags: Flag for timeout (monotonic/realtime) * @timeout: Optional absolute timeout. * @clockid: Clock to be used for the timeout, realtime or monotonic. * * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes * if a futex_wake() is performed at any uaddr. The syscall returns immediately * if any waiter has *uaddr != val. *timeout is an optional timeout value for * the operation. Each waiter has individual flags. The `flags` argument for * the syscall should be used solely for specifying the timeout as realtime, if * needed. Flags for private futexes, sizes, etc. should be used on the * individual flags of each waiter. * * Returns the array index of one of the woken futexes. No further information * is provided: any number of other futexes may also have been woken by the * same event, and if more than one futex was woken, the retrned index may * refer to any one of them. (It is not necessaryily the futex with the * smallest index, nor the one most recently woken, nor...) */ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, unsigned int, nr_futexes, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; struct futex_vector *futexv; int ret; /* This syscall supports no flags for now */ if (flags) return -EINVAL; if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { ret = -ENOMEM; goto destroy_timer; } ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_wake - Wake a number of futexes * @uaddr: Address of the futex(es) to wake * @mask: bitmask * @nr: Number of the futexes to wake * @flags: FUTEX2 flags * * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_wake, void __user *, uaddr, unsigned long, mask, int, nr, unsigned int, flags) { if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, mask)) return -EINVAL; return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } /* * sys_futex_wait - Wait on a futex * @uaddr: Address of the futex to wait on * @val: Value of @uaddr * @mask: bitmask * @flags: FUTEX2 flags * @timeout: Optional absolute timeout * @clockid: Clock to be used for the timeout, realtime or monotonic * * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the * futex2 familiy of calls. */ SYSCALL_DEFINE6(futex_wait, void __user *, uaddr, unsigned long, val, unsigned long, mask, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; int ret; if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, val) || !futex_validate_input(flags, mask)) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_requeue - Requeue a waiter from one futex to another * @waiters: array describing the source and destination futex * @flags: unused * @nr_wake: number of futexes to wake * @nr_requeue: number of futexes to requeue * * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_requeue, struct futex_waitv __user *, waiters, unsigned int, flags, int, nr_wake, int, nr_requeue) { struct futex_vector futexes[2]; u32 cmpval; int ret; if (flags) return -EINVAL; if (!waiters) return -EINVAL; ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); if (ret) return ret; cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, nr_wake, nr_requeue, &cmpval, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; current->compat_robust_list = head; return 0; } COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { struct compat_robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); err_unlock: rcu_read_unlock(); return ret; } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ |
| 210 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash func */ int (*cmp)(const void *key1, const void *key2); /* comparison func */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; u64 chain2_len_sum; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig, int (*copy)(struct hashtab_node *new, const struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #else static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info) { return; } #endif #endif /* _SS_HASHTAB_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; bool inaccessible; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the page again. */ void (*page_free)(struct page *page); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; DECLARE_FLEX_ARRAY(struct range, ranges); }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) { return is_device_private_page(&folio->page); } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) { return is_device_coherent_page(&folio->page); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 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 | /* * include/net/tipc.h: Include file for TIPC message header routines * * Copyright (c) 2017 Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_HDR_H #define _TIPC_HDR_H #include <linux/random.h> #define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */ struct tipc_basic_hdr { __be32 w[4]; }; static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) { u32 w0 = ntohl(hdr->w[0]); bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK; __be32 key; /* Return source node identity as key */ if (likely(!keepalive_msg)) return hdr->w[3]; /* Spread PROBE/PROBE_REPLY messages across the cores */ get_random_bytes(&key, sizeof(key)); return key; } #endif |
| 3 3 31 31 31 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/drivers/net/netconsole.c * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * * This file contains the implementation of an IRQ-safe, crash-safe * kernel console implementation that outputs kernel messages to the * network. * * Modification history: * * 2001-09-17 started by Ingo Molnar. * 2003-08-11 2.6 port by Matt Mackall * simplified options * generic card hooks * works non-modular * 2003-09-07 rewritten with netpoll api */ /**************************************************************** * ****************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/console.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/netpoll.h> #include <linux/inet.h> #include <linux/configfs.h> #include <linux/etherdevice.h> #include <linux/u64_stats_sync.h> #include <linux/utsname.h> #include <linux/rtnetlink.h> MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); #define MAX_PARAM_LENGTH 256 #define MAX_USERDATA_ENTRY_LENGTH 256 #define MAX_USERDATA_VALUE_LENGTH 200 /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ #define MAX_USERDATA_NAME_LENGTH (MAX_USERDATA_ENTRY_LENGTH - \ MAX_USERDATA_VALUE_LENGTH - 3) #define MAX_USERDATA_ITEMS 16 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]"); static bool oops_only; module_param(oops_only, bool, 0600); MODULE_PARM_DESC(oops_only, "Only log oops messages"); #define NETCONSOLE_PARAM_TARGET_PREFIX "cmdline" #ifndef MODULE static int __init option_setup(char *opt) { strscpy(config, opt, MAX_PARAM_LENGTH); return 1; } __setup("netconsole=", option_setup); #endif /* MODULE */ /* Linked list of all configured targets */ static LIST_HEAD(target_list); /* target_cleanup_list is used to track targets that need to be cleaned outside * of target_list_lock. It should be cleaned in the same function it is * populated. */ static LIST_HEAD(target_cleanup_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); /* This needs to be a mutex because netpoll_cleanup might sleep */ static DEFINE_MUTEX(target_cleanup_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to * avoid unnecessarily enabling ext message formatting. */ static struct console netconsole_ext; struct netconsole_target_stats { u64_stats_t xmit_drop_count; u64_stats_t enomem_count; struct u64_stats_sync syncp; }; /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. * @group: Links us into the configfs subsystem hierarchy. * @userdata_group: Links to the userdata configfs hierarchy * @userdata_complete: Cached, formatted string of append * @userdata_length: String length of userdata_complete * @stats: Packet send stats for the target. Used for debugging. * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). * @extended: Denotes whether console is extended or not. * @release: Denotes whether kernel release version should be prepended * to the message. Depends on extended console. * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) * local_port (read-write) * remote_port (read-write) * local_ip (read-write) * remote_ip (read-write) * local_mac (read-only) * remote_mac (read-write) */ struct netconsole_target { struct list_head list; #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_group group; struct config_group userdata_group; char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS]; size_t userdata_length; #endif struct netconsole_target_stats stats; bool enabled; bool extended; bool release; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { config_group_init(&netconsole_subsys.su_group); mutex_init(&netconsole_subsys.su_mutex); return configfs_register_subsystem(&netconsole_subsys); } static void __exit dynamic_netconsole_exit(void) { configfs_unregister_subsystem(&netconsole_subsys); } /* * Targets that were created by parsing the boot/module option string * do not exist in the configfs hierarchy (and have NULL names) and will * never go away, so make these a no-op for them. */ static void netconsole_target_get(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_get(&nt->group); } static void netconsole_target_put(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_put(&nt->group); } #else /* !CONFIG_NETCONSOLE_DYNAMIC */ static int __init dynamic_netconsole_init(void) { return 0; } static void __exit dynamic_netconsole_exit(void) { } /* * No danger of targets going away from under us when dynamic * reconfigurability is off. */ static void netconsole_target_get(struct netconsole_target *nt) { } static void netconsole_target_put(struct netconsole_target *nt) { } static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Allocate and initialize with defaults. * Note that these targets get their config_item fields zeroed-out. */ static struct netconsole_target *alloc_and_init(void) { struct netconsole_target *nt; nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return nt; if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG)) nt->extended = true; if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE)) nt->release = true; nt->np.name = "netconsole"; strscpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); return nt; } /* Clean up every target in the cleanup_list and move the clean targets back to * the main target_list. */ static void netconsole_process_cleanups_core(void) { struct netconsole_target *nt, *tmp; unsigned long flags; /* The cleanup needs RTNL locked */ ASSERT_RTNL(); mutex_lock(&target_cleanup_list_lock); list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) { /* all entries in the cleanup_list needs to be disabled */ WARN_ON_ONCE(nt->enabled); do_netpoll_cleanup(&nt->np); /* moved the cleaned target to target_list. Need to hold both * locks */ spin_lock_irqsave(&target_list_lock, flags); list_move(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); } WARN_ON_ONCE(!list_empty(&target_cleanup_list)); mutex_unlock(&target_cleanup_list_lock); } #ifdef CONFIG_NETCONSOLE_DYNAMIC /* * Our subsystem hierarchy is: * * /sys/kernel/config/netconsole/ * | * <target>/ * | enabled * | release * | dev_name * | local_port * | remote_port * | local_ip * | remote_ip * | local_mac * | remote_mac * | transmit_errors * | userdata/ * | <key>/ * | value * | ... * | * <target>/... */ static struct netconsole_target *to_target(struct config_item *item) { struct config_group *cfg_group; cfg_group = to_config_group(item); if (!cfg_group) return NULL; return container_of(to_config_group(item), struct netconsole_target, group); } /* Do the list cleanup with the rtnl lock hold. rtnl lock is necessary because * netdev might be cleaned-up by calling __netpoll_cleanup(), */ static void netconsole_process_cleanups(void) { /* rtnl lock is called here, because it has precedence over * target_cleanup_list_lock mutex and target_cleanup_list */ rtnl_lock(); netconsole_process_cleanups_core(); rtnl_unlock(); } /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { size_t len; len = strnlen(s, maxlen); if (s[len - 1] == '\n') s[len - 1] = '\0'; } /* * Attribute operations for netconsole_target. */ static ssize_t enabled_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->enabled); } static ssize_t extended_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->extended); } static ssize_t release_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->release); } static ssize_t dev_name_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", to_target(item)->np.dev_name); } static ssize_t local_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port); } static ssize_t remote_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port); } static ssize_t local_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.local_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.local_ip); } static ssize_t remote_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.remote_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.remote_ip); } static ssize_t local_mac_show(struct config_item *item, char *buf) { struct net_device *dev = to_target(item)->np.dev; static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; return sysfs_emit(buf, "%pM\n", dev ? dev->dev_addr : bcast); } static ssize_t remote_mac_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac); } static ssize_t transmit_errors_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); u64 xmit_drop_count, enomem_count; unsigned int start; do { start = u64_stats_fetch_begin(&nt->stats.syncp); xmit_drop_count = u64_stats_read(&nt->stats.xmit_drop_count); enomem_count = u64_stats_read(&nt->stats.enomem_count); } while (u64_stats_fetch_retry(&nt->stats.syncp, start)); return sysfs_emit(buf, "%llu\n", xmit_drop_count + enomem_count); } /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. * The user is expected to set the desired parameters first (which * would enable him to dynamically add new netpoll targets for new * network interfaces as and when they come up). */ static ssize_t enabled_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); ret = kstrtobool(buf, &enabled); if (ret) goto out_unlock; ret = -EINVAL; if (enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); goto out_unlock; } if (enabled) { /* true */ if (nt->release && !nt->extended) { pr_err("Not enabling netconsole. Release feature requires extended log message"); goto out_unlock; } if (nt->extended && !console_is_registered(&netconsole_ext)) register_console(&netconsole_ext); /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. */ netpoll_print_options(&nt->np); ret = netpoll_setup(&nt->np); if (ret) goto out_unlock; nt->enabled = true; pr_info("network logging started\n"); } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; /* Remove the target from the list, while holding * target_list_lock */ list_move(&nt->list, &target_cleanup_list); spin_unlock_irqrestore(&target_list_lock, flags); mutex_unlock(&target_cleanup_list_lock); } ret = strnlen(buf, count); /* Deferred cleanup */ netconsole_process_cleanups(); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t release_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool release; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); ret = -EINVAL; goto out_unlock; } ret = kstrtobool(buf, &release); if (ret) goto out_unlock; nt->release = release; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t extended_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool extended; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); ret = -EINVAL; goto out_unlock; } ret = kstrtobool(buf, &extended); if (ret) goto out_unlock; nt->extended = extended; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } strscpy(nt->np.dev_name, buf, IFNAMSIZ); trim_newline(nt->np.dev_name, IFNAMSIZ); mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); } static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } ret = kstrtou16(buf, 10, &nt->np.local_port); if (ret < 0) goto out_unlock; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } ret = kstrtou16(buf, 10, &nt->np.remote_port); if (ret < 0) goto out_unlock; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.local_ip.ip = in_aton(buf); else goto out_unlock; } ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.remote_ip.ip = in_aton(buf); else goto out_unlock; } ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (!mac_pton(buf, remote_mac)) goto out_unlock; if (buf[3 * ETH_ALEN - 1] && buf[3 * ETH_ALEN - 1] != '\n') goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } struct userdatum { struct config_item item; char value[MAX_USERDATA_VALUE_LENGTH]; }; static struct userdatum *to_userdatum(struct config_item *item) { return container_of(item, struct userdatum, item); } struct userdata { struct config_group group; }; static struct userdata *to_userdata(struct config_item *item) { return container_of(to_config_group(item), struct userdata, group); } static struct netconsole_target *userdata_to_target(struct userdata *ud) { struct config_group *netconsole_group; netconsole_group = to_config_group(ud->group.cg_item.ci_parent); return to_target(&netconsole_group->cg_item); } static ssize_t userdatum_value_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", &(to_userdatum(item)->value[0])); } static void update_userdata(struct netconsole_target *nt) { int complete_idx = 0, child_count = 0; struct list_head *entry; /* Clear the current string in case the last userdatum was deleted */ nt->userdata_length = 0; nt->userdata_complete[0] = 0; list_for_each(entry, &nt->userdata_group.cg_children) { struct userdatum *udm_item; struct config_item *item; if (WARN_ON_ONCE(child_count >= MAX_USERDATA_ITEMS)) break; child_count++; item = container_of(entry, struct config_item, ci_entry); udm_item = to_userdatum(item); /* Skip userdata with no value set */ if (strnlen(udm_item->value, MAX_USERDATA_VALUE_LENGTH) == 0) continue; /* This doesn't overflow userdata_complete since it will write * one entry length (1/MAX_USERDATA_ITEMS long), entry count is * checked to not exceed MAX items with child_count above */ complete_idx += scnprintf(&nt->userdata_complete[complete_idx], MAX_USERDATA_ENTRY_LENGTH, " %s=%s\n", item->ci_name, udm_item->value); } nt->userdata_length = strnlen(nt->userdata_complete, sizeof(nt->userdata_complete)); } static ssize_t userdatum_value_store(struct config_item *item, const char *buf, size_t count) { struct userdatum *udm = to_userdatum(item); struct netconsole_target *nt; struct userdata *ud; ssize_t ret; if (count > MAX_USERDATA_VALUE_LENGTH) return -EMSGSIZE; mutex_lock(&dynamic_netconsole_mutex); ret = strscpy(udm->value, buf, sizeof(udm->value)); if (ret < 0) goto out_unlock; trim_newline(udm->value, sizeof(udm->value)); ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); update_userdata(nt); ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } CONFIGFS_ATTR(userdatum_, value); static struct configfs_attribute *userdatum_attrs[] = { &userdatum_attr_value, NULL, }; static void userdatum_release(struct config_item *item) { kfree(to_userdatum(item)); } static struct configfs_item_operations userdatum_ops = { .release = userdatum_release, }; static const struct config_item_type userdatum_type = { .ct_item_ops = &userdatum_ops, .ct_attrs = userdatum_attrs, .ct_owner = THIS_MODULE, }; static struct config_item *userdatum_make_item(struct config_group *group, const char *name) { struct netconsole_target *nt; struct userdatum *udm; struct userdata *ud; size_t child_count; if (strlen(name) > MAX_USERDATA_NAME_LENGTH) return ERR_PTR(-ENAMETOOLONG); ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); child_count = list_count_nodes(&nt->userdata_group.cg_children); if (child_count >= MAX_USERDATA_ITEMS) return ERR_PTR(-ENOSPC); udm = kzalloc(sizeof(*udm), GFP_KERNEL); if (!udm) return ERR_PTR(-ENOMEM); config_item_init_type_name(&udm->item, name, &userdatum_type); return &udm->item; } static void userdatum_drop(struct config_group *group, struct config_item *item) { struct netconsole_target *nt; struct userdata *ud; ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); mutex_lock(&dynamic_netconsole_mutex); update_userdata(nt); config_item_put(item); mutex_unlock(&dynamic_netconsole_mutex); } static struct configfs_attribute *userdata_attrs[] = { NULL, }; static struct configfs_group_operations userdata_ops = { .make_item = userdatum_make_item, .drop_item = userdatum_drop, }; static const struct config_item_type userdata_type = { .ct_item_ops = &userdatum_ops, .ct_group_ops = &userdata_ops, .ct_attrs = userdata_attrs, .ct_owner = THIS_MODULE, }; CONFIGFS_ATTR(, enabled); CONFIGFS_ATTR(, extended); CONFIGFS_ATTR(, dev_name); CONFIGFS_ATTR(, local_port); CONFIGFS_ATTR(, remote_port); CONFIGFS_ATTR(, local_ip); CONFIGFS_ATTR(, remote_ip); CONFIGFS_ATTR_RO(, local_mac); CONFIGFS_ATTR(, remote_mac); CONFIGFS_ATTR(, release); CONFIGFS_ATTR_RO(, transmit_errors); static struct configfs_attribute *netconsole_target_attrs[] = { &attr_enabled, &attr_extended, &attr_release, &attr_dev_name, &attr_local_port, &attr_remote_port, &attr_local_ip, &attr_remote_ip, &attr_local_mac, &attr_remote_mac, &attr_transmit_errors, NULL, }; /* * Item operations and type for netconsole_target. */ static void netconsole_target_release(struct config_item *item) { kfree(to_target(item)); } static struct configfs_item_operations netconsole_target_item_ops = { .release = netconsole_target_release, }; static const struct config_item_type netconsole_target_type = { .ct_attrs = netconsole_target_attrs, .ct_item_ops = &netconsole_target_item_ops, .ct_owner = THIS_MODULE, }; static void init_target_config_group(struct netconsole_target *nt, const char *name) { config_group_init_type_name(&nt->group, name, &netconsole_target_type); config_group_init_type_name(&nt->userdata_group, "userdata", &userdata_type); configfs_add_default_group(&nt->userdata_group, &nt->group); } static struct netconsole_target *find_cmdline_target(const char *name) { struct netconsole_target *nt, *ret = NULL; unsigned long flags; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!strcmp(nt->group.cg_item.ci_name, name)) { ret = nt; break; } } spin_unlock_irqrestore(&target_list_lock, flags); return ret; } /* * Group operations and type for netconsole_subsys. */ static struct config_group *make_netconsole_target(struct config_group *group, const char *name) { struct netconsole_target *nt; unsigned long flags; /* Checking if a target by this name was created at boot time. If so, * attach a configfs entry to that target. This enables dynamic * control. */ if (!strncmp(name, NETCONSOLE_PARAM_TARGET_PREFIX, strlen(NETCONSOLE_PARAM_TARGET_PREFIX))) { nt = find_cmdline_target(name); if (nt) { init_target_config_group(nt, name); return &nt->group; } } nt = alloc_and_init(); if (!nt) return ERR_PTR(-ENOMEM); /* Initialize the config_group member */ init_target_config_group(nt, name); /* Adding, but it is disabled */ spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); return &nt->group; } static void drop_netconsole_target(struct config_group *group, struct config_item *item) { unsigned long flags; struct netconsole_target *nt = to_target(item); spin_lock_irqsave(&target_list_lock, flags); list_del(&nt->list); spin_unlock_irqrestore(&target_list_lock, flags); /* * The target may have never been enabled, or was manually disabled * before being removed so netpoll may have already been cleaned up. */ if (nt->enabled) netpoll_cleanup(&nt->np); config_item_put(&nt->group.cg_item); } static struct configfs_group_operations netconsole_subsys_group_ops = { .make_group = make_netconsole_target, .drop_item = drop_netconsole_target, }; static const struct config_item_type netconsole_subsys_type = { .ct_group_ops = &netconsole_subsys_group_ops, .ct_owner = THIS_MODULE, }; /* The netconsole configfs subsystem */ static struct configfs_subsystem netconsole_subsys = { .su_group = { .cg_item = { .ci_namebuf = "netconsole", .ci_type = &netconsole_subsys_type, }, }, }; static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { char target_name[16]; snprintf(target_name, sizeof(target_name), "%s%d", NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); init_target_config_group(nt, target_name); } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Handle network interface device notifications */ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; struct netconsole_target *nt, *tmp; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER || event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry_safe(nt, tmp, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { case NETDEV_CHANGENAME: strscpy(nt->np.dev_name, dev->name, IFNAMSIZ); break; case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: nt->enabled = false; list_move(&nt->list, &target_cleanup_list); stopped = true; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); mutex_unlock(&target_cleanup_list_lock); if (stopped) { const char *msg = "had an event"; switch (event) { case NETDEV_UNREGISTER: msg = "unregistered"; break; case NETDEV_RELEASE: msg = "released slaves"; break; case NETDEV_JOIN: msg = "is joining a master device"; break; } pr_info("network logging stopped on interface %s as it %s\n", dev->name, msg); } /* Process target_cleanup_list entries. By the end, target_cleanup_list * should be empty */ netconsole_process_cleanups_core(); done: return NOTIFY_DONE; } static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; /** * send_udp - Wrapper for netpoll_send_udp that counts errors * @nt: target to send message to * @msg: message to send * @len: length of message * * Calls netpoll_send_udp and classifies the return value. If an error * occurred it increments statistics in nt->stats accordingly. * Only calls netpoll_send_udp if CONFIG_NETCONSOLE_DYNAMIC is disabled. */ static void send_udp(struct netconsole_target *nt, const char *msg, int len) { int result = netpoll_send_udp(&nt->np, msg, len); if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) { if (result == NET_XMIT_DROP) { u64_stats_update_begin(&nt->stats.syncp); u64_stats_inc(&nt->stats.xmit_drop_count); u64_stats_update_end(&nt->stats.syncp); } else if (result == -ENOMEM) { u64_stats_update_begin(&nt->stats.syncp); u64_stats_inc(&nt->stats.enomem_count); u64_stats_update_end(&nt->stats.syncp); } } } static void send_msg_no_fragmentation(struct netconsole_target *nt, const char *msg, int msg_len, int release_len) { static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ const char *userdata = NULL; const char *release; #ifdef CONFIG_NETCONSOLE_DYNAMIC userdata = nt->userdata_complete; #endif if (release_len) { release = init_utsname()->release; scnprintf(buf, MAX_PRINT_CHUNK, "%s,%s", release, msg); msg_len += release_len; } else { memcpy(buf, msg, msg_len); } if (userdata) msg_len += scnprintf(&buf[msg_len], MAX_PRINT_CHUNK - msg_len, "%s", userdata); send_udp(nt, buf, msg_len); } static void append_release(char *buf) { const char *release; release = init_utsname()->release; scnprintf(buf, MAX_PRINT_CHUNK, "%s,", release); } static void send_fragmented_body(struct netconsole_target *nt, char *buf, const char *msgbody, int header_len, int msgbody_len) { const char *userdata = NULL; int body_len, offset = 0; int userdata_len = 0; #ifdef CONFIG_NETCONSOLE_DYNAMIC userdata = nt->userdata_complete; userdata_len = nt->userdata_length; #endif /* body_len represents the number of bytes that will be sent. This is * bigger than MAX_PRINT_CHUNK, thus, it will be split in multiple * packets */ body_len = msgbody_len + userdata_len; /* In each iteration of the while loop below, we send a packet * containing the header and a portion of the body. The body is * composed of two parts: msgbody and userdata. We keep track of how * many bytes have been sent so far using the offset variable, which * ranges from 0 to the total length of the body. */ while (offset < body_len) { int this_header = header_len; bool msgbody_written = false; int this_offset = 0; int this_chunk = 0; this_header += scnprintf(buf + this_header, MAX_PRINT_CHUNK - this_header, ",ncfrag=%d/%d;", offset, body_len); /* Not all msgbody data has been written yet */ if (offset < msgbody_len) { this_chunk = min(msgbody_len - offset, MAX_PRINT_CHUNK - this_header); if (WARN_ON_ONCE(this_chunk <= 0)) return; memcpy(buf + this_header, msgbody + offset, this_chunk); this_offset += this_chunk; } /* msgbody was finally written, either in the previous * messages and/or in the current buf. Time to write * the userdata. */ msgbody_written |= offset + this_offset >= msgbody_len; /* Msg body is fully written and there is pending userdata to * write, append userdata in this chunk */ if (msgbody_written && offset + this_offset < body_len) { /* Track how much user data was already sent. First * time here, sent_userdata is zero */ int sent_userdata = (offset + this_offset) - msgbody_len; /* offset of bytes used in current buf */ int preceding_bytes = this_chunk + this_header; if (WARN_ON_ONCE(sent_userdata < 0)) return; this_chunk = min(userdata_len - sent_userdata, MAX_PRINT_CHUNK - preceding_bytes); if (WARN_ON_ONCE(this_chunk < 0)) /* this_chunk could be zero if all the previous * message used all the buffer. This is not a * problem, userdata will be sent in the next * iteration */ return; memcpy(buf + this_header + this_offset, userdata + sent_userdata, this_chunk); this_offset += this_chunk; } send_udp(nt, buf, this_header + this_offset); offset += this_offset; } } static void send_msg_fragmented(struct netconsole_target *nt, const char *msg, int msg_len, int release_len) { static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ int header_len, msgbody_len; const char *msgbody; /* need to insert extra header fields, detect header and msgbody */ msgbody = memchr(msg, ';', msg_len); if (WARN_ON_ONCE(!msgbody)) return; header_len = msgbody - msg; msgbody_len = msg_len - header_len - 1; msgbody++; /* * Transfer multiple chunks with the following extra header. * "ncfrag=<byte-offset>/<total-bytes>" */ if (release_len) append_release(buf); /* Copy the header into the buffer */ memcpy(buf + release_len, msg, header_len); header_len += release_len; /* for now on, the header will be persisted, and the msgbody * will be replaced */ send_fragmented_body(nt, buf, msgbody, header_len, msgbody_len); } /** * send_ext_msg_udp - send extended log message to target * @nt: target to send message to * @msg: extended log message to send * @msg_len: length of message * * Transfer extended log @msg to @nt. If @msg is longer than * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with * ncfrag header field added to identify them. */ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { int userdata_len = 0; int release_len = 0; #ifdef CONFIG_NETCONSOLE_DYNAMIC userdata_len = nt->userdata_length; #endif if (nt->release) release_len = strlen(init_utsname()->release) + 1; if (msg_len + release_len + userdata_len <= MAX_PRINT_CHUNK) return send_msg_no_fragmentation(nt, msg, msg_len, release_len); return send_msg_fragmented(nt, msg, msg_len, release_len); } static void write_ext_msg(struct console *con, const char *msg, unsigned int len) { struct netconsole_target *nt; unsigned long flags; if ((oops_only && !oops_in_progress) || list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) if (nt->extended && nt->enabled && netif_running(nt->np.dev)) send_ext_msg_udp(nt, msg, len); spin_unlock_irqrestore(&target_list_lock, flags); } static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; unsigned long flags; struct netconsole_target *nt; const char *tmp; if (oops_only && !oops_in_progress) return; /* Avoid taking lock and disabling interrupts unnecessarily */ if (list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!nt->extended && nt->enabled && netif_running(nt->np.dev)) { /* * We nest this inside the for-each-target loop above * so that we're able to get as much logging out to * at least one target if we die inside here, instead * of unnecessarily keeping all targets in lock-step. */ tmp = msg; for (left = len; left;) { frag = min(left, MAX_PRINT_CHUNK); send_udp(nt, tmp, frag); tmp += frag; left -= frag; } } } spin_unlock_irqrestore(&target_list_lock, flags); } /* Allocate new target (from boot/module param) and setup netpoll for it */ static struct netconsole_target *alloc_param_target(char *target_config, int cmdline_count) { struct netconsole_target *nt; int err; nt = alloc_and_init(); if (!nt) { err = -ENOMEM; goto fail; } if (*target_config == '+') { nt->extended = true; target_config++; } if (*target_config == 'r') { if (!nt->extended) { pr_err("Netconsole configuration error. Release feature requires extended log message"); err = -EINVAL; goto fail; } nt->release = true; target_config++; } /* Parse parameters and setup netpoll */ err = netpoll_parse_options(&nt->np, target_config); if (err) goto fail; err = netpoll_setup(&nt->np); if (err) { pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n", NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) /* only fail if dynamic reconfiguration is set, * otherwise, keep the target in the list, but disabled. */ goto fail; } else { nt->enabled = true; } populate_configfs_item(nt, cmdline_count); return nt; fail: kfree(nt); return ERR_PTR(err); } /* Cleanup netpoll for given target (from boot/module param) and free it */ static void free_param_target(struct netconsole_target *nt) { netpoll_cleanup(&nt->np); kfree(nt); } static struct console netconsole_ext = { .name = "netcon_ext", .flags = CON_ENABLED | CON_EXTENDED, .write = write_ext_msg, }; static struct console netconsole = { .name = "netcon", .flags = CON_ENABLED, .write = write_msg, }; static int __init init_netconsole(void) { int err; struct netconsole_target *nt, *tmp; unsigned int count = 0; bool extended = false; unsigned long flags; char *target_config; char *input = config; if (strnlen(input, MAX_PARAM_LENGTH)) { while ((target_config = strsep(&input, ";"))) { nt = alloc_param_target(target_config, count); if (IS_ERR(nt)) { if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) continue; err = PTR_ERR(nt); goto fail; } /* Dump existing printks when we register */ if (nt->extended) { extended = true; netconsole_ext.flags |= CON_PRINTBUFFER; } else { netconsole.flags |= CON_PRINTBUFFER; } spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); count++; } } err = register_netdevice_notifier(&netconsole_netdev_notifier); if (err) goto fail; err = dynamic_netconsole_init(); if (err) goto undonotifier; if (extended) register_console(&netconsole_ext); register_console(&netconsole); pr_info("network logging started\n"); return err; undonotifier: unregister_netdevice_notifier(&netconsole_netdev_notifier); fail: pr_err("cleaning up\n"); /* * Remove all targets and destroy them (only targets created * from the boot/module option exist here). Skipping the list * lock is safe here, and netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } return err; } static void __exit cleanup_netconsole(void) { struct netconsole_target *nt, *tmp; if (console_is_registered(&netconsole_ext)) unregister_console(&netconsole_ext); unregister_console(&netconsole); dynamic_netconsole_exit(); unregister_netdevice_notifier(&netconsole_netdev_notifier); /* * Targets created via configfs pin references on our module * and would first be rmdir(2)'ed from userspace. We reach * here only when they are already destroyed, and only those * created from the boot/module option are left, so remove and * destroy them. Skipping the list lock is safe here, and * netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } } /* * Use late_initcall to ensure netconsole is * initialized after network device driver if built-in. * * late_initcall() and module_init() are identical if built as module. */ late_initcall(init_netconsole); module_exit(cleanup_netconsole); |
| 2 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; spinlock_t lock; seqcount_spinlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { spin_lock(&fs->lock); *root = fs->root; path_get(root); spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); spin_unlock(&fs->lock); } extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ |
| 422 422 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); ), TP_printk("root=%d id=%llu level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_level ) __field( u64, dst_id ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); __entry->val = val; ), TP_printk("root=%d id=%llu level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DECLARE_EVENT_CLASS(cgroup_rstat, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __field( int, cpu ) __field( bool, contended ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __entry->cpu = cpu; __entry->contended = contended; ), TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d", __entry->root, __entry->id, __entry->level, __entry->cpu, __entry->contended) ); /* Related to global: cgroup_rstat_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); /* Related to per CPU: cgroup_rstat_cpu_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 3 147 147 13 12 1 14 2 13 13 13 13 13 13 2 1 1 11 3 1 2 2 1 1 1 1 1 2 2 2 2 60 23 23 4 21 4 31 31 1 32 31 1 2 2 2 2 32 32 31 7 4 3 2 1 2 3 10 6 2 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 | // SPDX-License-Identifier: GPL-2.0-only /* * VGICv3 MMIO handling functions */ #include <linux/bitfield.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/interrupt.h> #include <kvm/iodev.h> #include <kvm/arm_vgic.h> #include <asm/kvm_emulate.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include "vgic.h" #include "vgic-mmio.h" /* extract @num bytes at @offset bytes offset in data */ unsigned long extract_bytes(u64 data, unsigned int offset, unsigned int num) { return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0); } /* allows updates of any half of a 64-bit register (or the whole thing) */ u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len, unsigned long val) { int lower = (offset & 4) * 8; int upper = lower + 8 * len - 1; reg &= ~GENMASK_ULL(upper, lower); val &= GENMASK_ULL(len * 8 - 1, 0); return reg | ((u64)val << lower); } bool vgic_has_its(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; if (dist->vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3) return false; return dist->has_its; } bool vgic_supports_direct_msis(struct kvm *kvm) { return (kvm_vgic_global_state.has_gicv4_1 || (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); } /* * The Revision field in the IIDR have the following meanings: * * Revision 2: Interrupt groups are guest-configurable and signaled using * their configured groups. */ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; u32 value = 0; switch (addr & 0x0c) { case GICD_CTLR: if (vgic->enabled) value |= GICD_CTLR_ENABLE_SS_G1; value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; if (vgic->nassgireq) value |= GICD_CTLR_nASSGIreq; break; case GICD_TYPER: value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; value = (value >> 5) - 1; if (vgic_has_its(vcpu->kvm)) { value |= (INTERRUPT_ID_BITS_ITS - 1) << 19; value |= GICD_TYPER_LPIS; } else { value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19; } break; case GICD_TYPER2: if (kvm_vgic_global_state.has_gicv4_1 && gic_cpuif_has_vsgi()) value = GICD_TYPER2_nASSGIcap; break; case GICD_IIDR: value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | (IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT); break; default: return 0; } return value; } static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; switch (addr & 0x0c) { case GICD_CTLR: { bool was_enabled, is_hwsgi; mutex_lock(&vcpu->kvm->arch.config_lock); was_enabled = dist->enabled; is_hwsgi = dist->nassgireq; dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; /* Not a GICv4.1? No HW SGIs */ if (!kvm_vgic_global_state.has_gicv4_1 || !gic_cpuif_has_vsgi()) val &= ~GICD_CTLR_nASSGIreq; /* Dist stays enabled? nASSGIreq is RO */ if (was_enabled && dist->enabled) { val &= ~GICD_CTLR_nASSGIreq; val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi); } /* Switching HW SGIs? */ dist->nassgireq = val & GICD_CTLR_nASSGIreq; if (is_hwsgi != dist->nassgireq) vgic_v4_configure_vsgis(vcpu->kvm); if (kvm_vgic_global_state.has_gicv4_1 && was_enabled != dist->enabled) kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4); else if (!was_enabled && dist->enabled) vgic_kick_vcpus(vcpu->kvm); mutex_unlock(&vcpu->kvm->arch.config_lock); break; } case GICD_TYPER: case GICD_TYPER2: case GICD_IIDR: /* This is at best for documentation purposes... */ return; } } static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; u32 reg; switch (addr & 0x0c) { case GICD_TYPER2: if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) return -EINVAL; return 0; case GICD_IIDR: reg = vgic_mmio_read_v3_misc(vcpu, addr, len); if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK) return -EINVAL; reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg); switch (reg) { case KVM_VGIC_IMP_REV_2: case KVM_VGIC_IMP_REV_3: dist->implementation_rev = reg; return 0; default: return -EINVAL; } case GICD_CTLR: /* Not a GICv4.1? No HW SGIs */ if (!kvm_vgic_global_state.has_gicv4_1) val &= ~GICD_CTLR_nASSGIreq; dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; dist->nassgireq = val & GICD_CTLR_nASSGIreq; return 0; } vgic_mmio_write_v3_misc(vcpu, addr, len, val); return 0; } static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { int intid = VGIC_ADDR_TO_INTID(addr, 64); struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, intid); unsigned long ret = 0; if (!irq) return 0; /* The upper word is RAZ for us. */ if (!(addr & 4)) ret = extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len); vgic_put_irq(vcpu->kvm, irq); return ret; } static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { int intid = VGIC_ADDR_TO_INTID(addr, 64); struct vgic_irq *irq; unsigned long flags; /* The upper word is WI for us since we don't implement Aff3. */ if (addr & 4) return; irq = vgic_get_irq(vcpu->kvm, intid); if (!irq) return; raw_spin_lock_irqsave(&irq->irq_lock, flags); /* We only care about and preserve Aff0, Aff1 and Aff2. */ irq->mpidr = val & GENMASK(23, 0); irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } bool vgic_lpis_enabled(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; return atomic_read(&vgic_cpu->ctlr) == GICR_CTLR_ENABLE_LPIS; } static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; unsigned long val; val = atomic_read(&vgic_cpu->ctlr); if (vgic_get_implementation_rev(vcpu) >= KVM_VGIC_IMP_REV_3) val |= GICR_CTLR_IR | GICR_CTLR_CES; return val; } static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; u32 ctlr; if (!vgic_has_its(vcpu->kvm)) return; if (!(val & GICR_CTLR_ENABLE_LPIS)) { /* * Don't disable if RWP is set, as there already an * ongoing disable. Funky guest... */ ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, GICR_CTLR_ENABLE_LPIS, GICR_CTLR_RWP); if (ctlr != GICR_CTLR_ENABLE_LPIS) return; vgic_flush_pending_lpis(vcpu); vgic_its_invalidate_all_caches(vcpu->kvm); atomic_set_release(&vgic_cpu->ctlr, 0); } else { ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, 0, GICR_CTLR_ENABLE_LPIS); if (ctlr != 0) return; vgic_enable_lpis(vcpu); } } static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu) { struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_redist_region *iter, *rdreg = vgic_cpu->rdreg; if (!rdreg) return false; if (vgic_cpu->rdreg_index < rdreg->free_index - 1) { return false; } else if (rdreg->count && vgic_cpu->rdreg_index == (rdreg->count - 1)) { struct list_head *rd_regions = &vgic->rd_regions; gpa_t end = rdreg->base + rdreg->count * KVM_VGIC_V3_REDIST_SIZE; /* * the rdist is the last one of the redist region, * check whether there is no other contiguous rdist region */ list_for_each_entry(iter, rd_regions, list) { if (iter->base == end && iter->free_index > 0) return false; } } return true; } static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); int target_vcpu_id = vcpu->vcpu_id; u64 value; value = (u64)(mpidr & GENMASK(23, 0)) << 32; value |= ((target_vcpu_id & 0xffff) << 8); if (vgic_has_its(vcpu->kvm)) value |= GICR_TYPER_PLPIS; if (vgic_mmio_vcpu_rdist_is_last(vcpu)) value |= GICR_TYPER_LAST; return extract_bytes(value, addr & 7, len); } static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0); } static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { switch (addr & 0xffff) { case GICD_PIDR2: /* report a GICv3 compliant implementation */ return 0x3b; } return 0; } static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { int ret; ret = vgic_uaccess_write_spending(vcpu, addr, len, val); if (ret) return ret; return vgic_uaccess_write_cpending(vcpu, addr, len, ~val); } /* We want to avoid outer shareable. */ u64 vgic_sanitise_shareability(u64 field) { switch (field) { case GIC_BASER_OuterShareable: return GIC_BASER_InnerShareable; default: return field; } } /* Avoid any inner non-cacheable mapping. */ u64 vgic_sanitise_inner_cacheability(u64 field) { switch (field) { case GIC_BASER_CACHE_nCnB: case GIC_BASER_CACHE_nC: return GIC_BASER_CACHE_RaWb; default: return field; } } /* Non-cacheable or same-as-inner are OK. */ u64 vgic_sanitise_outer_cacheability(u64 field) { switch (field) { case GIC_BASER_CACHE_SameAsInner: case GIC_BASER_CACHE_nC: return field; default: return GIC_BASER_CACHE_SameAsInner; } } u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift, u64 (*sanitise_fn)(u64)) { u64 field = (reg & field_mask) >> field_shift; field = sanitise_fn(field) << field_shift; return (reg & ~field_mask) | field; } #define PROPBASER_RES0_MASK \ (GENMASK_ULL(63, 59) | GENMASK_ULL(55, 52) | GENMASK_ULL(6, 5)) #define PENDBASER_RES0_MASK \ (BIT_ULL(63) | GENMASK_ULL(61, 59) | GENMASK_ULL(55, 52) | \ GENMASK_ULL(15, 12) | GENMASK_ULL(6, 0)) static u64 vgic_sanitise_pendbaser(u64 reg) { reg = vgic_sanitise_field(reg, GICR_PENDBASER_SHAREABILITY_MASK, GICR_PENDBASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GICR_PENDBASER_INNER_CACHEABILITY_MASK, GICR_PENDBASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GICR_PENDBASER_OUTER_CACHEABILITY_MASK, GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); reg &= ~PENDBASER_RES0_MASK; return reg; } static u64 vgic_sanitise_propbaser(u64 reg) { reg = vgic_sanitise_field(reg, GICR_PROPBASER_SHAREABILITY_MASK, GICR_PROPBASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GICR_PROPBASER_INNER_CACHEABILITY_MASK, GICR_PROPBASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GICR_PROPBASER_OUTER_CACHEABILITY_MASK, GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); reg &= ~PROPBASER_RES0_MASK; return reg; } static unsigned long vgic_mmio_read_propbase(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; return extract_bytes(dist->propbaser, addr & 7, len); } static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_lpis_enabled(vcpu)) return; do { old_propbaser = READ_ONCE(dist->propbaser); propbaser = old_propbaser; propbaser = update_64bit_reg(propbaser, addr & 4, len, val); propbaser = vgic_sanitise_propbaser(propbaser); } while (cmpxchg64(&dist->propbaser, old_propbaser, propbaser) != old_propbaser); } static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; u64 value = vgic_cpu->pendbaser; value &= ~GICR_PENDBASER_PTZ; return extract_bytes(value, addr & 7, len); } static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_lpis_enabled(vcpu)) return; do { old_pendbaser = READ_ONCE(vgic_cpu->pendbaser); pendbaser = old_pendbaser; pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); pendbaser = vgic_sanitise_pendbaser(pendbaser); } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, pendbaser) != old_pendbaser); } static unsigned long vgic_mmio_read_sync(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return !!atomic_read(&vcpu->arch.vgic_cpu.syncr_busy); } static void vgic_set_rdist_busy(struct kvm_vcpu *vcpu, bool busy) { if (busy) { atomic_inc(&vcpu->arch.vgic_cpu.syncr_busy); smp_mb__after_atomic(); } else { smp_mb__before_atomic(); atomic_dec(&vcpu->arch.vgic_cpu.syncr_busy); } } static void vgic_mmio_write_invlpi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_irq *irq; u32 intid; /* * If the guest wrote only to the upper 32bit part of the * register, drop the write on the floor, as it is only for * vPEs (which we don't support for obvious reasons). * * Also discard the access if LPIs are not enabled. */ if ((addr & 4) || !vgic_lpis_enabled(vcpu)) return; intid = lower_32_bits(val); if (intid < VGIC_MIN_LPI) return; vgic_set_rdist_busy(vcpu, true); irq = vgic_get_irq(vcpu->kvm, intid); if (irq) { vgic_its_inv_lpi(vcpu->kvm, irq); vgic_put_irq(vcpu->kvm, irq); } vgic_set_rdist_busy(vcpu, false); } static void vgic_mmio_write_invall(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* See vgic_mmio_write_invlpi() for the early return rationale */ if ((addr & 4) || !vgic_lpis_enabled(vcpu)) return; vgic_set_rdist_busy(vcpu, true); vgic_its_invall(vcpu); vgic_set_rdist_busy(vcpu, false); } /* * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the * redistributors, while SPIs are covered by registers in the distributor * block. Trying to set private IRQs in this block gets ignored. * We take some special care here to fix the calculation of the register * offset. */ #define REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(off, rd, wr, ur, uw, bpi, acc) \ { \ .reg_offset = off, \ .bits_per_irq = bpi, \ .len = (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ .access_flags = acc, \ .read = vgic_mmio_read_raz, \ .write = vgic_mmio_write_wi, \ }, { \ .reg_offset = off + (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ .bits_per_irq = bpi, \ .len = (bpi * (1024 - VGIC_NR_PRIVATE_IRQS)) / 8, \ .access_flags = acc, \ .read = rd, \ .write = wr, \ .uaccess_read = ur, \ .uaccess_write = uw, \ } static const struct vgic_register_region vgic_v3_dist_registers[] = { REGISTER_DESC_WITH_LENGTH_UACCESS(GICD_CTLR, vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc, NULL, vgic_mmio_uaccess_write_v3_misc, 16, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICD_STATUSR, vgic_mmio_read_rao, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR, vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR, vgic_mmio_read_pending, vgic_mmio_write_cpending, vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ITARGETSR, vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICFGR, vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGRPMODR, vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IROUTER, vgic_mmio_read_irouter, vgic_mmio_write_irouter, NULL, NULL, 64, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICD_IDREGS, vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, VGIC_ACCESS_32bit), }; static const struct vgic_register_region vgic_v3_rd_registers[] = { /* RD_base registers */ REGISTER_DESC_WITH_LENGTH(GICR_CTLR, vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_STATUSR, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_IIDR, vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, NULL, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER, vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER, vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_INVLPIR, vgic_mmio_read_raz, vgic_mmio_write_invlpi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_INVALLR, vgic_mmio_read_raz, vgic_mmio_write_invall, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_SYNCR, vgic_mmio_read_sync, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_IDREGS, vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, VGIC_ACCESS_32bit), /* SGI_base registers */ REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, vgic_uaccess_write_senable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, vgic_uaccess_write_cenable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0, vgic_mmio_read_pending, vgic_mmio_write_cpending, vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICFGR0, vgic_mmio_read_config, vgic_mmio_write_config, 8, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGRPMODR0, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_NSACR, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), }; unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev) { dev->regions = vgic_v3_dist_registers; dev->nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops); return SZ_64K; } /** * vgic_register_redist_iodev - register a single redist iodev * @vcpu: The VCPU to which the redistributor belongs * * Register a KVM iodev for this VCPU's redistributor using the address * provided. * * Return 0 on success, -ERRNO otherwise. */ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *vgic = &kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; struct vgic_redist_region *rdreg; gpa_t rd_base; int ret = 0; lockdep_assert_held(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) goto out_unlock; /* * We may be creating VCPUs before having set the base address for the * redistributor region, in which case we will come back to this * function for all VCPUs when the base address is set. Just return * without doing any work for now. */ rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); if (!rdreg) goto out_unlock; if (!vgic_v3_check_base(kvm)) { ret = -EINVAL; goto out_unlock; } vgic_cpu->rdreg = rdreg; vgic_cpu->rdreg_index = rdreg->free_index; rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); rd_dev->base_addr = rd_base; rd_dev->iodev_type = IODEV_REDIST; rd_dev->regions = vgic_v3_rd_registers; rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); rd_dev->redist_vcpu = vcpu; mutex_unlock(&kvm->arch.config_lock); ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, 2 * SZ_64K, &rd_dev->dev); if (ret) return ret; /* Protected by slots_lock */ rdreg->free_index++; return 0; out_unlock: mutex_unlock(&kvm->arch.config_lock); return ret; } void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev); } static int vgic_register_all_redist_iodevs(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long c; int ret = 0; lockdep_assert_held(&kvm->slots_lock); kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); if (ret) break; } if (ret) { /* The current c failed, so iterate over the previous ones. */ int i; for (i = 0; i < c; i++) { vcpu = kvm_get_vcpu(kvm, i); vgic_unregister_redist_iodev(vcpu); } } return ret; } /** * vgic_v3_alloc_redist_region - Allocate a new redistributor region * * Performs various checks before inserting the rdist region in the list. * Those tests depend on whether the size of the rdist region is known * (ie. count != 0). The list is sorted by rdist region index. * * @kvm: kvm handle * @index: redist region index * @base: base of the new rdist region * @count: number of redistributors the region is made of (0 in the old style * single region, whose size is induced from the number of vcpus) * * Return 0 on success, < 0 otherwise */ static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index, gpa_t base, uint32_t count) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; struct list_head *rd_regions = &d->rd_regions; int nr_vcpus = atomic_read(&kvm->online_vcpus); size_t size = count ? count * KVM_VGIC_V3_REDIST_SIZE : nr_vcpus * KVM_VGIC_V3_REDIST_SIZE; int ret; /* cross the end of memory ? */ if (base + size < base) return -EINVAL; if (list_empty(rd_regions)) { if (index != 0) return -EINVAL; } else { rdreg = list_last_entry(rd_regions, struct vgic_redist_region, list); /* Don't mix single region and discrete redist regions */ if (!count && rdreg->count) return -EINVAL; if (!count) return -EEXIST; if (index != rdreg->index + 1) return -EINVAL; } /* * For legacy single-region redistributor regions (!count), * check that the redistributor region does not overlap with the * distributor's address space. */ if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && vgic_dist_overlap(kvm, base, size)) return -EINVAL; /* collision with any other rdist region? */ if (vgic_v3_rdist_overlap(kvm, base, size)) return -EINVAL; rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL_ACCOUNT); if (!rdreg) return -ENOMEM; rdreg->base = VGIC_ADDR_UNDEF; ret = vgic_check_iorange(kvm, rdreg->base, base, SZ_64K, size); if (ret) goto free; rdreg->base = base; rdreg->count = count; rdreg->free_index = 0; rdreg->index = index; list_add_tail(&rdreg->list, rd_regions); return 0; free: kfree(rdreg); return ret; } void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg) { struct kvm_vcpu *vcpu; unsigned long c; lockdep_assert_held(&kvm->arch.config_lock); /* Garbage collect the region */ kvm_for_each_vcpu(c, vcpu, kvm) { if (vcpu->arch.vgic_cpu.rdreg == rdreg) vcpu->arch.vgic_cpu.rdreg = NULL; } list_del(&rdreg->list); kfree(rdreg); } int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) { int ret; mutex_lock(&kvm->arch.config_lock); ret = vgic_v3_alloc_redist_region(kvm, index, addr, count); mutex_unlock(&kvm->arch.config_lock); if (ret) return ret; /* * Register iodevs for each existing VCPU. Adding more VCPUs * afterwards will register the iodevs when needed. */ ret = vgic_register_all_redist_iodevs(kvm); if (ret) { struct vgic_redist_region *rdreg; mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); vgic_v3_free_redist_region(kvm, rdreg); mutex_unlock(&kvm->arch.config_lock); return ret; } return 0; } int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) { const struct vgic_register_region *region; struct vgic_io_device iodev; struct vgic_reg_attr reg_attr; struct kvm_vcpu *vcpu; gpa_t addr; int ret; ret = vgic_v3_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: iodev.regions = vgic_v3_dist_registers; iodev.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); iodev.base_addr = 0; break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{ iodev.regions = vgic_v3_rd_registers; iodev.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); iodev.base_addr = 0; break; } case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_cpu_sysregs_attr(vcpu, attr); default: return -ENXIO; } /* We only support aligned 32-bit accesses. */ if (addr & 3) return -ENXIO; region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32)); if (!region) return -ENXIO; return 0; } /* * The ICC_SGI* registers encode the affinity differently from the MPIDR, * so provide a wrapper to use the existing defines to isolate a certain * affinity level. */ #define SGI_AFFINITY_LEVEL(reg, level) \ ((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \ >> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) static void vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, u32 sgi, bool allow_group1) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, sgi); unsigned long flags; raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * An access targeting Group0 SGIs can only generate * those, while an access targeting Group1 SGIs can * generate interrupts of either group. */ if (!irq->group || allow_group1) { if (!irq->hw) { irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { /* HW SGI? Ask the GIC to inject it */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } } else { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); } /** * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs * @vcpu: The VCPU requesting a SGI * @reg: The value written into ICC_{ASGI1,SGI0,SGI1}R by that VCPU * @allow_group1: Does the sysreg access allow generation of G1 SGIs * * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register. * This will trap in sys_regs.c and call this function. * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the * target processors as well as a bitmask of 16 Aff0 CPUs. * * If the interrupt routing mode bit is not set, we iterate over the Aff0 * bits and signal the VCPUs matching the provided Aff{3,2,1}. * * If this bit is set, we signal all, but not the calling VCPU. */ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) { struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *c_vcpu; unsigned long target_cpus; u64 mpidr; u32 sgi, aff0; unsigned long c; sgi = FIELD_GET(ICC_SGI1R_SGI_ID_MASK, reg); /* Broadcast */ if (unlikely(reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT))) { kvm_for_each_vcpu(c, c_vcpu, kvm) { /* Don't signal the calling VCPU */ if (c_vcpu == vcpu) continue; vgic_v3_queue_sgi(c_vcpu, sgi, allow_group1); } return; } /* We iterate over affinities to find the corresponding vcpus */ mpidr = SGI_AFFINITY_LEVEL(reg, 3); mpidr |= SGI_AFFINITY_LEVEL(reg, 2); mpidr |= SGI_AFFINITY_LEVEL(reg, 1); target_cpus = FIELD_GET(ICC_SGI1R_TARGET_LIST_MASK, reg); for_each_set_bit(aff0, &target_cpus, hweight_long(ICC_SGI1R_TARGET_LIST_MASK)) { c_vcpu = kvm_mpidr_to_vcpu(kvm, mpidr | aff0); if (c_vcpu) vgic_v3_queue_sgi(c_vcpu, sgi, allow_group1); } } int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val) { struct vgic_io_device dev = { .regions = vgic_v3_dist_registers, .nr_regions = ARRAY_SIZE(vgic_v3_dist_registers), }; return vgic_uaccess(vcpu, &dev, is_write, offset, val); } int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val) { struct vgic_io_device rd_dev = { .regions = vgic_v3_rd_registers, .nr_regions = ARRAY_SIZE(vgic_v3_rd_registers), }; return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val); } int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, u32 intid, u32 *val) { if (intid % 32) return -EINVAL; if (is_write) vgic_write_irq_line_level_info(vcpu, intid, *val); else *val = vgic_read_irq_line_level_info(vcpu, intid); return 0; } |
| 2 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PIPE_FS_I_H #define _LINUX_PIPE_FS_I_H #define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ #define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */ #ifdef CONFIG_WATCH_QUEUE #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer * @offset: offset of data inside the @page * @len: length of data inside the @page * @ops: operations associated with this buffer. See @pipe_buf_operations. * @flags: pipe buffer flags. See above. * @private: private data owned by the ops. **/ struct pipe_buffer { struct page *page; unsigned int offset, len; const struct pipe_buf_operations *ops; unsigned int flags; unsigned long private; }; /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; unsigned int head; unsigned int tail; unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; unsigned int r_counter; unsigned int w_counter; bool poll_usage; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; #ifdef CONFIG_WATCH_QUEUE struct watch_queue *watch_queue; #endif }; /* * Note on the nesting of these functions: * * ->confirm() * ->try_steal() * * That is, ->try_steal() must be called on a confirmed buffer. See below for * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); /* * When the contents of this pipe buffer has been completely * consumed by a reader, ->release() is called. */ void (*release)(struct pipe_inode_info *, struct pipe_buffer *); /* * Attempt to take ownership of the pipe buffer and its contents. * ->try_steal() returns %true for success, in which case the contents * of the pipe (the buf->page) is locked and now completely owned by the * caller. The page may then be transferred to a different mapping, the * most often used case is insertion into different file address space * cache. */ bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. */ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_has_watch_queue - Check whether the pipe is a watch_queue, * i.e. it was created with O_NOTIFICATION_PIPE * @pipe: The pipe to check * * Return: true if pipe is a watch queue, false otherwise. */ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) { #ifdef CONFIG_WATCH_QUEUE return pipe->watch_queue != NULL; #else return false; #endif } /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline bool pipe_empty(unsigned int head, unsigned int tail) { return head == tail; } /** * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { return head - tail; } /** * pipe_full - Return true if the pipe is full * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer * @limit: The maximum amount of slots available. */ static inline bool pipe_full(unsigned int head, unsigned int tail, unsigned int limit) { return pipe_occupancy(head, tail) >= limit; } /** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest */ static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, unsigned int slot) { return &pipe->bufs[slot & (pipe->ring_size - 1)]; } /** * pipe_head_buf - Return the pipe buffer at the head of the pipe ring * @pipe: The pipe to access */ static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) { return pipe_buf(pipe, pipe->head); } /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Return: %true if the reference was successfully obtained. */ static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return buf->ops->get(pipe, buf); } /** * pipe_buf_release - put a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to */ static inline void pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { const struct pipe_buf_operations *ops = buf->ops; buf->ops = NULL; ops->release(pipe, buf); } /** * pipe_buf_confirm - verify contents of the pipe buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to confirm */ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->confirm) return 0; return buf->ops->confirm(pipe, buf); } /** * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->try_steal) return false; return buf->ops->try_steal(pipe, buf); } static inline void pipe_discard_from(struct pipe_inode_info *pipe, unsigned int old_head) { unsigned int mask = pipe->ring_size - 1; while (pipe->head > old_head) pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE /* Pipe lock and unlock operations */ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); long pipe_fcntl(struct file *, unsigned int, unsigned int arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned int size); #endif |
| 634 634 581 593 594 591 594 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, #endif NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable folios are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a folio is on one of lrugen->folios[]. Otherwise it stores 0. * * After a folio is faulted in, the aging needs to check the accessed bit at * least twice before handing this folio over to the eviction. The first check * clears the accessed bit from the initial fault; the second check makes sure * this folio hasn't been used since then. This process, AKA second chance, * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two * generations are considered active; the rest of generations, if they exist, * are considered inactive. See lru_gen_is_active(). * * PG_active is always cleared while a folio is on one of lrugen->folios[] so * that the sliding window needs not to worry about it. And it's set again when * a folio considered active is isolated for non-reclaiming purposes, e.g., * migration. See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags, masked by LRU_GEN_MASK. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A folio accessed N times * through file descriptors is in tier order_base_2(N). A folio in the first * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by * PG_workingset. A folio in any other tier (1<N<5) between the first and last * is marked by additional bits of LRU_REFS_WIDTH in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the rest * infer whether folios accessed multiple times through file descriptors are * statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags, masked by LRU_REFS_MASK. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) /* * For folios accessed multiple times through file descriptors, * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily * promoted into the second oldest generation in the eviction path. And when * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is * only valid when PG_referenced is set. * * For folios accessed multiple times through page tables, folio_update_gen() * from a page table walk or lru_gen_set_refs() from a rmap walk sets * PG_referenced after the accessed bit is cleared for the first time. * Thereafter, those two paths set PG_workingset and promote folios to the * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. * * For both cases above, after PG_workingset is set on a folio, it remains until * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It * can be set again if lru_gen_test_recent() returns true upon a refault. */ #define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) struct lruvec; struct page_vma_mapped_walk; #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types so that they can be * incremented independently. Ideally min_seq[] are kept in sync when both anon * and file types are evictable. However, to adapt to situations like extreme * swappiness, they are allowed to be out of sync by at most * MAX_NR_GENS-MIN_NR_GENS-1. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* can only be modified under the LRU lock */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; int swappiness; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long wmark_pages(const struct zone *z, enum zone_watermarks w) { return z->_watermark[w] + z->watermark_boost; } static inline unsigned long min_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_MIN); } static inline unsigned long low_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_LOW); } static inline unsigned long high_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_HIGH); } static inline unsigned long promo_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_PROMO); } static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return a->pgmap == b->pgmap; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!zonelist_zone(z)) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 113 111 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * IRQ subsystem internal functions and variables: * * Do not ever include this file from anything else than * kernel/irq/. Do not even think about using any information outside * of this file for your non core code. */ #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/pm_runtime.h> #include <linux/sched/clock.h> #ifdef CONFIG_SPARSE_IRQ # define MAX_SPARSE_IRQS INT_MAX #else # define MAX_SPARSE_IRQS NR_IRQS #endif #define istate core_internal_state__do_not_mess_with_it extern bool noirqdebug; extern struct irqaction chained_action; /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, IRQTF_READY, }; /* * Bit masks for desc->core_internal_state__do_not_mess_with_it * * IRQS_AUTODETECT - autodetection in progress * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt * detection * IRQS_POLL_INPROGRESS - polling in progress * IRQS_ONESHOT - irq is not unmasked in primary handler * IRQS_REPLAY - irq has been resent and will not be resent * again until the handler has run and cleared * this flag. * IRQS_WAITING - irq is waiting * IRQS_PENDING - irq needs to be resent and should be resent * at the next available opportunity. * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, IRQS_SPURIOUS_DISABLED = 0x00000002, IRQS_POLL_INPROGRESS = 0x00000008, IRQS_ONESHOT = 0x00000020, IRQS_REPLAY = 0x00000040, IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, IRQS_SYSFS = 0x00004000, }; #include "debug.h" #include "settings.h" extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags); extern void __disable_irq(struct irq_desc *desc); extern void __enable_irq(struct irq_desc *desc); #define IRQ_RESEND true #define IRQ_NORESEND false #define IRQ_START_FORCE true #define IRQ_START_COND false extern int irq_activate(struct irq_desc *desc); extern int irq_activate_and_startup(struct irq_desc *desc, bool resend); extern int irq_startup(struct irq_desc *desc, bool resend, bool force); extern void irq_shutdown(struct irq_desc *desc); extern void irq_shutdown_and_deactivate(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); extern void unmask_threaded_irq(struct irq_desc *desc); extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask); #ifdef CONFIG_SPARSE_IRQ static inline void irq_mark_irq(unsigned int irq) { } #else extern void irq_mark_irq(unsigned int irq); #endif extern int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state); irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ int check_irq_resend(struct irq_desc *desc, bool inject); void clear_irq_resend(struct irq_desc *desc); void irq_resend_init(struct irq_desc *desc); bool irq_wait_for_poll(struct irq_desc *desc); void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); void wake_threads_waitq(struct irq_desc *desc); #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); #else static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void register_handler_proc(unsigned int irq, struct irqaction *action) { } static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif extern bool irq_can_set_affinity_usr(unsigned int irq); extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force); #ifdef CONFIG_SMP extern int irq_setup_affinity(struct irq_desc *desc); #else static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; } #endif /* Inline functions for support of irq chips on slow busses */ static inline void chip_bus_lock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_lock)) desc->irq_data.chip->irq_bus_lock(&desc->irq_data); } static inline void chip_bus_sync_unlock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock)) desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data); } #define _IRQ_DESC_CHECK (1 << 0) #define _IRQ_DESC_PERCPU (1 << 1) #define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) #define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) #define for_each_action_of_desc(desc, act) \ for (act = desc->action; act; act = act->next) struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check); void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus); static inline struct irq_desc * irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, true, check); } static inline void irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, true); } static inline struct irq_desc * irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, false, check); } static inline void irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, false); } #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) static inline unsigned int irqd_get(struct irq_data *d) { return __irqd_to_state(d); } /* * Manipulation functions for irq_data.state */ static inline void irqd_set_move_pending(struct irq_data *d) { __irqd_to_state(d) |= IRQD_SETAFFINITY_PENDING; } static inline void irqd_clr_move_pending(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING; } static inline void irqd_set_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) |= IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clr_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clear(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) &= ~mask; } static inline void irqd_set(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) |= mask; } static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) { return __irqd_to_state(d) & mask; } static inline void irq_state_set_disabled(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); } static inline void irq_state_set_masked(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } #undef __irqd_to_state static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __kstat_incr_irqs_this_cpu(desc); desc->tot_count++; } static inline int irq_desc_get_node(struct irq_desc *desc) { return irq_common_data_get_node(&desc->irq_common_data); } static inline int irq_desc_is_chained(struct irq_desc *desc) { return (desc->action && desc->action == &chained_action); } static inline bool irq_is_nmi(struct irq_desc *desc) { return desc->istate & IRQS_NMI; } #ifdef CONFIG_PM_SLEEP bool irq_pm_check_wakeup(struct irq_desc *desc); void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action); #else static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; } static inline void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif #ifdef CONFIG_IRQ_TIMINGS #define IRQ_TIMINGS_SHIFT 5 #define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) #define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) /** * struct irq_timings - irq timings storing structure * @values: a circular buffer of u64 encoded <timestamp,irq> values * @count: the number of elements in the array */ struct irq_timings { u64 values[IRQ_TIMINGS_SIZE]; int count; }; DECLARE_PER_CPU(struct irq_timings, irq_timings); extern void irq_timings_free(int irq); extern int irq_timings_alloc(int irq); static inline void irq_remove_timings(struct irq_desc *desc) { desc->istate &= ~IRQS_TIMINGS; irq_timings_free(irq_desc_get_irq(desc)); } static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) { int irq = irq_desc_get_irq(desc); int ret; /* * We don't need the measurement because the idle code already * knows the next expiry event. */ if (act->flags & __IRQF_TIMER) return; /* * In case the timing allocation fails, we just want to warn, * not fail, so letting the system boot anyway. */ ret = irq_timings_alloc(irq); if (ret) { pr_warn("Failed to allocate irq timing stats for irq%d (%d)", irq, ret); return; } desc->istate |= IRQS_TIMINGS; } extern void irq_timings_enable(void); extern void irq_timings_disable(void); DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); /* * The interrupt number and the timestamp are encoded into a single * u64 variable to optimize the size. * 48 bit time stamp and 16 bit IRQ number is way sufficient. * Who cares an IRQ after 78 hours of idle time? */ static inline u64 irq_timing_encode(u64 timestamp, int irq) { return (timestamp << 16) | irq; } static inline int irq_timing_decode(u64 value, u64 *timestamp) { *timestamp = value >> 16; return value & U16_MAX; } static __always_inline void irq_timings_push(u64 ts, int irq) { struct irq_timings *timings = this_cpu_ptr(&irq_timings); timings->values[timings->count & IRQ_TIMINGS_MASK] = irq_timing_encode(ts, irq); timings->count++; } /* * The function record_irq_time is only called in one place in the * interrupts handler. We want this function always inline so the code * inside is embedded in the function and the static key branching * code can act at the higher level. Without the explicit * __always_inline we can end up with a function call and a small * overhead in the hotpath for nothing. */ static __always_inline void record_irq_time(struct irq_desc *desc) { if (!static_branch_likely(&irq_timing_enabled)) return; if (desc->istate & IRQS_TIMINGS) irq_timings_push(local_clock(), irq_desc_get_irq(desc)); } #else static inline void irq_remove_timings(struct irq_desc *desc) {} static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) {}; static inline void record_irq_time(struct irq_desc *desc) {} #endif /* CONFIG_IRQ_TIMINGS */ #ifdef CONFIG_GENERIC_IRQ_CHIP void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); #else static inline void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ #ifdef CONFIG_GENERIC_PENDING_IRQ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED); } static inline bool irq_move_pending(struct irq_data *data) { return irqd_is_setaffinity_pending(data); } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { cpumask_copy(desc->pending_mask, mask); } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { cpumask_copy(mask, desc->pending_mask); } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } static inline bool irq_move_pending(struct irq_data *data) { return false; } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return NULL; } static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve) { irqd_set_activated(data); return 0; } static inline void irq_domain_deactivate_irq(struct irq_data *data) { irqd_clr_activated(data); } #endif static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd) { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY return irqd->parent_data; #else return NULL; #endif } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include <linux/debugfs.h> struct irq_bit_descr { unsigned int mask; char *name; }; #define BIT_MASK_DESCR(m) { .mask = m, .name = #m } void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, const struct irq_bit_descr *sd, int size); void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { debugfs_remove(desc->debugfs_file); kfree(desc->dev_name); } void irq_debugfs_copy_devname(int irq, struct device *dev); # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else static inline void irq_domain_debugfs_init(struct dentry *root) { } # endif #else /* CONFIG_GENERIC_IRQ_DEBUGFS */ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) { } static inline void irq_remove_debugfs_entry(struct irq_desc *d) { } static inline void irq_debugfs_copy_devname(int irq, struct device *dev) { } #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ |
| 44 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU #ifdef CONFIG_SWAP #include <linux/swapfile.h> #endif /* CONFIG_SWAP */ /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS #define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ #define SWP_PFN_BITS min_t(int, \ sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ #define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: * * |----------+--------------------| * | swp_type | swp_offset | * |----------+--------+-+-+-------| * | | resv |D|A| PFN | * |----------+--------+-+-+-------| * * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) * * Note: A/D bits will be stored in migration entries iff there're enough * free bits in arch specific swp offset. By default we'll ignore A/D bits * when migrating a page. Please refer to migration_entry_supports_ad() * for more information. If there're more bits besides PFN and A/D bits, * they should be reserved and always be zeros. */ #define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) #define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) #define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) #define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) #define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) static inline bool is_pfn_swap_entry(swp_entry_t entry); /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_exclusive(pte)) pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* * This should only be called upon a pfn swap entry to get the PFN stored * in the swap entry. Please refers to is_pfn_swap_entry() for definition * of pfn swap entry. */ static inline unsigned long swp_offset_pfn(swp_entry_t entry) { VM_BUG_ON(!is_pfn_swap_entry(entry)); return swp_offset(entry) & SWP_PFN_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_READ, offset); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_readable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ); } static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); } static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } /* * Returns whether the host has large enough swap offset field to support * carrying over pgtable A/D bits for page migrations. The result is * pretty much arch specific. */ static inline bool migration_entry_supports_ad(void) { #ifdef CONFIG_SWAP return swap_migration_ad_supported; #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_YOUNG); return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG; /* Keep the old behavior of aging page after migration */ return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_DIRTY); return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_DIRTY; /* Keep the old behavior of clean page after migration */ return false; } extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } static inline int is_readable_migration_entry(swp_entry_t entry) { return 0; } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { return false; } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } #endif typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) /* * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. * * Note that, when encountered by the faulting logic, PTEs with this marker will * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error * logic. */ #define PTE_MARKER_POISONED BIT(1) /* * Indicates that, on fault, this PTE will case a SIGSEGV signal to be * sent. This means guard markers behave in effect as if the region were mapped * PROT_NONE, rather than if they were a memory hole or equivalent. */ #define PTE_MARKER_GUARD BIT(2) #define PTE_MARKER_MASK (BIT(3) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { return swp_entry(SWP_PTE_MARKER, marker); } static inline bool is_pte_marker_entry(swp_entry_t entry) { return swp_type(entry) == SWP_PTE_MARKER; } static inline pte_marker pte_marker_get(swp_entry_t entry) { return swp_offset(entry) & PTE_MARKER_MASK; } static inline bool is_pte_marker(pte_t pte) { return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); } static inline pte_t make_pte_marker(pte_marker marker) { return swp_entry_to_pte(make_pte_marker_entry(marker)); } static inline swp_entry_t make_poisoned_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_POISONED); } static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); } static inline swp_entry_t make_guard_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_GUARD); } static inline int is_guard_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_GUARD); } /* * This is a special version to check pte_none() just to cover the case when * the pte is a pte marker. It existed because in many cases the pte marker * should be seen as a none pte; it's just that we have stored some information * onto the none pte so it becomes not-none any more. * * It should be used when the pte is file-backed, ram-based and backing * userspace pages, like shmem. It is not needed upon pgtables that do not * support pte markers at all. For example, it's not needed on anonymous * memory, kernel-only memory (including when the system is during-boot), * non-ram based generic file-system. It's fine to be used even there, but the * extra pte marker check will be pure overhead. */ static inline int pte_none_mostly(pte_t pte) { return pte_none(pte) || is_pte_marker(pte); } static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(is_migration_entry(entry) && !PageLocked(p)); return p; } static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) { struct folio *folio = pfn_folio(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding folio is locked */ BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio)); return folio; } /* * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They can either be used to represent unaddressable device * memory, to restrict access to a page undergoing migration or to represent a * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { /* Make sure the swp offset can always store the needed fields */ BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 443 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/nodemask.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> struct kernel_clone_args; /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 #ifdef CONFIG_CGROUPS enum { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; extern spinlock_t css_set_lock; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); void cgroup_file_show(struct cgroup_file *cfile, bool show); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_exit(struct task_struct *p); void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ #ifdef CONFIG_DEBUG_CGROUP_REF void css_get(struct cgroup_subsys_state *css); void css_get_many(struct cgroup_subsys_state *css, unsigned int n); bool css_tryget(struct cgroup_subsys_state *css); bool css_tryget_online(struct cgroup_subsys_state *css); void css_put(struct cgroup_subsys_state *css); void css_put_many(struct cgroup_subsys_state *css, unsigned int n); #else #define CGROUP_REF_FN_ATTRS static inline #define CGROUP_REF_EXPORT(fn) #include <linux/cgroup_refcnt.h> #endif static inline u64 cgroup_id(const struct cgroup *cgrp) { return cgrp->kn->id; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } extern struct mutex cgroup_mutex; static inline void cgroup_lock(void) { mutex_lock(&cgroup_mutex); } static inline void cgroup_unlock(void) { mutex_unlock(&cgroup_mutex); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestors[ancestor->level] == ancestor; } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (ancestor_level < 0 || ancestor_level > cgrp->level) return NULL; return cgrp->ancestors[ancestor_level]; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); struct cgroup *cgroup_get_from_id(u64 id); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline void cgroup_lock(void) {} static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline bool cgroup_psi_enabled(void) { return false; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(struct cgroup *cgrp); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ struct cgroup_namespace { struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; struct css_set *root_cset; }; extern struct cgroup_namespace init_cgroup_ns; #ifdef CONFIG_CGROUPS void free_cgroup_ns(struct cgroup_namespace *ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns); int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } static inline struct cgroup_namespace * copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { return old_ns; } #endif /* !CONFIG_CGROUPS */ static inline void get_cgroup_ns(struct cgroup_namespace *ns) { if (ns) refcount_inc(&ns->ns.count); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { if (ns && refcount_dec_and_test(&ns->ns.count)) free_cgroup_ns(ns); } #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); struct cgroup_of_peak *of_peak(struct kernfs_open_file *of); #endif /* _LINUX_CGROUP_H */ |
| 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 | // SPDX-License-Identifier: GPL-2.0-only /* * VFIO core * * Copyright (C) 2012 Red Hat, Inc. All rights reserved. * Author: Alex Williamson <alex.williamson@redhat.com> * * Derived from original vfio: * Copyright 2010 Cisco Systems, Inc. All rights reserved. * Author: Tom Lyon, pugs@cisco.com */ #include <linux/vfio.h> #include <linux/iommufd.h> #include <linux/anon_inodes.h> #include "vfio.h" static struct vfio { struct class *class; struct list_head group_list; struct mutex group_lock; /* locks group_list */ struct ida group_ida; dev_t group_devt; } vfio; static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group, char *buf) { struct vfio_device *it, *device = ERR_PTR(-ENODEV); mutex_lock(&group->device_lock); list_for_each_entry(it, &group->device_list, group_next) { int ret; if (it->ops->match) { ret = it->ops->match(it, buf); if (ret < 0) { device = ERR_PTR(ret); break; } } else { ret = !strcmp(dev_name(it->dev), buf); } if (ret && vfio_device_try_get_registration(it)) { device = it; break; } } mutex_unlock(&group->device_lock); return device; } /* * VFIO Group fd, /dev/vfio/$GROUP */ static bool vfio_group_has_iommu(struct vfio_group *group) { lockdep_assert_held(&group->group_lock); /* * There can only be users if there is a container, and if there is a * container there must be users. */ WARN_ON(!group->container != !group->container_users); return group->container || group->iommufd; } /* * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or * if there was no container to unset. Since the ioctl is called on * the group, we know that still exists, therefore the only valid * transition here is 1->0. */ static int vfio_group_ioctl_unset_container(struct vfio_group *group) { int ret = 0; mutex_lock(&group->group_lock); if (!vfio_group_has_iommu(group)) { ret = -EINVAL; goto out_unlock; } if (group->container) { if (group->container_users != 1) { ret = -EBUSY; goto out_unlock; } vfio_group_detach_container(group); } if (group->iommufd) { iommufd_ctx_put(group->iommufd); group->iommufd = NULL; } out_unlock: mutex_unlock(&group->group_lock); return ret; } static int vfio_group_ioctl_set_container(struct vfio_group *group, int __user *arg) { struct vfio_container *container; struct iommufd_ctx *iommufd; int ret; int fd; if (get_user(fd, arg)) return -EFAULT; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; mutex_lock(&group->group_lock); if (vfio_group_has_iommu(group)) { ret = -EINVAL; goto out_unlock; } if (!group->iommu_group) { ret = -ENODEV; goto out_unlock; } container = vfio_container_from_file(fd_file(f)); if (container) { ret = vfio_container_attach_group(container, group); goto out_unlock; } iommufd = iommufd_ctx_from_file(fd_file(f)); if (!IS_ERR(iommufd)) { if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && group->type == VFIO_NO_IOMMU) ret = iommufd_vfio_compat_set_no_iommu(iommufd); else ret = iommufd_vfio_compat_ioas_create(iommufd); if (ret) { iommufd_ctx_put(iommufd); goto out_unlock; } group->iommufd = iommufd; goto out_unlock; } /* The FD passed is not recognized. */ ret = -EBADFD; out_unlock: mutex_unlock(&group->group_lock); return ret; } static void vfio_device_group_get_kvm_safe(struct vfio_device *device) { spin_lock(&device->group->kvm_ref_lock); vfio_device_get_kvm_safe(device, device->group->kvm); spin_unlock(&device->group->kvm_ref_lock); } static int vfio_df_group_open(struct vfio_device_file *df) { struct vfio_device *device = df->device; int ret; mutex_lock(&device->group->group_lock); if (!vfio_group_has_iommu(device->group)) { ret = -EINVAL; goto out_unlock; } mutex_lock(&device->dev_set->lock); /* * Before the first device open, get the KVM pointer currently * associated with the group (if there is one) and obtain a reference * now that will be held until the open_count reaches 0 again. Save * the pointer in the device for use by drivers. */ if (device->open_count == 0) vfio_device_group_get_kvm_safe(device); df->iommufd = device->group->iommufd; if (df->iommufd && vfio_device_is_noiommu(device) && device->open_count == 0) { /* * Require no compat ioas to be assigned to proceed. The basic * statement is that the user cannot have done something that * implies they expected translation to exist */ if (!capable(CAP_SYS_RAWIO) || vfio_iommufd_device_has_compat_ioas(device, df->iommufd)) ret = -EPERM; else ret = 0; goto out_put_kvm; } ret = vfio_df_open(df); if (ret) goto out_put_kvm; if (df->iommufd && device->open_count == 1) { ret = vfio_iommufd_compat_attach_ioas(device, df->iommufd); if (ret) goto out_close_device; } /* * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ * read/write/mmap and vfio_file_has_device_access() */ smp_store_release(&df->access_granted, true); mutex_unlock(&device->dev_set->lock); mutex_unlock(&device->group->group_lock); return 0; out_close_device: vfio_df_close(df); out_put_kvm: df->iommufd = NULL; if (device->open_count == 0) vfio_device_put_kvm(device); mutex_unlock(&device->dev_set->lock); out_unlock: mutex_unlock(&device->group->group_lock); return ret; } void vfio_df_group_close(struct vfio_device_file *df) { struct vfio_device *device = df->device; mutex_lock(&device->group->group_lock); mutex_lock(&device->dev_set->lock); vfio_df_close(df); df->iommufd = NULL; if (device->open_count == 0) vfio_device_put_kvm(device); mutex_unlock(&device->dev_set->lock); mutex_unlock(&device->group->group_lock); } static struct file *vfio_device_open_file(struct vfio_device *device) { struct vfio_device_file *df; struct file *filep; int ret; df = vfio_allocate_device_file(device); if (IS_ERR(df)) { ret = PTR_ERR(df); goto err_out; } df->group = device->group; ret = vfio_df_group_open(df); if (ret) goto err_free; /* * We can't use anon_inode_getfd() because we need to modify * the f_mode flags directly to allow more than just ioctls */ filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops, df, O_RDWR); if (IS_ERR(filep)) { ret = PTR_ERR(filep); goto err_close_device; } /* * TODO: add an anon_inode interface to do this. * Appears to be missing by lack of need rather than * explicitly prevented. Now there's need. */ filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE); /* * Use the pseudo fs inode on the device to link all mmaps * to the same address space, allowing us to unmap all vmas * associated to this device using unmap_mapping_range(). */ filep->f_mapping = device->inode->i_mapping; if (device->group->type == VFIO_NO_IOMMU) dev_warn(device->dev, "vfio-noiommu device opened by user " "(%s:%d)\n", current->comm, task_pid_nr(current)); /* * On success the ref of device is moved to the file and * put in vfio_device_fops_release() */ return filep; err_close_device: vfio_df_group_close(df); err_free: kfree(df); err_out: return ERR_PTR(ret); } static int vfio_group_ioctl_get_device_fd(struct vfio_group *group, char __user *arg) { struct vfio_device *device; struct file *filep; char *buf; int fdno; int ret; buf = strndup_user(arg, PAGE_SIZE); if (IS_ERR(buf)) return PTR_ERR(buf); device = vfio_device_get_from_name(group, buf); kfree(buf); if (IS_ERR(device)) return PTR_ERR(device); fdno = get_unused_fd_flags(O_CLOEXEC); if (fdno < 0) { ret = fdno; goto err_put_device; } filep = vfio_device_open_file(device); if (IS_ERR(filep)) { ret = PTR_ERR(filep); goto err_put_fdno; } fd_install(fdno, filep); return fdno; err_put_fdno: put_unused_fd(fdno); err_put_device: vfio_device_put_registration(device); return ret; } static int vfio_group_ioctl_get_status(struct vfio_group *group, struct vfio_group_status __user *arg) { unsigned long minsz = offsetofend(struct vfio_group_status, flags); struct vfio_group_status status; if (copy_from_user(&status, arg, minsz)) return -EFAULT; if (status.argsz < minsz) return -EINVAL; status.flags = 0; mutex_lock(&group->group_lock); if (!group->iommu_group) { mutex_unlock(&group->group_lock); return -ENODEV; } /* * With the container FD the iommu_group_claim_dma_owner() is done * during SET_CONTAINER but for IOMMFD this is done during * VFIO_GROUP_GET_DEVICE_FD. Meaning that with iommufd * VFIO_GROUP_FLAGS_VIABLE could be set but GET_DEVICE_FD will fail due * to viability. */ if (vfio_group_has_iommu(group)) status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET | VFIO_GROUP_FLAGS_VIABLE; else if (!iommu_group_dma_owner_claimed(group->iommu_group)) status.flags |= VFIO_GROUP_FLAGS_VIABLE; mutex_unlock(&group->group_lock); if (copy_to_user(arg, &status, minsz)) return -EFAULT; return 0; } static long vfio_group_fops_unl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct vfio_group *group = filep->private_data; void __user *uarg = (void __user *)arg; switch (cmd) { case VFIO_GROUP_GET_DEVICE_FD: return vfio_group_ioctl_get_device_fd(group, uarg); case VFIO_GROUP_GET_STATUS: return vfio_group_ioctl_get_status(group, uarg); case VFIO_GROUP_SET_CONTAINER: return vfio_group_ioctl_set_container(group, uarg); case VFIO_GROUP_UNSET_CONTAINER: return vfio_group_ioctl_unset_container(group); default: return -ENOTTY; } } int vfio_device_block_group(struct vfio_device *device) { struct vfio_group *group = device->group; int ret = 0; mutex_lock(&group->group_lock); if (group->opened_file) { ret = -EBUSY; goto out_unlock; } group->cdev_device_open_cnt++; out_unlock: mutex_unlock(&group->group_lock); return ret; } void vfio_device_unblock_group(struct vfio_device *device) { struct vfio_group *group = device->group; mutex_lock(&group->group_lock); group->cdev_device_open_cnt--; mutex_unlock(&group->group_lock); } static int vfio_group_fops_open(struct inode *inode, struct file *filep) { struct vfio_group *group = container_of(inode->i_cdev, struct vfio_group, cdev); int ret; mutex_lock(&group->group_lock); /* * drivers can be zero if this races with vfio_device_remove_group(), it * will be stable at 0 under the group rwsem */ if (refcount_read(&group->drivers) == 0) { ret = -ENODEV; goto out_unlock; } if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) { ret = -EPERM; goto out_unlock; } if (group->cdev_device_open_cnt) { ret = -EBUSY; goto out_unlock; } /* * Do we need multiple instances of the group open? Seems not. */ if (group->opened_file) { ret = -EBUSY; goto out_unlock; } group->opened_file = filep; filep->private_data = group; ret = 0; out_unlock: mutex_unlock(&group->group_lock); return ret; } static int vfio_group_fops_release(struct inode *inode, struct file *filep) { struct vfio_group *group = filep->private_data; filep->private_data = NULL; mutex_lock(&group->group_lock); /* * Device FDs hold a group file reference, therefore the group release * is only called when there are no open devices. */ WARN_ON(group->notifier.head); if (group->container) vfio_group_detach_container(group); if (group->iommufd) { iommufd_ctx_put(group->iommufd); group->iommufd = NULL; } group->opened_file = NULL; mutex_unlock(&group->group_lock); return 0; } static const struct file_operations vfio_group_fops = { .owner = THIS_MODULE, .unlocked_ioctl = vfio_group_fops_unl_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = vfio_group_fops_open, .release = vfio_group_fops_release, }; /* * Group objects - create, release, get, put, search */ static struct vfio_group * vfio_group_find_from_iommu(struct iommu_group *iommu_group) { struct vfio_group *group; lockdep_assert_held(&vfio.group_lock); /* * group->iommu_group from the vfio.group_list cannot be NULL * under the vfio.group_lock. */ list_for_each_entry(group, &vfio.group_list, vfio_next) { if (group->iommu_group == iommu_group) return group; } return NULL; } static void vfio_group_release(struct device *dev) { struct vfio_group *group = container_of(dev, struct vfio_group, dev); mutex_destroy(&group->device_lock); mutex_destroy(&group->group_lock); WARN_ON(group->iommu_group); WARN_ON(group->cdev_device_open_cnt); ida_free(&vfio.group_ida, MINOR(group->dev.devt)); kfree(group); } static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group, enum vfio_group_type type) { struct vfio_group *group; int minor; group = kzalloc(sizeof(*group), GFP_KERNEL); if (!group) return ERR_PTR(-ENOMEM); minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL); if (minor < 0) { kfree(group); return ERR_PTR(minor); } device_initialize(&group->dev); group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor); group->dev.class = vfio.class; group->dev.release = vfio_group_release; cdev_init(&group->cdev, &vfio_group_fops); group->cdev.owner = THIS_MODULE; refcount_set(&group->drivers, 1); mutex_init(&group->group_lock); spin_lock_init(&group->kvm_ref_lock); INIT_LIST_HEAD(&group->device_list); mutex_init(&group->device_lock); group->iommu_group = iommu_group; /* put in vfio_group_release() */ iommu_group_ref_get(iommu_group); group->type = type; BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); return group; } static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, enum vfio_group_type type) { struct vfio_group *group; struct vfio_group *ret; int err; lockdep_assert_held(&vfio.group_lock); group = vfio_group_alloc(iommu_group, type); if (IS_ERR(group)) return group; err = dev_set_name(&group->dev, "%s%d", group->type == VFIO_NO_IOMMU ? "noiommu-" : "", iommu_group_id(iommu_group)); if (err) { ret = ERR_PTR(err); goto err_put; } err = cdev_device_add(&group->cdev, &group->dev); if (err) { ret = ERR_PTR(err); goto err_put; } list_add(&group->vfio_next, &vfio.group_list); return group; err_put: put_device(&group->dev); return ret; } static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev, enum vfio_group_type type) { struct iommu_group *iommu_group; struct vfio_group *group; int ret; iommu_group = iommu_group_alloc(); if (IS_ERR(iommu_group)) return ERR_CAST(iommu_group); ret = iommu_group_set_name(iommu_group, "vfio-noiommu"); if (ret) goto out_put_group; ret = iommu_group_add_device(iommu_group, dev); if (ret) goto out_put_group; mutex_lock(&vfio.group_lock); group = vfio_create_group(iommu_group, type); mutex_unlock(&vfio.group_lock); if (IS_ERR(group)) { ret = PTR_ERR(group); goto out_remove_device; } iommu_group_put(iommu_group); return group; out_remove_device: iommu_group_remove_device(dev); out_put_group: iommu_group_put(iommu_group); return ERR_PTR(ret); } static bool vfio_group_has_device(struct vfio_group *group, struct device *dev) { struct vfio_device *device; mutex_lock(&group->device_lock); list_for_each_entry(device, &group->device_list, group_next) { if (device->dev == dev) { mutex_unlock(&group->device_lock); return true; } } mutex_unlock(&group->device_lock); return false; } static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) { struct iommu_group *iommu_group; struct vfio_group *group; iommu_group = iommu_group_get(dev); if (!iommu_group && vfio_noiommu) { /* * With noiommu enabled, create an IOMMU group for devices that * don't already have one, implying no IOMMU hardware/driver * exists. Taint the kernel because we're about to give a DMA * capable device to a user without IOMMU protection. */ group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU); if (!IS_ERR(group)) { add_taint(TAINT_USER, LOCKDEP_STILL_OK); dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); } return group; } if (!iommu_group) return ERR_PTR(-EINVAL); mutex_lock(&vfio.group_lock); group = vfio_group_find_from_iommu(iommu_group); if (group) { if (WARN_ON(vfio_group_has_device(group, dev))) group = ERR_PTR(-EINVAL); else refcount_inc(&group->drivers); } else { group = vfio_create_group(iommu_group, VFIO_IOMMU); } mutex_unlock(&vfio.group_lock); /* The vfio_group holds a reference to the iommu_group */ iommu_group_put(iommu_group); return group; } int vfio_device_set_group(struct vfio_device *device, enum vfio_group_type type) { struct vfio_group *group; if (type == VFIO_IOMMU) group = vfio_group_find_or_alloc(device->dev); else group = vfio_noiommu_group_alloc(device->dev, type); if (IS_ERR(group)) return PTR_ERR(group); /* Our reference on group is moved to the device */ device->group = group; return 0; } void vfio_device_remove_group(struct vfio_device *device) { struct vfio_group *group = device->group; struct iommu_group *iommu_group; if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU) iommu_group_remove_device(device->dev); /* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */ if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock)) return; list_del(&group->vfio_next); /* * We could concurrently probe another driver in the group that might * race vfio_device_remove_group() with vfio_get_group(), so we have to * ensure that the sysfs is all cleaned up under lock otherwise the * cdev_device_add() will fail due to the name aready existing. */ cdev_device_del(&group->cdev, &group->dev); mutex_lock(&group->group_lock); /* * These data structures all have paired operations that can only be * undone when the caller holds a live reference on the device. Since * all pairs must be undone these WARN_ON's indicate some caller did not * properly hold the group reference. */ WARN_ON(!list_empty(&group->device_list)); WARN_ON(group->notifier.head); /* * Revoke all users of group->iommu_group. At this point we know there * are no devices active because we are unplugging the last one. Setting * iommu_group to NULL blocks all new users. */ if (group->container) vfio_group_detach_container(group); iommu_group = group->iommu_group; group->iommu_group = NULL; mutex_unlock(&group->group_lock); mutex_unlock(&vfio.group_lock); iommu_group_put(iommu_group); put_device(&group->dev); } void vfio_device_group_register(struct vfio_device *device) { mutex_lock(&device->group->device_lock); list_add(&device->group_next, &device->group->device_list); mutex_unlock(&device->group->device_lock); } void vfio_device_group_unregister(struct vfio_device *device) { mutex_lock(&device->group->device_lock); list_del(&device->group_next); mutex_unlock(&device->group->device_lock); } int vfio_device_group_use_iommu(struct vfio_device *device) { struct vfio_group *group = device->group; int ret = 0; lockdep_assert_held(&group->group_lock); if (WARN_ON(!group->container)) return -EINVAL; ret = vfio_group_use_container(group); if (ret) return ret; vfio_device_container_register(device); return 0; } void vfio_device_group_unuse_iommu(struct vfio_device *device) { struct vfio_group *group = device->group; lockdep_assert_held(&group->group_lock); if (WARN_ON(!group->container)) return; vfio_device_container_unregister(device); vfio_group_unuse_container(group); } bool vfio_device_has_container(struct vfio_device *device) { return device->group->container; } struct vfio_group *vfio_group_from_file(struct file *file) { struct vfio_group *group = file->private_data; if (file->f_op != &vfio_group_fops) return NULL; return group; } /** * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file * @file: VFIO group file * * The returned iommu_group is valid as long as a ref is held on the file. This * returns a reference on the group. This function is deprecated, only the SPAPR * path in kvm should call it. */ struct iommu_group *vfio_file_iommu_group(struct file *file) { struct vfio_group *group = vfio_group_from_file(file); struct iommu_group *iommu_group = NULL; if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU)) return NULL; if (!group) return NULL; mutex_lock(&group->group_lock); if (group->iommu_group) { iommu_group = group->iommu_group; iommu_group_ref_get(iommu_group); } mutex_unlock(&group->group_lock); return iommu_group; } EXPORT_SYMBOL_GPL(vfio_file_iommu_group); /** * vfio_file_is_group - True if the file is a vfio group file * @file: VFIO group file */ bool vfio_file_is_group(struct file *file) { return vfio_group_from_file(file); } EXPORT_SYMBOL_GPL(vfio_file_is_group); bool vfio_group_enforced_coherent(struct vfio_group *group) { struct vfio_device *device; bool ret = true; /* * If the device does not have IOMMU_CAP_ENFORCE_CACHE_COHERENCY then * any domain later attached to it will also not support it. If the cap * is set then the iommu_domain eventually attached to the device/group * must use a domain with enforce_cache_coherency(). */ mutex_lock(&group->device_lock); list_for_each_entry(device, &group->device_list, group_next) { if (!device_iommu_capable(device->dev, IOMMU_CAP_ENFORCE_CACHE_COHERENCY)) { ret = false; break; } } mutex_unlock(&group->device_lock); return ret; } void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm) { spin_lock(&group->kvm_ref_lock); group->kvm = kvm; spin_unlock(&group->kvm_ref_lock); } /** * vfio_file_has_dev - True if the VFIO file is a handle for device * @file: VFIO file to check * @device: Device that must be part of the file * * Returns true if given file has permission to manipulate the given device. */ bool vfio_file_has_dev(struct file *file, struct vfio_device *device) { struct vfio_group *group = vfio_group_from_file(file); if (!group) return false; return group == device->group; } EXPORT_SYMBOL_GPL(vfio_file_has_dev); static char *vfio_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev)); } int __init vfio_group_init(void) { int ret; ida_init(&vfio.group_ida); mutex_init(&vfio.group_lock); INIT_LIST_HEAD(&vfio.group_list); ret = vfio_container_init(); if (ret) return ret; /* /dev/vfio/$GROUP */ vfio.class = class_create("vfio"); if (IS_ERR(vfio.class)) { ret = PTR_ERR(vfio.class); goto err_group_class; } vfio.class->devnode = vfio_devnode; ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio"); if (ret) goto err_alloc_chrdev; return 0; err_alloc_chrdev: class_destroy(vfio.class); vfio.class = NULL; err_group_class: vfio_container_cleanup(); return ret; } void vfio_group_cleanup(void) { WARN_ON(!list_empty(&vfio.group_list)); ida_destroy(&vfio.group_ida); unregister_chrdev_region(vfio.group_devt, MINORMASK + 1); class_destroy(vfio.class); vfio.class = NULL; vfio_container_cleanup(); } |
| 4 4 1 341 342 1 1 19 19 1 1 1 1 1 1 1 1 23 23 1 276 4 277 278 4 4 4 4 18 19 19 19 19 18 19 19 18 19 19 19 19 19 19 18 19 19 4 4 19 19 343 343 341 340 1 343 342 4 4 646 647 278 4 647 645 18 401 403 193 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the kernel access vector cache (AVC). * * Authors: Stephen Smalley, <stephen.smalley.work@gmail.com> * James Morris <jmorris@redhat.com> * * Update: KaiGai, Kohei <kaigai@ak.jp.nec.com> * Replaced the avc_lock spinlock by RCU. * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/dcache.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/percpu.h> #include <linux/list.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/ip.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include "avc.h" #include "avc_ss.h" #include "classmap.h" #define CREATE_TRACE_POINTS #include <trace/events/avc.h> #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 #define AVC_CACHE_RECLAIM 16 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS #define avc_cache_stats_incr(field) this_cpu_inc(avc_cache_stats.field) #else #define avc_cache_stats_incr(field) do {} while (0) #endif struct avc_entry { u32 ssid; u32 tsid; u16 tclass; struct av_decision avd; struct avc_xperms_node *xp_node; }; struct avc_node { struct avc_entry ae; struct hlist_node list; /* anchored in avc_cache->slots[i] */ struct rcu_head rhead; }; struct avc_xperms_decision_node { struct extended_perms_decision xpd; struct list_head xpd_list; /* list of extended_perms_decision */ }; struct avc_xperms_node { struct extended_perms xp; struct list_head xpd_head; /* list head of extended_perms_decision */ }; struct avc_cache { struct hlist_head slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */ spinlock_t slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */ atomic_t lru_hint; /* LRU hint for reclaim scan */ atomic_t active_nodes; u32 latest_notif; /* latest revocation notification */ }; struct avc_callback_node { int (*callback) (u32 event); u32 events; struct avc_callback_node *next; }; #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 }; #endif struct selinux_avc { unsigned int avc_cache_threshold; struct avc_cache avc_cache; }; static struct selinux_avc selinux_avc; void selinux_avc_init(void) { int i; selinux_avc.avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD; for (i = 0; i < AVC_CACHE_SLOTS; i++) { INIT_HLIST_HEAD(&selinux_avc.avc_cache.slots[i]); spin_lock_init(&selinux_avc.avc_cache.slots_lock[i]); } atomic_set(&selinux_avc.avc_cache.active_nodes, 0); atomic_set(&selinux_avc.avc_cache.lru_hint, 0); } unsigned int avc_get_cache_threshold(void) { return selinux_avc.avc_cache_threshold; } void avc_set_cache_threshold(unsigned int cache_threshold) { selinux_avc.avc_cache_threshold = cache_threshold; } static struct avc_callback_node *avc_callbacks __ro_after_init; static struct kmem_cache *avc_node_cachep __ro_after_init; static struct kmem_cache *avc_xperms_data_cachep __ro_after_init; static struct kmem_cache *avc_xperms_decision_cachep __ro_after_init; static struct kmem_cache *avc_xperms_cachep __ro_after_init; static inline u32 avc_hash(u32 ssid, u32 tsid, u16 tclass) { return (ssid ^ (tsid<<2) ^ (tclass<<4)) & (AVC_CACHE_SLOTS - 1); } /** * avc_init - Initialize the AVC. * * Initialize the access vector cache. */ void __init avc_init(void) { avc_node_cachep = KMEM_CACHE(avc_node, SLAB_PANIC); avc_xperms_cachep = KMEM_CACHE(avc_xperms_node, SLAB_PANIC); avc_xperms_decision_cachep = KMEM_CACHE(avc_xperms_decision_node, SLAB_PANIC); avc_xperms_data_cachep = KMEM_CACHE(extended_perms_data, SLAB_PANIC); } int avc_get_hash_stats(char *page) { int i, chain_len, max_chain_len, slots_used; struct avc_node *node; struct hlist_head *head; rcu_read_lock(); slots_used = 0; max_chain_len = 0; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &selinux_avc.avc_cache.slots[i]; if (!hlist_empty(head)) { slots_used++; chain_len = 0; hlist_for_each_entry_rcu(node, head, list) chain_len++; if (chain_len > max_chain_len) max_chain_len = chain_len; } } rcu_read_unlock(); return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", atomic_read(&selinux_avc.avc_cache.active_nodes), slots_used, AVC_CACHE_SLOTS, max_chain_len); } /* * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ static struct extended_perms_decision * avc_xperms_decision_lookup(u8 driver, u8 base_perm, struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { if (xpd_node->xpd.driver == driver && xpd_node->xpd.base_perm == base_perm) return &xpd_node->xpd; } return NULL; } static inline unsigned int avc_xperms_has_perm(struct extended_perms_decision *xpd, u8 perm, u8 which) { unsigned int rc = 0; if ((which == XPERMS_ALLOWED) && (xpd->used & XPERMS_ALLOWED)) rc = security_xperm_test(xpd->allowed->p, perm); else if ((which == XPERMS_AUDITALLOW) && (xpd->used & XPERMS_AUDITALLOW)) rc = security_xperm_test(xpd->auditallow->p, perm); else if ((which == XPERMS_DONTAUDIT) && (xpd->used & XPERMS_DONTAUDIT)) rc = security_xperm_test(xpd->dontaudit->p, perm); return rc; } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, u8 driver, u8 base_perm, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); xp_node->xp.base_perms |= base_perm; xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node) { struct extended_perms_decision *xpd; xpd = &xpd_node->xpd; if (xpd->allowed) kmem_cache_free(avc_xperms_data_cachep, xpd->allowed); if (xpd->auditallow) kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow); if (xpd->dontaudit) kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit); kmem_cache_free(avc_xperms_decision_cachep, xpd_node); } static void avc_xperms_free(struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node, *tmp; if (!xp_node) return; list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) { list_del(&xpd_node->xpd_list); avc_xperms_decision_free(xpd_node); } kmem_cache_free(avc_xperms_cachep, xp_node); } static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { dest->base_perm = src->base_perm; dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) memcpy(dest->allowed->p, src->allowed->p, sizeof(src->allowed->p)); if (dest->used & XPERMS_AUDITALLOW) memcpy(dest->auditallow->p, src->auditallow->p, sizeof(src->auditallow->p)); if (dest->used & XPERMS_DONTAUDIT) memcpy(dest->dontaudit->p, src->dontaudit->p, sizeof(src->dontaudit->p)); } /* * similar to avc_copy_xperms_decision, but only copy decision * information relevant to this perm */ static inline void avc_quick_copy_xperms_decision(u8 perm, struct extended_perms_decision *dest, struct extended_perms_decision *src) { /* * compute index of the u32 of the 256 bits (8 u32s) that contain this * command permission */ u8 i = perm >> 5; dest->base_perm = src->base_perm; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; if (dest->used & XPERMS_AUDITALLOW) dest->auditallow->p[i] = src->auditallow->p[i]; if (dest->used & XPERMS_DONTAUDIT) dest->dontaudit->p[i] = src->dontaudit->p[i]; } static struct avc_xperms_decision_node *avc_xperms_decision_alloc(u8 which) { struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } return xpd_node; error: avc_xperms_decision_free(xpd_node); return NULL; } static int avc_add_xperms_decision(struct avc_node *node, struct extended_perms_decision *src) { struct avc_xperms_decision_node *dest_xpd; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); node->ae.xp_node->xp.len++; return 0; } static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); return xp_node; } static int avc_xperms_populate(struct avc_node *node, struct avc_xperms_node *src) { struct avc_xperms_node *dest; struct avc_xperms_decision_node *dest_xpd; struct avc_xperms_decision_node *src_xpd; if (src->xp.len == 0) return 0; dest = avc_xperms_alloc(); if (!dest) return -ENOMEM; memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; dest->xp.base_perms = src->xp.base_perms; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used); if (!dest_xpd) goto error; avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd); list_add(&dest_xpd->xpd_list, &dest->xpd_head); } node->ae.xp_node = dest; return 0; error: avc_xperms_free(dest); return -ENOMEM; } static inline u32 avc_xperms_audit_required(u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; if (audited && xpd) { if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT)) audited = 0; } } else if (result) { audited = denied = requested; } else { audited = requested & avd->auditallow; if (audited && xpd) { if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW)) audited = 0; } } *deniedp = denied; return audited; } static inline int avc_xperms_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, struct common_audit_data *ad) { u32 audited, denied; audited = avc_xperms_audit_required( requested, avd, xpd, perm, result, &denied); if (likely(!audited)) return 0; return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied, result, ad); } static void avc_node_free(struct rcu_head *rhead) { struct avc_node *node = container_of(rhead, struct avc_node, rhead); avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); } static void avc_node_delete(struct avc_node *node) { hlist_del_rcu(&node->list); call_rcu(&node->rhead, avc_node_free); atomic_dec(&selinux_avc.avc_cache.active_nodes); } static void avc_node_kill(struct avc_node *node) { avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); atomic_dec(&selinux_avc.avc_cache.active_nodes); } static void avc_node_replace(struct avc_node *new, struct avc_node *old) { hlist_replace_rcu(&old->list, &new->list); call_rcu(&old->rhead, avc_node_free); atomic_dec(&selinux_avc.avc_cache.active_nodes); } static inline int avc_reclaim_node(void) { struct avc_node *node; int hvalue, try, ecx; unsigned long flags; struct hlist_head *head; spinlock_t *lock; for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) { hvalue = atomic_inc_return(&selinux_avc.avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1); head = &selinux_avc.avc_cache.slots[hvalue]; lock = &selinux_avc.avc_cache.slots_lock[hvalue]; if (!spin_trylock_irqsave(lock, flags)) continue; rcu_read_lock(); hlist_for_each_entry(node, head, list) { avc_node_delete(node); avc_cache_stats_incr(reclaims); ecx++; if (ecx >= AVC_CACHE_RECLAIM) { rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); goto out; } } rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); } out: return ecx; } static struct avc_node *avc_alloc_node(void) { struct avc_node *node; node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; INIT_HLIST_NODE(&node->list); avc_cache_stats_incr(allocations); if (atomic_inc_return(&selinux_avc.avc_cache.active_nodes) > selinux_avc.avc_cache_threshold) avc_reclaim_node(); out: return node; } static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { node->ae.ssid = ssid; node->ae.tsid = tsid; node->ae.tclass = tclass; memcpy(&node->ae.avd, avd, sizeof(node->ae.avd)); } static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node, *ret = NULL; u32 hvalue; struct hlist_head *head; hvalue = avc_hash(ssid, tsid, tclass); head = &selinux_avc.avc_cache.slots[hvalue]; hlist_for_each_entry_rcu(node, head, list) { if (ssid == node->ae.ssid && tclass == node->ae.tclass && tsid == node->ae.tsid) { ret = node; break; } } return ret; } /** * avc_lookup - Look up an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * * Look up an AVC entry that is valid for the * (@ssid, @tsid), interpreting the permissions * based on @tclass. If a valid AVC entry exists, * then this function returns the avc_node. * Otherwise, this function returns NULL. */ static struct avc_node *avc_lookup(u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node; avc_cache_stats_incr(lookups); node = avc_search_node(ssid, tsid, tclass); if (node) return node; avc_cache_stats_incr(misses); return NULL; } static int avc_latest_notif_update(u32 seqno, int is_insert) { int ret = 0; static DEFINE_SPINLOCK(notif_lock); unsigned long flag; spin_lock_irqsave(¬if_lock, flag); if (is_insert) { if (seqno < selinux_avc.avc_cache.latest_notif) { pr_warn("SELinux: avc: seqno %d < latest_notif %d\n", seqno, selinux_avc.avc_cache.latest_notif); ret = -EAGAIN; } } else { if (seqno > selinux_avc.avc_cache.latest_notif) selinux_avc.avc_cache.latest_notif = seqno; } spin_unlock_irqrestore(¬if_lock, flag); return ret; } /** * avc_insert - Insert an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @avd: resulting av decision * @xp_node: resulting extended permissions * * Insert an AVC entry for the SID pair * (@ssid, @tsid) and class @tclass. * The access vectors and the sequence number are * normally provided by the security server in * response to a security_compute_av() call. If the * sequence number @avd->seqno is not less than the latest * revocation notification, then the function copies * the access vectors into a cache entry. */ static void avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { struct avc_node *pos, *node = NULL; u32 hvalue; unsigned long flag; spinlock_t *lock; struct hlist_head *head; if (avc_latest_notif_update(avd->seqno, 1)) return; node = avc_alloc_node(); if (!node) return; avc_node_populate(node, ssid, tsid, tclass, avd); if (avc_xperms_populate(node, xp_node)) { avc_node_kill(node); return; } hvalue = avc_hash(ssid, tsid, tclass); head = &selinux_avc.avc_cache.slots[hvalue]; lock = &selinux_avc.avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (pos->ae.ssid == ssid && pos->ae.tsid == tsid && pos->ae.tclass == tclass) { avc_node_replace(node, pos); goto found; } } hlist_add_head_rcu(&node->list, head); found: spin_unlock_irqrestore(lock, flag); } /** * avc_audit_pre_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; u32 av = sad->audited, perm; const char *const *perms; u32 i; audit_log_format(ab, "avc: %s ", sad->denied ? "denied" : "granted"); if (av == 0) { audit_log_format(ab, " null"); return; } perms = secclass_map[sad->tclass-1].perms; audit_log_format(ab, " {"); i = 0; perm = 1; while (i < (sizeof(av) * 8)) { if ((perm & av) && perms[i]) { audit_log_format(ab, " %s", perms[i]); av &= ~perm; } i++; perm <<= 1; } if (av) audit_log_format(ab, " 0x%x", av); audit_log_format(ab, " } for "); } /** * avc_audit_post_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; char *scontext = NULL; char *tcontext = NULL; const char *tclass = NULL; u32 scontext_len; u32 tcontext_len; int rc; rc = security_sid_to_context(sad->ssid, &scontext, &scontext_len); if (rc) audit_log_format(ab, " ssid=%d", sad->ssid); else audit_log_format(ab, " scontext=%s", scontext); rc = security_sid_to_context(sad->tsid, &tcontext, &tcontext_len); if (rc) audit_log_format(ab, " tsid=%d", sad->tsid); else audit_log_format(ab, " tcontext=%s", tcontext); tclass = secclass_map[sad->tclass-1].name; audit_log_format(ab, " tclass=%s", tclass); if (sad->denied) audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1); trace_selinux_audited(sad, scontext, tcontext, tclass); kfree(tcontext); kfree(scontext); /* in case of invalid context report also the actual context string */ rc = security_sid_to_context_inval(sad->ssid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " srawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } rc = security_sid_to_context_inval(sad->tsid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " trawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } } /* * This is the slow part of avc audit with big stack footprint. * Note that it is non-blocking and can be called from under * rcu_read_lock(). */ noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a) { struct common_audit_data stack_data; struct selinux_audit_data sad; if (WARN_ON(!tclass || tclass >= ARRAY_SIZE(secclass_map))) return -EINVAL; if (!a) { a = &stack_data; a->type = LSM_AUDIT_DATA_NONE; } sad.tclass = tclass; sad.requested = requested; sad.ssid = ssid; sad.tsid = tsid; sad.audited = audited; sad.denied = denied; sad.result = result; a->selinux_audit_data = &sad; common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback); return 0; } /** * avc_add_callback - Register a callback for security events. * @callback: callback function * @events: security events * * Register a callback function for events in the set @events. * Returns %0 on success or -%ENOMEM if insufficient memory * exists to add the callback. */ int __init avc_add_callback(int (*callback)(u32 event), u32 events) { struct avc_callback_node *c; int rc = 0; c = kmalloc(sizeof(*c), GFP_KERNEL); if (!c) { rc = -ENOMEM; goto out; } c->callback = callback; c->events = events; c->next = avc_callbacks; avc_callbacks = c; out: return rc; } /** * avc_update_node - Update an AVC entry * @event : Updating event * @perms : Permission mask bits * @driver: xperm driver information * @base_perm: the base permission associated with the extended permission * @xperm: xperm permissions * @ssid: AVC entry source sid * @tsid: AVC entry target sid * @tclass : AVC entry target object class * @seqno : sequence number when decision was made * @xpd: extended_perms_decision to be added to the node * @flags: the AVC_* flags, e.g. AVC_EXTENDED_PERMS, or 0. * * if a valid AVC entry doesn't exist,this function returns -ENOENT. * if kmalloc() called internal returns NULL, this function returns -ENOMEM. * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 base_perm, u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, struct extended_perms_decision *xpd, u32 flags) { u32 hvalue; int rc = 0; unsigned long flag; struct avc_node *pos, *node, *orig = NULL; struct hlist_head *head; spinlock_t *lock; node = avc_alloc_node(); if (!node) { rc = -ENOMEM; goto out; } /* Lock the target slot */ hvalue = avc_hash(ssid, tsid, tclass); head = &selinux_avc.avc_cache.slots[hvalue]; lock = &selinux_avc.avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (ssid == pos->ae.ssid && tsid == pos->ae.tsid && tclass == pos->ae.tclass && seqno == pos->ae.avd.seqno){ orig = pos; break; } } if (!orig) { rc = -ENOENT; avc_node_kill(node); goto out_unlock; } /* * Copy and replace original node. */ avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd); if (orig->ae.xp_node) { rc = avc_xperms_populate(node, orig->ae.xp_node); if (rc) { avc_node_kill(node); goto out_unlock; } } switch (event) { case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) avc_xperms_allow_perm(node->ae.xp_node, driver, base_perm, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: node->ae.avd.allowed &= ~perms; break; case AVC_CALLBACK_AUDITALLOW_ENABLE: node->ae.avd.auditallow |= perms; break; case AVC_CALLBACK_AUDITALLOW_DISABLE: node->ae.avd.auditallow &= ~perms; break; case AVC_CALLBACK_AUDITDENY_ENABLE: node->ae.avd.auditdeny |= perms; break; case AVC_CALLBACK_AUDITDENY_DISABLE: node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: rc = avc_add_xperms_decision(node, xpd); if (rc) { avc_node_kill(node); goto out_unlock; } break; } avc_node_replace(node, orig); out_unlock: spin_unlock_irqrestore(lock, flag); out: return rc; } /** * avc_flush - Flush the cache */ static void avc_flush(void) { struct hlist_head *head; struct avc_node *node; spinlock_t *lock; unsigned long flag; int i; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &selinux_avc.avc_cache.slots[i]; lock = &selinux_avc.avc_cache.slots_lock[i]; spin_lock_irqsave(lock, flag); /* * With preemptable RCU, the outer spinlock does not * prevent RCU grace periods from ending. */ rcu_read_lock(); hlist_for_each_entry(node, head, list) avc_node_delete(node); rcu_read_unlock(); spin_unlock_irqrestore(lock, flag); } } /** * avc_ss_reset - Flush the cache and revalidate migrated permissions. * @seqno: policy sequence number */ int avc_ss_reset(u32 seqno) { struct avc_callback_node *c; int rc = 0, tmprc; avc_flush(); for (c = avc_callbacks; c; c = c->next) { if (c->events & AVC_CALLBACK_RESET) { tmprc = c->callback(AVC_CALLBACK_RESET); /* save the first error encountered for the return value and continue processing the callbacks */ if (!rc) rc = tmprc; } } avc_latest_notif_update(seqno, 0); return rc; } /** * avc_compute_av - Add an entry to the AVC based on the security policy * @ssid: subject * @tsid: object/target * @tclass: object class * @avd: access vector decision * @xp_node: AVC extended permissions node * * Slow-path helper function for avc_has_perm_noaudit, when the avc_node lookup * fails. Don't inline this, since it's the slow-path and just results in a * bigger stack frame. */ static noinline void avc_compute_av(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { INIT_LIST_HEAD(&xp_node->xpd_head); security_compute_av(ssid, tsid, tclass, avd, &xp_node->xp); avc_insert(ssid, tsid, tclass, avd, xp_node); } static noinline int avc_denied(u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 base_perm, u8 xperm, unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; if (enforcing_enabled() && !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; avc_update_node(AVC_CALLBACK_GRANT, requested, driver, base_perm, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } /* * The avc extended permissions logic adds an additional 256 bits of * permissions to an avc node when extended permissions for that node are * specified in the avtab. If the additional 256 permissions is not adequate, * as-is the case with ioctls, then multiple may be chained together and the * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 base_perm, u8 xperm, struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; u32 denied; struct extended_perms_decision local_xpd; struct extended_perms_decision *xpd = NULL; struct extended_perms_data allowed; struct extended_perms_data auditallow; struct extended_perms_data dontaudit; struct avc_xperms_node local_xp_node; struct avc_xperms_node *xp_node; int rc = 0, rc2; xp_node = &local_xp_node; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(ssid, tsid, tclass); if (unlikely(!node)) { avc_compute_av(ssid, tsid, tclass, &avd, xp_node); } else { memcpy(&avd, &node->ae.avd, sizeof(avd)); xp_node = node->ae.xp_node; } /* if extended permissions are not defined, only consider av_decision */ if (!xp_node || !xp_node->xp.len) goto decision; local_xpd.allowed = &allowed; local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver * is flagged and the base permission is known. */ if (!security_xperm_test(xp_node->xp.drivers.p, driver) || !(xp_node->xp.base_perms & base_perm)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); security_compute_xperms_decision(ssid, tsid, tclass, driver, base_perm, &local_xpd); rcu_read_lock(); avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver, base_perm, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); } xpd = &local_xpd; if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED)) avd.allowed &= ~requested; decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) rc = avc_denied(ssid, tsid, tclass, requested, driver, base_perm, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); rc2 = avc_xperms_audit(ssid, tsid, tclass, requested, &avd, xpd, xperm, rc, ad); if (rc2) return rc2; return rc; } /** * avc_perm_nonode - Add an entry to the AVC * @ssid: subject * @tsid: object/target * @tclass: object class * @requested: requested permissions * @flags: AVC flags * @avd: access vector decision * * This is the "we have no node" part of avc_has_perm_noaudit(), which is * unlikely and needs extra stack space for the new node that we generate, so * don't inline it. */ static noinline int avc_perm_nonode(u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd) { u32 denied; struct avc_xperms_node xp_node; avc_compute_av(ssid, tsid, tclass, avd, &xp_node); denied = requested & ~(avd->allowed); if (unlikely(denied)) return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } /** * avc_has_perm_noaudit - Check permissions but perform no auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @flags: AVC_STRICT or 0 * @avd: access vector decisions * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Return a copy of the decisions * in @avd. Return %0 if all @requested permissions are granted, * -%EACCES if any permissions are denied, or another -errno upon * other errors. This function is typically called by avc_has_perm(), * but may also be called directly to separate permission checking from * auditing, e.g. in cases where a lock must be held for the check but * should be released for the auditing. */ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd) { u32 denied; struct avc_node *node; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(ssid, tsid, tclass); if (unlikely(!node)) { rcu_read_unlock(); return avc_perm_nonode(ssid, tsid, tclass, requested, flags, avd); } denied = requested & ~node->ae.avd.allowed; memcpy(avd, &node->ae.avd, sizeof(*avd)); rcu_read_unlock(); if (unlikely(denied)) return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } /** * avc_has_perm - Check permissions and perform any appropriate auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @auditdata: auxiliary audit data * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Audit the granting or denial of * permissions in accordance with the policy. Return %0 if all @requested * permissions are granted, -%EACCES if any permissions are denied, or * another -errno upon other errors. */ int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd); rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata); if (rc2) return rc2; return rc; } u32 avc_policy_seqno(void) { return selinux_avc.avc_cache.latest_notif; } |
| 233 232 233 18 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Return: >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { unsigned int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * @node: memory node from which to allocate or %NUMA_NO_NODE * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * Return: TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free(mask, cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu based on NUMA distances * @i: index number * @node: local numa_node * * Return: online CPU according to a numa aware policy; local cpus are returned * first, followed by non-local ones, then it wraps around. * * For those who wants to enumerate all CPUs based on their NUMA distances, * i.e. call this function in a loop, like: * * for (i = 0; i < num_online_cpus(); i++) { * cpu = cpumask_local_spread(i, node); * do_something(cpu); * } * * There's a better alternative based on for_each()-like iterators: * * for_each_numa_hop_mask(mask, node) { * for_each_cpu_andnot(cpu, mask, prev) * do_something(cpu); * prev = mask; * } * * It's simpler and more verbose than above. Complexity of iterator-based * enumeration is O(sched_domains_numa_levels * nr_cpu_ids), while * cpumask_local_spread() when called for each cpu is * O(sched_domains_numa_levels * nr_cpu_ids * log(nr_cpu_ids)). */ unsigned int cpumask_local_spread(unsigned int i, int node) { unsigned int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); cpu = sched_numa_find_nth_cpu(cpu_online_mask, i, node); WARN_ON(cpu >= nr_cpu_ids); return cpu; } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * cpumask_any_and_distribute - Return an arbitrary cpu within src1p & src2p. * @src1p: first &cpumask for intersection * @src2p: second &cpumask for intersection * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Return: >= nr_cpu_ids if the intersection is empty. */ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute); /** * cpumask_any_distribute - Return an arbitrary cpu from srcp * @srcp: &cpumask for selection * * Return: >= nr_cpu_ids if the intersection is empty. */ unsigned int cpumask_any_distribute(const struct cpumask *srcp) { unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = find_next_bit_wrap(cpumask_bits(srcp), nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_distribute); |
| 27 14 13 13 2 2 2 2 2 2 2 3 3 3 3 1 1 2 2 2 2 10 79 79 45 78 78 78 8 8 8 8 3 3 3 3 3 83 2 2 3 2 3 3 3 2 3 3 3 3 3 3 3 3 107 3 2 60 60 46 45 2 110 109 110 110 2 2 3 3 2 3 3 1 2 2 2 3 3 3 3 3 2 2 2 2 2 2 2 2 2 12 3 3 3 3 3 112 107 2 3 3 1 1 1 1 1 1 12 12 12 12 2 2 1 1 1 1 26 27 2 1 1 1 3 1 1 14 14 14 1 1 2 9 6 5 3 3 4 1 1 1 1 3 1 2 77 90 3 83 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Linaro Ltd. * Author: Shannon Zhao <shannon.zhao@linaro.org> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/perf_event.h> #include <linux/perf/arm_pmu.h> #include <linux/uaccess.h> #include <asm/kvm_emulate.h> #include <kvm/arm_pmu.h> #include <kvm/arm_vgic.h> #define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0) DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static LIST_HEAD(arm_pmus); static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]); } static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx) { return &vcpu->arch.pmu.pmc[cnt_idx]; } static u32 __kvm_pmu_event_mask(unsigned int pmuver) { switch (pmuver) { case ID_AA64DFR0_EL1_PMUVer_IMP: return GENMASK(9, 0); case ID_AA64DFR0_EL1_PMUVer_V3P1: case ID_AA64DFR0_EL1_PMUVer_V3P4: case ID_AA64DFR0_EL1_PMUVer_V3P5: case ID_AA64DFR0_EL1_PMUVer_V3P7: return GENMASK(15, 0); default: /* Shouldn't be here, just for sanity */ WARN_ONCE(1, "Unknown PMU version %d\n", pmuver); return 0; } } static u32 kvm_pmu_event_mask(struct kvm *kvm) { u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1); u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0); return __kvm_pmu_event_mask(pmuver); } u64 kvm_pmu_evtyper_mask(struct kvm *kvm) { u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 | kvm_pmu_event_mask(kvm); if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL2, IMP)) mask |= ARMV8_PMU_INCLUDE_EL2; if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP)) mask |= ARMV8_PMU_EXCLUDE_NS_EL0 | ARMV8_PMU_EXCLUDE_NS_EL1 | ARMV8_PMU_EXCLUDE_EL3; return mask; } /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context */ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (pmc->idx == ARMV8_PMU_CYCLE_IDX || kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)); } static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 val = kvm_vcpu_read_pmcr(vcpu); if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return __vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HLP; return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); } static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc) { return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX && !kvm_pmc_has_64bit_overflow(pmc)); } static u32 counter_index_to_reg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx; } static u32 counter_index_to_evtreg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx; } static u64 kvm_pmc_read_evtreg(const struct kvm_pmc *pmc) { return __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), counter_index_to_evtreg(pmc->idx)); } static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 counter, reg, enabled, running; reg = counter_index_to_reg(pmc->idx); counter = __vcpu_sys_reg(vcpu, reg); /* * The real counter value is equal to the value of counter register plus * the value perf event counts. */ if (pmc->perf_event) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); if (!kvm_pmc_is_64bit(pmc)) counter = lower_32_bits(counter); return counter; } /** * kvm_pmu_get_counter_value - get PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index */ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); } static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg; kvm_pmu_release_perf_event(pmc); reg = counter_index_to_reg(pmc->idx); if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX && !force) { /* * Even with PMUv3p5, AArch32 cannot write to the top * 32bit of the counters. The only possible course of * action is to use PMCR.P, which will reset them to * 0 (the only use of the 'force' parameter). */ val = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32); val |= lower_32_bits(val); } __vcpu_sys_reg(vcpu, reg) = val; /* Recreate the perf event to reflect the updated sample_period */ kvm_pmu_create_perf_event(pmc); } /** * kvm_pmu_set_counter_value - set PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index * @val: The counter value */ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { if (!kvm_vcpu_has_pmu(vcpu)) return; kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** * kvm_pmu_release_perf_event - remove the perf event * @pmc: The PMU counter pointer */ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { perf_event_disable(pmc->perf_event); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; } } /** * kvm_pmu_stop_counter - stop PMU counter * @pmc: The PMU counter pointer * * If this counter has been configured to monitor some event, release it here. */ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg, val; if (!pmc->perf_event) return; val = kvm_pmu_get_pmc_value(pmc); reg = counter_index_to_reg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = val; kvm_pmu_release_perf_event(pmc); } /** * kvm_pmu_vcpu_init - assign pmu counter idx for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) { int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) pmu->pmc[i].idx = i; } /** * kvm_pmu_vcpu_reset - reset pmu state for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) { unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu); int i; for_each_set_bit(i, &mask, 32) kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i)); } /** * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu) { unsigned int hpmn, n; if (!vcpu_has_nv(vcpu)) return 0; hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2)); n = vcpu->kvm->arch.pmcr_n; /* * Programming HPMN to a value greater than PMCR_EL0.N is * CONSTRAINED UNPREDICTABLE. Make the implementation choice that an * UNKNOWN number of counters (in our case, zero) are reserved for EL2. */ if (hpmn >= n) return 0; /* * Programming HPMN=0 is CONSTRAINED UNPREDICTABLE if FEAT_HPMN0 isn't * implemented. Since KVM's ability to emulate HPMN=0 does not directly * depend on hardware (all PMU registers are trapped), make the * implementation choice that all counters are included in the second * range reserved for EL2/EL3. */ return GENMASK(n - 1, hpmn); } bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx) { return kvm_pmu_hyp_counter_mask(vcpu) & BIT(idx); } u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu)) return mask; return mask & ~kvm_pmu_hyp_counter_mask(vcpu); } u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) { u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu)); if (val == 0) return BIT(ARMV8_PMU_CYCLE_IDX); else return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { if (!pmc->perf_event) { kvm_pmu_create_perf_event(pmc); return; } perf_event_enable(pmc->perf_event); if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) kvm_debug("fail to enable perf event\n"); } static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) perf_event_disable(pmc->perf_event); } void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; if (kvm_pmu_counter_is_enabled(pmc)) kvm_pmc_enable_perf_event(pmc); else kvm_pmc_disable_perf_event(pmc); } kvm_vcpu_pmu_restore_guest(vcpu); } /* * Returns the PMU overflow state, which is true if there exists an event * counter where the values of the global enable control, PMOVSSET_EL0[n], and * PMINTENSET_EL1[n] are all 1. */ static bool kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) { u64 reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); /* * PMCR_EL0.E is the global enable control for event counters available * to EL0 and EL1. */ if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) reg &= kvm_pmu_hyp_counter_mask(vcpu); /* * Otherwise, MDCR_EL2.HPME is the global enable control for event * counters reserved for EL2. */ if (!(vcpu_read_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HPME)) reg &= ~kvm_pmu_hyp_counter_mask(vcpu); return reg; } static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; bool overflow; if (!kvm_vcpu_has_pmu(vcpu)) return; overflow = kvm_pmu_overflow_status(vcpu); if (pmu->irq_level == overflow) return; pmu->irq_level = overflow; if (likely(irqchip_in_kernel(vcpu->kvm))) { int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, pmu->irq_num, overflow, pmu); WARN_ON(ret); } } bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_sync_regs *sregs = &vcpu->run->s.regs; bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU; if (likely(irqchip_in_kernel(vcpu->kvm))) return false; return pmu->irq_level != run_level; } /* * Reflect the PMU overflow interrupt output level into the kvm_run structure */ void kvm_pmu_update_run(struct kvm_vcpu *vcpu) { struct kvm_sync_regs *regs = &vcpu->run->s.regs; /* Populate the timer bitmap for user space */ regs->device_irq_level &= ~KVM_ARM_DEV_PMU; if (vcpu->arch.pmu.irq_level) regs->device_irq_level |= KVM_ARM_DEV_PMU; } /** * kvm_pmu_flush_hwstate - flush pmu state to cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the host, and inject * an interrupt if that was the case. */ void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /** * kvm_pmu_sync_hwstate - sync pmu state from cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the guest, and * inject an interrupt if that was the case. */ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /* * When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding * to the event. * This is why we need a callback to do it once outside of the NMI context. */ static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work) { struct kvm_vcpu *vcpu; vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work); kvm_vcpu_kick(vcpu); } /* * Perform an increment on any of the counters described in @mask, * generating the overflow if required, and propagate it as a chained * event if possible. */ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, unsigned long mask, u32 event) { int i; if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) return; /* Weed out disabled counters */ mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); u64 type, reg; /* Filter on event type */ type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i)); type &= kvm_pmu_event_mask(vcpu->kvm); if (type != event) continue; /* Increment this counter */ reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1; if (!kvm_pmc_is_64bit(pmc)) reg = lower_32_bits(reg); __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg; /* No overflow? move on */ if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg)) continue; /* Mark overflow */ __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(i + 1), ARMV8_PMUV3_PERFCTR_CHAIN); } } /* Compute the sample period for a given counter value */ static u64 compute_period(struct kvm_pmc *pmc, u64 counter) { u64 val; if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc)) val = (-counter) & GENMASK(63, 0); else val = (-counter) & GENMASK(31, 0); return val; } /* * When the perf event overflows, set the overflow status and inform the vcpu. */ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, struct perf_sample_data *data, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); int idx = pmc->idx; u64 period; cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); /* * Reset the sample period to the architectural limit, * i.e. the point where the counter overflows. */ period = compute_period(pmc, local64_read(&perf_event->count)); local64_set(&perf_event->hw.period_left, 0); perf_event->attr.sample_period = period; perf_event->hw.sample_period = period; __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(idx + 1), ARMV8_PMUV3_PERFCTR_CHAIN); if (kvm_pmu_overflow_status(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); if (!in_nmi()) kvm_vcpu_kick(vcpu); else irq_work_queue(&vcpu->arch.pmu.overflow_work); } cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); } /** * kvm_pmu_software_increment - do software increment * @vcpu: The vcpu pointer * @val: the value guest writes to PMSWINC register */ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) { kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR); } /** * kvm_pmu_handle_pmcr - handle PMCR register * @vcpu: The vcpu pointer * @val: the value guest writes to PMCR register */ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu)) return; /* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */ if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; /* Request a reload of the PMU to enable/disable affected counters */ if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { /* * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply * to the 'guest' range of counters and never the 'hyp' range. */ unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & ~kvm_pmu_hyp_counter_mask(vcpu) & ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx))) return false; if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return mdcr & MDCR_EL2_HPME; return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E; } static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc) { u64 evtreg = kvm_pmc_read_evtreg(pmc); bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0; bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0; return u == nsu; } static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc) { u64 evtreg = kvm_pmc_read_evtreg(pmc); bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1; bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1; return p == nsk; } static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD)) return false; return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2; } /** * kvm_pmu_create_perf_event - create a perf event for a counter * @pmc: Counter context */ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; struct perf_event *event; struct perf_event_attr attr; u64 eventsel, evtreg; evtreg = kvm_pmc_read_evtreg(pmc); kvm_pmu_stop_counter(pmc); if (pmc->idx == ARMV8_PMU_CYCLE_IDX) eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES; else eventsel = evtreg & kvm_pmu_event_mask(vcpu->kvm); /* * Neither SW increment nor chained events need to be backed * by a perf event. */ if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR || eventsel == ARMV8_PMUV3_PERFCTR_CHAIN) return; /* * If we have a filter in place and that the event isn't allowed, do * not install a perf event either. */ if (vcpu->kvm->arch.pmu_filter && !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; attr.disabled = !kvm_pmu_counter_is_enabled(pmc); attr.exclude_user = !kvm_pmc_counts_at_el0(pmc); attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; /* * Filter events at EL1 (i.e. vEL2) when in a hyp context based on the * guest's EL2 filter. */ if (unlikely(is_hyp_ctxt(vcpu))) attr.exclude_kernel = !kvm_pmc_counts_at_el2(pmc); else attr.exclude_kernel = !kvm_pmc_counts_at_el1(pmc); /* * If counting with a 64bit counter, advertise it to the perf * code, carefully dealing with the initial sample period * which also depends on the overflow. */ if (kvm_pmc_is_64bit(pmc)) attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT; attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc)); event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc); if (IS_ERR(event)) { pr_err_once("kvm: pmu event creation failed %ld\n", PTR_ERR(event)); return; } pmc->perf_event = event; } /** * kvm_pmu_set_counter_event_type - set selected counter to monitor some event * @vcpu: The vcpu pointer * @data: The data guest writes to PMXEVTYPER_EL0 * @select_idx: The number of selected counter * * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an * event with given hardware event number. Here we call perf_event API to * emulate this action and create a kernel perf event for it. */ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); u64 reg; if (!kvm_vcpu_has_pmu(vcpu)) return; reg = counter_index_to_evtreg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); kvm_pmu_create_perf_event(pmc); } void kvm_host_pmu_init(struct arm_pmu *pmu) { struct arm_pmu_entry *entry; /* * Check the sanitised PMU version for the system, as KVM does not * support implementations where PMUv3 exists on a subset of CPUs. */ if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit())) return; mutex_lock(&arm_pmus_lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) goto out_unlock; entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus); if (list_is_singular(&arm_pmus)) static_branch_enable(&kvm_arm_pmu_available); out_unlock: mutex_unlock(&arm_pmus_lock); } static struct arm_pmu *kvm_pmu_probe_armpmu(void) { struct arm_pmu *tmp, *pmu = NULL; struct arm_pmu_entry *entry; int cpu; mutex_lock(&arm_pmus_lock); /* * It is safe to use a stale cpu to iterate the list of PMUs so long as * the same value is used for the entirety of the loop. Given this, and * the fact that no percpu data is used for the lookup there is no need * to disable preemption. * * It is still necessary to get a valid cpu, though, to probe for the * default PMU instance as userspace is not required to specify a PMU * type. In order to uphold the preexisting behavior KVM selects the * PMU instance for the core during vcpu init. A dependent use * case would be a user with disdain of all things big.LITTLE that * affines the VMM to a particular cluster of cores. * * In any case, userspace should just do the sane thing and use the UAPI * to select a PMU type directly. But, be wary of the baggage being * carried here. */ cpu = raw_smp_processor_id(); list_for_each_entry(entry, &arm_pmus, entry) { tmp = entry->arm_pmu; if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) { pmu = tmp; break; } } mutex_unlock(&arm_pmus_lock); return pmu; } u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; int base, i, nr_events; if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!pmceid1) { val = read_sysreg(pmceid0_el0); /* always support CHAIN */ val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); base = 0; } else { val = read_sysreg(pmceid1_el0); /* * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled * as RAZ */ val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32)); base = 32; } if (!bmap) return val; nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; if (nr_events >= (0x4000 + base + 32)) { byte = bitmap_get_value8(bmap, 0x4000 + base + i); mask |= byte << (32 + i); } } return val & mask; } void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!vcpu->arch.pmu.created) return -EINVAL; /* * A valid interrupt configuration for the PMU is either to have a * properly configured interrupt number and using an in-kernel * irqchip, or to not have an in-kernel GIC and not set an IRQ. */ if (irqchip_in_kernel(vcpu->kvm)) { int irq = vcpu->arch.pmu.irq_num; /* * If we are using an in-kernel vgic, at this point we know * the vgic will be initialized, so we can check the PMU irq * number against the dimensions of the vgic and make sure * it's valid. */ if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq)) return -EINVAL; } else if (kvm_arm_pmu_irq_initialized(vcpu)) { return -EINVAL; } /* One-off reload of the PMU on first run */ kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) { int ret; /* * If using the PMU with an in-kernel virtual GIC * implementation, we require the GIC to be already * initialized when initializing the PMU. */ if (!vgic_initialized(vcpu->kvm)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, &vcpu->arch.pmu); if (ret) return ret; } init_irq_work(&vcpu->arch.pmu.overflow_work, kvm_pmu_perf_overflow_notify_vcpu); vcpu->arch.pmu.created = true; return 0; } /* * For one VM the interrupt type must be same for each vcpu. * As a PPI, the interrupt number is the same for all vcpus, * while as an SPI it must be a separate number per vcpu. */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu)) continue; if (irq_is_ppi(irq)) { if (vcpu->arch.pmu.irq_num != irq) return false; } else { if (vcpu->arch.pmu.irq_num == irq) return false; } } return true; } /** * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters. * @kvm: The kvm pointer */ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* * The arm_pmu->cntr_mask considers the fixed counter(s) as well. * Ignore those and return only the general-purpose counters. */ return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) { lockdep_assert_held(&kvm->arch.config_lock); kvm->arch.arm_pmu = arm_pmu; kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm); } /** * kvm_arm_set_default_pmu - No PMU set, get the default one. * @kvm: The kvm pointer * * The observant among you will notice that the supported_cpus * mask does not get updated for the default PMU even though it * is quite possible the selected instance supports only a * subset of cores in the system. This is intentional, and * upholds the preexisting behavior on heterogeneous systems * where vCPUs can be scheduled on any core but the guest * counters could stop working. */ int kvm_arm_set_default_pmu(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu(); if (!arm_pmu) return -ENODEV; kvm_arm_set_pmu(kvm, arm_pmu); return 0; } static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) { struct kvm *kvm = vcpu->kvm; struct arm_pmu_entry *entry; struct arm_pmu *arm_pmu; int ret = -ENXIO; lockdep_assert_held(&kvm->arch.config_lock); mutex_lock(&arm_pmus_lock); list_for_each_entry(entry, &arm_pmus, entry) { arm_pmu = entry->arm_pmu; if (arm_pmu->pmu.type == pmu_id) { if (kvm_vm_has_ran_once(kvm) || (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) { ret = -EBUSY; break; } kvm_arm_set_pmu(kvm, arm_pmu); cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus); ret = 0; break; } } mutex_unlock(&arm_pmus_lock); return ret; } int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) return -EBUSY; switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(kvm)) return -EINVAL; if (get_user(irq, uaddr)) return -EFAULT; /* The PMU overflow interrupt can be a PPI or a valid SPI. */ if (!(irq_is_ppi(irq) || irq_is_spi(irq))) return -EINVAL; if (!pmu_irq_is_valid(kvm, irq)) return -EINVAL; if (kvm_arm_pmu_irq_initialized(vcpu)) return -EBUSY; kvm_debug("Set kvm ARM PMU irq: %d\n", irq); vcpu->arch.pmu.irq_num = irq; return 0; } case KVM_ARM_VCPU_PMU_V3_FILTER: { u8 pmuver = kvm_arm_pmu_get_pmuver_limit(); struct kvm_pmu_event_filter __user *uaddr; struct kvm_pmu_event_filter filter; int nr_events; /* * Allow userspace to specify an event filter for the entire * event range supported by PMUVer of the hardware, rather * than the guest's PMUVer for KVM backward compatibility. */ nr_events = __kvm_pmu_event_mask(pmuver) + 1; uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (((u32)filter.base_event + filter.nevents) > nr_events || (filter.action != KVM_PMU_EVENT_ALLOW && filter.action != KVM_PMU_EVENT_DENY)) return -EINVAL; if (kvm_vm_has_ran_once(kvm)) return -EBUSY; if (!kvm->arch.pmu_filter) { kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT); if (!kvm->arch.pmu_filter) return -ENOMEM; /* * The default depends on the first applied filter. * If it allows events, the default is to deny. * Conversely, if the first filter denies a set of * events, the default is to allow. */ if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_zero(kvm->arch.pmu_filter, nr_events); else bitmap_fill(kvm->arch.pmu_filter, nr_events); } if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents); else bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents); return 0; } case KVM_ARM_VCPU_PMU_V3_SET_PMU: { int __user *uaddr = (int __user *)(long)attr->addr; int pmu_id; if (get_user(pmu_id, uaddr)) return -EFAULT; return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id); } case KVM_ARM_VCPU_PMU_V3_INIT: return kvm_arm_pmu_v3_init(vcpu); } return -ENXIO; } int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; irq = vcpu->arch.pmu.irq_num; return put_user(irq, uaddr); } } return -ENXIO; } int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: case KVM_ARM_VCPU_PMU_V3_INIT: case KVM_ARM_VCPU_PMU_V3_FILTER: case KVM_ARM_VCPU_PMU_V3_SET_PMU: if (kvm_vcpu_has_pmu(vcpu)) return 0; } return -ENXIO; } u8 kvm_arm_pmu_get_pmuver_limit(void) { u64 tmp; tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); tmp = cpuid_feature_cap_perfmon_field(tmp, ID_AA64DFR0_EL1_PMUVer_SHIFT, ID_AA64DFR0_EL1_PMUVer_V3P5); return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); } /** * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU * @vcpu: The vcpu pointer */ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N); } void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) { bool reprogrammed = false; unsigned long mask; int i; if (!kvm_vcpu_has_pmu(vcpu)) return; mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, 32) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); /* * We only need to reconfigure events where the filter is * different at EL1 vs. EL2, as we're multiplexing the true EL1 * event filter bit for nested. */ if (kvm_pmc_counts_at_el1(pmc) == kvm_pmc_counts_at_el2(pmc)) continue; kvm_pmu_create_perf_event(pmc); reprogrammed = true; } if (reprogrammed) kvm_vcpu_pmu_restore_guest(vcpu); } |
| 583 201 524 1023 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ #include <linux/atomic.h> #include <linux/compiler.h> #include <asm/barrier.h> /* * Implementation of atomic bitops using atomic-fetch ops. * See Documentation/atomic_bitops.txt for details. */ static __always_inline void arch_set_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_clear_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_change_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline int arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_or(mask, (atomic_long_t *)p); return !!(old & mask); } static __always_inline int arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_andnot(mask, (atomic_long_t *)p); return !!(old & mask); } static __always_inline int arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_xor(mask, (atomic_long_t *)p); return !!(old & mask); } #include <asm-generic/bitops/instrumented-atomic.h> #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */ |
| 21 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 19 19 19 19 19 19 20 20 20 19 19 20 20 112 52 52 52 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 | // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> #include "internal.h" static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /** * may_write_xattr - check whether inode allows writing xattr * @idmap: idmap of the mount the inode was found from * @inode: the inode on which to set an xattr * * Check whether the inode allows writing xattrs. Specifically, we can never * set or remove an extended attribute on a read-only filesystem or on an * immutable / append-only inode. * * We also need to ensure that the inode has a mapping in the mount to * not risk writing back invalid i_{g,u}id values. * * Return: On success zero is returned. On error a negative errno is returned. */ int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode) { if (IS_IMMUTABLE(inode)) return -EPERM; if (IS_APPEND(inode)) return -EPERM; if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; return 0; } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct mnt_idmap *idmap, struct inode *inode, const char *name, int mask) { if (mask & MAY_WRITE) { int ret; ret = may_write_xattr(idmap, inode); if (ret) return ret; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && !inode_owner_or_capable(idmap, inode)) return -EPERM; } return inode_permission(idmap, inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supports_user_prefix(struct inode *inode) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supports_user_prefix); int __vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, idmap, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @idmap: idmap of the mount the inode was found from * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_mutex before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(idmap, dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(idmap, dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(idmap, dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; const void *orig_value = value; int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(idmap, dentry, &value, size); if (error < 0) return error; size = error; } retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(idmap, dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } if (value != orig_value) kfree(value); return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(idmap, inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(idmap, inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. The xattr value buffer should * always be freed by the caller, even on error. * * Returns the result of alloc, if failed, or the getxattr operation. */ int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(idmap, inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: return __vfs_getxattr(dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); /** * vfs_listxattr - retrieve \0 separated list of xattr names * @dentry: the dentry from whose inode the xattr names are retrieved * @list: buffer to store xattr names into * @size: size of the buffer * * This function returns the names of all xattrs associated with the * inode of @dentry. * * Note, for legacy reasons the vfs_listxattr() function lists POSIX * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the * vfs_listxattr() function doesn't check for this flag since a * filesystem could implement POSIX ACLs without implementing any other * xattrs. * * However, since all codepaths that remove IOP_XATTR also assign of * inode operations that either don't implement or implement a stub * ->listxattr() operation. * * Return: On success, the size of the buffer that was used. On error a * negative error code. */ ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_GPL(vfs_listxattr); int __vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, idmap, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(idmap, dentry, name); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_removexattr(idmap, dentry, name); if (error) return error; fsnotify_xattr(dentry); security_inode_post_removexattr(dentry, name); out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(idmap, dentry, name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); int import_xattr_name(struct xattr_name *kname, const char __user *name) { int error = strncpy_from_user(kname->name, name, sizeof(kname->name)); if (error == 0 || error == sizeof(kname->name)) return -ERANGE; if (error < 0) return error; return 0; } /* * Extended attribute SET operations */ int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx) { int error; if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = import_xattr_name(ctx->kname, name); if (error) return error; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) return -E2BIG; ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size); if (IS_ERR(ctx->kvalue)) { error = PTR_ERR(ctx->kvalue); ctx->kvalue = NULL; } } return error; } static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct kernel_xattr_ctx *ctx) { if (is_posix_acl_xattr(ctx->kname->name)) return do_set_acl(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size); return vfs_setxattr(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size, ctx->flags); } int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); mnt_drop_write_file(f); } return error; } /* unconditionally consumes filename */ int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = mnt_want_write(path.mnt); if (!error) { error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static int path_setxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, const void __user *value, size_t size, int flags) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .cvalue = value, .kvalue = NULL, .size = size, .kname = &kname, .flags = flags, }; struct filename *filename; unsigned int lookup_flags = 0; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; error = setxattr_copy(name, &ctx); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) error = -EBADF; else error = file_setxattr(fd_file(f), &ctx); } else { error = filename_setxattr(dfd, filename, lookup_flags, &ctx); } kvfree(ctx.kvalue); return error; } SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, const struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; return path_setxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size, args.flags); } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size, flags); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size, flags); } /* * Extended attribute GET operations */ static ssize_t do_getxattr(struct mnt_idmap *idmap, struct dentry *d, struct kernel_xattr_ctx *ctx) { ssize_t error; char *kname = ctx->kname->name; void *kvalue = NULL; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) ctx->size = XATTR_SIZE_MAX; kvalue = kvzalloc(ctx->size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } if (is_posix_acl_xattr(kname)) error = do_get_acl(idmap, d, kname, kvalue, ctx->size); else error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size); if (error > 0) { if (ctx->size && copy_to_user(ctx->value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx) { audit_file(f); return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); } /* unconditionally consumes filename */ ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static ssize_t path_getxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, void __user *value, size_t size) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .value = value, .size = size, .kname = &kname, .flags = 0, }; struct filename *filename; ssize_t error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_getxattr(fd_file(f), &ctx); } else { int lookup_flags = 0; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; return filename_getxattr(dfd, filename, lookup_flags, &ctx); } } SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; if (args.flags != 0) return -EINVAL; return path_getxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size); } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size); } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t file_listxattr(struct file *f, char __user *list, size_t size) { audit_file(f); return listxattr(f->f_path.dentry, list, size); } /* unconditionally consumes filename */ static ssize_t filename_listxattr(int dfd, struct filename *filename, unsigned int lookup_flags, char __user *list, size_t size) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static ssize_t path_listxattrat(int dfd, const char __user *pathname, unsigned int at_flags, char __user *list, size_t size) { struct filename *filename; int lookup_flags; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_listxattr(fd_file(f), list, size); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_listxattr(dfd, filename, lookup_flags, list, size); } SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, char __user *, list, size_t, size) { return path_listxattrat(dfd, pathname, at_flags, list, size); } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, 0, list, size); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size); } /* * Extended attribute REMOVE operations */ static long removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name) { if (is_posix_acl_xattr(name)) return vfs_remove_acl(idmap, d, name); return vfs_removexattr(idmap, d, name); } static int file_removexattr(struct file *f, struct xattr_name *kname) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = removexattr(file_mnt_idmap(f), f->f_path.dentry, kname->name); mnt_drop_write_file(f); } return error; } /* unconditionally consumes filename */ static int filename_removexattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct xattr_name *kname) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static int path_removexattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name) { struct xattr_name kname; struct filename *filename; unsigned int lookup_flags; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_removexattr(fd_file(f), &kname); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_removexattr(dfd, filename, lookup_flags, &kname); } SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name) { return path_removexattrat(dfd, pathname, at_flags, name); } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, 0, name); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name); } int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len; len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /** * generic_listxattr - run through a dentry's xattr list() operations * @dentry: dentry to list the xattrs * @buffer: result buffer * @buffer_size: size of @buffer * * Combine the results of the list() operation from every xattr_handler in the * xattr_handler stack. * * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr; ssize_t remaining_size = buffer_size; for_each_xattr_handler(handlers, handler) { int err; if (!handler->name || (handler->list && !handler->list(dentry))) continue; err = xattr_list_one(&buffer, &remaining_size, handler->name); if (err) return err; } return buffer_size - remaining_size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /** * simple_xattr_space - estimate the memory used by a simple xattr * @name: the full name of the xattr * @size: the size of its value * * This takes no account of how much larger the two slab objects actually are: * that would depend on the slab implementation, when what is required is a * deterministic number, which grows with name length and size and quantity. * * Return: The approximate number of bytes of memory used by such an xattr. */ size_t simple_xattr_space(const char *name, size_t size) { /* * Use "40" instead of sizeof(struct simple_xattr), to return the * same result on 32-bit and 64-bit, and even if simple_xattr grows. */ return 40 + size + strlen(name); } /** * simple_xattr_free - free an xattr object * @xattr: the xattr object * * Free the xattr object. Can handle @xattr being NULL. */ void simple_xattr_free(struct simple_xattr *xattr) { if (xattr) kfree(xattr->name); kvfree(xattr); } /** * simple_xattr_alloc - allocate new xattr object * @value: value of the xattr object * @size: size of @value * * Allocate a new xattr object and initialize respective members. The caller is * responsible for handling the name of the xattr. * * Return: On success a new xattr object is returned. On failure NULL is * returned. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return NULL; new_xattr = kvmalloc(len, GFP_KERNEL_ACCOUNT); if (!new_xattr) return NULL; new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } /** * rbtree_simple_xattr_cmp - compare xattr name with current rbtree xattr entry * @key: xattr name * @node: current node * * Compare the xattr name with the xattr name attached to @node in the rbtree. * * Return: Negative value if continuing left, positive if continuing right, 0 * if the xattr attached to @node matches @key. */ static int rbtree_simple_xattr_cmp(const void *key, const struct rb_node *node) { const char *xattr_name = key; const struct simple_xattr *xattr; xattr = rb_entry(node, struct simple_xattr, rb_node); return strcmp(xattr->name, xattr_name); } /** * rbtree_simple_xattr_node_cmp - compare two xattr rbtree nodes * @new_node: new node * @node: current node * * Compare the xattr attached to @new_node with the xattr attached to @node. * * Return: Negative value if continuing left, positive if continuing right, 0 * if the xattr attached to @new_node matches the xattr attached to @node. */ static int rbtree_simple_xattr_node_cmp(struct rb_node *new_node, const struct rb_node *node) { struct simple_xattr *xattr; xattr = rb_entry(new_node, struct simple_xattr, rb_node); return rbtree_simple_xattr_cmp(xattr->name, node); } /** * simple_xattr_get - get an xattr object * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @buffer: the buffer to store the value into * @size: the size of @buffer * * Try to find and retrieve the xattr object associated with @name. * If @buffer is provided store the value of @xattr in @buffer * otherwise just return the length. The size of @buffer is limited * to XATTR_SIZE_MAX which currently is 65536. * * Return: On success the length of the xattr value is returned. On error a * negative error code is returned. */ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr = NULL; struct rb_node *rbp; int ret = -ENODATA; read_lock(&xattrs->lock); rbp = rb_find(name, &xattrs->rb_root, rbtree_simple_xattr_cmp); if (rbp) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } } read_unlock(&xattrs->lock); return ret; } /** * simple_xattr_set - set an xattr object * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @value: the value to store along the xattr * @size: the size of @value * @flags: the flags determining how to set the xattr * * Set a new xattr object. * If @value is passed a new xattr object will be allocated. If XATTR_REPLACE * is specified in @flags a matching xattr object for @name must already exist. * If it does it will be replaced with the new xattr object. If it doesn't we * fail. If XATTR_CREATE is specified and a matching xattr does already exist * we fail. If it doesn't we create a new xattr. If @flags is zero we simply * insert the new xattr replacing any existing one. * * If @value is empty and a matching xattr object is found we delete it if * XATTR_REPLACE is specified in @flags or @flags is zero. * * If @value is empty and no matching xattr object for @name is found we do * nothing if XATTR_CREATE is specified in @flags or @flags is zero. For * XATTR_REPLACE we fail as mentioned above. * * Return: On success, the removed or replaced xattr is returned, to be freed * by the caller; or NULL if none. On failure a negative error code is returned. */ struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags) { struct simple_xattr *old_xattr = NULL, *new_xattr = NULL; struct rb_node *parent = NULL, **rbp; int err = 0, ret; /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); if (!new_xattr) return ERR_PTR(-ENOMEM); new_xattr->name = kstrdup(name, GFP_KERNEL_ACCOUNT); if (!new_xattr->name) { simple_xattr_free(new_xattr); return ERR_PTR(-ENOMEM); } } write_lock(&xattrs->lock); rbp = &xattrs->rb_root.rb_node; while (*rbp) { parent = *rbp; ret = rbtree_simple_xattr_cmp(name, *rbp); if (ret < 0) rbp = &(*rbp)->rb_left; else if (ret > 0) rbp = &(*rbp)->rb_right; else old_xattr = rb_entry(*rbp, struct simple_xattr, rb_node); if (old_xattr) break; } if (old_xattr) { /* Fail if XATTR_CREATE is requested and the xattr exists. */ if (flags & XATTR_CREATE) { err = -EEXIST; goto out_unlock; } if (new_xattr) rb_replace_node(&old_xattr->rb_node, &new_xattr->rb_node, &xattrs->rb_root); else rb_erase(&old_xattr->rb_node, &xattrs->rb_root); } else { /* Fail if XATTR_REPLACE is requested but no xattr is found. */ if (flags & XATTR_REPLACE) { err = -ENODATA; goto out_unlock; } /* * If XATTR_CREATE or no flags are specified together with a * new value simply insert it. */ if (new_xattr) { rb_link_node(&new_xattr->rb_node, parent, rbp); rb_insert_color(&new_xattr->rb_node, &xattrs->rb_root); } /* * If XATTR_CREATE or no flags are specified and neither an * old or new xattr exist then we don't need to do anything. */ } out_unlock: write_unlock(&xattrs->lock); if (!err) return old_xattr; simple_xattr_free(new_xattr); return ERR_PTR(err); } static bool xattr_is_trusted(const char *name) { return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } /** * simple_xattr_list - list all xattr objects * @inode: inode from which to get the xattrs * @xattrs: the header of the xattr object * @buffer: the buffer to store all xattrs into * @size: the size of @buffer * * List all xattrs associated with @inode. If @buffer is NULL we returned * the required size of the buffer. If @buffer is provided we store the * xattrs value into it provided it is big enough. * * Note, the number of xattr names that can be listed with listxattr(2) is * limited to XATTR_LIST_MAX aka 65536 bytes. If a larger buffer is passed * then vfs_listxattr() caps it to XATTR_LIST_MAX and if more xattr names * are found it will return -E2BIG. * * Return: On success the required size or the size of the copied xattrs is * returned. On error a negative error code is returned. */ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; struct rb_node *rbp; ssize_t remaining_size = size; int err = 0; err = posix_acl_listxattr(inode, &buffer, &remaining_size); if (err) return err; read_lock(&xattrs->lock); for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; } read_unlock(&xattrs->lock); return err ? err : size - remaining_size; } /** * rbtree_simple_xattr_less - compare two xattr rbtree nodes * @new_node: new node * @node: current node * * Compare the xattr attached to @new_node with the xattr attached to @node. * Note that this function technically tolerates duplicate entries. * * Return: True if insertion point in the rbtree is found. */ static bool rbtree_simple_xattr_less(struct rb_node *new_node, const struct rb_node *node) { return rbtree_simple_xattr_node_cmp(new_node, node) < 0; } /** * simple_xattr_add - add xattr objects * @xattrs: the header of the xattr object * @new_xattr: the xattr object to add * * Add an xattr object to @xattrs. This assumes no replacement or removal * of matching xattrs is wanted. Should only be called during inode * initialization when a few distinct initial xattrs are supposed to be set. */ void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr) { write_lock(&xattrs->lock); rb_add(&new_xattr->rb_node, &xattrs->rb_root, rbtree_simple_xattr_less); write_unlock(&xattrs->lock); } /** * simple_xattrs_init - initialize new xattr header * @xattrs: header to initialize * * Initialize relevant fields of a an xattr header. */ void simple_xattrs_init(struct simple_xattrs *xattrs) { xattrs->rb_root = RB_ROOT; rwlock_init(&xattrs->lock); } /** * simple_xattrs_free - free xattrs * @xattrs: xattr header whose xattrs to destroy * @freed_space: approximate number of bytes of memory freed from @xattrs * * Destroy all xattrs in @xattr. When this is called no one can hold a * reference to any of the xattrs anymore. */ void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space) { struct rb_node *rbp; if (freed_space) *freed_space = 0; rbp = rb_first(&xattrs->rb_root); while (rbp) { struct simple_xattr *xattr; struct rb_node *rbp_next; rbp_next = rb_next(rbp); xattr = rb_entry(rbp, struct simple_xattr, rb_node); rb_erase(&xattr->rb_node, &xattrs->rb_root); if (freed_space) *freed_space += simple_xattr_space(xattr->name, xattr->size); simple_xattr_free(xattr); rbp = rbp_next; } } |
| 49 49 4 20 1 11 11 1 166 94 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /* * Return the ->prev pointer of a list_head in an rcu safe way. Don't * access it directly. * * Any list traversed with list_bidir_prev_rcu() must never use * list_del_rcu(). Doing so will poison the ->prev pointer that * list_bidir_prev_rcu() relies on, which will result in segfaults. * To prevent these segfaults, use list_bidir_del_rcu() instead * of list_del_rcu(). */ #define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * list_bidir_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * In contrast to list_del_rcu() doesn't poison the prev pointer thus * allowing backwards traversal via list_bidir_prev_rcu(). * * Note: list_empty() on entry does not return true after this because * the entry is in a special undefined state that permits RCU-based * lockfree reverse traversal. In particular this means that we can not * poison the forward and backwards pointers that may still be used for * walking the list. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another list-mutation * primitive, such as list_bidir_del_rcu() or list_add_rcu(), running on * this same list. However, it is perfectly legal to run concurrently * with the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that list_del_rcu() and list_bidir_del_rcu() must not be used on * the same list. * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_bidir_del_rcu(struct list_head *entry) { __list_del_entry(entry); } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. * * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the next element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 27 136 177 186 9 238 19 3 3 3 3 227 42 198 31 41 227 42 42 198 41 41 41 1 192 30 18 30 17 19 4 1 143 253 103 140 20 17 3 15 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <linux/file_ref.h> #include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 24)) /* * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) /* * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * The two FMODE_NONOTIFY* define which fsnotify events should not be generated * for a file. These are the possible values of (f->f_mode & * FMODE_FSNOTIFY_MASK) and their meaning: * * FMODE_NONOTIFY - suppress all (incl. non-permission) events. * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. */ #define FMODE_FSNOTIFY_MASK \ (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) #define FMODE_FSNOTIFY_NONE(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS #define FMODE_FSNOTIFY_PERM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) #define FMODE_FSNOTIFY_HSM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0) #else #define FMODE_FSNOTIFY_PERM(mode) 0 #define FMODE_FSNOTIFY_HSM(mode) 0 #endif /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) #define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) #define IOCB_HAS_METADATA (1 << 24) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC" }, \ { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 #define IOP_MGTIME 0x0020 #define IOP_CACHED_LINK 0x0040 /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ u32 i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; union { struct list_head i_devices; int i_linklen; }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { int testlen; /* * TODO: patch it into a debug-only check if relevant macros show up. * In the meantime, since we are suffering strlen even on production kernels * to find the right length, do a fixup if the wrong value got passed. */ testlen = strlen(link); if (testlen != linklen) { WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)", link, linklen, testlen); linklen = testlen; } inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; } /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ #define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit); static inline void inode_wake_up_bit(struct inode *inode, u32 bit) { /* Caller is responsible for correct memory barriers. */ wake_up_var(inode_state_wait_address(inode, bit)); } struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned int mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /** * struct file - Represents a file * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations * @f_mapping: Contents of a cacheable, mappable object. * @private_data: filesystem or driver specific data * @f_inode: cached inode * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; struct address_space *f_mapping; void *private_data; struct inode *f_inode; unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; /* pipes */ u64 f_pipe; }; loff_t f_pos; #ifdef CONFIG_SECURITY void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL struct hlist_head *f_ep; #endif union { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; freeptr_t f_freeptr; }; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif int file_f_owner_allocate(struct file *file); static inline struct fown_struct *file_f_owner(const struct file *file) { return READ_ONCE(file->f_owner); } extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } /* * Multigrain timestamps * * Conditionally use fine-grained ctime and mtime timestamps when there * are users actively observing them via getattr. The primary use-case * for this is NFS clients that use the ctime to distinguish between * different states of the file, and that are often fooled by multiple * operations that occur in the same coarse-grained timer tick. */ #define I_CTIME_QUERIED ((u32)BIT(31)) static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ #define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? * * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait * upon. There's one free address left. */ #define __I_NEW 0 #define I_NEW (1 << __I_NEW) #define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) #define __I_LRU_ISOLATING 2 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_SYNC (1 << 3) #define I_DIRTY_DATASYNC (1 << 4) #define I_DIRTY_PAGES (1 << 5) #define I_WILL_FREE (1 << 6) #define I_FREEING (1 << 7) #define I_CLEAR (1 << 8) #define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 12) #define I_OVL_INUSE (1 << 13) #define I_CREATING (1 << 14) #define I_DONTCACHE (1 << 15) #define I_SYNC_QUEUED (1 << 16) #define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) /** * is_mgtime: is this inode using multigrain timestamps * @inode: inode to test for multigrain timestamps * * Return true if the inode uses multigrain timestamps, false otherwise. */ static inline bool is_mgtime(const struct inode *inode) { return inode->i_opflags & IOP_MGTIME; } extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) ({ \ const struct file_operations *_fops = (fops); \ (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ }) #define fops_put(fops) ({ \ const struct file_operations *_fops = (fops); \ if (_fops) \ module_put((_fops)->owner); \ }) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who); int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) { if (!(flags & AT_EMPTY_PATH)) return getname(name); if (!name) return NULL; return __getname_maybe_null(name); } extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, iocb->ki_pos + count); } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } /* * Do not prevent write to executable file when watched by pre-content events. * * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at * the time of file open and remains constant for entire lifetime of the file, * so if pre-content watches are added post execution or removed before the end * of the execution, it will not cause i_writecount reference leak. */ static inline int exe_file_deny_write_access(struct file *exe_file) { if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return 0; return deny_write_access(exe_file); } static inline void exe_file_allow_write_access(struct file *exe_file) { if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return; allow_write_access(exe_file); } static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) { file->f_mode &= ~FMODE_FSNOTIFY_MASK; file->f_mode |= mode; } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); static inline int inode_init_always(struct super_block *sb, struct inode *inode) { return inode_init_always_gfp(sb, inode, GFP_NOFS); } extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); struct inode *iget5_locked_rcu(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } /* * inode->i_lock must be held */ static inline void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); #if IS_ENABLED(CONFIG_UNICODE) int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); /** * generic_ci_validate_strict_name - Check if a given name is suitable * for a directory * * This functions checks if the proposed filename is valid for the * parent directory. That means that only valid UTF-8 filenames will be * accepted for casefold directories from filesystems created with the * strict encoding flag. That also means that any name will be * accepted for directories that doesn't have casefold enabled, or * aren't being strict with the encoding. * * @dir: inode of the directory where the new file will be created * @name: name of the new file * * Return: * * True: if the filename is suitable for this directory. It can be * true if a given name is not suitable for a strict encoding * directory, but the directory being used isn't strict * * False if the filename isn't suitable for this directory. This only * happens when a directory is casefolded and the filesystem is strict * about its encoding. */ static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) { if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) return true; /* * A casefold dir must have a encoding set, unless the filesystem * is corrupted */ if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) return true; return !utf8_validate(dir->i_sb->s_encoding, name); } #else static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) { return true; } #endif static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return !!sb->s_encoding; #else return false; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } if (flags & RWF_DONTCACHE) { /* file system must support it */ if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) return -EOPNOTSUPP; /* DAX mappings not supported */ if (IS_DAX(ki->ki_filp->f_mapping->host)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); #endif /* _LINUX_FS_H */ |
| 68 68 63 6 327 327 327 308 309 369 68 68 68 68 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm)) return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; int nr_charged = 0; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; #ifdef CONFIG_PER_VMA_LOCK /* SLAB cache for vm_area_struct.lock */ static struct kmem_cache *vma_lock_cachep; static bool vma_lock_alloc(struct vm_area_struct *vma) { vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); if (!vma->vm_lock) return false; init_rwsem(&vma->vm_lock->lock); vma->vm_lock_seq = UINT_MAX; return true; } static inline void vma_lock_free(struct vm_area_struct *vma) { kmem_cache_free(vma_lock_cachep, vma->vm_lock); } #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } static inline void vma_lock_free(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!vma) return NULL; vma_init(vma, mm); if (!vma_lock_alloc(vma)) { kmem_cache_free(vm_area_cachep, vma); return NULL; } return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); if (!vma_lock_alloc(new)) { kmem_cache_free(vm_area_cachep, new); return NULL; } INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; } void __vm_area_free(struct vm_area_struct *vma) { vma_numab_state_free(vma); free_anon_vma_name(vma); vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } #ifdef CONFIG_PER_VMA_LOCK static void vm_area_free_rcu_cb(struct rcu_head *head) { struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); /* The vma should not be locked while being destroyed. */ VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); __vm_area_free(vma); } #endif void vm_area_free(struct vm_area_struct *vma) { #ifdef CONFIG_PER_VMA_LOCK call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); #else __vm_area_free(vma); #endif } static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm; int i; vm = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); if (mmap_write_lock_killable(oldmm)) return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } else { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ if (mpnt) { mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); /* Avoid OOM iterating a broken tree */ set_bit(MMF_OOM_SKIP, &mm->flags); } /* * The mm_struct is going to exit, but the locks will be dropped * first. Set the mm_struct as unstable is advisable as it is * not fully initialised. */ set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm w |